Journal of Physics: Conference Series

PAPER • OPEN ACCESS

Application analysis of machine learning in fault diagnosis: A bibliometric

analysis
To cite this article: Wenyan Tu et al 2020 J. Phys.: Conf. Ser. 1629 012020

View the article online for updates and enhancements.

This content was downloaded from IP address 140.213.54.168 on 17/12/2020 at 02:08

ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

Application analysis of machine learning in fault diagnosis: A

bibliometric analysis

Wenyan Tu1, Ji Fang1, Yihua He1 and Jin Huang1

1
Huazhong Univ Sci & Technol, Lib, Wuhan, Hubei, Peoples R China

Corresponding author and e-mail: Jin Huang, [email protected]

Abstract. This article to analyze the application of machine learning in fault diagnosis by using
bibliometrics, co-citation network analysis and cluster analysis methods. The analysis found that
in the application research of machine learning in fault diagnosis, China has the largest number
of published papers and cited papers, among which IEEE access is the most published journal,
MECHANICAL SYSTEMS AND SIGNAL PROCESSING is the most cited journal,followed
by the United States and India.. Using document co-citation relationship analysis, a set of key
documents in this field was identified. ,Currently, the important algorithms fault diagnosis
include support vector data description method, transfer learning algorithm, convolutional neural
network algorithm, natural inspired optimization algorithm, bayesian network, wavelet packet
decomposition algorithm, fuzzy logic algorithm and so on. All of them are clustered according
to keywords, and their application fields include acoustic emission and fault diagnosis of doubly-
fed induction generators.

1. Introduction
The earliest definition of fault is the deviation of observed variables or calculated parameters from the
acceptable range in a process [1-2]. Fault diagnosis refers to the process of finding the fault of equipment
or system. Fault diagnosis is developed due to the need of establishing monitoring system [3], which
has gone through three stages [3-4]. The first stage is fault diagnosis based on the experience of experts
and simple instruments; the second stage is the diagnosis technology based on signal analysis and
modeling by means of sensing and detection technology; the second stage is fault diagnosis based on
signal analysis and modeling; The third stage: with the development of computer, artificial intelligence
and information processing technology, fault diagnosis technology has entered a new development
stage—intelligent fault diagnosis stage based on machine learning [4-8].
This article uses bibliometrics, co-citation network analysis, and cluster analysis methods to analyze
the overall status of the application of machine learning in fault diagnosis, combined with visual analysis
methods to try to find the most concerned hot issues and the research field with the most development
potential, which will guide further in-depth research in the future.

2. Data sources and methods

2.1. Data sources

Based on the core collection data of Web of Science and the Incites database, this article uses the subject
search method to construct a search strategy of TS=("machine learning" and "fault diagnosis"). The
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 licence. Any further distribution
of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
Published under licence by IOP Publishing Ltd 1
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

publication time of the literature is as of 2019, regardless of language, and the type of literature for
article, review and proceedings paper, 752 academic papers were finally retrieved.

2.2. Analysis methods and tools

This article uses bibliometric analysis methods to analyze and explore the 752 papers retrieved from
multiple perspectives such as the country where the paper was published, the influence of the journal,
the co-citation of the literature, and the distribution of subject areas.
When analyzing the co-citation network of documents, use CiteSpace visualization software for
visual analysis and display, revealing important documents and key documents in this research field.
Through keyword clustering, understand and analyze specific research content and main research fields.

3. Bibliometric analysis

3.1. Basic overview of national or regional papers

Through the use of Incites data analysis platform to analyze the 752 papers that have been retrieved, it
can be seen that in the application analysis of machine learning in fault diagnosis, China has published
the most papers, followed by the United States and India. China is also cited the most frequently. In
terms of institutions, China has the largest number of institutions in the top 100 cited by frequency, with
31 institutions, but the number of institutions in the top 10 and 50 cited by frequency is less than that of
the United States. In addition to China and the United States, India is the country with the most cited
institutions in the top 100, but there is still a big gap between China and the United States.
Table 1. Ranking of the top ten countries and institutions in the number of published papers.
Top 10 Top 50 Top 100
Total number Total institutions by institutions institutions
Name
of papers citations citation by citation by citation
frequency frequency frequency
China 300 2580 3 14 31
America 115 2343 5 17 28
India 70 980 2 6 8
Canada 40 236 0 0 2
England 37 537 0 4 6
Korea 29 156 0 0 2
France 26 299 0 2 4
Spain 21 385 0 3 4
Ecuador 15 204 0 0 0
Australia 15 96 0 0 2

