Fault Detection of Associated Complex Systems Using Integrated Complex Network Theory with SVM

Fault detection in industrial process is a popular research because it is very important for production and quality. In this paper, we proposed a novel method, integrated complex network theory with support vector machine(SVM), for fault detection of associated complex systems. The proposed method takes global information of measured variables into account by complex network model and predicts whether a system has generated some faults or not by SVM. The experiments show that this method works well and can be a useful supplement for fault detection of associated complex systems.