An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data
The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
Abstract
Intelligent fault diagnosis is a promising tool to deal with mechanical big data due to its ability in rapidly and efficiently processing collected signals and providing accurate diagnosis results. In traditional intelligent diagnosis methods, however, the features are manually extracted depending on prior knowledge and diagnostic expertise. Such processes take advantage of human ingenuity but are time-consuming and labor-intensive. Inspired by the idea of unsupervised feature learning that uses artificial intelligence techniques to learn features from raw data, a two-stage learning method is proposed for intelligent diagnosis of machines. In the first learning stage of the method, sparse filtering, an unsupervised two-layer neural network, is used to directly learn features from mechanical vibration signals. In the second stage, softmax regression is employed to classify the health conditions based on the learned features. The proposed method is validated by a motor bearing dataset and a locomotive bearing dataset, respectively. The results show that the proposed method obtains fairly high diagnosis accuracies and is superior to the existing methods for the motor bearing dataset. Because of learning features adaptively, the proposed method reduces the need of human labor and makes intelligent fault diagnosis handle big data more easily.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“This would make intelligent fault diagnosis methods less dependent on the prior knowledge or human labor, so that novel applications could be done faster, and more importantly, to make mechanical fault diagnosis toward real artificial intelligence [20].”
BackgroundHinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260 · cited 1×
“tion [24], speech recognition [25], and high-energy physic [26], and state-of-the-art performances are obtained in these fields.”
BackgroundIndependent component analysis: algorithms and applications
Hyvärinen, A., & Oja, E. (2000) · Neural Networks · doi:10.1016/s0893-6080(00)00026-5 · Cited by 8,705 · cited 1×
“other and speed up the convergence of the sparse filtering training [37].”
BackgroundAn analysis of single-layer networks in unsupervised feature learning
Coates, A., Ng, A. Y., & Lee, H. (2011) · International Conference on Artificial Intelligence and Statistics · Cited by 4,675
Compressive Sensing [Lecture Notes]
Baraniuk, R. (2007) · IEEE Signal Processing Magazine · doi:10.1109/msp.2007.4286571 · Cited by 4,177
A Practical Guide to Training Restricted Boltzmann Machines
Hinton, G. E. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-35289-8_32 · Cited by 2,852 · cited 1×
“Once these parameters are set inappropriately, the learned features may result in poor diagnosis accuracy [28].”
BackgroundWu, X., Zhu, X., Wu, G.-Q., & Ding, W. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2013.109 · Cited by 2,410 · cited 1×
“2519325 new perspectives and challenges in processing and discovering valuable information [4], but also may prompt its power to affect other fields, such as the field of condition monitoring”
BackgroundBeyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006) · Lecture Notes in Computer Science · doi:10.1007/11941439_114 · Cited by 1,974 · cited 1×
“To compare their performances with that of the proposed method, F-score is adopted [40], which is a commonly used criterion measuring the performance of a classification method.”
MethodA Review on Basic Data-Driven Approaches for Industrial Process Monitoring
Yin, S., Ding, S. X., Xie, X., & Luo, H. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2301773 · Cited by 1,716 · cited 4×
“The comparisons are displayed in Table I. Du et al. [41] proposed a method based on wavelet leaders multifractal features and SVM.”
MethodInfluentialSelf-citationBig data deep learning: Challenges and perspectives
Chen, X.-W., & Lin, X. (2014) · IEEE Access · doi:10.1109/access.2014.2325029 · Cited by 1,255 · cited 1×
“Such explosion of data makes these fields endorse the concept and power of big data [1]–[3].”
BackgroundWhat Is the Goal of Sensory Coding?
Field, D. J. (1994) · Neural Computation · doi:10.1162/neco.1994.6.4.559 · Cited by 1,183 · cited 1×
“These principles have been explored in the field of neuroscience [31], [32].”
BackgroundSearching for exotic particles in high-energy physics with deep learning
Baldi, P., Sadowski, P., & Whiteson, D. (2014) · Nature Communications · doi:10.1038/ncomms5308 · Cited by 1,164 · cited 1×
“tion [24], speech recognition [25], and high-energy physic [26], and state-of-the-art performances are obtained in these fields.”
BackgroundUnsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., & LeCun, Y. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383157 · Cited by 1,086 · cited 1×
“tion [24], speech recognition [25], and high-energy physic [26], and state-of-the-art performances are obtained in these fields.”
BackgroundCondition monitoring and fault diagnosis of planetary gearboxes: A review
Lei, Y., Lin, J., Zuo, M. J., & He, Z. (2014) · Measurement · doi:10.1016/j.measurement.2013.11.012 · Cited by 731
Self-citationBearing fault diagnosis based on wavelet transform and fuzzy inference
Lou, X., & Loparo, K. A. (2004) · Mechanical Systems and Signal Processing · doi:10.1016/s0888-3270(03)00077-3 · Cited by 689 · cited 1×
“The motor bearing signals provided by Case Western Reserve University [39] are analyzed in this section.”
MethodWang, T., Gao, H., & Qiu, J. (2016) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2411671 · Cited by 636
Smith, E. C., & Lewicki, M. S. (2006) · Nature · doi:10.1038/nature04485 · Cited by 630 · cited 1×
“Therefore, we fit each weight vectors using Gabor function f(d) [46], [47]”
MethodZhang, X., Liang, Y., Zhou, J., & zang, Y. (2015) · Measurement · doi:10.1016/j.measurement.2015.03.017 · Cited by 586 · cited 1×
“[44] proposed a bearing diagnosis method integrating permutation entropy, ensemble empirical mode decomposition, and optimized SVM.”
MethodBig Data for Modern Industry: Challenges and Trends [Point of View]
Yin, S., & Kaynak, O. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2388958 · Cited by 565 · cited 1×
“and fault diagnosis of machines [5].”
A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis—Part I: Components and Subsystems
Qiao, W., & Lu, D. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2422112 · Cited by 533
Fault diagnosis of rotating machinery based on multiple ANFIS combination with gas
Lei, Y., He, Z., Zi, Y., & Hu, Q. (2007) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2006.11.003 · Cited by 500 · cited 1×
“[16] used an”
Self-citationPrieto, M. D., Cirrincione, G., Espinosa, A. G., Ortega, J. A., & Henao, H. (2013) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2012.2219838 · Cited by 461 · cited 1×
“Traditionally, the framework of intelligent fault diagnosis includes three main steps: 1) signal acquisition; 2) feature extraction and selection; and 3) fault classification [9]–[11], as shown in Fig.”
Motor Bearing Fault Diagnosis Using Trace Ratio Linear Discriminant Analysis
Jin, X., Zhao, M., Chow, T. W. S., & Pecht, M. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2013.2273471 · Cited by 423 · cited 1×
“In [42], nine time-domain statistical features combined with six features about the percentage of energy corresponding to wavelet coefficients were used to represent ten bearing health conditions under the load of 3 hp.”
MethodProcess data analytics in the era of big data
Qin, S. J. (2014) · AIChE Journal · doi:10.1002/aic.14523 · Cited by 383 · cited 1×
“Such explosion of data makes these fields endorse the concept and power of big data [1]–[3].”
BackgroundQiu, J., Ding, S. X., Gao, H., & Yin, S. (2016) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2015.2457934 · Cited by 382
Self-citationQiu, J., Feng, G., & Gao, H. (2010) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2010.2052259 · Cited by 329
Ngiam, J., Chen, Z., Bhaskar, S. A., Koh, P. W., & Ng, A. Y. (2011) · neural information processing systems · Cited by 297
Natural computing for mechanical systems research: A tutorial overview
Worden, K., Staszewski, W. J., & Hensman, J. J. (2011) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2010.07.013 · Cited by 288 · cited 2×
“It can be found that plenty of studies have been conducted on intelligent fault diagnosis and achieved good results [9].”
BackgroundWPD-PCA-Based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM
You, D., Gao, X., & Katayama, S. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2319216 · Cited by 271 · cited 1×
“In the second step, feature extraction aims to extract representative features from the collected signals based on signal processing techniques, such as time-domain statistical analysis, Fourier spectral analysis, and wavelet transformation [12].”