3.2. Analysis of high level journals

According to the analysis of the number of publications and citation frequency of the source journals of
752 papers, there are five journals that rank top ten in both publication volume and citation frequency,
and all the partitions in the JCR database are in region Q1.Among them, the journal with the largest
publication volume is IEEE ACCESS, and the journal with the highest citation frequency is
MECHANICAL SYSTEMS AND SIGNAL PROCESSING. IEEE TRANSACTIONS ON
INDUSTRIAL ELECTRONICS has the highest impact factor.
Table 2. Top ten journals with published papers and cited frequency.
Periodical Journal impact
Journal Papers Freq
Division factors
Ieee Access 26 206 Q1 4.098
Expert Systems With Applications 15 560 Q1 4.292

2
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

Mechanical Systems And Signal

14 813 Q1 5.005
Processing
Neurocomputing 13 318 Q1 4.072
Ieee Transactions On Industrial
11 270 Q1 7.503
Electronics

3.3. Co-citation analysis of literature

Co-citation analysis means that two articles appear together in the bibliography of the third cited article,
and the two articles form a co-citation relationship. Usually, two or more papers with co-citation
relationship are similar in research methods or research topics, and a group of key papers in a certain
topic field can be identified through co-citation analysis of the literature. By using CiteSpace to analyze
the co-citation of 752 literatures, figure 2-2 is obtained. From the figure, the larger the node is, the higher
the citation frequency is, and the connection between nodes indicates the co-citation relationship
between the two literatures. The nodes in red represent emergence citations, which are nodes guiding
the sudden rise or fall of dosage, and represent possible changes in the research direction of this field.
From the perspective of analysis, the three literatures ranking top in citation frequency are shown in
Table 2-3, and the citation frequency of these three literatures is increasing year by year, which may
become important and key achievements in this field.
Table 3. Top three papers cited by frequency.

Author Title Source Freq Year

Deep neural networks: A promising tool for fault
Mech Syst
Jia F characteristic mining and intelligent diagnosis of rotating 53 2016
Signal Pr
machinery with massive data
LeCun Y Deep learning Nature 42 2015
Janssens, Convolutional Neural Network Based Fault Detection for J Sound
27 2016
Olivier Rotating Machinery Vib

Figure 1. Chronological distribution of the cited frequency of the top three papers.
Through burst analysis of literature, it can be concluded that the articles written by Sugumaran V,
Widodo A and Witten I H have been cited with relatively high burst strength. Further analysis of the
change of citation frequency shows that these articles attracted a high level of attention in the early stage,

3
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

but with the change of time, the attention declined, which also indicates that the research focus or
direction has changed.
Table 4. The top three papers in mutant intensity.
Author Title Source Freq Burst Year
Feature selection using
Decision Tree and
classification through MECH SYST
Sugumaran V 15 7.67 2007
Proximal Support Vector SIGNAL PR
Machine for fault
diagnostics of roller bearing
Support vector machine in
machine condition MECH SYST
Widodo A 13 6.81 2007
monitoring and fault SIGNAL PR
diagnosis
DATA
Witten I H Data mining practica MINING 7 4.56 2005
PRACTICA

Figure 2. Document Co-Citation Network.

3.4. Analysis of discipline field

According to the discipline classification of Web of Science, an analysis of 752 papers related to the
application of machine learning in fault diagnosis showed that the disciplines were mainly distributed
in the fields of engineering and computer science. Specifically, it had been cited more frequently in
refined fields such as artificial intelligence, automation and control systems, information systems,
mechanical engineering, interdisciplinary applications, instruments & instrumentation. Among them,
the engineering field had the highest frequency of appearance, and the artificial intelligence field had
the highest betweenness centrality.

