Abstract
Fault classification plays a crucial role in the industrial process monitoring domain. In the datasets collected from real-life industrial processes, the data distribution is usually imbalanced. The datasets contain a large amount of normal data (majority) and only a small amount of faulty data (minority); this phenomenon is also known as the imbalanced fault classification problem. To solve the imbalanced fault classification problem, a novel reinforcement learning (RL)-based cost-sensitive classifier (RLCC) based on policy gradient is proposed in this paper. In RLCC, a novel cost-sensitive learning strategy based on policy gradient and the actor-critic of RL is developed. The novel cost-sensitive learning strategy can adaptively learn the cost matrix and dynamically yield the sample weights. In addition, RLCC uses a newly designed reward to train the sample weight learner and classifier using an alternating iterative approach. The alternating iterative approach makes RLCC highly flexible and effective in solving the imbalanced fault classification problem. The effectiveness and practicability of the proposed RLCC method are verified through its application in a real-world dataset and an industrial process benchmark.
Similar content being viewed by others
References
Kano M, Nakagawa Y. Data-based process monitoring, process control, and quality improvement: recent developments and applications in steel industry. Comput Chem Eng, 2008, 32: 12–24
Ge Z, Song Z, Ding S X, et al. Data mining and analytics in the process industry: the role of machine learning. IEEE Access, 2017, 5: 20590–20616
Zhu Z R, Chai Y, Yang Z M. A novel kind of sufficient conditions for safety judgement based on control barrier function. Sci China Inf Sci, 2021, 64: 199205
Zhang X, Wei C, Song Z. Fast locally weighted PLS modeling for large-scale industrial processes. Ind Eng Chem Res, 2020, 59: 20779–20786
Khatibisepehr S, Huang B, Khare S. Design of inferential sensors in the process industry: a review of Bayesian methods. J Process Control, 2013, 23: 1575–1596
Zhou D H, Qin L G, He X, et al. Distributed sensor fault diagnosis for a formation system with unknown constant time delays. Sci China Inf Sci, 2018, 61: 112205
Huang D Q, Fu Y Z, Qin N, et al. Fault diagnosis of high-speed train bogie based on LSTM neural network. Sci China Inf Sci, 2021, 64: 119203
Chen G, Liu Y, Ge Z. K-means Bayes algorithm for imbalanced fault classification and big data application. J Process Control, 2019, 81: 54–64
Kubat M, Holte R C, Matwin S. Machine learning for the detection of oil spills in satellite radar images. Machine Learn, 1998, 30: 195–215
Krawczyk B. Learning from imbalanced data: open challenges and future directions. Prog Artif Intell, 2016, 5: 221–232
Wang X Y, Liu B, Cao S Y, et al. Important sampling based active learning for imbalance classification. Sci China Inf Sci, 2020, 63: 182104
Jiang X, Ge Z. Data augmentation classifier for imbalanced fault classification. IEEE Trans Automat Sci Eng, 2020, 18: 1206–1217
Fan S, Zhang X, Song Z. Imbalanced sample selection with deep reinforcement learning for fault diagnosis. IEEE Trans Ind Inf, 2021, 18: 2518–2527
Yue G, Wei P, Liu Y, et al. Automated endoscopic image classification via deep neural network with class imbalance loss. IEEE Trans Instrum Meas, 2023, 72: 1–11
Santos M S, Abreu P H, Japkowicz N, et al. On the joint-effect of class imbalance and overlap: a critical review. Artif Intell Rev, 2022, 55: 6207–6275
Hoskins J C, Himmelblau D M. Artificial neural network models of knowledge representation in chemical engineering. Comput Chem Eng, 1988, 12: 881–890
Hastie T, Rosset S, Zhu J, et al. Multiclass AdaBoost. Stat Its Interface, 2009, 2: 349–360
Krempl G, Kottke D, Lemaire V. Optimised probabilistic active learning (OPAL). Mach Learn, 2015, 100: 449–476
Castro C L, Braga A P. Novel cost-sensitive approach to improve the multilayer perceptron performance on imbalanced data. IEEE Trans Neural Netw Learn Syst, 2013, 24: 888–899
Zheng J. Cost-sensitive boosting neural networks for software defect prediction. Expert Syst Appl, 2010, 37: 4537–4543
Zhang C, Tan K C, Ren R. Training cost-sensitive deep belief networks on imbalance data problems. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), 2016. 4362–4367
