ISSN 2087-3336 (Print) | 2721-4729 (Online)

TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika

Vol. 12, No. 1, 2025, page. 133-144
http://jurnal.sttmcileungsi.ac.id/index.php/tekno
DOI: 10.37373

Implementation of predictive maintenance in various Industry: A Review

Tito Lukito*, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
*Department of Industrial Engineering, Universitas Mercu Buana, Jl. Meruya Selatan No. 1 Kembangan, Jakarta
11650, Indonesia
* [email protected]

Submitted: 19/07/2024 Revised: 13/08/2024 Accepted: 23/08/2024

ABSTRACT
Predictive maintenance has become a crucial approach in the manufacturing industry, offering solutions to
minimize downtime, optimize maintenance costs, and enhance operational efficiency. This paper reviews the
definition, objectives, benefits, and implementation of predictive maintenance in the manufacturing sector. By
leveraging advanced technologies such as the Internet of Things (IoT), machine learning, big data analytics, and
cloud computing, predictive maintenance enables real-time monitoring of equipment conditions and failure
prediction before they occur. The objectives are to reduce operational costs, increase equipment reliability, and
optimize production performance. The benefits include reduced frequency and duration of downtime, lower
repair costs, extended equipment lifespan, and improved workplace safety. Case studies discussed show that
companies adopting this technology experience increased production efficiency and reduced maintenance costs.
The conclusion of this paper suggests that companies invest in technology and infrastructure, develop employee
skills, integrate systems, collaborate with technology providers, and conduct continuous monitoring and
evaluation. With these steps, companies can more effectively implement predictive maintenance and achieve
competitive advantages in an increasingly dynamic market.
Keywords: Predictive maintenance; manufacturing industry; Internet of things

1. INTRODUCTION
In the era of Industry 4.0, technology plays an increasingly important role in improving efficiency
and productivity in the manufacturing sector [1], [2]. One of the emerging technologies is predictive
maintenance. Predictive maintenance uses data analysis, sensors, and artificial intelligence algorithms
to predict equipment failures before they occur, enabling timely repairs and reducing downtime. This
contributes to cost savings and increased operational reliability. Thus, understanding the definition,
purpose, benefits, and application of predictive maintenance becomes very crucial in the context of the
modern manufacturing industry [3]–[6]. As the complexity of manufacturing equipment increases and
the pressure to improve operational efficiency increases, traditional maintenance methods such as
preventive maintenance and reactive maintenance are beginning to show their limitations. Preventive
maintenance is often carried out based on a predetermined schedule, without considering the actual
condition of the equipment. This can result in over-maintenance, which wastes resources, or under-
maintenance, which increases the risk of equipment failure. On the other hand, reactive maintenance
performed after equipment failure can lead to unexpected downtime and significant loss in production.
Therefore, there is an urgent need for a more efficient and proactive approach to maintenance, which
can be filled by predictive maintenance [7]–[9].
In the literature, there have been many studies discussing predictive maintenance, but many of
them focus on technical aspects, such as algorithm development and sensor technology. Studies that
discuss practical implementation and challenges in the field are still relatively few. In addition, there is
a gap in the literature regarding the evaluation of the economic and environmental benefits of
TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika is licensed under a Creative
Commons Attribution-NonCommercial 4.0 International License. ISSN 2087-3336
(Print) | 2721-4729 (Online)
 134 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

predictive maintenance, as well as how this technology can be effectively integrated into a broader
maintenance strategy.
This article aims to fill this gap by conducting a comprehensive literature review using the
PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) method. PRISMA is
a structured and transparent method for conducting literature reviews, which allows for the systematic
identification, screening, and synthesis of relevant research results. Using the PRISMA method, this
article will review various existing studies to understand the definition, objectives, benefits, and
application of predictive maintenance in the manufacturing industry, as well as identify future
challenges and opportunities. The novelty of this article lies in the systematic and comprehensive
approach used to study predictive maintenance, which focuses not only on technical aspects but also
on practical implementation aspects and comprehensive benefit evaluation. Thus, this article is
expected to provide a significant contribution to improving the understanding and application of
predictive maintenance in the manufacturing industry, as well as encouraging further research in this
field.
2. METHOD
This study used the PRISMA (preferred reporting items for systematic reviews and meta-analyses)
method to conduct a systematic literature review on the definition, purpose, benefits, and application
of predictive maintenance in the manufacturing industry. PRISMA is a guideline designed to assist
researchers in reporting systematic reviews and meta-analyses transparently and completely. This
method consists of several main stages, namely identification, screening, eligibility, and inclusion,
each of which is designed to ensure that the review process is carried out thoroughly and objectively.
Figure 1 the first stage in the PRISMA method is the identification stage. At this stage, researchers
search for and collect relevant literature from various sources, including academic databases such as
Scopus, PubMed, IEEE Xplore, and Google Scholar. Keywords used in the search include "predictive
maintenance," "industrial maintenance," "machine learning," "sensor technology," and "manufacturing
industry." The search was conducted without restrictions on the year of publication to ensure a broad
coverage of available research. All studies identified during this search were recorded, including
studies published in languages other than English, to ensure comprehensive inclusion.
After the identification stage, a screening stage was conducted to eliminate studies that were not
relevant or did not meet the inclusion criteria. At this stage, the title and abstract of each identified
study were read and evaluated to determine its relevance to the research topic. Studies that were not
directly related to predictive maintenance in the context of the manufacturing industry or that did not
provide sufficient empirical data were excluded from the list. In addition, duplicate studies were also
removed at this stage. The screening process was conducted by two independent researchers to
minimize bias and ensure consistency.

