Oppositional Particle Swarm Optimization Algorithm and Its Application to Fault Monitor

In order to improve the real time of aircraft engine fault diagnosis, particle swarm optimization (PSO) is applied to select feature parameters of fault monitor. To tackle the slow nature of PSO, an oppositional particle swarm optimization (OPSO) algorithm is presented in this paper. Utilizing the acceleration performance of opposition-based learning (OBL), it employs OBL for population initialization and also for generation updating to accelerate the evolutionary process, improve the searching capability, and shorten the computing time. Also it has some merits including simpleness and easy implement. Through the benchmark functions and feature parameters selection problem, it demonstrates that the proposed algorithm is effective and superior.