基于遗传算法优化BP神经网络的内燃机轴承故障诊断方法
Optimization of BP Neural Network Based on Genetic Algorithm for Fault Diagnosis of Internal Combustion Engine Bearings
汤捷中1
作者信息
- 1. 沈阳航空航天大学 航空发动机学院,辽宁 沈阳 110136
- 折叠
摘要
针对内燃机轴承故障发生率高、诊断困难的问题,提出了一种基于变分模态分解与遗传算法优化 BP神经网络的轴承故障诊断方法.使用轴承数据集对该方法进行验证.结果表明:该方法在多种工况下诊断准确率均可达到 96%以上,可以准确的识别轴承各故障类型,在一定程度上解决了内燃机轴承故障诊断困难的问题.
Abstract
A bearing fault diagnosis method based on variational modal decomposition and genetic algorithm optimized BP neural network is proposed to address the high occurrence rate and difficult diagnosis of bearing faults in internal combustion engines.The bearing data set of Jiangnan University is used to verify the method.The results show that the diagnostic accuracy of this method can reach over 96%under various working condi-tions,and it can accurately identify various types of bearing faults,solving the problem of difficult bearing fault diagnosis in internal combustion engines to a certain extent.
关键词
模态分解/机器学习/滚动轴承/故障诊断Key words
Modal decomposition/Machine learning/Rolling bearings/Fault diagnosis引用本文复制引用
出版年
2024
NETL
NSTL
万方数据