Abstract in English:

This paper studies data-driven distributed fault diagnosis for large-scale systems using sensor networks. To be specific, a distributed fault detection scheme based on correlation analysis is first proposed to improve the fault detection performance by minimizing the impact of noise-induced uncertainty. The core of the method is to implement the correlation of the coupled nodes to reduce the covariance of the residual signal in a distributed manner. Then, a fault localization approach is developed to locate the fault by measuring and comparing the degree of abnormality. A case study on Tennessee Eastman process is given in the end to demonstrate the proposed approach.