A data-driven distributed fault diagnosis scheme for large-scale systems based on correlation analysis

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. 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 mitigate the impact of noise-induced uncertainty on fault detection performance. Then, a fault localization approach is developed to locate the fault by measuring and comparing the degree of abnormality.image

Automated summary

This paper explores data-driven distributed fault diagnosis for large-scale systems using sensor networks. It introduces a distributed fault detection scheme based on correlation analysis to enhance fault detection performance by reducing the impact of noise-induced uncertainty. The method focuses on implementing the correlation of coupled nodes to minimize the covariance of the residual signal in a distributed manner. Additionally, a fault localization approach is developed to identify faults by measuring and comparing the degree of abnormality.