Please wait a minute...
Shopping Cart Email List Chinese
Advanced Search Fig/Tab
Frontiers in Energy

ISSN 2095-1701

ISSN 2095-1698(Online)

CN 11-6017/TK

Postal Subscription Code 80-972

2018 Impact Factor: 1.701

Featured Articles  |  Most Downloaded  |  Most Reading
Online Submission Subscribe to Our RSS Content Feed
Front. Energy    2023, Vol. 17 Issue (4) : 527-544    https://doi.org/10.1007/s11708-023-0880-x
RESEARCH ARTICLE
Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and unary classification
Xilian YANG1, Kanru CHENG2, Qunfei ZHAO1, Yuzhang WANG2()
1. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
 Download: PDF(2110 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

Intelligent power systems can improve operational efficiency by installing a large number of sensors. Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources. However, the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data. The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms. Moreover, sensor data faults in power systems are dynamically changing and pose another challenge. Therefore, a fault detection method based on self-supervised feature learning was proposed to address the above two challenges. First, self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data. The self-supervised representation learning uses a sequence-based Triplet Loss. The extracted features of large amounts of normal data are then fed into a unary classifier. The proposed method is validated on exhaust gas temperatures (EGTs) of a real-world 9F gas turbine with sudden, progressive, and hybrid faults. A comprehensive comparison study was also conducted with various feature extractors and unary classifiers. The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults. The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms of F1 score.
Keywords fault detection      unary classification      self-supervised representation learning      multivariate nonlinear time series     
Corresponding Author(s): Yuzhang WANG   
About author:

* These authors contributed equally to this work.
Online First Date: 16 June 2023    Issue Date: 29 August 2023
 Cite this article:   
Xilian YANG,Kanru CHENG,Qunfei ZHAO, et al. Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and unary classification[J]. Front. Energy, 2023, 17(4): 527-544.
 URL:  
https://academic.hep.com.cn/fie/EN/10.1007/s11708-023-0880-x
https://academic.hep.com.cn/fie/EN/Y2023/V17/I4/527
Fig.1  Statistics of sensor fault number from the average of three 9F gas turbines in power plants.
Fig.2  Schematic of the processing flow of the proposed method.
Fig.3  Proposed fault detection processing steps.
Fig.4  Schematic diagram of the self-supervised training process of the Triplet Loss function.
Fig.5  Real original EGT signals imposed with various fault data.
Fig.6  Various real data with fault data visualization (left: original scale; right: scatter with histogram).
Dataset Window length Input dimensions Hidden dimensions RNN layers Bidirectional parameter Output features
NASA 128 21 128 2 True 10
9F EGTs 36 20 100 1 True 10
Tab.1  Experiment parameters
Fig.7  Comparison of Triplet Loss coupling LOF of proposed method with original data using only unary classification under F1-score.
Unary classifier CPC TNC Triplet Loss Original data
Robust covariance 0.615 0.696 0.889 0.963
One-Class SVM 0.421 0.421 0.085 0.548
Isolation Forest 0.410 0.457 0.500 0.537
LOF 0.727 0.696 0.762 0.059
Tab.2  Short fault, F1-score of various unary classification algorithms coupling with various feature extractors
Unary classifier CPC TNC Triplet Loss Original data
Robust covariance 0.593 0.696 0.889 0.877
One-Class SVM 0.421 0.421 0.085 0.548
Isolation Forest 0.410 0.457 0.500 0.537
LOF 0.727 0.696 0.762 0.076
Tab.3  Step fault, F1-score of various unary classification algorithms coupling with various feature extractors
Unary classifier CPC TNC Triplet Loss Original data
Robust covariance 0.583 0.667 0.714 0.000
One-Class SVM 0.432 0.432 0.085 0.013
Isolation Forest 0.421 0.471 0.516 0.073
LOF 0.727 0.727 0.800 0.244
Tab.4  Drift fault, F1-score of various unary classification algorithms coupling with various feature extractors
Unary classifier CPC TNC Triplet Loss Original data
Robust covariance 0.593 0.636 0.824 0.094
One-Class SVM 0.333 0.286 0.085 0.473
Isolation Forest 0.368 0.457 0.452 0.468
LOF 0.727 0.696 0.700 0.319
Tab.5  Noise fault, F1-score of various unary classification algorithms coupling with various feature extractors
Unary classifier CPC TNC Triplet Loss Original data
Robust covariance 0.615 0.696 0.889 0.000
One-Class SVM 0.378 0.378 0.085 0.489
Isolation Forest 0.410 0.457 0.500 0.485
LOF 0.545 0.696 0.762 0.308
Tab.6  Periodic fault, F1-score of various unary classification algorithms coupling with various feature extractors
Fig.8  Matthews correlation coefficient (MCC) of four unary classifiers with self-supervised representation learning and original data (horizontal tick label denotation: 1 – Robust covariance; 2 – One-Class SVM; 3 – Isolation Forest; 4 – LOF).
Fig.9  Recall of four unary classifiers with self-supervised representation learning and original data (horizontal tick label denotation: 1 – Robust covariance; 2 – One-Class SVM; 3 – Isolation Forest; 4 – LOF).
Fig.10  False alarm of diverse coupling methods (horizontal tick label: 1 – Robust covariance; 2 – One-Class SVM; 3 – Isolation Forest; 4 – LOF).
Fig.11  Confusion matrix of noise fault using TNC (−1 denoting abnormal while 1 denoting normal).
Fig.12  Confusion matrix of noise fault using Triplet Loss (−1 denoting abnormal, while 1 denoting normal).
Fig.13  Confusion matrix of drift fault using TNC (−1 denoting abnormal while 1 denoting normal).
Fig.14  Confusion matrix of drift fault using Triplet Loss (−1 denoting abnormal while 1 denoting normal).
Fig.15  Denotation of different working states and corresponding encoded features of all sensor data.
Fig.16  Clustering visualization of original signals and extracted features using t-SNE.
Fig.17  Influence of self-supervised clustering evaluation metric with the change of the number of categories under Silhouette Score↑.
Unary classifier Original time/s Original CPU memory/GB After encoded time/s
Robust covariance 2.99 0.31 0.0550
One-Class SVM 0.53 0.32 0.0010
Isolation Forest 0.58 0.32 0.2100
LOF 2.67 0.35 0.0036
Tab.7  Comparison of unary classifier computation time
Feature CPC TNC Triplet Loss
Parameters 75210 75210 75210
GPU memory/MB 2.22 2.22 2.22
Time/s 0.025 0.021 0.025
Tab.8  Comparison of feature extractor computation time
1 M Tahan, E Tsoutsanis, M Muhammad. et al.. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review. Applied Energy, 2017, 198: 122–144
https://doi.org/10.1016/j.apenergy.2017.04.048
2 F H Jufri, V Widiputra, J Jung. State-of-the-art review on power grid resilience to extreme weather events: Definitions, frameworks, quantitative assessment methodologies, and enhancement strategies. Applied Energy, 2019, 239: 1049–1065
https://doi.org/10.1016/j.apenergy.2019.02.017
3 O Fink, Q Wang, M Svensén. et al.. Potential, challenges and future directions for deep learning in prognostics and health management applications. Engineering Applications of Artificial Intelligence, 2020, 92: 103678
https://doi.org/10.1016/j.engappai.2020.103678