Figure 1. PRISMA flow that has been carried out

 ISSN 2087-3336 (Print) | 2721-4729 (Online) 135
DOI 10.37373/tekno.v12i1.1338

The next stage is the eligibility stage, where the full text of the studies that passed the screening
was read and further evaluated. Eligibility criteria included clarity of the study methodology,
appropriateness to the topic, and the quality and credibility of the data presented. Studies that did not
meet these criteria were excluded from further analysis. At this stage, researchers also evaluated the
potential risk of bias in the reviewed studies, including publication bias and selection bias. The risk of
bias assessment was carried out using validated assessment tools, such as the Cochrane risk of bias
assessment tool.
The final stage in the PRISMA method is the inclusion stage, where studies that passed the
eligibility stage were included in the final analysis. Data from the selected studies were extracted and
qualitatively synthesized to provide a comprehensive picture of predictive maintenance in the
manufacturing industry. The extracted data included information on the definition and concept of
predictive maintenance, the methods and technologies used, the purpose of the implementation, the
benefits obtained, and the challenges and barriers faced. The data extraction process was carried out
using a standardized data extraction form to ensure the consistency and accuracy of the data collected.
In the data synthesis stage, researchers organized and categorized the findings from the selected
studies based on key themes relevant to the research topic. Qualitative analysis was conducted to
identify patterns, trends, and gaps in the existing literature. The researcher also compared findings
from different studies to identify consistencies or contradictions in the research results. This was done
to provide a deeper understanding of predictive maintenance and to identify areas that require further
research.
3. RESULT AND DISCUSSION
In the literature review conducted, various studies were found that provide an in-depth
understanding of predictive maintenance in the manufacturing industry. The results of this review
reveal that predictive maintenance is an approach that can significantly improve operational efficiency
and reduce machine downtime. The studies identified cover various aspects of predictive maintenance,
from basic definitions and concepts, the technology used, to the benefits and challenges faced in its
implementation. Through systematic analysis, these findings not only highlight the great potential of
predictive maintenance but also identify research gaps that need to be followed up. In detail, the
following are the results of a review of 30 journal articles from 2013 to 2024 that have been selected
using the PRISMA method. Table 1 explains the summary of research results related to the application
of predictive maintenance. Table 1 analyzes the objectives of each study. The research results are also
presented according to the context of the article content. Most of the research results provide positive
changes. Details can be seen in Table 1
Table 1. Summary of relevant articles
No. Identity Objective Research result
1 Zonta, T., Da This research aims to conduct a systematic This research concludes that the ability to predict
Costa, C.A., da literature review regarding predictive future asset maintenance needs is one of the main
Rosa Righi, R., maintenance (PdM) initiatives in the context of challenges in Industry 4.0. PdM contributes to
de Lima, M.J., Industry 4.0. The primary goal is to identify and increased machine downtime, cost control, and
da Trindade, catalog PdM methods, standards, and production quality. This study also found that a
E.S., & Li, applications, as well as discuss current time-based approach is a major challenge in PdM.
G.P. (2020). challenges and limitations in PdM. In addition, The proposed new taxonomy helps in classifying
[10] this study proposes a new taxonomy to classify research in this area, demonstrating the importance
PdM research areas, taking into account the of a multidisciplinary approach that combines
needs of Industry 4.0. computer science and engineering to effectively
address the challenges of Industry 4.0.
2 Carvalho, T.P., This research aims to present a systematic This research finds that ML techniques have
Soares, F.A., literature review regarding machine learning become a promising tool in PdM applications to
Vita, R., (ML) methods applied to predictive maintenance prevent equipment failures in production lines.
Francisco, (PdM). The main focus of this research is to This study shows that selecting the right ML
R.D.P., Basto, demonstrate the ML techniques explored in this method is critical for the performance of PdM
J.P., & Alcalá, field, as well as the performance of current ML applications. The results of this review provide a
S.G. (2019). techniques in PdM applications. This study also useful foundation on for ML techniques, key
[11] identifies challenges and opportunities in using results, challenges, and existing opportunities, and
ML for PdM. support new research in the field of PdM.
3 Paolanti, M., This research aims to develop a machine This research shows that the Random Forest
Romeo, L., learning (ML) architecture for predictive approach has good performance in predicting
Felicetti, A., maintenance, with a special focus on the use of various machine states with high accuracy. Data is
 136 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

