Review Not peer-reviewed version

Advancements in Fault Detection

Techniques for Transmission Lines: A
Literature Review

Jewelle Abbygale M. Daang * , Andrey M. Omas-as , Edwin R. Arboleda

Posted Date: 12 May 2024

doi: 10.20944/preprints202405.0662.v2

Keywords: Transmission line fault detection; Machine learning; Deep learning; Fault classification; Grid
resilience

Preprints.org is a free multidiscipline platform providing preprint service that

is dedicated to making early versions of research outputs permanently
available and citable. Preprints posted at Preprints.org appear in Web of
Science, Crossref, Google Scholar, Scilit, Europe PMC.

Copyright: This is an open access article distributed under the Creative Commons
Attribution License which permits unrestricted use, distribution, and reproduction in any
medium, provided the original work is properly cited.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

Disclaimer/Publisher’s Note: The statements, opinions, and data contained in all publications are solely those of the individual author(s) and
contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting
from any ideas, methods, instructions, or products referred to in the content.

Review
Advancements in Fault Detection Techniques for
Transmission Lines: A Literature Review
Jewelle Abbygale M. Daang 1,*, Andrey M. Omas-as 1 and Edwin R. Arboleda 2
1 College of Engineering and Information Technology, Cavite State University, Indang, Cavite, Philippines
2 Faculty of College of Engineering and Information Technology, Cavite State University, Indang, Cavite,
Philippines
* Correspondence: [email protected]

Abstract: This literature review delves into the realm of fault detection techniques for transmission
lines, aiming to provide a comprehensive overview of recent advancements and key trends in the
field. Employing a structured approach, the review synthesizes a plethora of research spanning
from 2019 to 2024, sourced from diverse databases including IEEE Xplore, ScienceDirect,
ResearchGate, Scopus, Litmaps, and Google Scholar. The methodology encompasses a systematic
literature search protocol, stringent inclusion and exclusion criteria, meticulous data extraction, and
a multi-dimensional analysis framework. The literature review uncovers a spectrum of fault
detection methodologies, ranging from traditional signal processing techniques like Discrete
Wavelet Transform and phase angle-based methods to cutting-edge deep learning algorithms such
as Capsule Networks and Convolutional Neural Networks. Insights gleaned from the review
underscore the critical importance of fault detection in maintaining the reliability, safety, and
efficiency of power grids, highlighting its role as a frontline defense against widespread outages
and equipment damage. Key findings from the review shed light on the efficacy of different fault
detection approaches, showcasing their strengths and limitations across diverse system conditions.
Furthermore, the review identifies common trends and challenges, including the need for real-
world validation, scalability, adaptability to various network configurations, and cybersecurity
considerations. This literature provides valuable insights and recommendations for future research
endeavors in fault detection for transmission lines. By embracing advancements in both traditional
and emerging techniques, researchers can continue to enhance the resilience and dependability of
power transmission systems, ensuring their ability to withstand evolving challenges and safeguard
critical infrastructure.

Keywords: transmission line fault detection; machine learning; deep learning; fault classification;
grid resilience

I. Introduction
Transmission lines are essential to communication networks and electricity distribution systems.
They are made of several kinds of conductors and are intended to direct the flow of energy from a
source to a load [1]. Usually, online devices are used to monitor the real-time state acquisition of
overhead transmission lines. This can be enhanced by employing directed transmission data
technology to increase the network lifetime [2]. Short transmission lines were the majority of
applications for direct secondary wire connections from instrument transformers to protection relays
[3]. One major issue with energy transfer is the act of moving electrical power from one location to
another over a considerable distance [4]. The extension of the lines over varied terrains and
geographic regions makes them the most vulnerable to various types of atmospheric tragedies, which
frequently cause faults in the line [5].
Numerous studies have been conducted on common transmission line faults, such as L-L, L-G,
and 2L-G faults [6–8]. Syncrophoresor signals can be used to discover and identify these problems,

© 2024 by the author(s). Distributed under a Creative Commons CC BY license.

Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

hence enhancing power quality [7]. In three-phase transmission lines, the Fortescue Theorem has
been used to evaluate symmetrical and unsymmetrical faults; the most common type of faults are
single L-G faults [8]. A fault analysis model has been established to direct preventive efforts in light
of the variety of sources of these defects, which include human activity and environmental elements
[9]. Faults can cause power losses in transmission lines as well as power failures [10].
Fault identification in transmission lines is critical because it has the ability to create power
interruptions and extend power outages. This is especially important given the increasing
industrialization and electricity consumption that has resulted in a more complex power system
network [11]. Advanced techniques like machine learning and deep learning have been found to
considerably increase the accuracy and speed of fault identification [12]. When applied to high and
medium voltage networks, these approaches have shown great promise and efficiency in fault
detection [10]. To keep the electricity system running smoothly, transmission line defects must be
detected and repaired quickly [13].
In line with this, the literature review explores the application of machine learning (ML)
techniques in fault detection and classification (FDC) for power transmission lines. Specifically, it
delves into the potential of various ML models to enhance FDC accuracy and efficiency. This review
critically examines the methodologies and findings of key studies in the field, offering insights into
the strengths and limitations of different approaches. Additionally, to facilitate understanding, a list
of abbreviations commonly used in the reviewed literature is provided.

Table 1. Abbreviations that appear in the study.

Abbreviation Expanded Form

AI Artificial Intelligence
ANFIS Adaptive Neuro-Fuzzy Inference Systems
ANN Artificial Neural Network
BN Bayesian Networks
BPNN Back Propagation Neural Networks
CapsNet Capsule Network
CNN Convolutional Neural Network
CT Current Transformer
DFT Discrete Fourier Transform
DL Deep Learning
DRNN Deep Recurrent Neural Networks
DRL Deep Reinforcement Learning
DSE Differential Spectral Energy
DT Decision Tree
DWT Discrete Wavelet Transform
FBSC Fractional Base Station Cooperation
FDC Fault Detection and Classification
FLP Fault Location Prediction
FRI Fault Region Identification
FTC Fault Type Classification
GFD Global Fault Detector
GCNN Graph Convolutional Neural Network
GNN Graph Neural Networks
HIF High Impedance Faults
HMM Hidden Markov Model
HVDC High-Voltage Direct Current
KMDD K-Means Data Description
KNN K-Nearest Neighbors
LSTM Long Short-Term Memory
IPA Instantaneous Phase Angles
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

ML Machine Learning
MLP Multi-Layer Perceptron
MODWT Maximal Overlap Discrete Wavelet Transform
NB Naïve Bayes
PMU PMU
PSCAD Positive Sequence Current Angle Differences
PSCM Positive Sequence Current Magnitude
PSVM Positive Sequence Voltage Magnitude
R-CNN Region-Based Convolutional Neural Network
RF Random Forest
RNN Recurrent Neural Networks
SAT-CNN Self-attention Convolutional Neural Network
SDL Sequential Deep Learning
SF Sparce Filtering
SE Spectral Energy
SOM Self-Organizing Maps
SSD Successive Signal Detection
SVM Support Vector Machine
TF Transfer Function
UPFC Unified Power Flow Controller