4
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

Table 5. Distribution of disciplinary.

Betweenness
Subject Categories Frequency
Centrality
Engineering 449 0.69
Computer Science 290 0
Engineering, Electrical & Electronic 242 0.41
Computer Science, Artificial Intelligence 149 1.03
Automation & Control Systems 87 0.35
Engineering, Multidisciplinary 71 0
Computer Science, Information Systems 70 0.18
Engineering, Mechanical 62 0.69
Computer Science, Interdisciplinary Applications 58 0
Instruments & Instrumentation 54 0.06

3.5. Cluster analysis

Keywords are an important manifestation of the research content of an article. By analyzing keywords,
the research direction and research hotspots in this field can be roughly understood. Further clustering
analysis was carried out on the keywords, and the clustering results were evaluated by two indexes: the
clustering module value (Q value) and the clustering average contour value (S value). It is generally
believed that Q>0.3 means that the cluster structure is significant, S>0.5 clustering is reasonable, and
S>0.7 means that the clustering is convincing. Through the cluster analysis of the keywords of the 752
articles, 9 clusters were obtained. Further analysis of clustering can divide the main research content
into two categories, one was the algorithm research of machine learning; the other was the specific
application of machine learning in different types of faults.

3.5.1. Algorithm research in the field of fault diagnosis. From the keyword clustering table, there were
many researches on the algorithm in fault diagnosis. Among them, clustering 0 (support vector data
description method), clustering 1 (transfer learning algorithm), clustering 3 (convolution neural network
algorithm), clustering 4 (natural inspired optimization algorithm), clustering 6 (Bayesian network),
clustering 7 (wavelet packet decomposition algorithm) and clustering 8 (fuzzy logic algorithm) were
related to the algorithm.

3.5.2. Application research in the field of fault diagnosis. In the field of practical application, the
research on fault diagnosis mainly involved acoustic emission and doubly-fed induction generators.
Cluster 2: The application of artificial neural network in acoustic emission. Acoustic emission is a
common physical phenomenon. Acoustic emission technology is a dynamic non-destructive testing
method that judges the degree of internal damage of the structure based on the stress wave emitted from
the material or structure. Some progress has been made in the use of artificial neural networks for
acoustic emission signal processing. Because the artificial neural network has the functions of self-
organization, self-adaptive and self-learning, and the network has high robustness, it can solve the
problem of noise interference in acoustic emission detection, and can accurately judge the activity of
acoustic emission source [9].
Cluster 5: Fault detection of doubly fed induction generator. Doubly fed induction motor is mainly
used in wind power generation system. Doubly fed induction generator (DFIG) is the main type of wind
power generation. With the development of wind power generation, the research on condition
monitoring and fault diagnosis of wind turbine is becoming more and more important. At present, early
fault intelligent diagnosis method based on multi-sensor information fusion and wavelet analysis method
are important analysis methods for fault detection of doubly fed induction generator [10].

5
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

Table 6. Keyword cluster.

Cluster Mean
Size Silhouelte Keywords
id year
functional failure (9.42, 0.005); machine
0 30 0.695 2011
learning (6.95, 0.01); svdd (6.26, 0.05);
turbofan engine (6.77, 0.01); transfer learning
1 26 0.594 2015
(6.77, 0.01); statistical features (4.26, 0.05);
pattern recognition (7.76, 0.01); acoustic
2 25 0.595 2015 emission (7.76, 0.01); artificial neural network
(4.25, 0.05);
cnn (14.48, 0.001); deep learning (12.13,
3 17 0.72 2016
0.001); k-means (9.6, 0.005);
big data (10.2, 0.005); fault injection (5.07,
4 17 0.729 2015 0.05); nature-inspired optimization algorithms
(5.07, 0.05);
doubly-fed induction generator (dfig) (9.08,
0.005); deep classifier (9.08, 0.005); rotor
5 16 0.745 2016
current (9.08, 0.005); fault detection (9.08,
0.005);
logical analysis of data (6.92, 0.01); bayesian
6 13 0.917 2017 networks (6.92, 0.01); tennessee eastman
process (6.92, 0.01);
machine learning (5.05, 0.05); wavelet packet
7 9 0.877 2016 decomposition (4.52, 0.05); asymmetrical fault
(4.52, 0.05);
fuzzy logic (6.59, 0.05); model-based
8 8 0.888 2008 reasoning (6.49, 0.05); artificial intelligence
(6.49, 0.05);

