A Two-Stage Fault Detection and Isolation Platform for Industrial Systems Using Residual Evaluation

作者：Heydarzadeh Mehrdad^*; Nourani Mehrdad

来源：IEEE Transactions on Instrumentation and Measurement, 2016, 65(10): 2424-2432.

DOI：10.1109/TIM.2016.2575179

• Discrete wavelet transforms (DWTs)
• fault detection
• fault diagnosis
• pneumatic actuators
• residual analysis
• support vector machines
• system identification

Fault detection and isolation (FDI) is an important part of modern industrial systems, and plays a vital role in maintainability, safety, and reliability of process. We propose a novel FDI architecture based on a predictive model for fault-free process. We use the least-square support vector machine for identifying a nonlinear system and detecting its faults that may occur. Wavelet analysis on residual is used for fault isolation. An average accuracy of 95% has been achieved for all the abrupt faults of the well-known development and application of methods for actuator diagnosis in industrial control systems benchmark.

• 出版日期2016-10