For transmission lines, a variety of fault locating, and detection methods have been put forth.
Zhuang (2021) presents a noncontact method utilizing electro-optic field sensors [14], whereas Kumar
(2019) recommends employing synchrophasor measurements to locate and categorize problems [7].
Fasihipour (2020) suggests a fault detection algorithm for TCSC-compensated lines [15], whereas
Abu-Siada (2019) offers an affordable online method based on V-I locus diagrams [16]. These
techniques have a number of advantages, including early failure identification and simplicity of use.
It would be beneficial to investigate these techniques further for potential power system applications.
The crucial necessity of fault detection and classification in guaranteeing the dependability,
security, and effectiveness of transmission lines in power systems is the driving force behind this
literature study. The foundation of electrical grids are transmission lines, which make it easier to
move electricity across great distances from sources of power supply to distribution networks and
final consumers. Transmission lines, however, are prone to a number of problems, including
insulation failures, line breakage, and short circuits, which can interfere with the power supply, harm
equipment, and present safety risks.
Through a detailed examination of the body of research on fault detection and classification
procedures for transmission lines, we expect to learn more about the most recent advances,
methodologies, and industry best practices in this critical area. Developing robust and efficient
strategies for early fault diagnosis, localization, and mitigation necessitates a grasp of the advantages
and disadvantages of various fault detection approaches, including impedance-based, wavelet
transform-based, and artificial intelligence-based procedures.
Furthermore, because modern power systems are becoming more complicated and because
renewable energy sources and smart grid technology are becoming increasingly integrated, problem
detection and classification techniques must be continuously improved. Through this literature
review, we hope to identify new trends, opportunities, and issues facing the industry that will help
to strengthen the resilience and reliability of transmission line networks in the face of shifting
operational and environmental conditions.
The objective of this literature review is to thoroughly examine the current state of fault detection
techniques in transmission line systems, considering both proven techniques and recently developed
advancements. We intend to shed light on important insights and opportunities that could direct
future efforts to increase the resilience and dependability of transmission line networks by delving
into the most recent research and developments in this vital field.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

• To compare and critically assess the current methods for fault detection used in transmission
line systems.
• To list the main obstacles and restrictions related to the existing techniques for transmission line
fault detection and classification.
• To investigate current developments as well as new directions in transmission line systems fault
detection technology.
• To evaluate the suitability and practicality of various fault detection techniques in actual
transmission line situations.
• To make suggestions on possible areas for future research and advancements in transmission
line fault detection techniques.
This analysis examines the latest advancements and growing patterns in fault detection
technology for transmission line systems, investigating creative methods and cutting-edge
approaches that could improve fault detection performance as well as the effectiveness,
dependability, and drawbacks of the current fault detection techniques in the context of actual
transmission line situations, compare and contrast them. Additionally, it assesses the applicability
and feasibility of several fault detection methods in real-world transmission line scenarios, taking
into account elements like accuracy, efficiency, and implementation difficulties. Finally, the review
aims to offer perspectives and suggestions for future research directions by pointing out possible
areas of progress and recommending pathways for additional investigation and development of
transmission line fault detection methods. The goal of the literature review is to increase transmission
line system resilience and dependability while also advancing fault detection technology through its
wide reach.

II. Methodology
This review employs a structured approach to identify and evaluate the latest advancements in
transmission line fault detection methods. The following sections detail the specific techniques
implemented to ensure a comprehensive and insightful investigation.

A. Literature Search Strategy

The literature search adheres to a structured protocol to guarantee the inclusion of pertinent and
up-to-date research. This protocol focuses on two primary aspects:
• Inclusion Period: The search prioritizes studies published between 2019 and 2024 to capture the
most recent developments. This timeframe ensures the review reflects the evolving landscape of
fault detection technologies for transmission lines.
• Database Selection: The search adopts a broad perspective by systematically exploring a variety
of databases. This includes industry-standard resources such as IEEE Xplore, ScienceDirect,
ResearchGate (https://www.researchgate.net/), Scopus (www.scopus.com), Litmaps, alongside
comprehensive platforms like Google Scholar. Additionally, relevant repositories are examined
to uncover potentially valuable specialized research. A defined set of keywords is utilized to
refine the search results and achieve a focused selection. These keywords encompass
fundamental terms like ʺtransmission line fault detectionʺ and delve into specific methodologies
like ʺimpedance-based techniquesʺ and ʺwavelet transform.ʺ Moreover, Boolean operators
(AND, OR) are strategically employed to maintain a balance between comprehensiveness and
specificity.

B. Establishing Inclusion and Exclusion Criteria

Strict selection criteria are established to ensure the quality and relevance of the reviewed
studies. This guarantees the review centers on the most influential and rigorously conducted
research.
• Inclusion Criteria:
o Peer-reviewed articles, conference papers, and relevant reviews focusing on fault detection
techniques for transmission lines are prioritized.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

o Studies exploring a wide range of approaches are included, encompassing traditional

techniques, advanced signal processing methods, applications of machine learning and
artificial intelligence, and hybrid methodologies that combine these approaches. This
ensures a thorough understanding of the current state-of-the-art.
• Exclusion Criteria:
o Publications not in English are excluded to maintain consistency and facilitate clear
analysis.
o Studies lacking clearly defined methodologies are excluded to ensure the review focuses on
robust research and avoids potentially unreliable data.

C. Detailed Data Extraction Process

Upon identification of relevant studies, a meticulous data extraction process commences. This
process involves three critical steps:
1. Creation of a Comprehensive Extraction Grid: A detailed extraction grid is designed to streamline
data extraction and ensure uniformity. This grid is formulated by analyzing recent, established
checklists relevant to fault detection research. Additionally, a thorough review of 21 related
studies identifies frequently reported data points. Utilizing this combined knowledge, a
comprehensive extraction grid is constructed, encompassing all essential data elements.
2. Thorough Information Extraction: Following the established extraction grid, relevant details are
meticulously extracted from each selected study. These details include bibliographic
information such as titles, authors, and publication years, as well as core research elements like
the employed fault detection techniques, key findings of the study, and the specific system
conditions evaluated.
3. Documenting Accuracy Metrics and Limitations: To facilitate a comparative analysis of the
effectiveness of various fault detection methods, reported accuracy rates and performance
metrics are documented from each study. This enables a nuanced understanding of the strengths
and weaknesses of different approaches. Additionally, any limitations mentioned by the authors
are identified and documented. Analyzing these limitations provides valuable insights into
potential challenges and areas for future research endeavors.

D. Multi-Dimensional Analysis of Selected Studies

A multi-dimensional approach is adopted to analyze the selected studies, enabling a
comprehensive understanding of the current landscape of fault detection techniques. This approach
encompasses five key components:
1. Rigorous Study Selection: Clear and rigorous selection criteria, meticulously aligned with the
overall research objectives, are established to ensure only the most relevant studies are included
for analysis.
2. Data Synthesis and Evaluation: Key findings from each selected study are carefully summarized,
providing a concise overview of the research contributions. These summaries are then evaluated
based on two crucial aspects: the specific fault detection techniques employed and the system
conditions under which the techniques were tested. This allows for insights into the applicability
and limitations of different approaches under varying circumstances.
3. Comparative Analysis: A comprehensive comparative analysis is conducted, meticulously
examining the reported accuracy, strengths, and limitations of different fault detection
approaches. This comparative analysis provides a clear understanding of which methodologies
excel in specific scenarios and identifies areas where certain approaches might fall short.
4. Discussing Implications and Recommendations: The review delves into the broader implications of
the findings, exploring how these advancements can potentially impact the field of fault
detection for transmission lines. Furthermore, common trends and challenges identified
throughout the analysis are highlighted. Based on these insights, the review provides well-
considered recommendations for future research endeavors, paving the way for continued
advancements.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

This methodological approach employs a multi-faceted exploration to identify recent advancements in

transmission line fault detection, utilizing a structured literature search, rigorous selection criteria,
detailed data extraction, and multi-dimensional analysis for a comprehensive understanding of the
field.

