Abstract
Intelligent fault diagnosis plays an important role in machine health management. Fault data in real applications are usually imbalanced, which makes some categories unknown to the learner. Some recent approaches assign an unknown label to all these categories, which may not be sufficient for further remending operations. This paper proposes unknown fault category exploration through active query evidence model (UFAE), which effectively distinguishes unknown faults, and balances the query to various unknown sub-faults, thereby providing better fault identification. First, we introduce subjective logic to model data evidence, to effectively explore instances with unknown faults. Second, we propose an active query strategy to select unknown subfaults. This process is executed iteratively to explore as many unknown sub-faults as possible, and eventually produces a high quality learner. We conducted experiments on classic fault datasets, including bearing structured data and pumping unit image data. The experimental results showed that UFAE achieved effective unknown sub-fault identification and outperformed competitors in open fault identification. Additionally, UFAE was more robust to unknown faults.
Similar content being viewed by others
References
Li, S, Cui, Z, Ye, X, Feng, J, Yang, Y, He, Z (2020). Chip-Based Microwave-Photonic Radar for High-Resolution Imaging. Laser & Photonics Reviews, 14(10). http://ides.nuaa.edu.cn
Asad B, Vaimann T, Belahcen A, Kallaste A, Rassõlkin A, Iqbal MN (2020) The cluster computation-based hybrid fem-analytical model of induction motor for fault diagnostics. Applied Sciences 10(21). https://doi.org/10.3390/app10217572. https://www.mdpi.com/2076-3417/10/21/7572
Bendale A, Boult TE (2016) Towards open set deep networks. In: Proc IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 1563–1572. IEEE Computer Society
Bosman AS, Engelbrecht A, Helbig M (2020) Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions. Neurocomputing 400:113–136. https://doi.org/10.1016/j.neucom.2020.02.113. https://www.sciencedirect.com/science/article/pii/S0925231220303593
Boztas G, Tuncer T (2022) A fault classification method using dynamic centered one-dimensional local angular binary pattern for a pmsm and drive system. Neural Comput Appl 34(3):1981–1992. https://doi.org/10.1007/s00521-021-06534-1
Chang N, Yu ZD, Wang YX, Anandkumar A, Fidler S, Alvarez JM (2021) Image-level or object-level? A tale of two resampling strategies for long-tailed detection. In: Proc Int Conf Mach Learn (ICML), pp 1463–1472
Chen M, Zhu K, Wang R, Niyato D (2020) Active learning-based fault diagnosis in self-organizing cellular networks. IEEE Commun Lett 24(8):1734–1737. https://doi.org/10.1109/LCOMM.2020.2991449
Cheng DD, Liu LJ, Yu Z (2021) Cnn-based intelligent fault-tolerant control design for turbofan engines with actuator faults. IEEE Access 9:28122–28139
Chu P, Bian X, Liu SP, Ling HB (2020) Feature space augmentation for long-tailed data. In: Proc Eur Conf Comput Vis (ECCV), pp 694–710
De Almeida LF, Bizarria JW, Bizarria FC, Mathias MH (2015) Condition-based monitoring system for rolling element bearing using a generic multi-layer perceptron. J Vib Control 21(16):3456–3464
Dempster AP (1967) Upper and lower probabilities induced by a multivalued mapping. Annals Math Stat 38(2):325–339
Du WL, Tao JF, Li YM, Liu CL (2014) Wavelet leaders multifractal features based fault diagnosis of rotating mechanism. Mech Syst Signal Proc 43(1–2):57–75
Gal Y, Ghahramani Z (2016) Bayesian convolutional neural networks with bernoulli approximate variational inference. Proc Int Conf Learn Represent (ICLR)
Han ZY, Wang J (2018) A fault diagnosis method based on active example selection. J Circuits Syst Comput 27(01):1850013
He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. In: Proc. IEEE Conf Comput Vis Pattern Recognit (CVPR), pp 770–778