No. Identity Objective Research result

Mancini, A., the Random Forest method. The system was collected from various sensors, machine PLCs, and
Frontoni, E., & tested on real industrial examples, involving data communication protocols, which is then analyzed
Loncarski, J. collection, data system analysis, application of using data analysis tools in the Azure Cloud
(2018, July). ML approaches, and comparison with simulation platform. Preliminary results show that this
[12] tool analysis. approach is effective in improving system
reliability and reducing economic losses due to
unexpected machine failures.
4 Selcuk, S. This research aims to discuss the latest trends This research finds that predictive maintenance has
(2017) [13] and techniques in the field of predictive been adopted by various manufacturing and service
maintenance, as well as provide suggestions on industry sectors to increase operational reliability
how to implement a predictive maintenance and efficiency. Predictive maintenance techniques
program in a factory or facility. The primary that are closely related to sensor technology show
focus is to improve reliability, safety, increased efficiency, wider application, and more
availability, efficiency, and quality, as well as affordable costs. This research also highlights that
protect the environment through a more advances in information, communications, and
proactive maintenance approach. computing technology, such as the Internet of
Things and radio frequency identification, have
enabled predictive maintenance applications to
become more efficient and common across a
variety of industries.
5 Wang, J., This research aims to investigate a new paradigm This research develops a cloud-based sensing and
Zhang, L., of cloud-based predictive maintenance using computing node with an embedded Linux
Duan, L., & mobile agents to enable the timely acquisition, operating system, mobile agent middleware, and
Gao, R.X. sharing, and utilization of information. The main open-source numerical libraries. The proposed
(2017) [14] goal is to improve accuracy and reliability in mobile agent approach increases system flexibility
fault diagnosis, remaining service life prediction, and adaptability, reduces raw data transmission,
and maintenance scheduling. and responds to dynamic changes in operations and
tasks instantly. This new paradigm was validated
on a motor test system, demonstrating increased
accuracy and reliability in cloud-based predictive
maintenance.
6 Lee, J., Ni, J., This research aims to provide a comprehensive This research found that intelligent maintenance
Singh, J., Jiang, overview of the latest efforts and advances in systems play an important role in minimizing
B., Azamfar, maintenance methods in the manufacturing unplanned downtime, ensuring product quality,
M., & Feng, J. industry over the past few decades. This research reducing customer dissatisfaction, and maintaining
(2020). [15] focuses on the importance of intelligent a competitive advantage in the market. Intelligent
maintenance systems (IMS) which are designed prognostic and health management tools are critical
to provide decision support tools to optimize to identifying effective, reliable, and cost-effective
maintenance operations. This research also maintenance strategies. The results of this review
identifies existing research challenges and show that despite significant progress, there are
directs future research in this area. still major challenges to be overcome, such as the
integration of new technologies and improving
prediction accuracy.
7 Pech, M., This research aims to review the latest literature The research results show an increase in the
Vrchota, J., & related to predictive maintenance and smart number of papers related to the main concepts
Bednář, J. sensors in smart factories. The main focus of this studied, indicating the importance of predictive
(2021). [16] research is on contemporary trends and future maintenance continues to grow along with Industry
challenges in the application of intelligent 4.0 technology. This research proposes Smart and
sensors for predictive maintenance. This research Intelligent Predictive Maintenance (SIPM) based
uses burst analysis, systematic review, keyword on full-text analysis of relevant papers. The main
co-occurrence analysis, and cluster analysis to contribution of this research is a summary and
provide a comprehensive overview of current overview of current trends in the use of smart
trends and classifications in this field. sensors for predictive maintenance in smart
factories, which provides important guidance for
future research in this area.
8 Ayvaz, S., & This research aims to develop a data-based The system successfully identified potential failure
Alpay, K. predictive maintenance system for production indicators and prevented several production
(2021) [17] lines in the manufacturing sector. This system outages. Comparative evaluation of machine
uses real-time data from IoT sensors to detect learning algorithms shows that Random Forest and
potential failures before they occur, by utilizing XGBoost models, which are bagging and boosting
machine learning methods. methods, provide the best performance in this
study. These models have been integrated into the
production system at the factory.
9 Li, Z., Wang, This research aims to investigate the diagnosis This system framework consists of five modules:
 ISSN 2087-3336 (Print) | 2721-4729 (Online) 137
DOI 10.37373/tekno.v12i1.1338

No. Identity Objective Research result

Y., & Wang, and prognosis of faults in machining centers sensor data selection and acquisition, data
K.S. (2017). using a data mining approach in the context of preprocessing, data mining, decision support, and
[14] Industry 4.0. This research introduces a system maintenance implementation. The presented case
framework based on the Industry 4.0 concept for study shows the application of data mining
predictive maintenance in machine centers. methods for fault diagnosis and prognosis in an
Industry 4.0 scenario.
10 Dalzochio, J., This research aims to investigate academic This research identifies challenges related to big
Kunst, R., advances in failure prediction and predictive data such as scalability, latency, and data security.
Pignaton, E., maintenance in the context of Industry 4.0. The Although predictive maintenance is a rapidly
Binotto, A., focus of this research is on the use of machine growing topic in Industry 4.0, this research
Sanyal, S., learning and reasoning, as well as the challenges concludes that there are still many challenges that
Favilla, J., & in implementing them. need to be overcome for more effective
Barbosa, J. implementation and use of machine learning and
(2020) [18] reasoning.
11 Yu, W., Dillon, This research aims to introduce a global big data This research develops an architecture that
T., Mostafa, F., ecosystem for error detection and diagnosis in addresses various challenges such as big data
Rahayu, W., & predictive maintenance using large-scale ingestion, integration, transformation, storage,
Liu, Y. (2019) industrial data collected directly from global analysis, and real-time visualization using various
[19] manufacturing plants. technologies such as data lakes, NoSQL databases,
Apache Spark, Apache Drill, and Apache Hive.
The system was successfully implemented in a real
industrial production environment, providing
warnings days before an error occurred.
12 Sezer, E., This research aims to develop a predictive This research produces a cheap and easy-to-
Romero, D., maintenance architecture based on low-cost develop CPS architecture, which stores data in the
Guedea, F., principles so that it can be accessed by Small and cloud and uses Recursive Partitioning and
Macchi, M., & Medium Enterprises (SMEs). This research Regression Tree models to predict machine output
Emmanouilidis, focuses on the use of cyber-physical systems quality based on temperature and vibration data.
C. (2018) [20] (CPS) to monitor temperature and vibration Experimental results show promising prediction
variables in machining processes. accuracy in determining the quality of machine
output.
13 Yan, J., Meng, This research aims to explore industrial big data The proposed framework includes organizing
Y., Lu, L., & processing for predictive maintenance in the heterogeneous multi-source information,
Li, L. (2017). context of Industry 4.0. This research proposes a characterization of structured data considering
new framework for processing heterogeneous spatiotemporal properties, and modeling of unseen
multi-source information. factors. The effectiveness of this scheme is verified
through analysis of multisource industrial data for
prediction of the remaining life of key components
of machine tools, demonstrating improved system
reliability.
14 Sajid, S., This research aims to explore the application of This research identifies five critical processes for
Haleem, A., data science techniques in predictive data scientists in predictive maintenance through a
Bahl, S., maintenance and materials science in the context literature review. Data science uses scientific
Javaid, M., of Industry 4.0. With the increasing complexity methods and algorithms to extract knowledge from
Goyal, T., & of machines and massive data production, this industrial big data, which can improve the
Mittal, M. research focuses on using data science to identify efficiency and reliability of manufacturing systems,
(2021) [21] the causes of failures and quality deviations, as as well as predict material quality, reducing costs
well as discovering new elements with desired and production time.
properties through materials theory and
computational skills.
15 Compare, M., This research aims to identify and analyze the This research identifies various challenges in the
Baraldi, P., & main challenges in implementing predictive development and implementation of IoT-based
Zio, E. (2019) maintenance (PdM) supported by IoT in the PdM, including the integration of IoT technology
[22] context of Industry 4.0. The focus is on the IoT with data science capabilities to support optimal
infrastructure and data management required to decision-making. This article presents a
support PdM as well as challenges in PHM comprehensive view of the strengths, limitations,
(prognostics and health management) challenges, and opportunities of IoT-based PdM.
algorithms.
16 Kanawaday, This research aims to explore the use of machine This research shows that the ARIMA model can be
A., & Sane, A. learning, specifically the AutoRegressive used to predict failures and quality defects based
(2017) [23] Integrated Moving Average (ARIMA) model, in on time series data from machine sensors. The
predictive maintenance for industrial machines application of machine learning in IIoT is proving
using IoT sensor data. The focus is on applying vital for quality management and quality control,
analytics to machine sensor data to predict reducing maintenance costs, and improving overall
 138 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