4. Conclusions
Machine learning is one of the most intelligent and cutting-edge research fields of artificial intelligence.
The core of intelligent fault diagnosis is to effectively acquire, transmit, process, regenerate and utilize
diagnostic information, so that it has the ability to accurately identify and predict the status of the
diagnostic object in a given environment [11]. At present, in the research of fault diagnosis, China is not
only the country with the most published papers, but also the country with the most cited frequency
Based on the analysis of document co-citation relationship, a group of key documents in this field are
identified. It is concluded that the papers published by Jia F, LeCun Y, Janssens, Olivier have received
more citations. From the keyword clustering analysis, the important fault diagnosis algorithms include
support vector data description method, transfer learning algorithm, convolution neural network
algorithm, natural inspired optimization algorithm, bayesian network, wavelet packet decomposition
algorithm, fuzzy logic algorithm and so on. Their research fields consist of acoustic emission and fault
diagnosis of doubly fed induction generator.
With the development of artificial intelligence technology and the improvement of mechanical
equipment automation and intelligent level in China, machine learning algorithm will play a greater role
in the improvement of power system, mechanical equipment and performance.

References
[1] HIMMELBLAU D M. Fault Detection and Diagnosis in Chemical and Petrochemical Processes
[M]. New York: Elsevier Science Ltd, 1978:45–70.
[2] Zhou Donghua, Xi Yugeng. Fault detection and diagnosis technology [J]. Journal of Control

6
ICAMLDS 2020 IOP Publishing
Journal of Physics: Conference Series 1629 (2020) 012020 doi:10.1088/1742-6596/1629/1/012020

theory and Applications, 1991, 8 (1):1-7.

[3] Li Wei. Advance of Intelligent Fault Diagnosis for Complex System and Its Present Situation [J].
Computer Simulation, 2004, 21(10):4-7.
[4] Zhou Donghua, Liu Yang, He Xiao. Review on Fault Diagnosis Techniques for Closed-loop
Systems [J]. Acta Automatica Sinica, 2013, 39(11):1933-1943.
[5] Li Chunlin, Xiong Jianbin, Su Naiquan, Zhang Qinghua, Liang Qiong, Ye Baoyu. Application
Review of Deep Learning in Fault Diagnosis [J]. Machine Tool & Hydraulics, 2020,
48(13):174-184.
[6] Wang Xiaofeng, Mao Deqiang, Feng Shangcong. Review on modern fault diagnosis technologies
[J]. China Measurement & Test, 2013, 39(06):93-98.
[7] Zhou Donghua, Shi Jiantao, HeXiao. Review of Intermittent Fault Diagnosis Techniques for
Dynamic Systems [J]. Acta Automatica Sinica, 2014, 40(02):161-171.
[8] Wen Chenlin, Lv Feiya. Review on Deep Learning Based Fault Diagnosis [J]. Journal of
Electronics & Information Technology, 2020, 42(01):234-248.
[9] Li Jialin, Dong Yunchao, Ma Yukuan. Pattern Recognition of the Characteristics of Acoustic
Emission Source Using Neural Network [J]. Nondestructive Testing,2001(06):231-233+272
[10] Xiao Yali, Fang Ruiming, Li Wenpeng. Overview of the Condition Monitoring Method for
Doubly-Fed Induction Wind Power Generation Systems [J]. Power System and Clean Energy,
2012, 28(03):67-73+78.
[11] Xiao Xiao. Machine learning in intelligent fault diagnosis [D]. Chongqing University, 2002.