4 C Yan, J Chen, H Liu. et al.. Health management for PEM fuel cells based on an active fault tolerant control strategy. IEEE Transactions on Sustainable Energy, 2021, 12(2): 1311–1320
https://doi.org/10.1109/TSTE.2020.3042990
5 T Jain, J J Yamé. Fault-tolerant economic model predictive control for wind turbines. IEEE Transactions on Sustainable Energy, 2019, 10(4): 1696–1704
https://doi.org/10.1109/TSTE.2018.2869480
6 D Zhang, Z Ye, X Dong. Co-design of fault detection and consensus control protocol for multi-agent systems under hidden DoS attack. IEEE Transactions on Circuits and Systems. I, Regular Papers, 2021, 68(5): 2158–2170
https://doi.org/10.1109/TCSI.2021.3058216
7 L Feng, C Zhao. Fault description based attribute transfer for zero-sample industrial fault diagnosis. IEEE Transactions on Industrial Informatics, 2021, 17(3): 1852–1862
https://doi.org/10.1109/TII.2020.2988208
8 D W Gao, Q Wang, F Zhang. et al.. Application of AI techniques in monitoring and operation of power systems. Frontiers in Energy, 2019, 13(1): 71–85
https://doi.org/10.1007/s11708-018-0589-4
9 G Michau, O Fink. Unsupervised transfer learning for anomaly detection: Application to complementary operating condition transfer. Knowledge-Based Systems, 2021, 216: 106816
https://doi.org/10.1016/j.knosys.2021.106816
10 Y Chen, M J Zuo. A sparse multivariate time series model-based fault detection method for gearboxes under variable speed condition. Mechanical Systems and Signal Processing, 2022, 167: 108539
https://doi.org/10.1016/j.ymssp.2021.108539
11 M Gallo, C Costabile, M Sorrentino. et al.. Development and application of a comprehensive model-based methodology for fault mitigation of fuel cell powered systems. Applied Energy, 2020, 279: 115698
https://doi.org/10.1016/j.apenergy.2020.115698
12 P Singla, M Duhan, S Saroha. A comprehensive review and analysis of solar forecasting techniques. Frontiers in Energy, 2022, 16(2): 187–223
https://doi.org/10.1007/s11708-021-0722-7
13 F Fu, D Wang, S X Ding. et al.. Fault identifiability analysis of linear discrete time-varying systems. IEEE Transactions on Circuits and Systems. I, Regular Papers, 2019, 66(6): 2371–2381
https://doi.org/10.1109/TCSI.2018.2889907
14 Y Li, M Zhang, C Chen. A deep-learning intelligent system incorporating data augmentation for short-term voltage stability assessment of power systems. Applied Energy, 2022, 308: 118347
https://doi.org/10.1016/j.apenergy.2021.118347
15 M Waqar Akram, G Li, Y Jin. et al.. Failures of photovoltaic modules and their detection: A review. Applied Energy, 2022, 313: 118822
https://doi.org/10.1016/j.apenergy.2022.118822
16 A Ajagekar, F You. Quantum computing based hybrid deep learning for fault diagnosis in electrical power systems. Applied Energy, 2021, 303: 117628
https://doi.org/10.1016/j.apenergy.2021.117628
17 C C Yang, C S Soh, V V Yap. A systematic approach in load disaggregation utilizing a multi-stage classification algorithm for consumer electrical appliances classification. Frontiers in Energy, 2019, 13(2): 386–398
https://doi.org/10.1007/s11708-017-0497-z
18 Z Sun, Y Han, Z Wang. et al.. Detection of voltage fault in the battery system of electric vehicles using statistical analysis. Applied Energy, 2021, 307: 118172
https://doi.org/10.1016/j.apenergy.2021.118172
19 M Dey, S P Rana, C V Simmons. et al.. Solar farm voltage anomaly detection using high-resolution μPMU data-driven unsupervised machine learning. Applied Energy, 2021, 303: 117656
https://doi.org/10.1016/j.apenergy.2021.117656
20 Y Zhao, D Li, T Lu. et al.. Collaborative fault detection for large-scale photovoltaic systems. IEEE Transactions on Sustainable Energy, 2020, 11(4): 2745–2754
https://doi.org/10.1109/TSTE.2020.2974404
21 L Wei, Z Qian, H Zareipour. Wind turbine pitch system condition monitoring and fault detection based on optimized relevance vector machine regression. IEEE Transactions on Sustainable Energy, 2020, 11(4): 2326–2336
https://doi.org/10.1109/TSTE.2019.2954834
22 Y Zhuo, Z Ge. Auxiliary information-guided industrial data augmentation for any-shot fault learning and diagnosis. IEEE Transactions on Industrial Informatics, 2021, 17(11): 7535–7545
https://doi.org/10.1109/TII.2021.3053106
23 Y Zhao, T Li, X Zhang. et al.. Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future. Renewable & Sustainable Energy Reviews, 2019, 109: 85–101
https://doi.org/10.1016/j.rser.2019.04.021
24 B Li, C Delpha, D Diallo. et al.. Application of artificial neural networks to photovoltaic fault detection and diagnosis: A review. Renewable & Sustainable Energy Reviews, 2021, 138: 110512
https://doi.org/10.1016/j.rser.2020.110512
25 X Lu, P Lin, S Cheng. et al.. Fault diagnosis model for photovoltaic array using a dual-channels convolutional neural network with a feature selection structure. Energy Conversion and Management, 2021, 248: 114777
https://doi.org/10.1016/j.enconman.2021.114777
26 B Zuo, Z Zhang, J Cheng. et al.. Data-driven flooding fault diagnosis method for proton-exchange membrane fuel cells using deep learning technologies. Energy Conversion and Management, 2022, 251: 115004
https://doi.org/10.1016/j.enconman.2021.115004
27 J NandyW HsuM L Lee. Towards maximizing the representation gap between in-domain & out-of-distribution examples. In: 34th Conference on Neural Information Processing Systems, 2020
