摘要
为提高对失水事故的诊断能力,在反向传播(BP)算法基础上,建立基于粒子群优化(PSO)算法的故障诊断网络,利用PSO算法训练神经网络的权重和阈值,以克服BP算法易陷入局部极小问题。仿真试验表明,该诊断网络对失水事故有较高的诊断精度。
In order to improve the diagnosis performance of Loss of Coolant Accident（LOCA）, based on Back Propagation（BP） algorithm study, a fault diagnosis network is established based on Particle Swarm Optimization（PSO） algorithm in this paper. The PSO algorithm is used to train the weights and the thresholds of neural network, which can conquer part convergence problem of BP algorithm. The test results show that the diagnosis network has higher accuracy bf LOCA.
出处
《核动力工程》
EI
CAS
CSCD
北大核心
2012年第3期89-91,96,共4页
Nuclear Power Engineering
关键词
失水事故
群智能
粒子群优化算法
优化
故障诊断
Loss of coolant accident, Swarm intelligence, Particle swarm optimization algorithm,Optimization, Fault diagnosis
