基于ZOA与CNN的电梯故障诊断
Fault Diagnosis of Elevator based on ZOA and CNN
王赛男 1柏智 1杨云涛2
作者信息
- 1. 湖南电气职业技术学院 电梯工程学院,湖南 湘潭 411101
- 2. 湖南大学 物理与微电子科学学院,湖南 长沙 410082
- 折叠
摘要
采用ZOA-CNN方法对电梯轴承故障进行诊断,旨在通过分析电梯运行过程中的轴承振动信号,进一步判断电梯是否存在故障.卷积神经网络(Convolutional Neural Network,CNN)具有出色的数据特征提取能力,为电梯轴承故障诊断提供了有力支持.同时结合斑马优化算法(Zebra Optimization Algorithm,ZOA)对CNN模型参数进行优化,以提升诊断性能.研究结果表明,该方法在轴承电梯故障诊断方面取得了显著的成果,其诊断准确率达到了99.75%,明显高于传统故障诊断方法对电梯故障的正确率.
Abstract
This study used the ZOA-CNN method to diagnose elevator bearing faults,aiming to further determine whether there are faults in the elevator by analyzing the bearing vibration signals during elevator operation.Convolutional neural network(CNN)has excellent automatic feature extraction ability,which provides strong support for elevator bearing fault diagnosis.Meantime,the paper combined the Zebra Optimization Algorithm(ZOA)to optimize the CNN model parameters to improve diagnostic performance.The research results show that this method has achieved significant results in diagnosing elevator bearing faults,with a diagnostic accuracy of 99.75%,which is significantly higher than the correct rate of traditional fault diagnosis methods for elevator faults.
关键词
电梯故障/卷积神经网络/斑马优化算法/故障诊断Key words
elevator failure/Convolutional Neural Network(CNN)/Zebra Optimization Algorithm(ZOA)/fault diagnosis引用本文复制引用
基金项目
湖南省自然科学基金课题(2022JJ60025)
湖南省自然科学基金课题(2021JJ60024)
出版年
2024
NETL
NSTL
维普
万方数据