基于粒子群优化算法的压水堆失水事故研究  

Research on Loss of Coolant Accident of Pressurized-Water Reactor Based on PSO Algorithm

作　　者：马杰[1] 郭立峰[1] 彭俏[1] 

机构地区：[1]海军工程大学船舶与动力学院,武汉430033

出　　处：《核动力工程》2012年第3期89-91,96,共4页Nuclear Power Engineering

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.

关 键 词：失水事故 群智能 粒子群优化算法 优化 故障诊断 

分 类 号：TL383[核科学技术—核技术及应用]