A Hybrid Deep Neural Network for Nonlinear Causality Analysis in Complex Industrial Control System

It is important to efficiently and accurately locate the fault root cause to maintain the control performance, when the industrial control system fails. However, this task is very challenging because the industrial control system is large in scale and complex in connection. This paper proposes a novel neural causality analysis network with directed acyclic graph to locate the root cause for complex industrial systems. This network fits the temporal nonlinearity and intervariable non-linearity to mine the causal graph. The proposed method is data-driven, which acts without process knowledge. Compared with the state-of-the-art, this method can effectively output accurate root cause from nonlinear and highly coupled data. The effectiveness and advantages are demonstrated by industrial cases.

1. INTRODUCTION

Many safety-critical industrial systems’ requirements for the accuracy and efficiency of system’s fault troubleshooting are increasing with the modern industry [1]. People are becoming less tolerant of performance degradation, productivity loss and security concerns. However, it is a challenging task to locate the root cause, because the industrial systems are with large scale and complex structure. Model-based approaches for root cause diagnosis require accruate process knowledges to analysis the process dynamics. Nevertheness, the more complex the mechanism model, the more uncertain assumptions it contains. Therefore, it is difficult to analyze the fault root cause by utilizing model-based methods in complex industrial systems.