III. Results and Discussion

This section delves further into an examination of a wide range of methodologies applied in a
variety of research-compiled publications. By carefully analyzing these many sources, we want to
identify the approaches used, their effectiveness, underlying benefits, and associated drawbacks. We
also try to deepen our understanding through additional literature studies and comparative analysis.
These additional studies are used to make comparisons as well as to map the historical development
of fault detection techniques in transmission lines.
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
7

A. Advanced Signal Processing Techniques:

Table 2. Literatures for Fault Detection on Transmission Lines Using Signal Processing Techniques.

Ref Literature Technique Used Effectiveness Limitations

[17] Phase angle-based fault detection and ● Estimation of IPA ● Effectively and precisely identify fault ● It does not discuss the possible
classification for protection of ● DFT conditions from non-fault conditions computational or resource needs involved
transmission lines - Kumar, B., ● GFD ● Removing the requirement for phasor in putting the suggested model into
Mohapatra, A., Chakrabarti, S., magnitudes and naturally lowering the practice in practical applications
Kumar, A. (2021) influence of noise in measurement signals ● Its efficiency in real-life situations with
● Exhibits robustness against CT saturation different environmental and operating
and CT/PT measurement errors variables has yet to be completely proven
● Capability in identifying and categorizing ● The precision and dependability of the
HIFs measurement tools may have an impact on
performance
[18] A critical fault detection analysis & fault ● Combination of DWT and ● Efficiency in identifying errors under a ● More verification and testing may be
time in a UPFC transmission line - Mishra, DFT range of demanding circumstances is required to evaluate the scheme s
S., Tripathy, L. (2019) ● SE and DSE computation demonstrated effectiveness in real-world circumstances
● Daubechy mother wavelet ● Detects faults in less than one cycle (20 ● Precise measures or benchmarks that were
(db4) milliseconds) utilized in db4 to make the comparison
● Takes performance indicators like yield, were not stated
security, and dependability into account
to confirm the correctness and
dependability of the model
[19] Fault detection through discrete wavelet ● DWT ● Appropriate for fault detection in ● Proposes utilizing DWT to investigate how
transform in overhead power transmission transmission lines in continuous noise affects feature extraction from fault

doi:10.20944/preprints202405.0662.v2
lines - Ahmed, N., Hashmani, A., Khokhar, monitoring signals
S., Tuni, M., Faheem, M. (2023) ● Precisely discern between the healthy and ● It would benefit from more verification and
faulty phases in various fault scenarios, testing in actual situations to evaluate the
increasing the fault detection s robustness and practical usability of DWT-
dependability based fault detecting systems
● Robust fault detection is ensured by the
fact that fault signals examined using
DWT are insensitive to changes in factors
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
8

like fault inception angle, fault resistance,

and transmission line length
[20] Fault Detection and Classification of Shunt ● DWT ● DWT decomposes the current signal ● Choosing the right way to analyze the
Compensated Transmission Line Using ● NB classifiers during faults, allowing for the signal DWT and the classifier NB can affect
Discrete Wavelet Transform and Naive identification of characteristic patterns accuracy.
Bayes Classifier - Aker, E., Othman, M., within the signal. ● Real-world noise and dependencies
Veerasamy, V., Aris, I., Wahab, N., Hizam, ● The study suggests that the NB classifier between fault features can lead to errors.
H. (2020) outperforms other classifiers like MLP ● The method is optimized for shunt-
Neural Networks in terms of accuracy, compensated lines and might need
misclassification rate, and various error adjustments for other cases.
metrics. ● Results from simulations may not directly
apply to complex real-world power
systems.
[21] MODWT-based fault detection and ● MODWT ● A complete method for locating cross- ● Primarily concentrates on fault
classification scheme for cross-country and country and evolving faults in a real 400 classification and detection in a 400 kV
evolving faults - Ashok, V., Yadav, A., kV dual-circuit transmission line network dual-circuit transmission line network in
Abdelaziz, A. (2019) is provided by the application of the state of Chhattisgarh
MODWT-based fault detection and ● Implementation and maintenance may
classification become more complex if a two-stage
● The method displays its resilience by development procedure and fault classifier
effectively identifying and categorizing algorithms based on fault coordinates are
defects across a broad range of fault used
parameters and operational circumstances ● Although the system s performance is
● A method based on MODWT is noise- assessed by experimental data from a
resistant hardware setup, other factors like
● The model has a small time delay, with an scalability, cost-effectiveness, and

doi:10.20944/preprints202405.0662.v2
operating time that can be as little as ¼ compatibility with current infrastructure
cycle or as much as 1 cycle may need to be taken into account before
● Verified by means of experimental data the scheme is actually deployed in
gathered in a lab setting utilizing a transmission line networks
hardware configuration
[22] Faults detection and classification of ● DWT ● Shows dependability in identifying ● Possible difficulties for professionals who
HVDC transmission lines of using discrete different kinds of defects through the don t have much experience with
wavelet transform - Saleem, U., Arshad, examination of current signals received sophisticated signal processing methods
U., Masood, B., Gul, T., Khan, W., Ellahi, from high-voltage DC transmission lines ● May be quite difficult computationally,
M. (2018) which could limit its application in real
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
9

● It is stated that the suggested strategy is time or necessitate a large amount of

more accurate than previous fault computing power to implement
detection techniques for HVDC ● There may be a limit to its applicability to
transmission lines different kinds of transmission networks or
● Flexible enough to accommodate various failure circumstances
fault situations and positions on HVDC
transmission lines
[23] Transmission Line Fault Detection and ● PMUs ● Uses two steps to identify and detect ● Restricted to identifying short circuit faults;
Identification in an Interconnected Power faults: the first stage uses PSVM and without additional modification, it is
Network using Phasor Measurement Units PSCADs, while the second stage uses unable to recognize open circuit faults
- Khan, A., Ullah, Q., Sarwar, M., Gul, S., PSCM ● It might need more testing and
Iqbal, N. (2018) ● The suggested framework s efficiency is modification to determine whether it is
demonstrated by the simulation results, appropriate for larger applications or
which correctly identify 11 different types different kinds of power networks
of failures at 6 different network nodes ● Dependence on PMU infrastructure
● Carried out and evaluated on a 5-bus availability and dependability is implied
linked power network when using PMU data for voltage and
● PMUs are used to collect the voltage and current measurement
current data needed for fault ● The successful implementation of the two-
identification and detection stage procedure implies a certain amount
of complexity in its implementation, which
may need proficiency in fault detection
techniques and power system analysis
● The inability to detect open circuit faults
without alteration suggests that further
research or improvement of the suggested

doi:10.20944/preprints202405.0662.v2
method may be necessary to handle a
greater variety of fault circumstances
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

10

This table presents recent research in FDC for power transmission lines, showcasing several
innovative techniques, each with its own advantages and limitations. One approach utilizes phase
angle-based methods employing IPA estimation and DFT. This method boasts precise fault
identification and robustness against measurement errors and current transformer saturation.
However, its real-world implementation requirements and effectiveness under diverse operating
conditions remain unclear and warrant further investigation.
Another promising technique combines DWT with DFT and SE computation for fault detection
in UPFC transmission lines. This method achieves efficient fault detection within a single cycle.
However, the lack of comprehensive validation under real-world conditions and a clear definition of
the benchmarks used for comparison limit its current applicability. Similarly, a separate study
proposes a DWT-based fault detection technique that exhibits promising fault discrimination and
robustness. However, similar to the previously mentioned methods, this approach requires further
verification and testing in real-world scenarios to assess its effectiveness and adaptability in practical
applications.
Furthermore, a method combining DWT with NB classifiers proves effective for fault detection
and classification in shunt-compensated transmission lines. While this approach demonstrates
effectiveness, its accuracy under real-world noise conditions and generalizability to complex power
systems with various configurations pose challenges that need to be addressed.
Additionally, MODWT method provides a complete fault identification and classification
capability in the field of fault detection techniques. Its potential for practical deployment is
highlighted by its successful implementation in an actual 400 kV dual-circuit transmission line
network, noise resistance, and short time delay. However, concerns over the method s scalability and
adaptability to different network designs are raised by its concentration on particular transmission
line topologies in Chhattisgarh. Furthermore, the complexity of implementation raises the possibility
that additional analysis of scalability, cost-effectiveness, and compatibility with current
infrastructure is necessary, especially in light of two-stage development and fault classifier
algorithms.
Moreover, a viable method for identifying defects in HVDC transmission lines is the
independent application of DWT. Its potential utility is highlighted by its proven dependability and
versatility in accommodating different fault scenarios on HVDC lines. Nevertheless, much thought
should be given to potential computing difficulties and applicability restrictions to various
transmission networks or failure scenarios. Furthermore, in real-time implementation or resource-
constrained contexts, the computing needs of the approach and the requirement for expertise in
signal processing may present difficulties.
Finally, using PMUs to detect faults provides a thorough method that makes use of voltage and
current data to precisely pinpoint fault circumstances. Fault circumstances can be properly diagnosed
and categorized using a two-stage procedure that involves PSVM, PSCADs, and PSCM. Even though
it has been successful in identifying short circuit faults, its drawbacks—such as its need on the
availability of PMU infrastructure and its complicated implementation—make more testing and
improvement necessary. Furthermore, the method s incapacity to identify open circuit failures
without alterations points to potential areas for further investigation to expand its applicability to a
wider variety of fault scenarios and transmission line topologies.
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
11

B. Machine Learning (ML) and Artificial Intelligence (AI) Techniques:

Table 3. Literatures for Fault Detection on Transmission Lines Using Machine Learning (ML) and Artificial Intelligence (AI) Techniques.

Ref Literature Algorithms Used Strengths Limitations

[24] Deep learning through LSTM ● DL (Presents three ● Accurate region classification in large- ● The dependency on synchrophasors indicates a
classification and regression for innovative DL scale multi-machine power systems possible constraint in application to systems
transmission line fault detection, classifier regression ● Excellent performance in fault location lacking access to modern synchrophasor
diagnosis and location in large-scale models based on prediction technology
multi-machine power systems - DRNN for FRI, FTC, ● Excellent categorization and prediction ● Scalability and generalizability
Belagoune, S., Bali, N., Bakdi, A., Baadji, and FLP) accuracy
B., Atif, K. (2021) ● Current and voltage
signals are monitored
using PMUs at various
terminals and used as
input characteristics
for DRNN models
● SDL with LSTM to
model spatiotemporal
sequences of high-
dimensional
multivariate
characteristics
[25] A deep learning based intelligent approach Capsule Network with SF ● Accurately manage limited system ● The evaluation focuses primarily on simulated
in detection and classification of model information and develop resistance to datasets
transmission line faults - Fahim, S., Sarker, system sounds ● Does not discuss the possible computational or

doi:10.20944/preprints202405.0662.v2
S., Muyeen, S., Das, S., Kamwa I. (2021) ● Extracts faulty features into a single resource needs involved in putting the
characteristic, making the fault suggested model into practice in practical
identification procedure easier applications
● Does not call for manual labeling of data ● Does not offer the model s generalizability to
during training and testing, increasing other transmission line layouts and operating
its scalability and applicability to varied situations outside of those that were evaluated
datasets
● Accuracy rates surpassing 99% in
identifying and classifying faults, even
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
12

under difficult conditions such as the

presence of system disturbances, high
impedance faults, and line parameter
fluctuations
[26] Self-attention convolutional neural network ● SAT-CNN model ● Ability to adjust to various operating ● It does not discuss the possible computational
with time series imaging based feature ● DWT environments or resource needs involved in putting the
extraction for transmission line fault ● Imperceptibly concentrates on the suggested model into practice in practical
detection and classification - Fahim, S., output data from the hidden layer, applications
Sarker, Y., Sarker, S., Sheikh, M., Das, S. improving the system s classification ● The evaluation focuses primarily on simulated
(2020) precision datasets
● Operates well with a variety of sampling ● Future deployment of the classifier utilizing
frequencies and signal kinds, actual data gathered from equipment in real-
demonstrating its robustness and world power grids may necessitate careful
adaptability consideration of data quality, calibration, and
● Withstand noise interference measurement errors
● It does not offer the model s generalizability to
other transmission line layouts and operating
situations outside of those that were evaluated
[27] End to end machine learning for fault ‘End to end’ ML model ● Removal of the requirement for intricate ● Further examination is necessary in order to
detection and classification in power employing LSTM feature extraction procedures determine its efficacy and dependability in real-
transmission lines - Rafique, F., Fu, L., Mai, ● Differentiate between several states, such world applications using data from real power
R. (2021) as fault and non-fault, and between systems in both recorded and real-world
various kinds of faults settings
● Flexibility to different problem scenarios ● Necessary to carefully evaluate the
and system specifications computational load that comes with
● Capable of handling voltage and current reconfiguring operational data using a

doi:10.20944/preprints202405.0662.v2
signals, providing a variety of data Timesteps strategy to reduce computational
sources load, particularly for large-scale power systems
● Ability to recognize and function in with substantial data requirements
situations of power swings, increasing its● The degree of noise in the signals, the intricacy
usefulness in practical situations of the power system structure, and the
● Strong performance across a range of availability of measuring instruments could
fault scenarios, including as changes in affect the robustness of the model
fault impedance, loading circumstances,
distance from measurement nodes, and
signal noise levels
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
13

[28] Detection and classification of transmission ● GCNN ● Permits building a model for graph ● The suggested solution uses a spectral
line transient faults based on graph classification convolution for graph convolution, which is
convolutional neural network - Tong, H., ● Integrating topological data into the theoretically sound but not very flexible
Qiu, R., Zhang, D., Yang, H., Ding, Q., Shi, network to deliver temporal and spatial ● It is considered that the edge weight is essential
X. (2021) data for fault identification and for locating faults, indicating that more
categorization investigation is required to improve the
● Show the suggested method s high weighing system
accuracy and excellent generalizability in● Recommended investigation in the application
identifying a variety of transient defects of dynamic GNN in order to overcome the
in a variety of settings drawbacks of spectral convolution and facilitate
● Demonstrates sensitive and steady the identification, categorization, and
performance with respect to robustness localization of malfunctions in dynamic power
and response speed grids
[29] Transmission Line Fault Classification Using ● ANN, SVM, KNN, and ● When it came to fault classification, the ● The study used a particular dataset, UFPA
Hidden Markov Models - Freire, J., Castro, RF HMM algorithm performed better and Faults, and concentrated mostly on short-circuit
A., Homci, M., Meiguins, B., Morais, J. (2019) had reduced error rates faults
● About 90% faster processing times were ● As the stated findings were produced on a
demonstrated by the HMM method than workstation with particular hardware
by any of the FBSC architecture s requirements (i7 CPU, 16GB memory), the
classifiers algorithm s application to systems with varying
● Direct fault event classification is made processing capacities may be limited
possible by the HMM method, which ● Its usefulness in practical applications has not
streamlines the classification procedure yet been confirmed
and may even result in less processing
cost
[30] High Impedance Single-Phase Faults ● TF method ● Exhibited greater performance in ● Mainly concerned with single-phase to ground