Sun Y, Kamel M S, Wang Y. Boosting for learning multiple classes with imbalanced class distribution. In: Proceedings of the 6th International Conference on Data Mining (ICDM’06), 2006. 592–602
Williams R J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn, 1992, 8: 229–256
Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique. J Artif Intell Res, 2002, 16: 321–357
Ling C X, Yang Q, Wang J, et al. Decision trees with minimal costs. In: Proceedings of the 21st International Conference on Machine Learning, 2004. 69
Zadrozny B, Elkan C. Learning and making decisions when costs and probabilities are both unknown. In: Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2001. 204–213
Zadrozny B, Langford J, Abe N. Cost-sensitive learning by cost-proportionate example weighting. In: Proceedings of the 3rd IEEE International Conference on Data Mining, 2003. 435–442
Sun Y, Kamel M S, Wong A K C, et al. Cost-sensitive boosting for classification of imbalanced data. Pattern Recognition, 2007, 40: 3358–3378
Ting K M. A comparative study of cost-sensitive boosting algorithms. In: Proceedings of the 17th International Conference on Machine Learning, 2000. 983–990
Shawe-Taylor G K J, Karakoulas G. Optimizing classiffiers for imbalanced training sets. In: Proceedings of Advances in Neural Information Processing Systems, 1999. 11: 253
Viola P, Jones M. Fast and robust classiffication using asymmetric adaboost and a detector cascade. In: Proceedings of Advances in Neural Information Processing System, 2001. 14
Zhou Z-H, Liu X-Y. Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng, 2005, 18: 63–77
Sutton R S, McAllester D A, Singh S P, et al. Policy gradient methods for reinforcement learning with function approximation. In: Proceedings of Advances in Neural Information Processing Systems, 2000. 1057–1063
Konda V R, Tsitsiklis J N. Actor-critic algorithms. In: Proceedings of Advances in Neural Information Processing Systems, 2000. 1008–1014
Bhatnagar S, Sutton R S, Ghavamzadeh M, et al. Natural actor-critic algorithms. Automatica, 2009, 45: 2471–2482
Chen J, Tsai C-A, Chen J J, et al. Decision threshold adjustment in class prediction. SAR QSAR Environ Res, 2006, 17: 337–352
Alejo R, Sotoca J M, Casañ G A. An empirical study for the multiclass imbalance problem with neural networks. In: Proceedings of Iberoamerican Congress on Pattern Recognition, 2008. 479–486
Joshi M V, Kumar V, Agarwal R C. Evaluating boosting algorithms to classify rare classes: comparison and improvements. In: Proceedings of IEEE International Conference on Data Mining, 2001. 257–264
Brodersen K H, Ong C S, Stephan K E, et al. The balanced accuracy and its posterior distribution. In: Proceedings of the 20th International Conference on Pattern Recognition, 2010. 3121–3124
Opitz J, Burst S. Macro F1 and Macro F1. 2019. ArXiv:1911.03347
Alejo R, García V, Sotoca J M, et al. Improving the performance of the RBF neural networks trained with imbalanced samples. In: Proceedings of International Work Conference on Artificial Neural Networks, 2007. 162–169
Wu Z, Lin W, Ji Y. An integrated ensemble learning model for imbalanced fault diagnostics and prognostics. IEEE Access, 2018, 6: 8394–8402
Moreno-Torres J G, Sáez J A, Herrera F. Study on the impact of partition-induced dataset shift on k-fold cross-validation. IEEE Tr ans Neural Netw Learn Syst, 2012, 23: 1304–1312
van Maaten L D. Accelerating t-SNE using tree-based algorithms. J Machine Learn Res, 2014, 15: 3221–3245
Lyman P R, Georgakis C. Plant-wide control of the Tennessee Eastman problem. Comput Chem Eng, 1995, 19: 321–331
Yin S, Ding S X, Haghani A, et al. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process. J Process Control, 2012, 22: 1567–1581
Acknowledgements This work was supported in part by National Natural Science Foundation of China (Grant Nos. 62003301, 61833014) and Natural Science Foundation of Zhejiang Province (Grant No. LQ21F030018).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, X., Fan, S. & Song, Z. Reinforcement learning-based cost-sensitive classifier for imbalanced fault classification. Sci. China Inf. Sci. 66, 212201 (2023). https://doi.org/10.1007/s11432-021-3775-4
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-021-3775-4