A Novel Data-Driven Fault Detection Method Based on Stable Kernel Representation for Dynamic Systems

Abstract

With the steady improvement of advanced manufacturing processes and big data technologies, modern industrial systems have become large-scale. To enhance the sensitivity of fault detection (FD) and overcome the drawbacks of the centralized FD framework in dynamic systems, a new data-driven FD method based on Hellinger distance and subspace techniques is proposed for dynamic systems. Specifically, the proposed approach uses only system input/output data collected via sensor networks, and the distributed residual signals can be generated directly through the stable kernel representation of the process. Based on this, each sensor node can obtain the identical residual signal and test statistic through the average consensus algorithms. In addition, this paper integrates the Hellinger distance into the residual signal analysis for improving the FD performance. Finally, the effectiveness and accuracy of the proposed method have been verified in a real multiphase flow facility.

Sensor Fusion for Power Line Sensitive Monitoring and Load State Estimation

“…The importance of this task is not just limited to technical systems; it is important and crucial in any field of application. In this context, a recent proposed approach in [ 3 ] investigates a general method that uses only system input/output data collected via sensor networks. It proposes a new method to analyze the residual signals, which are combined with the Hellinger distance to improve the performance of the method.…”

“…It proposes a new method to analyze the residual signals, which are combined with the Hellinger distance to improve the performance of the method. The method proposed in [ 3 ] takes into particular consideration the presence of noise. In fact, in the presence of strong noise, detecting faults becomes a difficult task.…”