Active learning-assisted semi-supervised learning for fault detection and diagnostics with imbalanced dataset

• Published in: IIE transactions Vol. 55; no. 7; pp. 672 - 686
• Main Authors: Peng, Xiaomeng, Jin, Xiaoning, Duan, Shiming, Sankavaram, Chaitanya
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis 03.07.2023; Taylor & Francis Ltd
• Subjects: Active learning; Air intakes; Algorithms; Datasets; Failure modes; Fault detection; fault detection and diagnostics; imbalanced data; Intake systems; Labels; Machine learning; Multiple criterion; Prediction models; Semi-supervised learning; Synthetic data
• ISSN: 2472-5854; 2472-5862
• DOI: 10.1080/24725854.2022.2074579

Data-driven Fault Detection and Diagnostics (FDD) methods often assume that sufficient labeled samples are class-balanced and faulty classes in testing are precedent or seen previously during model training. When monitoring a large fleet of assets at scale, these assumptions may be violated: (I) only a limited number of samples can be manually labeled due to constraints of time and/or cost; (II) most of the samples collected in the engineering systems are under normal conditions, leading to a highly imbalanced class distribution and a biased prediction model. This work presents a robust and cost-effective FDD framework that integrates active learning and semi-supervised learning methods to detect both known and unknown failure modes iteratively. This framework allows to strategically select the samples to be annotated from a fully unlabeled dataset, while labeling cost is minimal. Specifically, a novel graph-based semi-supervised classifier with adaptive graph construction is developed to predict labels with imbalanced data and detect novel classes. We designed a multi-criteria active learning sampling strategy to select the most informative samples from unlabeled data in order to query minimal number of labels for classification. We tested the framework and algorithms in three synthetic datasets and one real-world dataset of vehicle air intake systems, and demonstrated the superior performance compared to the state-of-the-art methods for fleet-level FDD.