No. Identity Objective Research result

quality failures and defects. manufacturing processes.
17 Kiangala, K.S., This research aims to design an experimental This research succeeded in developing a system
& Wang, Z. method for integrating Industry 4.0 concepts into that monitors motor vibration speed data through
(2018) [8] predictive maintenance for conveyor motors in vibration sensors, using a Siemens S7-1200
small bottling plants. The focus is on the early programmable logic controller (PLC). The system
detection of faults or threats to conveyor motors generates efficient predictive maintenance plans
and the creation of predictive maintenance and enables decentralized monitoring and instant
schedules. notification via email to maintenance supervisors.
18 Kamat, P., & This research aims to describe the challenges in This research highlights the importance of anomaly
Sugandhi, R. traditional anomaly detection strategies and detection in PdM and how deep learning
(2020) [24] proposes a new deep learning technique to techniques can improve the early detection of
predict abnormalities before machine failure in anomalies, enabling manufacturing supervisors to
the context of predictive maintenance. perform timely maintenance activities. The
proposed technique successfully identifies
anomalies earlier than traditional methods.
19 Zhang, W., This research aims to present a comprehensive This research identifies that most of the data used
Yang, D., & survey of data-driven methods for predictive comes from public datasets and shows a trend of
Wang, H. maintenance (PdM) and their industrial increasing use of deep learning algorithms in PdM
(2019) [25] applications, with a focus on machine learning research. This research also analyzes the accuracy
and deep learning algorithms and performance of various PdM applications, identifies the
metrics analysis. challenges faced, and guides further developments
in data-driven PdM.
20 Ruiz- This research aims to develop a Bayesian Filter- The proposed predictive model successfully
Sarmiento, based predictive model to estimate the state of combines expert knowledge with real-time data
J.R., Monroy, machine degradation in the Hot Rolling process from the Hot Rolling process, enabling operators to
J., Moreno, in the stainless-steel industry. This project is part make more informed maintenance decisions. The
F.A., Galindo, of the innovative SiMoDiM project which model has been tested with data from more than
C., Bonelo, focuses on the integration of predictive 118 thousand processes in real factories, and has
J.M., & maintenance systems to improve the proven to be effective in promoting the Industry
Gonzalez- maintenance of critical assets in factories. 4.0 era by improving machine health assessment
Jimenez, J. and predictive maintenance operations.
(2020) [26]
21 Susto, G.A., This research aims to develop a machine The proposed methodology uses classification
Schirru, A., learning-based predictive maintenance modules with varying prediction horizons to
Pampuri, S., methodology that uses a dual classifier approach provide a performance tradeoff in terms of
McLoone, S., to minimize downtime and associated costs in unexpected disruption frequency and unexploited
& Beghi, A. maintenance management. The main objective is lifetime. The resulting operational cost-based
(2014) [27] to generate quantitative health factors and maintenance decision system succeeded in
determine their relationship with operational minimizing expected costs. The effectiveness of
costs and failure risk. this method is demonstrated through simulation
examples and maintenance problems in the
semiconductor industry.
22 Schmidt, B., & This research aims to improve predictive The proposed framework and initial methodology
Wang, L. condition-based maintenance decision making have been tested through case studies aimed at
(2018). [28] with a cloud-based approach. The primary focus validating its work in the context of real industrial
is identifying and tracking condition-related data applications. The cloud-based approach enables the
as well as context data for better utilization of collection and analysis of maintenance, production,
condition monitoring data and machine and plant data from the initial phase through the
population-based analysis. operations and maintenance phases, increasing the
efficiency and precision of maintenance decision-
making.
23 Ran, Y., Zhou, This paper aims to provide a comprehensive This research identifies PdM system architectures,
X., Lin, P., review of the latest maintenance techniques, such as PdM 4.0 and Open System Architecture for
Wen, Y., & especially Predictive Maintenance (PdM), with Condition-Based Monitoring (OSA-CBM), as well
Deng, R. emphasis on system architecture, optimization as cloud-based approaches. This research also
(2019) [29] objectives, and optimization methods. This reviews key optimization objectives, such as cost
research aims to evaluate existing maintenance minimization and availability/reliability
techniques and highlight the need for a new maximization. Optimization methods including
maintenance paradigm in the fourth industrial traditional machine learning and deep learning are
revolution. discussed in detail, indicating future research
directions needed to support the application of DL-
based PdM techniques.
24 He, Y., Gu, C., This research aims to develop an integrated The proposed integrated PdM strategy combining
Chen, Z., & predictive maintenance strategy that considers quality control and mission reliability analysis
 ISSN 2087-3336 (Print) | 2721-4729 (Online) 139
DOI 10.37373/tekno.v12i1.1338

