A Rule-Based Fault Detection Approach for Aircraft Control System Using Data Correlation

The normal operation of an aircraft control system directly determines whether the aircraft can successfully carry out flight missions. Therefore, it is of great significance to conduct fault detection on the control system. Currently, common engineering methods for anomaly detection based on design thresholds have some problems, which are as follows. Firstly, the thresholds determined in the design phase differ from actual usage, resulting in poor anomaly detection effectiveness. Secondly, the control system has various types of faults, some of which cannot be detected through threshold-based methods. To solve these problems, this paper proposes a method based on the Inductive Monitoring System (IMS) algorithm to update thresholds for improving fault detection performance, and utilizes the FP-Growth algorithm for parameter association analysis to handle anomalies that cannot be detected through threshold-based methods. The effectiveness of the proposed method is proved by experiments.