基于PSO-BP神经网络的发动机故障诊断

Engine Fault Diagnosis Based on PSO-BP Neural Network

提出一种将粒子群优化算法与BP网络结合的新算法——PSO-BP来训练神经网络的权值和阈值,并将该算法用于汽车发动机的故障诊断。仿真结果表明:PSO-BP算法较传统BP网络的故障诊断结果具有收敛速度快、准确度和精度高的特点。

A novel algorithm which combing PSO and BP was presented for engine fault diagnosis and to train both weight and threshold value of neural network.The simulation results show that this PSO-BP algorithm outperforms the traditional BP network diagnosis in convergence rate and diagnosis precision.