28 M N NguyenX L LiS K Ng. Positive unlabeled learning for time series classification. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence—Volume Two, Barcelona, Catalonia, Spain, 2011
29 Y Wang, R Liu, D Lin. et al.. Coarse-to-fine: Progressive knowledge transfer-based multitask convolutional neural network for intelligent large-scale fault diagnosis. IEEE Transactions on Neural Networks and Learning Systems, 2021, 34(2): 761–774
https://doi.org/10.1109/TNNLS.2021.3100928
30 S Sun, T Wang, H Yang. et al.. Condition monitoring of wind turbine blades based on self-supervised health representation learning: A conducive technique to effective and reliable utilization of wind energy. Applied Energy, 2022, 313: 118882
https://doi.org/10.1016/j.apenergy.2022.118882
31 J Chen, X Xu, Z Yan. et al.. Data-driven distribution network topology identification considering correlated generation power of distributed energy resource. Frontiers in Energy, 2022, 16(1): 121–129
https://doi.org/10.1007/s11708-021-0780-x
32 X ZhaoJ YaoW Deng, et al.. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network. IEEE Transactions on Neural Networks and Learning Systems, 2022, online, https://doi.org/10.1109/TNNLS.2021.3135877
33 B Patnaik, M Mishra, R C Bansal. et al.. MODWT-XGBoost based smart energy solution for fault detection and classification in a smart microgrid. Applied Energy, 2021, 285: 116457
https://doi.org/10.1016/j.apenergy.2021.116457
34 H Shi, Y Li, X Bai. et al.. A two-stage sound-vibration signal fusion method for weak fault detection in rolling bearing systems. Mechanical Systems and Signal Processing, 2022, 172: 109012
https://doi.org/10.1016/j.ymssp.2022.109012
35 J Liang, K Zhang, A Al-Durra. et al.. A novel fault diagnostic method in power converters for wind power generation system. Applied Energy, 2020, 266: 114851
https://doi.org/10.1016/j.apenergy.2020.114851
36 N Sapountzoglou, J Lago, B De Schutter. et al.. A generalizable and sensor-independent deep learning method for fault detection and location in low-voltage distribution grids. Applied Energy, 2020, 276: 115299
https://doi.org/10.1016/j.apenergy.2020.115299
37 J Van Gompel, D Spina, C Develder. Satellite based fault diagnosis of photovoltaic systems using recurrent neural networks. Applied Energy, 2022, 305: 117874
https://doi.org/10.1016/j.apenergy.2021.117874
38 M Bai, X Yang, J Liu. et al.. Convolutional neural network-based deep transfer learning for fault detection of gas turbine combustion chambers. Applied Energy, 2021, 302: 117509
https://doi.org/10.1016/j.apenergy.2021.117509
39 Y Feng, J Chen, S He. et al.. Globally localized multisource domain adaptation for cross-domain fault diagnosis with category shift. IEEE Transactions on Neural Networks and Learning Systems, 2021, 1–15
https://doi.org/10.1109/TNNLS.2021.3111732
40 F SchroffD KalenichenkoJ Philbin. FaceNet: A unified embedding for face recognition and clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, 2015
41 T MikolovI SutskeverK Chen, et al.. Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013
42 M M Breunig, H P Kriegel, R T Ng. et al.. LOF: Identifying density-based local outliers. SIGMOD Record, 2000, 29(2): 93–104
https://doi.org/10.1145/335191.335388
43 A SaxenaK GoebelD Simon, et al.. Damage propagation modeling for aircraft engine run-to-failure simulation. In: 2008 International Conference on Prognostics and Health Management, Denver, CO, USA, 2008
44 R Sun, L Shi, X Yang. et al.. A coupling diagnosis method of sensors faults in gas turbine control system. Energy, 2020, 205: 117999
https://doi.org/10.1016/j.energy.2020.117999
45 J Chen, L Zhang, Y Li. et al.. A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems. Renewable & Sustainable Energy Reviews, 2022, 161: 112395
https://doi.org/10.1016/j.rser.2022.112395
46 H ZhouS ZhangJ Peng, et al.. Informer: Beyond efficient transformer for long sequence time-series forecasting. In: The 35th Conference on Artificial Intelligence, 2021
47 X Yang, Q Zhao, Y Wang. et al.. Fault signal reconstruction for multi-sensors in gas turbine control systems based on prior knowledge from time series representation. Energy, 2023, 262: 124996
https://doi.org/10.1016/j.energy.2022.124996
48 P J Rousseeuw, K V Driessen. A fast algorithm for the minimum covariance determinant estimator. Technometrics, 1999, 41(3): 212–223
https://doi.org/10.1080/00401706.1999.10485670
49 D M J Tax, R P W Duin. Support vector data description. Machine Learning, 2004, 54(1): 45–66
https://doi.org/10.1023/B:MACH.0000008084.60811.49
50 F T Liu, K M Ting, Z H Zhou. Isolation-based anomaly detection. ACM Transactions on Knowledge Discovery from Data, 2012, 6(1): 3
https://doi.org/10.1145/2133360.2133363
51 A van den OordY LiO Vinyals. Representation learning with contrastive predictive coding. arXiv:1807.03748 [cs.LG], 2019
52 S TonekaboniD EytanA Goldengerg. Unsupervised representation learning for time series with temporal neighborhood coding. In: International Conference on Learning Representations, 2021
53 L van der Maaten, G Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9: 2579–2605
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed