PSO-BP网络模型在柱塞泵故障诊断中的应用

Application of PSO-BP network model in the fault diagnosis of plunger pump

本文针对BP神经网络存在的一些缺陷,将粒子群算法引入神经网络,通过粒子群算法来优化神经网络的初始权值与阈值。最后分别建立基于柱塞泵故障诊断的PSO-BP网络诊断模型与BP神经网络诊断模型,对比这两种模型的分类精度与迭代收敛速度,实验证明PSO-BP网络在柱塞泵故障诊断方面的性能要优于BP神经网络。

For the shortcomings of BP neural network, particle swarm optimization algorithm is introduced into neural network, and particle swarm optimization is applied to optimize initial weights and thresholds of neural network. Finally, the PSO-BP network diagnosis model and BP neural network diagnosis model based on the plunger pump fault diagnosis are established respectively, and the classification accuracy and iterative convergence speed of the two models are compared.. Through the experiment, it is proved that the performance of the PSO-BP network in the fault diagnosis of plunger pump is better than the BP neural network.