Genetic algorithm optimized artificial immune system for fault detection in flight control systems

Purpose A genetic algorithm (GA)-optimized artificial immune system (AIS) for detecting potential failures in the flight control system was developed using a real-valued negative selection algorithm (RNSA) and V-detector algorithms. This paper aims to achieve the highest possible fault detection rate and the lowest false alarm rate. Design/methodology/approach GA-AIS software was developed using MATLAB R2023b for flight control system aileron position detection, using real flight data from a Turkish Airlines B737 aircraft. To test the GA-AIS software and evaluate its performance, faulty data were randomly generated. Findings To assess the performance of the GA-AIS software, fault detection rate, false alarm rate and sensitivity values were calculated and are presented comparatively in this paper. In addition, RNSA and V-detector algorithm self-space and detector-space visualizations, as well as fault detection rate versus false alarm rate graphs, are provided. Practical implications In the event of a fault occurring in flight control systems, this approach can facilitate the reliable and rapid implementation of anomaly detection and identification. Originality/value This paper presents a novel method based on GA-AIS for fault detection in flight control systems. The methodology is cost-effective as it is implemented entirely through software.