MethodCharacterizing the sparseness of neural codes
Willmore, B. D. B., & Tolhurst, D. J. (2001) · Network Computation in Neural Systems · doi:10.1088/0954-898x/12/3/302 · Cited by 263
New clustering algorithm-based fault diagnosis using compensation distance evaluation technique
Lei, Y., He, Z., Zi, Y., & Chen, X. (2008) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2007.07.013 · Cited by 244 · cited 1×
“feature selection is used to select sensitive features through dimension reduction strategies, such as principal component (PC) analysis (PCA), distance evaluation technique [13], and”
MethodSelf-citationLearning a better representation of speech soundwaves using restricted boltzmann machines
Jaitly, N., & Hinton, G. (2011) · 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2011.5947700 · Cited by 231 · cited 1×
“Traditionally, the learned features f i of x is obtained by combining these local features f i j in an aggregate way [38].”
BackgroundCharacterizing the sparseness of neural codes
Willmore, B., & Tolhurst, D. J. (2001) · Network: Computation in Neural Systems · doi:10.1080/net.12.3.255.270 · Cited by 229 · cited 1×
“These principles have been explored in the field of neuroscience [31], [32].”
BackgroundVergence eye movements in response to binocular disparity without depth perception
Masson, G. S., Busettini, C., & Miles, F. A. (1997) · Nature · doi:10.1038/38496 · Cited by 222 · cited 1×
“Therefore, we fit each weight vectors using Gabor function f(d) [46], [47]”
MethodVibration Spectrum Imaging: A Novel Bearing Fault Classification Approach
Amar, M., Gondal, I., & Wilson, C. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2014.2327555 · Cited by 222 · cited 1×
“[18] proposed a feature enhancement procedure to obtain robust image fea-”
MethodLearning image representations from the pixel level via hierarchical sparse coding
Yu, K., Lin, Y., & Lafferty, J. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995732 · Cited by 212 · cited 1×
“Unsupervised feature learning has been widely used in various fields, such as image classification [23], object detec-”
MethodModel reduction for interval type-2 Takagi–Sugeno fuzzy systems
Li, H., Yin, S., Pan, Y., & Lam, H.-K. (2015) · Automatica · doi:10.1016/j.automatica.2015.08.020 · Cited by 210
Smartphone based visible iris recognition using deep sparse filtering
Raja, K. B., Raghavendra, R., Vemuri, V. K., & Busch, C. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.09.006 · Cited by 177 · cited 1×
“Therefore, sparse filtering does not necessarily include the parameter tuning and easily converges to an optimal solution [30].”
BackgroundKang, M., Kim, J., Kim, J.-M., Tan, A. C. C., Kim, E. Y., & Choi, B.-K. (2015) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2014.2358494 · Cited by 169 · cited 1×
“feature discriminant analysis [14].”
Yu, J. (2012) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2011.2167893 · Cited by 167 · cited 1×
“Yu [17] presented a fault classification method for bearings in which”
MethodBig data: Distilling meaning from data
Frankell, F. C., & Reid, R. (2008) · Nature · doi:10.1038/455030a · Cited by 162
Big Data for Modern Industry: Challenges and Trends
Yin, S., & Kaynak, O. (2015) · Cited by 161
Wavelet leaders multifractal features based fault diagnosis of rotating mechanism
Du, W., Tao, J., Li, Y., & Liu, C. (2013) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2013.09.003 · Cited by 145 · cited 1×
“[41] proposed a method based on wavelet leaders multifractal features and SVM.”
MethodTwo-Stage Learning to Predict Human Eye Fixations via SDAEs
Han, J., Zhang, D., Wen, S., Guo, L., Liu, T., & Li, X. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2404432 · Cited by 137 · cited 1×
“of softmax regression to take values close to zero while permits other parameters to retain their relatively large values, thereby improving the generalization ability [35].”
BackgroundFault Diagnosis in Internal Combustion Engines Using Extension Neural Network
Shatnawi, Y., & Al-khassaweneh, M. (2014) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2013.2261033 · Cited by 135
The Haar Wavelet Transform in the Time Series Similarity Paradigm
Struzik, Z. R., & Siebes, A. P. J. M. (1999) · Lecture notes in computer science · doi:10.1007/978-3-540-48247-5_2 · Cited by 133 · cited 1×
“Therefore, sparse filtering can be interpreted to measure the similarity between the input signals and a series of weight vectors, such as wavelet transform providing estimates of similarity between the signals and basis functions [45].”