No. Identity Objective Research result

Han, X. (2017) the product quality level and mission reliability successfully minimizes total costs and increases
[30] state in the intelligent manufacturing philosophy maintenance effectiveness. A case study on a
of 'prediction and manufacturing'. The main cylinder head manufacturing system shows that
focus is to integrate key process variables in the this method achieves a cost increase of
evaluation of the equipment degradation state approximately 26.02% compared to periodic
and analyze mission reliability to characterize preventive maintenance and 20.54% compared to
the production state of the equipment. conventional condition-based maintenance.
25 Sakib, N., & This research aims to provide an overview of This review identifies challenges in predicting tool
Wuest, T. condition-based predictive maintenance damage and degradation, especially in unexpected
(2018)[31] solutions aimed at avoiding unexpected and situations such as shock damage. This research
unplanned failures during manufacturing and shows that historical data analysis, modeling,
operational processes. The primary focus is simulation, and failure probability play an
discussing the challenges and opportunities of important role in the development of condition-
condition-based predictive maintenance and based predictive maintenance solutions. Challenges
concluding a summary of future research. faced include data availability, accurate data
analysis, and development of more effective
prediction methods.
26 Theissler, A., This research aims to review and categorize This research identifies that the availability of
Pérez- research on machine learning-based predictive public data will increase research activity and that
Velázquez, J., maintenance in the automotive industry. The most research relies on supervision methods that
Kettelgerdes, main focus is to make the field more accessible require labeled data. Using multiple data sources
M., & Elger, G. to maintenance or machine learning experts, as can improve prediction accuracy. Although deep
(2021) [32] well as to identify challenges and future research learning methods will continue to improve, they
directions. require efficient and interpretable methods and the
availability of large amounts of data.
27 Ruiz- This research aims to develop a Bayesian Filter- This predictive model was evaluated using data
Sarmiento, based predictive model to predict machine from more than 118 thousand processes in real
J.R., Monroy, degradation in the stainless-steel industry, factories. The results show that the model is
J., Moreno, especially in the Hot Rolling process. The model effective in predicting machine degradation,
F.A., Galindo, is designed to combine expert knowledge and enabling operators to carry out more timely and
C., Bonelo, real-time data from the plant to help operators data-driven maintenance interventions, and
J.M., & make more informed maintenance decisions. encouraging the adoption of the Industry 4.0
Gonzalez- paradigm in the manufacturing sector.
Jimenez, J.
(2020) [26]
28 Susto, G. A., This research aims to develop a machine The methodology is tested using simulated
Schirru, A., learning-based predictive methodology using examples and maintenance problems in the
Pampuri, S., various classification modules for predictive semiconductor industry. The results show that this
McLoone, S., maintenance. The main goal is to adopt dynamic approach can predict maintenance more
& Beghi, A. decision rules in maintenance management to effectively, reduce the frequency of unexpected
(2014) [27] minimize operational costs and failure risks. breakdowns, and maximize system lifetime by
minimizing expected costs.
29 Schmidt, B., & This research aims to improve condition-based The proposed approach is tested through real
Wang, L. maintenance decision-making through a cloud- industrial case studies. The results show that
(2018) [28] based approach by utilizing condition monitoring leveraging cloud-based data and more
data and contextual data to improve data comprehensive data analysis can improve the
analysis. reliability of machine condition predictions, as well
as provide more accurate and data-based
maintenance guidance.
30 Aivaliotis, P., This research aims to calculate the remaining The proposed methodology is tested through a case
Georgoulias, service life (RUL) of machine tools using study of RUL prediction of industrial robots. The
K., & physics-based simulation models and the Digital results show that physics model-based simulations
Chryssolouris, Twin concept to enable predictive maintenance can provide accurate predictions of machine
G. (2019) [33] in manufacturing environments. conditions, enabling better monitoring and
predictions without using invasive techniques.