He Y, Song KC, Meng QG, Yan YH (2019) An end-to-end steel surface defect detection approach via fusing multiple hierarchical features. IEEE Trans Instrum Meas 69(4):1493–1504
Hong W, Cai WJ, Wang S, Mileta MT (2018) Mechanical wear debris feature, detection, and diagnosis: A review. Chin J Aeronaut 31(5):867–882
Jian CX, Yang KJ, Ao YH (2021) Industrial fault diagnosis based on active learning and semi-supervised learning using small training set. Eng Appl Artif Intell 104:104365. https://doi.org/10.1016/j.engappai.2021.104365
Jøsang A (2016) Subjective Logic: A formalism for reasoning under uncertainty. Intell. Found. Theory Algorithms. Springer, Artif. https://doi.org/10.1007/978-3-319-42337-1
Jun LW, Hui L, Sai G, Tao C (2020) Process fault diagnosis with model- and knowledge-based approaches: Advances and opportunities. Control Eng Pract 105:104637. https://doi.org/10.1016/j.conengprac.2020.104637. https://www.sciencedirect.com/science/article/pii/S0967066120302070
Jung D (2020) Data-driven open-set fault classification of residual data using bayesian filtering. IEEE Trans Control Syst Technol 28(5):2045–2052
Kingma DP, Salimans T, Welling M (2015) Variational dropout and the local reparameterization trick. Proc Neural Inf Process Syst (NIPS) 28
Lao ZP, He DQ, Wei ZX, Hui S, Jin ZZ, Jian M, Hui RC (2023) Intelligent fault diagnosis for rail transit switch machine based on adaptive feature selection and improved lightgbm. Eng Failure Anal 148:107219. https://doi.org/10.1016/j.engfailanal.2023.107219. https://www.sciencedirect.com/science/article/pii/S1350630723001735
Lee K, Lee H, Lee K, Shin, J (2018) Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: Proc Int Conf Learn Represent (ICLR)
Liu XM, Ming XN (2019) A nonlinear grey forecasting model with double shape parameters and its application. Appl Math Comput 360:203–212. https://doi.org/10.1016/j.amc.2019.05.012. https://www.sciencedirect.com/science/article/pii/S0096300319304059
Lv XX, Wang HX, Zhang X, Liu YX, Jiang D, Wei B (2021) An evolutional svm method based on incremental algorithm and simulated indicator diagrams for fault diagnosis in sucker rod pumping systems. J Pet Sci Eng 203:108806. https://doi.org/10.1016/j.petrol.2021.108806
Molchanov D, Ashukha A, Vetrov D (2017) Variational dropout sparsifies deep neural networks. In: Proc Int Conf Mach Learn (ICML), pp 2498–2507
Mundt M, Pliushch I, Majumder S, Ramesh V (2019) Open set recognition through deep neural network uncertainty: does out-of-distribution detection require generative classifiers?. In: Proc IEEE/CVF Int Conf Comput Vis (ICCV), pp 753–757
Nielsen, F (2022) The kullback–leibler divergence between lattice gaussian distributions. Journal of the Indian Institute of Science pp 1–12
Riaz N, Shah SIA, Rehman F, Gilani SO, Udin E (2020) A novel 2-d current signal-based residual learning with optimized softmax to identify faults in ball screw actuators. IEEE Access 8:115299–115313. https://doi.org/10.1109/ACCESS.2020.3004489
Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: ECCV, pp. 213–226. Springer
Sensoy M, Kaplan L, Kandemir M (2018) Evidential deep learning to quantify classification uncertainty. pp 3183–3193
Shafer G (1976) A mathematical theory of evidence. Princeton University Press
Smith WA, Randall RB (2015) Rolling element bearing diagnostics using the case western reserve university data: A benchmark study. Mech Syst Signal Proc 64:100–131
Tang YP, Huang SJ (2019) Self-paced active learning: Query the right thing at the right time. Proc. AAAI 33:5117–5124
Thomas JB, Chaudhari SG, Shihabudheen KV, Verma NK (2023) Cnn-based transformer model for fault detection in power system networks. IEEE Trans Instrum Meas 72:1–10. https://doi.org/10.1109/TIM.2023.3238059
Tian Y, Wang ZL, Zhang LP, Lu C, Ma J (2018) A subspace learning-based feature fusion and open-set fault diagnosis approach for machinery components. Adv Eng Inform 36:194–206
