基于纵横交叉算法优化BP神经网络的风机齿轮箱故障诊断方法

马留洋; 孟安波; 葛佳菲

doi:10.12052/gdutxb.170019

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于纵横交叉算法优化BP神经网络的风机齿轮箱故障诊断方法

更新时间：2026-05-27

- 基于纵横交叉算法优化BP神经网络的风机齿轮箱故障诊断方法
- A Fault Diagnosis Method of Wind Turbine Gearbox Based on BP Neural Network Optimized by Crisscross Optimization Algorithm
- 广东工业大学学报 2018年35卷第2期页码：57-62
- 作者机构：
  
  广东工业大学　自动化学院,广东,广州,510006
- 作者简介：
  
  马留洋(1992–)，男，硕士研究生，主要研究方向为电力系统经济调度与风机故障诊断
- 基金信息：
  
  广东省科技计划项目(2016A010104016);广东电网公司科技项目(GDKJQQ20152066)
- DOI：10.12052/gdutxb.170019
  中图分类号： TM315
- 纸质出版：2018
- 稿件说明：
移动端阅览
马留洋, 孟安波, 葛佳菲. 基于纵横交叉算法优化BP神经网络的风机齿轮箱故障诊断方法[J]. 广东工业大学学报, 2018, 35(2): 57-62.

Ma Liu-yang, Meng An-bo, Ge Jia-fei. A Fault Diagnosis Method of Wind Turbine Gearbox Based on BP Neural Network Optimized by Crisscross Optimization Algorithm[J]. 2018, 35(2): 57-62.
马留洋, 孟安波, 葛佳菲. 基于纵横交叉算法优化BP神经网络的风机齿轮箱故障诊断方法[J]. 广东工业大学学报, 2018, 35(2): 57-62. DOI： 10.12052/gdutxb.170019.

Ma Liu-yang, Meng An-bo, Ge Jia-fei. A Fault Diagnosis Method of Wind Turbine Gearbox Based on BP Neural Network Optimized by Crisscross Optimization Algorithm[J]. 2018, 35(2): 57-62. DOI： 10.12052/gdutxb.170019.

摘要

风电机组齿轮箱的运行工况比较复杂

容易发生故障. 针对常规BP(Back Propagation)神经网络故障诊断容易陷入局部最优的问题

提出一种基于纵横交叉算法(Crisscross Optimization Algorithm

CSO)优化BP神经网络的风电齿轮箱故障诊断新方法. 考虑到风电齿轮箱振动信号的波动性和非线性

首先从信号中提取故障特征参数

建立带评价因子的误差分析模型

然后通过纵横交叉算法优化BP的权值和阈值对神经网络进行训练

最后用训练好的神经网络对样本进行测试. 经实验仿真并与其他方法的对比

验证了本文方法用于风电机组故障诊断有效性及优越性.

Abstract

Wind turbine gearbox has high failure rate in its complex operation. In order to overcome the drawbacks of the conventional BP (Back Propagation) neural network which is easy to trap into local optimal

a new fault diagnosis model of turbine gearbox is presented based on BP neural network optimized by crisscross optimization (CSO)algorithm. Considering the instability and complexity of vibration signal of the wind turbine gearbox. The fault feature for gearbox is first extracted and a new error analysis model is established with assessment factors

CSO is then used to optimize the weights and bias of BP neural network

and finally the trained neural network is used to test the samples. The simulation and comparison with other methods show that the proposed method is effective and efficient in fault diagnosis of wind turbines.

关键词

Keywords

references

LONG Q, LIU Y Q, YANG Y P. Fault diagnosis method of wind turbine gearbox based on BP neural network trained by particle swarm optimization algorithm[J]. Acta Energiae Solaris Sinica, 2012, 33(1): 120-125.

LI T, TANG M Z, TAN X X. Fault diagnosis of wind turbine gearbox based on cost-sensitive least squares support vector machine[J]. Renewable Energy Resources, 2015, 33(2): 232-237.

QIN D L, YU D J. Ontology-based diagnostic Bayesian networks for mechanical fault diagnosis[J]. China Mechanical Engineering, 2013, 24(9): 1195-1209.

GU Y J, JIA Z W, WANG R, et al . Early fault diagnosis for wind turbine gearbox based on improved multivariate outlier detection [J ] . China Mechanical Engineering, 2016, 27(14): 1905-1910.

ZHANG S M, MAO D, WANG B Y. Application of big data processing technology in fault diagnosis and early warning of wind turbine gearbox. Automation of Electric Power Systems, 2016, 40(14): 129-134.

GU K K, GUO J. Transformer fault diagnosis method based on compact fusion of fuzzy set and fault tree[J]. High Voltage Engineering, 2014, 40(5): 1507-1513.

赵文清. 基于数据挖掘的变压器故障诊断和预测研究[D]. 保定: 华北电力大学(保定)计算机科学与技术学院, 2009.

YIN Y P, LIU W J, WEI L. Fault diagnosis of wind turbine gearbox based on harmony search and ant colony algorithm[J]. Computer Engineering, 2014, 40(12): 172-181.

DAI L, HUANG S D, HUANG K Y, et al . Combination forecasting model based on neural networks for wind speed in wind farm[J ] . Proceedings of the Chinese Society of Universities, 2011, 23(4): 27-31.

ZHU S, JIANG C W, HOU Z J. Application of a weather component based Elman neural network to short-term load forecasting [J]. Proceedings of the CSU-EPSA, 2005, 17(1): 23-26.

ZHAO W Q, ZHU Y L, ZHANG X Q , et al . Rough set theory based fault diagnosis on power transformers [J ] . Chinese Journal of Scientific Instrument, 2006, 27(2): 1722-1723.

韩力群.人工神经网络教程[M].北京: 北京邮电大学出版社, 2006.

MENG A B, CHEN Y C, YIN H, et al . Crisscross optimization algorithm and its application [J ] . Knowledge-Based Systems, 2014, 67(4): 218-229.

YANG W, LI Q Q. A Survey on particle swarm optimization algorithm [J]. Engineering Science, 2004, 6(5): 87-92.

LUO P, LIU W, ZHOU S B. Gravitational search algorithm of adaptive chaos mutation[J]. Journal of Guangdong University of Technology, 2016, 33(1): 57-61

WU W M, TIAN L, LIN Z Y. Hybrid big bang-big crunch algorithm based on particle swarm optimization[J]. Journal of Guangdong University of Technology, 2016, 33(4): 12-17

龙泉. 风电机组齿轮传动系统动态特性及故障诊断方法研究[D]. 北京: 华北电力大学源动力与机械工程学院, 2012.

ZHANG H, PU J, ZHANG X C. A model for predicting vacuum in the condenser based on Elman neural network by using particle swarm optimization algorithm[J]. Thermal Power Generation, 2010, 39(4): 7-11

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

纵横交叉算法在梯级水库优化调度中的应用

基于可拓学的故障诊断及预防方法研究

基于BP神经网络的工艺球缺陷检测

模糊理论在设备故障诊断神经网络中的典型应用

人工噪声辅助无人机太赫兹安全通信的鲁棒设计