Based on the analysis of the 30 journal articles that have been discussed, we can classify the types
of topics into several main categories that cover various important aspects in the development and
implementation of predictive and intelligent maintenance systems. The following is a detailed
description of the classification of the types of topics along with examples of articles in each category:
A. System architecture and framework:
 140 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

The discussion of system architecture and frameworks in these articles generally emphasizes the
design and the development of systems that support predictive maintenance by utilizing modern
technologies such as the Internet of Things (IoT), cloud computing, and advanced data analytics. The
main focus of this category is to create a system that can collect, process, and analyze data from
machines in real-time to detect and prevent failures before they occur [27], [28], [31], [32].
B. Predictive techniques and algorithms:
Articles in this category focus on the development and testing of various techniques and algorithms for
predictive maintenance. These techniques include the use of machine learning, deep learning, time
series analysis, and image processing techniques to predict machine failures. The main goal is to
improve the accuracy and reliability of failure predictions, thereby reducing downtime and
maintenance costs [14],[19] .
C. Applications in specific industries
Many articles discuss the application of predictive maintenance in the context of specific industries.
These industries include aviation, manufacturing, automotive, and others. These articles often present
case studies or practical implementations to demonstrate the effectiveness of their approach in real-
world industrial settings [20].
D. Predictive models and data analysis
This category includes articles that discuss specific predictive models and data analysis techniques
used to detect and predict machine failures. Commonly used techniques include regression, artificial
neural networks, probabilistic models, and clustering algorithms. These articles aim to develop models
that are capable of providing accurate predictions of machine conditions based on historical and real-
time data.
E. Challenges and Opportunities in Implementation
Articles in this category discuss the challenges and opportunities associated with implementing
predictive and intelligent maintenance in the industry. These challenges include technical issues, data
limitations, the need for system integration, and changes in management and organizational culture.
These articles also often propose solutions to overcome these challenges and capitalize on the
opportunities [10], [13], [14], [16].
Figure 2 classifying these articles into these categories, we can gain a deeper understanding of the
various approaches and perspectives taken by researchers in the field of predictive and intelligent
maintenance. Each category offers unique insights into how new technologies and methodologies can
be applied to improve maintenance efficiency and effectiveness, reduce downtime, and increase
machine life. It also helps identify areas that require further research and technological innovation to
address existing challenges and capitalize on opportunities available in the development of predictive
and intelligent maintenance systems.
Number of Articles

6 6 6 6

2 2
0 0 0 0 1

2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024
Publication Year

Figure 2. Number of articles by publication year

 ISSN 2087-3336 (Print) | 2721-4729 (Online) 141
DOI 10.37373/tekno.v12i1.1338

The distribution data of selected articles shows an interesting trend related to research in the field
of predictive maintenance in the manufacturing industry. It can be seen that there are no selected
articles from 2013, 2015, and 2016, which may indicate a lack of relevant publications or an increase
in the quality of literature selection in those years. The peak number of articles occurred from 2017 to
2020, with each year having 6 articles. This could reflect an intensive period of research and
development in this field, along with the increasing adoption of Industry 4.0 technology and the
urgency of predictive maintenance. In 2021, the number of selected articles decreased slightly to 4
articles, 2023 and 2024 respectively as many as 2 and 1 article, this may indicate a shift in research
focus or the stabilization of innovation in this area. The years after 2021 show that there are selected
articles but the number tends to decrease which may indicate a significant amount of new research in
predictive maintenance or that the latest articles have not been published at the time of data collection.
Figure 3 This distribution helps identify active periods in predictive maintenance research and can
serve as a reference for researchers in evaluating developments and trends in this field.
Logistic and
Transportation Textile Industry
Industry 13%
10%
Health Care
Industry
7%
General
Manufacture
Factory and
Industry
Process
17%
Industries
13%

Oil and Gas Automotive

Industry Industry
10% 10%
Aviation
Energy and Utilities Industry Industry
13% 7%
Figure 3. Distribution of industry types discussed in the article
The data presentation above shows that research on predictive maintenance is spread across various
industrial sectors, with a fairly even focus. However, there is a higher concentration in the general
manufacturing industry, energy and utilities, and the plant and process industry. This indicates that
predictive maintenance is a very relevant topic and is widely applied in industries that have high needs
for operational efficiency and downtime reduction. Other sectors such as automotive, aviation, and oil
and gas also show significant interest, reflecting their specific needs in improving operational
reliability and safety through predictive maintenance techniques.
Discussion
In the Industry 4.0 era, predictive maintenance has become one of the key elements that determine
operational efficiency and equipment reliability in various industrial sectors. Unlike reactive
maintenance which carried out after a failure occurs, or preventive maintenance which based on a
fixed schedule, predictive maintenance focuses on real-time data analysis to predict failures before
they occur. The use of advanced technologies such as IoT, cloud computing, machine learning, and
data analytics allows this approach to provide significant benefits in terms of reducing downtime, and
maintenance costs, and increasing machine life.
The implementation of predictive maintenance is not limited to one type of industry. For example,
the article "Predictive Maintenance: How Big Data Analysis Can Improve Maintenance" by Jim Daily
 142 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

and Jeff Peterson describes how big data analytics is applied in the aviation industry to improve
operational reliability and efficiency. This study emphasizes the importance of integrating cloud-based
analytics with industrial machines for more effective data collection and analysis. In the automotive
industry, the article "Predictive Maintenance Enabled by Machine Learning: Use Cases and
Challenges in the Automotive Industry" identifies the challenges and opportunities associated with the
application of machine learning methods for predictive maintenance.
Based on the analysis of the journal articles discussed it can be concluded that predictive
maintenance is an important component in improving operational efficiency and equipment reliability
in various industrial sectors. Through solid system architecture, the development of effective
techniques and algorithms, and successful implementation in various industries, predictive
maintenance has been proven to provide significant benefits. However, technical and operational
challenges remain, and technological innovation is needed to overcome these challenges and take
advantage of the opportunities. Thus, predictive maintenance remains a dynamic and important
research area for a more efficient and reliable industrial future.
4. CONCLUSION
Predictive maintenance has emerged as a very important approach in the manufacturing industry,
providing solutions to minimize downtime, optimize maintenance costs, and improve operational
efficiency. In understanding the definition of predictive maintenance, we can conclude that it is an
approach that leverages advanced technologies such as the Internet of Things (IoT), machine learning,
big data analytics, and cloud computing to monitor equipment conditions in real time. Predictive
maintenance focuses on the use of historical data and sensor data to predict equipment failures before
they occur, enabling timely maintenance actions and preventing further damage. The application of
predictive maintenance in the manufacturing industry has shown significant success in various sectors,
ranging from automotive, and aviation, to metal processing. The case studies reviewed show that
companies that adopt this technology experience increased production efficiency, reduced
maintenance costs, and improved operational safety. For example, the use of machine learning and AI
algorithms to monitor machine tool conditions and predict cutting tool wear has resulted in more
accurate predictions and more effective maintenance interventions.
REFERENCE

