摘要： 基于和声搜索和蚁群算法优化后的BP神经网络,提出一种风电机组齿轮箱故障诊断方法。将蚁群算法的信息素更新机制用于和声搜索算法中,提高和声搜索算法的收敛速度,并利用和声搜索算法的个体扰动策略和随机搜索机制改善蚁群算法过早收敛的问题。利用该方法对BP神经网络的权值和阈值进行优化,克服BP神经网络算法易陷入局部最优解的缺点,提高神经网络的训练效率和收敛速度。测试结果表明,该方法诊断结果正确且精度高,将经和声蚁群耦合算法优化后的BP神经网络用于风电机组齿轮箱故障诊断是有效的。

关键词: 蚁群算法, 和声搜索算法, BP神经网络, 风电机组, 齿轮箱, 故障诊断

Abstract: A method based on BP neural network trained by Harmony Search and Ant Colony(HS-AC) algorithm is presented for fault diagnosis of wind turbine gearbox.The Ant Colony Algorithm(ACA) pheromone updates mechanism for harmony search algorithm which improves the convergence speed of harmony search algorithm and uses harmony search algorithm individual perturbation strategies and stochastic search mechanisms to improve the ant colony algorithm update premature problem.It can reduce the risk of BP neural network algorithm falling into local minimum,improve the training efficiency,and speed up convergence by using HS-AC algorithm to optimize the weights and bias of BP neural network.The new algorithm is applied to wind turbine gearbox fault diagnosis forecast.The method is tested and results of fault diagnosis are right.The validity and practicability of BP neural network algorithm trained by HS-AC algorithm for the wind turbine gearbox fault diagnosis are proved.

Key words: Ant Colony Algorithm(ACA), Harmony Search Algorithm(HSA), BP neural network, wind turbine, gearbox, fault diagnosis

中图分类号: 

• TP277