AI-Based Actuator/Sensor Fault Detection With Low Computational Cost for Industrial Applications

Abstract—A low computational cost method is proposed for detecting actuator/sensor faults. Typical model-based fault detection units for multiple sensor faults, require a bank of estimators (i.e., conventional Kalman estimators or artificial intelligence based ones). The proposed fault detection scheme uses an artificial intelligence approach for developing of a low computational power fault detection unit abbreviated as ‘iFD’. In contrast to the bank-of-estimators approach, the proposed iFD unit employs a single estimator for multiple actuator/sensor fault detection. The efficacy of the proposed fault detection scheme is illustrated through a rigorous analysis of the results for a number of sensor fault scenarios on an electromagnetic suspension system.

• Type: Journal
• Year: 2016
• Where: TCST
• Authors: Konstantinos Michail, Kyriakos M. Deliparaschos, Spyros G. Tzafestas, Argyrios C. Zolotas
• Keywords: TCST 2016