[1] T Budi Agung, Miftahul Imtihan, and Suwaryo Nugroho, “Usulan Perbaikan Melalui
Penerapan Total Productive Maintenance Dengan Metode Oee Pada Mesin Twin Screw
Extruder Pvc Di Pt. Xyz,” TEKNOSAINS J. Sains, Teknol. dan Inform., vol. 8, no. 1,
pp. 10–22, 2021, doi: 10.37373/tekno.v8i1.78.
[2] F. Fauliyadi, A. Nalhadi, D. Cahyadi, E. H. Sucipto, and S. Supriyadi, “Perencanaan
Sistem Perawatan Mesin Dust Collector Pecs Id Fan Menggunakan Metode Reliability
Centered Maintenance,” JENIUS J. Terap. Tek. Ind., vol. 2, no. 1, pp. 30–40, 2021,
doi: 10.37373/jenius.v2i1.102.
[3] W. J. Lee, H. Wu, H. Yun, H. Kim, M. B. G. Jun, and J. W. Sutherland, “Predictive
maintenance of machine tool systems using artificial intelligence techniques applied to
machine condition data,” Procedia CIRP, vol. 80, no. March, pp. 506–511, 2019, doi:
10.1016/j.procir.2018.12.019.
[4] R. Sahal, J. G. Breslin, and M. I. Ali, “Big data and stream processing platforms for
Industry 4.0 requirements mapping for a predictive maintenance use case,” J. Manuf.
Syst., vol. 54, no. November 2019, pp. 138–151, 2020, doi:
10.1016/j.jmsy.2019.11.004.
[5] Y. K. Teoh, S. S. Gill, and A. K. Parlikad, “IoT and Fog-Computing-Based Predictive
Maintenance Model for Effective Asset Management in Industry 4.0 Using Machine
Learning,” IEEE Internet Things J., vol. 10, no. 3, pp. 2087–2094, 2023, doi:
10.1109/JIOT.2021.3050441.
 ISSN 2087-3336 (Print) | 2721-4729 (Online) 143
DOI 10.37373/tekno.v12i1.1338

[6] E. Traini, G. Bruno, G. D’Antonio, and F. Lombardi, “Machine learning framework for
predictive maintenance in milling,” IFAC-PapersOnLine, vol. 52, no. 13, pp. 177–182,
2019, doi: 10.1016/j.ifacol.2019.11.172.
[7] X. Han, Z. Wang, M. Xie, Y. He, Y. Li, and W. Wang, “Remaining useful life
prediction and predictive maintenance strategies for multi-state manufacturing systems
considering functional dependence,” Reliab. Eng. Syst. Saf., vol. 210, no. July 2020, p.
107560, 2021, doi: 10.1016/j.ress.2021.107560.
[8] K. S. Kiangala and Z. Wang, “An Effective Predictive Maintenance Framework for
Conveyor Motors Using Dual Time-Series Imaging and Convolutional Neural Network
in an Industry 4.0 Environment,” IEEE Access, vol. 8, pp. 121033–121049, 2020, doi:
10.1109/ACCESS.2020.3006788.
[9] S. M. Lee, D. Lee, and Y. S. Kim, “13. Lee, S. M., Lee, D., & Kim, Y. S. (2019). The
quality management ecosystem for predictive maintenance in the Industry 4.0 era.
International Journal.pdf,” vol. 5, 2019.
[10] T. Zonta, C. A. da Costa, R. da Rosa Righi, M. J. de Lima, E. S. da Trindade, and G. P.
Li, “Predictive maintenance in the Industry 4.0: A systematic literature review,”
Comput. Ind. Eng., vol. 150, no. August, p. 106889, 2020, doi:
10.1016/j.cie.2020.106889.
[11] T. P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. da P. Francisco, J. P. Basto, and S.
G. S. Alcalá, “A systematic literature review of machine learning methods applied to
predictive maintenance,” Comput. Ind. Eng., vol. 137, no. September, p. 106024, 2019,
doi: 10.1016/j.cie.2019.106024.
[12] M. Calabrese et al., “SOPHIA: An event-based IoT and machine learning architecture
for predictive maintenance in industry 4.0,” Inf., vol. 11, no. 4, pp. 1–17, 2020, doi:
10.3390/INFO11040202.
[13] S. Selcuk, “Predictive maintenance, its implementation and latest trends,” Proc. Inst.
Mech. Eng. Part B J. Eng. Manuf., vol. 231, no. 9, pp. 1670–1679, 2017, doi:
10.1177/0954405415601640.
[14] J. Wang, L. Zhang, L. Duan, and R. X. Gao, “A new paradigm of cloud-based
predictive maintenance for intelligent manufacturing,” J. Intell. Manuf., vol. 28, no. 5,
pp. 1125–1137, 2017, doi: 10.1007/s10845-015-1066-0.
[15] J. Lee, J. Ni, J. Singh, B. Jiang, M. Azamfar, and J. Feng, “Intelligent Maintenance
Systems and Predictive Manufacturing,” J. Manuf. Sci. Eng. Trans. ASME, vol. 142,
no. 11, 2020, doi: 10.1115/1.4047856.
[16] M. Pech, J. Vrchota, and J. Bednář, “Predictive maintenance and intelligent sensors in
smart factory: Review,” Sensors, vol. 21, no. 4, pp. 1–39, 2021, doi:
10.3390/s21041470.
[17] S. Ayvaz and K. Alpay, “Predictive maintenance system for production lines in
manufacturing: A machine learning approach using IoT data in real-time,” Expert Syst.
Appl., vol. 173, no. September 2020, p. 114598, 2021, doi:
10.1016/j.eswa.2021.114598.
[18] J. Dalzochio et al., “Machine learning and reasoning for predictive maintenance in
Industry 4.0: Current status and challenges,” Comput. Ind., vol. 123, p. 103298, 2020,
doi: 10.1016/j.compind.2020.103298.
[19] W. Yu, T. Dillon, F. Mostafa, W. Rahayu, and Y. Liu, “A Global Manufacturing Big
Data Ecosystem for Fault Detection in Predictive Maintenance,” IEEE Trans. Ind.
Informatics, vol. 16, no. 1, pp. 183–192, 2020, doi: 10.1109/TII.2019.2915846.
[20] E. Sezer, D. Romero, F. Guedea, M. Macchi, and C. Emmanouilidis, “An Industry 4.0-
Enabled Low Cost Predictive Maintenance Approach for SMEs,” 2018 IEEE Int. Conf.
 144 Tito Lukito, Rosi Herlianti, Malinda Mayanti, Lien Herliani Kusumah
Implementation of predictive maintenance in various industry: A Review

