A Genetic-Based Fuzzy Clustering Algorithm for Fault Diagnosis in Satellite Attitude Determination System

摘要

The paper presents a genetic-based fuzzy clustering algorithm for fault diagnosis in satellite attitude determination system (ADS). The traditional fuzzy c-means(FCM) algorithm is local search techniques that search for the optimum by using a hill-climbing techniques. Thus, it often fail in the search for global optimum. Genetic algorithm is a stochastic global optimization algorithm, their combination can prevent FCM being trapped in a local optimum and sensitive to the initializations. Simulation results show that the proposed approach have much higher probabilities of finding global optimal solutions than traditional FCM algorithm, and provide accurate clustering for fault mode