BackgroundLi, W., Zhang, S., & He, G. (2013) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2013.2245180 · Cited by 109 · cited 1×
“A method [43] using 19 time-domain and frequency-domain features combined with semisupervised self-organizing map was proposed by Li et al.”
MethodLaser-based segment classification using a mixture of bag-of-words
Behley, J., Steinhage, V., & Cremers, A. B. (2013) · 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2013.6696957 · Cited by 98 · cited 1×
“In neural networks, softmax regression is often implemented at the final layer for multiclass classification [34].”
MethodAn Enhanced Diagnostic Scheme for Bearing Condition Monitoring
Liu, J., Wang, W., & Golnaraghi, F. (2010) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2009.2023814 · Cited by 87 · cited 1×
“[19] and an enhanced neuro-fuzzy classifier was employed to classify bearing health conditions.”
MethodBielza, C., Robles, V., & Larrañaga, P. (2010) · Expert Systems with Applications · doi:10.1016/j.eswa.2010.09.140 · Cited by 70 · cited 1×
“weight decay term (for any λ > 0), the cost function J(θ) is strictly convex and the softmax regression model is guaranteed to have a unique solution theoretically [36].”
BackgroundA nonlinear probabilistic method and contribution analysis for machine condition monitoring
Yu, J. (2013) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2013.01.010 · Cited by 46 · cited 1×
“In modern industries, machines have become more automatic, precise, and efficient than ever before [6]–[8], which”
Background
Cited by
Applications of machine learning to machine fault diagnosis: A review and roadmap
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106587 · Cited by 2,997
Self-citationA new convolutional neural network-based data-driven fault diagnosis method
Wen, L., Li, X., Gao, L., & Zhang, Y. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2774777 · Cited by 2,222
“They are sparse filter [16], DBN) [12], DBN-based HDN [27], SVM [43], ANN [12], and adaptive deep convolution neural network (ADCNN) [30].”
MethodArtificial intelligence for fault diagnosis of rotating machinery: A review
Liu, R., Yang, B., Zio, E., & Chen, X. (2018) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2018.02.016 · Cited by 2,188
Zhang, W., Peng, G., Li, C., Chen, Y., & Zhang, Z. (2017) · Sensors · doi:10.3390/s17020425 · Cited by 1,925
“Therefore, some studies proposed that the classifier should have the ability to classify the data from the raw signal directly, without feature extraction or manual selection [24,27].”
BackgroundDeep learning for smart manufacturing: Methods and applications
Wang, J., Ma, Y., Zhang, L., Gao, R. X., & Wu, D. (2018) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2018.01.003 · Cited by 1,740
Metadata
- Authors
- Lei, Y., Jia, F., Lin, J., Xing, S., & Ding, S. X.
- Affiliations
- Xi'an Jiaotong University (CN)
- University of Duisburg-Essen (DE)
- Venue
- IEEE Transactions on Industrial Electronics
- Published
- 2016-05
- Volume
- 63
- Issue
- 5
- Pages
- 3137-3147
- ISSN
- 0278-0046 (ISSN-L)
- 1557-9948
- OpenAlex
- W2317595875
- Semantic Scholar
- 2d2fe4a73c98933ae9b8df73c8452b0d8be6475e
- Cited by
- 1,191
- References
- 53
- Citations by year
- 2026: 53 · 2025: 69 · 2024: 88 · 2023: 130 · 2022: 168 · 2021: 177 · 2020: 199 · 2019: 142 · 2018: 97 · 2017: 63 · 2016: 5
- FWCI
- 85.94
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Industrial Electronics (publishedVersion)
- Funders
- National Natural Science Foundation of China (51222503, 51475355, 51421004)
- Fundamental Research Funds for the Central Universities (2012jdgz01, XTD2014001)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- intelligent fault diagnosis, unsupervised feature learning, mechanical vibration signals, sparse filtering, two-layer neural networks, softmax regression, bearing fault classification, motor bearings
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.