Explainable fault diagnosis method for process flow based on data augmentation with system graph relationship

Abstract

The main objective of process industrial systems is to ensure safe operation. Signal fluctuations resulting from equipment failures and variable abnormalities can progressively propagate over the entire system, potentially resulting in fault conditions. However, the sporadic occurrence of fault conditions leads to a scarcity of data samples for diagnosis models. A fault diagnosis method for process flow based on data augmentation with system graph relationships is proposed. Propagation paths of fault signals are generated through graph relationships of systems. Simultaneously, the data of multiple nodes in paths is transformed to generate augmentation samples. To ensure comprehensive learning of the information included in augmentation samples, a large number of samples are generated for pre-training based on real-world data from a system. The explainability analysis method is used to analyze the focus area of diagnostic networks on samples with and without augmentation. The experimental results demonstrate that the proposed method can substantially improve diagnostic accuracy and explainability, hence offering advantages for diagnosis tasks in small sample cases.