A Novel Adaptive Undersampling Framework for Class-Imbalance Fault Detection

• Published in: IEEE transactions on reliability Vol. 72; no. 3; pp. 1 - 15
• Main Authors: Qian, Min, Li, Yan-Fu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Class-imbalance; cluster analysis; Clustering; Datasets; Decision making; Deep learning; Divergence; Diversity reception; Fault detection; High speed rail; Markov processes; Optimization; Reinforcement learning; Samplers; Sampling; Task analysis; Training; Turbine blades; undersampling ensemble; Wind turbines
• ISSN: 0018-9529; 1558-1721
• DOI: 10.1109/TR.2022.3214519

Class-imbalance is a prevalent and challenging problem in the field of fault detection. The undersampling ensemble framework is an effective method to deal with imbalance problems. However, designing a suitable sampling strategy to generate effective and divergent subsets is a major difficulty of this type of method. Hence, we propose a novel adaptive undersampling framework. It models the entire training process as a Markov decision process (MDP), thus, enabling dynamic decision-making for subsequent sampling strategies based on the current training performance of the ensemble framework. The sampler is optimized by the soft actor-critic reinforcement learning method. Considering the imbalance dataset's nature and the need for state definition, the clustering method is applied to the original training dataset. The state (training performance) and the action (sampling strategy) are determined according to the clustering results. The unique state definition and sampling decision mechanism are designed to ensure the convergence speed of MDP and improve the divergence of the subsets. We validate the effectiveness of the proposed framework on the real-world wind turbine blade cracking datasets and the high-speed train braking system dataset. The experimental results show that the classification performance and robustness of the proposed framework are significantly better than the 16 benchmark methods.