Eng. Technol. Innov., pp. 1–8, 2018.

[21] S. Sajid, A. Haleem, S. Bahl, M. Javaid, T. Goyal, and M. Mittal, “Data science
applications for predictive maintenance and materials science in context to Industry
4.0,” Mater. Today Proc., vol. 45, pp. 4898–4905, 2021, doi:
10.1016/j.matpr.2021.01.357.
[22] M. Compare, P. Baraldi, and E. Zio, “Challenges to IoT-Enabled Predictive
Maintenance for Industry 4.0,” IEEE Internet Things J., vol. 7, no. 5, pp. 4585–4597,
2020, doi: 10.1109/JIOT.2019.2957029.
[23] A. Kanawaday and A. Sane, “Machine learning for predictive maintenance of industrial
machines using IoT sensor data,” in 2017 8th IEEE International Conference on
Software Engineering and Service Science (ICSESS), 2017, pp. 87–90. doi:
10.1109/ICSESS.2017.8342870.
[24] P. Kamat and R. Sugandhi, “Anomaly detection for predictive maintenance in industry
4.0-A survey,” E3S Web Conf., vol. 170, pp. 1–8, 2020, doi:
10.1051/e3sconf/202017002007.
[25] W. Zhang, D. Yang, and H. Wang, “Data-Driven Methods for Predictive Maintenance
of Industrial Equipment: A Survey,” IEEE Syst. J., vol. 13, no. 3, pp. 2213–2227, 2019,
doi: 10.1109/JSYST.2019.2905565.
[26] J. R. Ruiz-Sarmiento, J. Monroy, F. A. Moreno, C. Galindo, J. M. Bonelo, and J.
Gonzalez-Jimenez, “A predictive model for the maintenance of industrial machinery in
the context of industry 4.0,” Eng. Appl. Artif. Intell., vol. 87, no. October 2019, p.
103289, 2020, doi: 10.1016/j.engappai.2019.103289.
[27] G. A. Susto, A. Schirru, S. Pampuri, S. McLoone, and A. Beghi, “Machine learning for
predictive maintenance: A multiple classifier approach,” IEEE Trans. Ind. Informatics,
vol. 11, no. 3, pp. 812–820, 2015, doi: 10.1109/TII.2014.2349359.
[28] B. Schmidt and L. Wang, “Cloud-enhanced predictive maintenance,” Int. J. Adv.
Manuf. Technol., vol. 99, no. 1–4, pp. 5–13, 2018, doi: 10.1007/s00170-016-8983-8.
[29] T. Zhu, Y. Ran, X. Zhou, and Y. Wen, “A Survey of Predictive Maintenance: Systems,
Purposes and Approaches,” no. Dl, pp. 1–38, 2019, [Online]. Available:
http://arxiv.org/abs/1912.07383
[30] Y. He, C. Gu, Z. Chen, and X. Han, “Integrated predictive maintenance strategy for
manufacturing systems by combining quality control and mission reliability analysis,”
Int. J. Prod. Res., vol. 55, no. 19, pp. 5841–5862, 2017, doi:
10.1080/00207543.2017.1346843.
[31] N. Sakib and T. Wuest, “Challenges and Opportunities of Condition-based Predictive
Maintenance: A Review,” Procedia CIRP, vol. 78, pp. 267–272, 2018, doi:
10.1016/j.procir.2018.08.318.
[32] A. Theissler, J. Pérez-Velázquez, M. Kettelgerdes, and G. Elger, “Predictive
maintenance enabled by machine learning: Use cases and challenges in the automotive
industry,” Reliab. Eng. Syst. Saf., vol. 215, p. 107864, 2021, doi:
10.1016/j.ress.2021.107864.
[33] P. Aivaliotis, K. Georgoulias, and G. Chryssolouris, “The use of Digital Twin for
predictive maintenance in manufacturing,” Int. J. Comput. Integr. Manuf., vol. 32, no.
11, pp. 1067–1080, 2019, doi: 10.1080/0951192X.2019.1686173.