doi:10.20944/preprints202405.0662.v2
Diagnosis in Transmission Lines via Deep ● CNN and the hybrid identifying and precisely finding single- short circuit problems by simulating data from
Reinforcement Learning of Transfer model of DRL phase to ground short circuit problems an IEEE transmission line
Functions - Teimourzadeh, H., Moradzadeh, in power networks ● Depends on local data gathered from the
A., Shoaran, M., Mohammadi-Ivatloo, B., ● Attained strong correlation values transmission line, which may restrict its
Razzaghi, R. (2021) during the training and testing phases, application in circumstances where access to
demonstrating the models efficacy in extensive or centralized data is restricted
fault classification ● Deep learning technique skill and substantial
● The DRL approach demonstrated its computational resources may be needed for its
effectiveness in identifying subtle fault installation and training
situations and perhaps averting
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
14

catastrophic failures by outperforming

the CNN method in the early
identification of high-impedance faults
(7000 and 9000 ohms)
[31] Detection and Evaluation Method of ● Faster R-CNN, an end- ● Identification of transmission line defects● The scope of the dataset collected by UAVs
Transmission Line Defects Based on Deep to-end and high using automation, which decreases labor may be constrained, which could result in
Learning - Liang, H., Zuo, C., Wei, W. (2020) recognition accuracy intensity and the necessity for manual missed and false detections in some
deep learning inspection circumstances, especially in the winter and in
algorithm ● The absence of accessible and non-rural locations
standardized datasets in the field of ● The present dataset may not fully capture the
transmission line components is fine features of transmission line components
addressed by the development of the since it classifies problems into broad categories
Wire_10 dataset, which consists of aerial ● In actuality, the precise categorization of
photos taken by UAVs transmission line components can be
● Based on the Wire_10 dataset, the defect complicated, necessitating close examination of
detection network achieves a low false a number of variables
detection rate of 0.68% and a mean
Average Precision (mAP) of 91.1%
[32] Detection and classification of internal faults ● KMDD method ● Exhibits excellent precision and ● Although the scheme s low sample frequency
in bipolar HVDC transmission lines based dependability while identifying and makes it more applicable in current systems, it
on K-means data description method - categorizing internal DC faults in bipolar might make it less capable of capturing high-
Farshad, M. (2019) HVDC transmission lines frequency transient events or intricate
● Demonstrates resilience to external waveform data
errors and standard operating ● Although the scheme s low sample frequency
circumstances makes it more applicable in current systems, it
● Demonstrates its flexibility and might make it less capable of capturing high-

doi:10.20944/preprints202405.0662.v2
adaptability by being able to handle a frequency transient events or intricate
variety of fault situations, including ones waveform data
that weren t taken into account during
creation
● Contributes to its accuracy and stability
by being less sensitive to elements
including measurement noise, fault
resistance, and fault location
● Lessens reliance on connected
equipment and communication channels
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
15

● Appropriate for integration into current

systems without requiring substantial
hardware modifications
[33] Fault Detection and Classification in Power ● BPNN ● The Π-modeling of the three-phase ● The transmission line system may become
Transmission Lines using Back Propagation medium power transmission line system overly simplistic if it is converted to a Π-model.
Neural Networks - Teja, O., Ramakrishna, simplifies representation and analysis, ● The analysis was limited to fault scenarios
M., Bhavana, G., Sireesha, K. (2020) making fault detection algorithms easier including AG and ABG, which may not
to construct accurately reflect the range of faults that might
● Compatibility and simplicity of use arise in real-world transmission line systems.
when MATLAB/Simulink® is used ● The system complexity, dataset size, and
● Creating training data from transmission computational resources are only a few of the
system simulated values guarantees a variables that may influence the optimization
regulated training environment for algorithm selection
neural networks ● In order to evaluate the efficacy of fault
● By utilizing feedforward BPNN detection algorithms in practical applications,
techniques, faults can be accurately performance analysis mostly concentrated on
classified and detected. This is because MSE, epochs, and training time, ignoring other
neural networks can identify intricate critical metrics like accuracy, precision, and
patterns from training data recall
● There are no specifics given about the
hybridization criteria, optimization method, or
anticipated performance gains
[34] Component identification and defect ● Faster R-CNN ● By eliminating the need for extra ● Limiting the suggested algorithm s application
detection in transmission lines based on specialist hardware, using power grid to situations involving different kinds of
deep learning - Zheng, X., Jia, R., Aisikaer, video surveillance technology for transmission line components by concentrating
Gong, L., Zhang, G., Dang, J. (2020) transmission line component on just five different kinds of transmission

doi:10.20944/preprints202405.0662.v2
classification and fault detection lowers widgets
installation costs ● The complete variety of transmission line
● The use of SSD, Mask R-CNN, and environments may not be captured if sample
Faster R-CNN algorithms shows how images are just derived from drone aerial
successful deep learning methods are in inspection shots of the power grid
target identification and semantic ● Lacks in-depth investigation into component
segmentation failure detection in favor of focusing mostly on
● Understanding the advantages and target detection of aerial photography
disadvantages of the Faster R-CNN, components
 Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024
16

SSD, and Mask R-CNN algorithms is

possible through comparison and study
● Contextual and semantic information are
better combined when an object
detection framework built on FPN-SSD
is introduced
● Attaining an average accuracy of 89.3%
on the dataset indicates how well the
suggested algorithm works for
identifying transmission line
components and detecting defects

doi:10.20944/preprints202405.0662.v2
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

17

This table shows previous studies proposing various novel deep learning-based approaches for
FDC in power transmission systems. The first method utilizes DRNNs with LSTM units within a SDL
framework. This approach demonstrates exceptional performance in fault region identification, type
classification, and location prediction. However, its reliance on synchrophasor data may limit its
applicability to systems lacking this infrastructure, raising concerns regarding scalability and
generalizability across diverse grid configurations.
Conversely, a CapsNet with SF exhibits remarkable performance, surpassing 99% accuracy in
FDC tasks even under challenging conditions. However, the evaluation primarily focused on
simulated datasets, and the discussion surrounding practical implementation hurdles and
generalizability remains limited. Similarly, a SAT-CNN combined with DWT showcases promising
adaptability and robustness. Nonetheless, a comprehensive evaluation of its real-world deployment
challenges and generalization to various system configurations is currently lacking.
Furthermore, an End-to-End ML approach offers flexibility and delivers strong performance
across diverse fault scenarios. Nevertheless, further investigation is necessary to assess its efficacy in
real-world applications, particularly regarding computational load considerations.
Moreover, the GCNN offers a new method by enabling the creation of a model for graph
classification and incorporating topological information into the identification and classification of
faults. This model exhibits potential for reliable and quick fault detection, as evidenced by its
excellent accuracy and generalizability across a range of problem scenarios and settings. However,
the need for more research indicates possibilities for future study and development in the fields of
edge weighting systems and graph convolution flexibility.
Additionally, when it comes to detecting internal DC faults in bipolar HVDC transmission lines,
the KMDD method excels in terms of accuracy and dependability. With less dependence on linked
devices and communication lines, its accuracy and stability are enhanced by its flexibility,
adaptability, and resistance to outside mistakes. The necessity for additional improvement and
validation in practical environments is highlighted by restrictions on sample frequency and the
ability to record high-frequency transient occurrences.
Finally, the Faster R-CNN algorithm solves the issues of human inspection and dataset
standardization, providing great opportunities for automated identification of transmission line
defects. This model shows promise for real-world implementation with the creation of specific
datasets and reduced false detection rates. However, there is a need for continued study to improve
applicability and reliability due to limits in accurate component categorization, representativeness,
and dataset coverage.

