GA-ACO优化BP神经网络在行星齿轮箱故障诊断中的应用

针对目前利用优化算法改进的BP神经网络算法对行星齿轮箱进行故障诊断过程中存在的故障识别率低、收敛速度慢和参数选择困难等问题,提出了一种用GA-ACO算法对神经网络参数进行优化的算法。给出GA-ACO-BP算法的基本原理和主要步骤,并将此方法应用到行星齿轮箱的故障诊断中。比较了ACO-BP神经网络算法和GA-ACO-BP算法的性能。结果表明,ACO优化BP神经网络算法对行星齿轮箱的故障诊断收敛速度慢且识别精度不高,而GA-ACO-BP算法能够对行星齿轮箱故障进行准确、快速的诊断和识别。

Application of GA-ACO Optimized BP Neural Network in Fault Diagnosis of Planetary Gearbox

Aiming at the problems of low fault recognition rate,slow convergence speed and difficult parameter selection in the process of fault diagnosis of planetary gearbox based on BP neural network improved by optimization algorithm,a GA-ACO algorithm is proposed to optimize the parameters of neural network.The basic principle and main steps of GA-ACO-BP algorithm are given.At the same time,this method is applied to the fault diagnosis of planetary gearbox.Comparing the performance of ACO-BP neural network algorithm and GA-ACO-BP algorithm,the results show that the convergence speed of ACO Optimized BP neural network is slow and the recognition accuracy is not high,while GA-ACO-BP algorithm can accurately and quickly diagnose and identify the fault of planetary gearbox.