Fault Detection and Isolation Based on Extreme Learning Machine optimized by Genetic Algorithm for Flight Control System

Fault detection and isolation (FDI) plays an important role in the safe operation of flight control system. For a complex flight control system, it is difficult to build an accurate physical model, so data-driven method has emerged. In this paper, an extreme learning machine (ELM) method optimized by genetic algorithm (GA) is proposed. Compared with traditional feed-forward neural network, ELM has great generalization performance at a high learning speed. Furthermore, GA is used in this method to adjust hidden nodes parameters to find the most suitable parameters that minimizes the ELM model error. What is more, different fault models are built respectively, so as to achieve the purpose of fault isolation. All in all, the proposed method can isolate fault while optimizing the extreme learning machine.