Van M, Kang HJ (2015) Bearing defect classification based on individual wavelet local fisher discriminant analysis with particle swarm optimization. IEEE Trans Ind Informat 12(1):124–135
Wang M, Fu K, Min F, Jia XY (2020) Active learning through label error statistical methods. Knowl-Based Syst 189:105140
Wang M, Yang CY, Zhao F, Min F, Wang XZ (2022) Cost-sensitive active learning for incomplete data. IEEE Trans Syst Man Cybern -Syst, pp 1–12. https://doi.org/10.1109/TSMC.2022.3182122
Wang M, Zhou L, Li Q, Aa Zhang (2023) Open world long-tailed data classification through active distribution optimization. Exp Syst Appl 213:119054. https://doi.org/10.1016/j.eswa.2022.119054. https://www.sciencedirect.com/science/article/pii/S0957417422020723
Wang T, Zhang L, Wang X (2023) Fault detection for motor drive control system of industrial robots using cnn-lstm-based observers. CES Transactions on Electrical Machines and Systems pp. 1–9. https://doi.org/10.30941/CESTEMS.2023.00014
Wang ZR, Wang J, Wang YR (2018) An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition. Neurocomputing 310:213–222. https://doi.org/10.1016/j.neucom.2018.05.024
Yan WH, Wang J, Lu S, Zhou M, Peng X (2023) A review of real-time fault diagnosis methods for industrial smart manufacturing. Processes 11(2). https://doi.org/10.3390/pr11020369. https://www.mdpi.com/2227-9717/11/2/369
Yang J, Yang Y, Xie G (2020) Diagnosis of incipient fault based on sliding-scale resampling strategy and improved deep autoencoder. IEEE Sensors J 20(15):8336–8348. https://doi.org/10.1109/JSEN.2020.2976523
Yu XL, Zhao ZB, Zhang XW, Sun C, Zhang QY, Chen XF (2020) Coupling deep models and extreme value theory for open set fault diagnosis. In: Int Conf Sens Meas Data Anal, pp 118–123
Zhang C, Guo QX, Li Y (2020) Fault detection in the tennessee eastman benchmark process using principal component difference based on k-nearest neighbors. IEEE Access 8:49999–50009
Zhang C, Xu LQ, Li XW, Wang HY (2018) A method of fault diagnosis for rotary equipment based on deep learning. In: Prognostics System Health Manag. Conf, pp 958–962
Zhang JQ, Sun Y, Guo L, Gao HL, Hong X, Song HL (2020) A new bearing fault diagnosis method based on modified convolutional neural networks. Chin J Aeronaut 33:439–447
Zhang TC, Chen JL, Li FD, Zhang KY, Lv HX, He SL, Xu EY (2022) Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions. ISA Trans 119:152–171. https://doi.org/10.1016/j.isatra.2021.02.042
Zhao X, Xiao J, Yu S, Li H, Zhang B (2023) Weight-guided class complementing for long-tailed image recognition. Pattern Recognit 138:109374. https://doi.org/10.1016/j.patcog.2023.109374. https://www.sciencedirect.com/science/article/pii/S0031320323000754
Zhou ZH (2022) Open-environment machine learning. Natl Sci Rev 9(8):nwac123
Zou L, Li Y, Xu FY (2020) An adversarial denoising convolutional neural network for fault diagnosis of rotating machinery under noisy environment and limited sample size case. Neurocomputing 407:105–120
Acknowledgements
This work was supported by the National Natural Science Foundation of China (62006200); the Natural Science Foundation of Sichuan Province (2022YFG0179); the Open Fund of State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation (Chengdu University of Technology) (PLC20211104); Science and Technology Cooperation Project of the CNPC-SWPU Innovation Alliance (2020CX020000). We thank Liwen Bianji (Edanz) (www.liwenbianji.cn/) for editing the English text of a draft of this manuscript.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, M., Jiang, X., Wen, T. et al. Discover unknown fault categories through active query evidence model. Appl Intell 53, 27808–27825 (2023). https://doi.org/10.1007/s10489-023-04965-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04965-y