C. Related Comparative Study and Literature Reviews Summary

● Advanced Fault Detection, Classification, and Localization in Transmission Lines: A
Comparative Study of ANFIS, Neural Networks, and Hybrid Methods by Kanwal, S.,
Jiriwibhakorn, S. (2024) [35]
○ Summary:
The study used a variety of computational tools to look at fault localization, classification, and
detection in power transmission networks. Faults were induced at four sites within the IEEE 9-
bus system, resulting in a total of forty distinct fault conditions being examined. ANN, ANFIS,
SOM, and a hybrid technique that combines DWT with ANFIS were among the models whose
performances were assessed.
With an error percentage of 0.008% on average, the ANFIS model showed remarkable defect
detection skills. Except for one instance when the error was -0.005%, it correctly categorized all
fault kinds. An average percentage inaccuracy of 0.547% was found for fault location. On the
other hand, the ANN-based models performed well in fault classification and localization, with
average percentage errors of 0.268% and 0.348%, respectively, and reached zero percent error
for fault detection.
The SOM-based models achieved zero percent error for all faults, demonstrating their
superiority in fault identification. However, there were a few minor mistakes in the fault location
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

18

and categorization, especially for certain fault circumstances. With zero percent error for fault
detection and respectable performance for fault classification and localization, the hybrid DWT-
ANFIS model produced encouraging results.
In comparison to other models, the ANFIS and hybrid techniques performed better overall in
defect identification, classification, and location. These results highlight how crucial it is to use
cutting-edge computational methods and hybrid approaches to improve the efficiency and
dependability of electricity transmission networks.
● Advanced techniques for fault detection and classification in electrical power transmission
systems: An overview by Tîrnovan, R. (2019) [36]
○ Summary:
This study provides an extensive overview of power transmission system fault detection and
classification techniques. It addresses signal acquisition, highlighting the critical role that feature
extraction plays in improving problem detection. It discusses model-based, knowledge-based,
and data-driven approaches to fault detection and groups them according to parameters like
information amount and quality. The usefulness of several fault detection techniques is
demonstrated by the results, which emphasize their importance in guaranteeing the safety and
dependability of the electrical grid.
The field of fault analysis techniques for power transmission systems has seen a significant
upsurge in development in recent years, with an emphasis on AI-based approaches and
contemporary techniques. These comprise PMU-based methods for phasor component rapid
estimate and fault detection, classification, and direction discrimination. Furthermore, methods
for improved defect detection have been used, including multi-information measurements and
GSM. Promising outcomes have been observed in AI-based approaches for pattern recognition
and ML, including ANNs, DT, BN, k-NN, SVMs, and DL. For example, DTs have been used to
identify and classify faults based on phase current data, while ANNs have been used to
accurately identify the type of fault in transmission lines. When utilizing wavelet decomposition
for fault classification, SVMs have proven to be efficacious, whereas Bayesian networks provide
precise fault section estimation in power systems. Moreover, in distance protection schemes, k-
NN algorithms have been applied for defect detection and classification. CNNs, one of the DL
techniques, have a lot of promise to enhance fault classification performance, particularly when
using three-phase current and voltage inputs in multi-channel sequence recognition issues. The
aforementioned developments highlight the need of incorporating AI methods into fault
identification and classification systems to guarantee the dependability and effectiveness of
power transmission networks.
● A Brief Review on Fault Detection, Classification and Location on Transmission Lines Using
PMUs by Swain, K., Mandal, S., Mahato, S., Cherukuri, M. (2018) [37]
○ Summary:
Examining fault localization, classification, and detection in power transmission networks using
PMUs demonstrates a wide range of approaches and algorithms designed to increase protection
systems dependability and effectiveness. A key method that makes use of the symmetrical
characteristics of electrical networks to precisely identify and categorize defects is symmetrical
component analysis. For example, a robust fault analysis methodology that leverages PMU data
concentrates on the symmetrical components of voltage and current phasors, allowing for rapid
fault diagnosis in a relatively short timeframe, often within 2-3 cycles after the incident. In
addition to symmetrical component analysis, additional signal processing techniques such as
the Stockwell transform have been used to detect and classify faults. This approach effectively
detects and classifies faults by examining differential sums and energy computations over half
cycles.
Algorithms for machine learning have also become effective tools for classifying and detecting
faults. Techniques like DTs and SVMs are used because of their capacity to manage intricate data
patterns and classification assignments. Additionally, in order to improve problem detection
capabilities, the integration of PMU data with other sources—like smart meters—has been
investigated. For instance, a technique is put forth to continually monitor transmission line
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

19

impedance and guarantee data integrity in order to identify potential cyberattacks on PMU data
transferred across wide area networks.
Large-scale network simulations and small-scale test cases are only two examples of the various
simulation studies that are frequently used to validate these approaches. Systems like
EMTP/ATP, DigSILENT PowerFactory, and MATLAB offer stable settings for evaluating and
verifying suggested algorithms, guaranteeing their effectiveness and dependability in practical
uses.
The research on fault localization, classification, and detection in PMU-based power
transmission systems is a constantly changing and dynamic topic. In order to meet the
challenges presented by changing grid dynamics and new threats, researchers work to improve
the efficiency, resilience, and dependability of power grid protection systems through creative
methods, cutting-edge signal processing techniques, and the integration of machine learning.

D. Discussion
Analyzing the outlined literature, it s evident that fault detection techniques for power
transmission lines have seen significant advancements driven by a blend of traditional signal
processing methods and emerging technologies like deep learning.

Overall Trends and Advancements:

Traditional signal processing techniques such as DWT, NB classifiers, and phase angle-based
methods have long been foundational in fault detection. These methods offer robustness and
efficiency in fault identification but often require further validation under diverse real-world
conditions to ascertain their practical applicability.
Moreover, the integration of machine learning, particularly deep learning algorithms like
CapsNet, CNNs, and RNNs with techniques like DWT and DFT, presents a paradigm shift in fault
detection. These approaches exhibit exceptional performance in fault identification, classification,
and localization, often surpassing traditional methods in accuracy and adaptability.

Potential of Emerging Techniques:

DL techniques offer promising avenues for fault detection, particularly in their ability to handle
complex data patterns and generalize across diverse system configurations. CapsNet, for instance,
show remarkable performance even under challenging conditions, while GCNN offer innovative
ways to incorporate topological information for fault detection. Integration with smart grid
technologies, such as PMUs, further enhances fault detection capabilities by leveraging real-time data
for precise fault localization and classification.

Key Challenges and Future Research Directions:

Despite the advancements, several challenges persist in fault detection for transmission lines.
Real-time implementation of complex algorithms remains a significant hurdle, particularly in
resource-constrained environments. Additionally, ensuring the scalability and adaptability of fault
detection techniques across different network designs and fault scenarios requires further
investigation. Cybersecurity threats also pose a growing concern, necessitating robust methods to
safeguard PMU data and infrastructure from potential attacks.
Future research directions should focus on addressing these challenges while exploring novel
techniques to improve fault detection efficiency and reliability. This includes investigating the
practical implementation of deep learning algorithms in real-world transmission systems,
developing robust cybersecurity measures to protect against cyber threats, and enhancing the
scalability and adaptability of fault detection methods across diverse network configurations.
The synergy between traditional and deep learning techniques presents a promising path
forward for fault detection in power transmission lines. However, addressing key challenges and
advancing research are crucial to ensure the resilience and dependability of power grid protection
systems in the face of evolving grid dynamics and emerging threats.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

20

IV. Conclusion
In conclusion, the extensive literature review provides a nuanced understanding of fault
detection and classification techniques for transmission lines, showcasing a blend of traditional signal
processing methodologies and cutting-edge advancements in deep learning. At its core, fault
detection remains a pivotal component in ensuring the reliability, safety, and efficiency of power
grids worldwide.
The significance of fault detection in transmission lines cannot be overstated, as it serves as a
frontline defense against widespread outages, equipment damage, and potential hazards to both
infrastructure and public safety. Through the lens of the reviewed literature, it becomes evident that
the continuous refinement and innovation in fault detection methodologies are imperative to meet
the evolving challenges posed by modern power grids.
The main findings of the literature review offer valuable insights into the efficacy of various fault
detection techniques. Traditional methods such as DWT and phase angle-based approaches
demonstrate robustness and reliability, particularly in fault identification and discrimination.
Concurrently, emerging deep learning algorithms, including CapsNet and CNN, exhibit promising
capabilities when integrated with smart grid technologies, showcasing superior performance in fault
localization, classification, and prediction.
Moreover, the review underscores the critical importance of future research avenues to address
existing limitations and propel the field forward. Key areas for improvement include the need for
comprehensive validation and real-world testing of existing fault detection techniques to assess their
applicability under diverse operating conditions. Additionally, the development of scalable and
adaptable algorithms is paramount to accommodate the intricacies of various network configurations
and fault scenarios. Furthermore, enhancing cybersecurity measures to safeguard PMU data and
infrastructure against potential threats emerges as a pressing concern in the context of modern grid
resilience.
By embracing these insights and recommendations, researchers can continue to advance fault
detection and classification techniques for transmission lines, contributing to the broader goal of
ensuring the reliability and resilience of power transmission systems. Through interdisciplinary
collaboration and concerted efforts, the field can strive towards comprehensive solutions that
effectively mitigate risks, optimize grid performance, and uphold the integrity of critical
infrastructure essential for societal well-being and economic prosperity.

Acknowledgments: The authors wish to extend their appreciation to their esteemed academic advisors and
mentors from the Department of Computer and Electronics Engineering at Cavite State University. Their
invaluable guidance and support were instrumental in shaping the literature review titled ʺAdvancements in
Fault Detection Techniques for Transmission Lines: A Literature Review.ʺ The authors also acknowledge the
pioneering researchers and scholars whose contributions provided the foundation for their study. Special
recognition is given to Cavite State University for providing essential resources, and to peers whose engaging
discussions enriched the research. Lastly, the authors express heartfelt gratitude to their families and friends for
their unwavering support throughout this endeavor.

Conflicts of Interest: The authors declare no conflict of interest.

References
1. S. Bhattacharyya, P. Debnath, A. Deyasi, and N. Dey, Eds., Contemporary Developments in High-Frequency
Photonic Devices: in Advances in Computer and Electrical Engineering. IGI Global, 2019.
https://doi.org/10.4018/978-1-5225-8531-2.
2. D. Bai, X. Lv, J. Wang, and W. Zheng, “Application of Directional Transmission Data Technology for
Transmission Lines,” J. Phys.: Conf. Ser., vol. 1584, no. 1, p. 012040, Jul. 2020. https://doi.org/10.1088/1742-
6596/1584/1/012040.
3. N. O. Mogaru, “The Basics of Transmission Line Protection,” in 2020 IEEE PES/IAS PowerAfrica, Nairobi,
Kenya: IEEE, Aug. 2020, pp. 1–5. https://doi.org/10.1109/PowerAfrica49420.2020.9219983.
4. J. Q. Fahad and R. K. Chillab, “Design aspects of high voltage transmission line,” Bulletin EEI, vol. 9, no. 3,
pp. 853–861, Jun. 2020. https://doi.org/10.11591/eei.v9i3.2062.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

