An approach to fault detection and isolation for control components in the aircraft environmental control system

Abstract

Control components of the aircraft environmental control system (AECS), which is fast becoming an increasingly complex system, are of significant importance from the viewpoint of safety. However, few studies have focused on fault diagnosis of the AECS. This study proposes a method based on adaptive threshold and parameter extraction (ATPE) to realize fault detection and isolation for control components in the AECS. To overcome the drawback of a fixed threshold for fault detection, a practical approach is employed by combining a radial basis function (RBF)-based observer with an RBF-based adaptive threshold producer. The RBF neural network observer is used to generate a residual error signal. By comparing the residual error signal with the adaptive threshold, fault occurrence can be detected. To improve the fault isolation accuracy, an RBF fault tracker is used; the parameters of this tracker are extracted for fault isolation along with the residual error, unlike in the case of conventional fault diagnosis methods that are based on a single residual error signal. Finally, an RBF-based fault isolator is adopted to realize fault isolation and classification. Two commonly occurring faults in the control components of the AECS are simulated to verify the performance and effectiveness of the proposed method. The experimental results demonstrate that the proposed method based on ATPE is effective for fault detection and isolation for the control components in the AECS.