Application of the Enhanced Dynamic Causal Digraph Method on a Three-Layer Board Machine

Abstract

This brief presents an enhanced dynamic causal digraph (EDCDG) reasoning method for fault diagnosis. In order to improve the fault isolation ability of the dynamic causal digraph method, a new algorithm for separating the positive and negative fault effect contributions is proposed. The proposed method was tested with an application on a three-layer board machine process. The results show that the proposed method, compared to the conventional dynamic causal digraph method, is able to detect the correct nodes, to form a better fault propagation path and to identify the responsible arcs when the system is affected by a process fault.