21

5. A. Mukherjee, P. K. Kundu, and A. Das, “Transmission Line Faults in Power System and the Different
Algorithms for Identification, Classification and Localization: A Brief Review of Methods,” J. Inst. Eng. India
Ser. B, vol. 102, no. 4, pp. 855–877, Aug. 2021. https://doi.org/10.1007/s40031-020-00530-0.
6. H. V. Patil, “Three-Phase Fault Analysis on Transmission Line in Matlab Simulink,” IJRASET, vol. 9, no.
VI, pp. 5386–5391, Jun. 2021. https://doi.org/10.22214/ijraset.2021.36027.
7. S. A. Kumar and D. Chandramohan, “Fault test analysis in transmission lines throughout interfering
synchrophasor signals,” ICT Express, vol. 5, no. 4, pp. 266–270, Dec. 2019.
https://doi.org/10.1016/j.icte.2018.03.003.
8. F. M. Gebru, A. O. Salau, S. H. Mohammed, and S. B. Goyal, “Analysis of 3-Phase Symmetrical and
Unsymmetrical Fault on Transmission Line using Fortescue Theorem,” WSEAS TRANSACTIONS ON
POWER SYSTEMS, vol. 17, pp. 316–323, Oct. 2022. https://doi.org/10.37394/232016.2022.17.32.
9. Z. Zhiqiang, C. Fuyong, Z. Han, G. Jieting, J. Peng, and W. Wenzhen, “Modeling and Technology
Application for Transmission Line Fault,” in 2018 2nd IEEE Conference on Energy Internet and Energy System
Integration (EI2), Beijing, China: IEEE, Oct. 2018, pp. 1–5. https://doi.org/10.1109/EI2.2018.8582187.
10. A. Reda, I. Al Kurdi, Z. Noun, A. Koubyssi, M. Arnaout, and R. Rammal, “Online Detection of Faults in
Transmission Lines,” in 2021 IEEE 3rd International Multidisciplinary Conference on Engineering Technology
(IMCET), Beirut, Lebanon: IEEE, Dec. 2021, pp. 37–42. https://doi.org/10.1109/IMCET53404.2021.9665620.
11. K. Nandhini and C. A. Prajith, “Review on Fault Detection and Classification in Transmission Line using
Machine Learning Methods,” in 2023 International Conference on Control, Communication and Computing
(ICCC), Thiruvananthapuram, India: IEEE, May 2023, pp. 1–6.
https://doi.org/10.1109/ICCC57789.2023.10164876.
12. T. S. Kumar et al., “Deep Learning based Fault Detection in Power Transmission Lines,” in 2022 4th
International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India: IEEE,
Sep. 2022, pp. 861–867. https://doi.org/10.1109/ICIRCA54612.2022.9985700.
13. B. J. Mampilly and S. V. S, “Transmission Lines Fault Detection using Empirical Mode Decomposition in a
Grid-Connected Power System,” in 2020 International Conference on Power Electronics and Renewable Energy
Applications (PEREA), Kannur, India: IEEE, Nov. 2020, pp. 1–6.
https://doi.org/10.1109/PEREA51218.2020.9339814.
14. C. Zhuang, S. Xie, H. Yang, H. Yu, Y. Geng, and R. Zeng, “Flexible Noncontact Approach for Fault Location
of Transmission Lines Using Electro-Optic Field Sensors,” IEEE Trans. Electromagn. Compat., vol. 63, no. 6,
pp. 2151–2158, Dec. 2021. https://doi.org/10.1109/TEMC.2021.3108938.
15. H. Fasihipour and S. Seyedtabaii, “Fault detection and faulty phase(s) identification in TCSC compensated
transmission lines,” IET Generation, Transmission & Distribution, vol. 14, no. 6, pp. 1042–1050, Mar. 2020.
https://doi.org/10.1049/iet-gtd.2019.1019.
16. A. Abu-Siada and S. Mir, “A new on-line technique to identify fault location within long transmission
lines,” Engineering Failure Analysis, vol. 105, pp. 52–64, Nov. 2019.
https://doi.org/10.1016/j.engfailanal.2019.06.071.
17. B. R. Kumar, A. Mohapatra, S. Chakrabarti, and A. Kumar, “Phase angle-based fault detection and
classification for protection of transmission lines,” International Journal of Electrical Power & Energy Systems,
vol. 133, p. 107258, Dec. 2021. https://doi.org/10.1016/j.ijepes.2021.107258.
18. S. K. Mishra and L. N. Tripathy, “A critical fault detection analysis & fault time in a UPFC transmission
line,” Prot Control Mod Power Syst, vol. 4, no. 1, p. 3, Dec. 2019. https://doi.org/10.1186/s41601-019-0117-5.
19. “Fault detection through discrete wavelet transform in overhead power transmission lines - Ahmed - 2023
- Energy Science & Engineering - Wiley Online Library.” Accessed: May 08, 2024. [Online]. Available:
https://onlinelibrary.wiley.com/doi/full/10.1002/ese3.1573
20. E. Aker, M. L. Othman, V. Veerasamy, I. bin Aris, N. I. A. Wahab, and H. Hizam, “Fault Detection and
Classification of Shunt Compensated Transmission Line Using Discrete Wavelet Transform and Naive
Bayes Classifier,” Energies, vol. 13, no. 1, Art. no. 1, Jan. 2020. https://doi.org/10.3390/en13010243.
21. V. Ashok, A. Yadav, and A. Y. Abdelaziz, “MODWT-based fault detection and classification scheme for
cross-country and evolving faults,” Electric Power Systems Research, vol. 175, p. 105897, Oct. 2019.
https://doi.org/10.1016/j.epsr.2019.105897.
22. U. Saleem, U. Arshad, B. Masood, T. Gul, W. A. Khan, and M. Ellahi, “Faults detection and classification of
HVDC transmission lines of using discrete wavelet transform,” in 2018 International Conference on
Engineering and Emerging Technologies (ICEET), Lahore, Pakistan: IEEE, Feb. 2018, pp. 1–6.
https://doi.org/10.1109/ICEET1.2018.8338615.
23. A. Q. Khan, Q. Ullah, M. Sarwar, S. T. Gul, and N. Iqbal, “Transmission Line Fault Detection and
Identification in an Interconnected Power Network using Phasor Measurement Units,” IFAC-PapersOnLine,
vol. 51, no. 24, pp. 1356–1363, Jan. 2018. https://doi.org/10.1016/j.ifacol.2018.09.558.
24. S. Belagoune, N. Bali, A. Bakdi, B. Baadji, and K. Atif, “Deep learning through LSTM classification and
regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power
systems,” Measurement, vol. 177, p. 109330, Jun. 2021. https://doi.org/10.1016/j.measurement.2021.109330.
Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 12 May 2024 doi:10.20944/preprints202405.0662.v2

22

25. S. R. Fahim, S. K. Sarker, S. M. Muyeen, S. K. Das, and I. Kamwa, “A deep learning based intelligent
approach in detection and classification of transmission line faults,” International Journal of Electrical Power
& Energy Systems, vol. 133, p. 107102, Dec. 2021. https://doi.org/10.1016/j.ijepes.2021.107102.
26. S. R. Fahim, Y. Sarker, S. K. Sarker, Md. R. I. Sheikh, and S. K. Das, “Self attention convolutional neural
network with time series imaging based feature extraction for transmission line fault detection and
classification,” Electric Power Systems Research, vol. 187, p. 106437, Oct. 2020.
https://doi.org/10.1016/j.epsr.2020.106437.
27. F. Rafique, L. Fu, and R. Mai, “End to end machine learning for fault detection and classification in power
transmission lines,” Electric Power Systems Research, vol. 199, p. 107430, Oct. 2021.
https://doi.org/10.1016/j.epsr.2021.107430.
28. H. Tong, R. C. Qiu, D. Zhang, H. Yang, Q. Ding, and X. Shi, “Detection and classification of transmission
line transient faults based on graph convolutional neural network,” CSEE Journal of Power and Energy
Systems, vol. 7, no. 3, pp. 456–471, May 2021. https://doi.org/10.17775/CSEEJPES.2020.04970.
29. “Transmission Line Fault Classification Using Hidden Markov Models | IEEE Journals & Magazine | IEEE
Xplore.” Accessed: May 08, 2024. [Online]. Available:
https://ieeexplore.ieee.org/abstract/document/8795474
30. “High Impedance Single-Phase Faults Diagnosis in Transmission Lines via Deep Reinforcement Learning
of Transfer Functions | IEEE Journals & Magazine | IEEE Xplore.” Accessed: May 08, 2024. [Online].
Available: https://ieeexplore.ieee.org/abstract/document/9328357
31. “Detection and Evaluation Method of Transmission Line Defects Based on Deep Learning | IEEE Journals
& Magazine | IEEE Xplore.” Accessed: May 09, 2024. [Online]. Available:
https://ieeexplore.ieee.org/abstract/document/9001041
32. M. Farshad, “Detection and classification of internal faults in bipolar HVDC transmission lines based on
K-means data description method,” International Journal of Electrical Power & Energy Systems, vol. 104, pp.
615–625, Jan. 2019. https://doi.org/10.1016/j.ijepes.2018.07.044.
33. O. N. Teja, M. S. Ramakrishna, G. B. Bhavana, and K. Sireesha, “Fault Detection and Classification in Power
Transmission Lines using Back Propagation Neural Networks,” in 2020 International Conference on Smart
Electronics and Communication (ICOSEC), Sep. 2020, pp. 1150–1156.
https://doi.org/10.1109/ICOSEC49089.2020.9215253.
34. X. Zheng, R. Jia, Aisikaer, L. Gong, G. Zhang, and J. Dang, “Component identification and defect detection
in transmission lines based on deep learning,” IFS, vol. 40, no. 2, pp. 3147–3158, Feb. 2021.
https://doi.org/10.3233/JIFS-189353.
35. S. Kanwal and S. Jiriwibhakorn, “Advanced Fault Detection, Classification, and Localization in
Transmission Lines: A Comparative Study of ANFIS, Neural Networks, and Hybrid Methods,” IEEE
Access, vol. 12, pp. 49017–49033, 2024. https://doi.org/10.1109/ACCESS.2024.3384761.
36. R.-A. Tirnovan and M. Cristea, “Advanced techniques for fault detection and classification in electrical
power transmission systems: An overview,” in 2019 8th International Conference on Modern Power Systems
(MPS), Cluj Napoca, Romania: IEEE, May 2019, pp. 1–10. https://doi.org/10.1109/MPS.2019.8759695.
37. K. Swain, S. Mandal, S. s Mahato, and M. Cherukuri, “A Brief Review on Fault Detection, Classification
and Location on Transmission Lines Using PMUs,” vol. 8, pp. 2608–2618, Dec. 2018.

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those
of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s)
disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or
products referred to in the content.