A New BP Network Based on Improved PSO Algorithm and Its Application on Fault Diagnosis of Gas Turbine

A New BP Network Based on Improved PSO Algorithm and Its Application on Fault Diagnosis of Gas Turbine
复制标题

DOI：
10.1007/978-3-540-72395-0_36
复制
发表时间：
2007-06
期刊：
--
影响因子：
--
通讯作者：
Weiqi Hu;Jingtao Hu
Weiqi Hu;Jingtao Hu
中科院分区：
其他
文献类型：
--
作者：
Weiqi Hu;Jingtao Hu

文献摘要

被引文献

相似文献

针对传统BP神经网络收敛性能差的问题，提出一种改进的粒子群优化算法代替梯度下降法对BP网络的权值和阈值进行优化。该算法的策略是在每一个迭代循环中，在包含个粒子的粒子群的每一个维度上，选择速度下降最快的粒子按一定的概率进行速度变异。仿真结果表明，新算法是非常有效的。将该算法成功地应用于燃气涡轮机故障诊断中。
Aiming at improving the convergence performance of conventional BP neural network, this paper presents an improved PSO algorithm instead of gradient descent method to optimize the weights and thresholds of BP network. The strategy of the algorithm is that in each iteration loop, on every dimensiondof particle swarm containingnparticles, choose the particle whose velocity decreases most quickly to mutate its velocity according to some probability. Simulation results show that the new algorithm is very effective. It is successful to apply the algorithm to gas turbine fault diagnosis.