A label description space embedded model for zero-shot intelligent diagnosis of mechanical compound faults

• Published in: Mechanical systems and signal processing 2022-01, Vol.162, p.108036, Article 108036
• Main Authors: Xing, Saibo, Lei, Yaguo, Wang, Shuhui, Lu, Na, Li, Naipeng
• Format: Article
• Language: English
• Subjects: Compound fault diagnosis; Datasets; Fault diagnosis; Gearboxes; Label description space; Mechanical fault diagnosis; Semantic relationship; Training; Zero-shot learning
• ISSN: 0888-3270; 1096-1216
• DOI: 10.1016/j.ymssp.2021.108036

•A zero-shot intelligent diagnosis method for mechanical compound faults is proposed.•A label description space is built to represent the semantic relationship among different fault patterns.•A new method is proposed to calculate prototypes of health conditions in the label description space.•A label description space embedded model is proposed for unseen compound fault diagnosis. It has always been an issue of significance to diagnose compound faults of machines. Existing intelligent diagnosis methods have to be trained by sufficient data of each compound fault. However, both labeled and unlabeled data of mechanical compound faults are usually difficult to collect or even completely inaccessible for training in real scenarios. Therefore, compound faults are usually unseen fault patterns. Unseen fault patterns are those that have no labeled or unlabeled training data. Without training data of compound faults, the current intelligent diagnosis methods usually fail in recognizing compound faults. This paper proposes a zero-shot intelligent diagnosis method for unseen compound faults of machines. The proposed method contains three stages, i.e., the feature learning, pre-judgment and fault recognition. The key to this method is a label description space embedded model for intelligent fault diagnosis (LDS-IFD) in Stage 3. In LDS-IFD, a label description space (LDS) is built to construct the relationship among different fault patterns. LDS is embedded between the feature space (FS) and the health condition label space (HCLS). Then the projection between FS and LDS is constructed by a linear supervised autoencoder (LSAE). By similarity evaluation in LDS or FS, LDS-IFD is able to recognize mechanical compound faults when only the data of single faults are accessible for training. The proposed method is demonstrated on a bearing dataset and a planetary gearbox dataset. Results show that the proposed method is effective in diagnosing unseen compound faults of machines.