摘要
针对发动机轴承磨损故障诊断精度低的问题,基于振动信号展开研究。通过采集发动机轴承在运行过程中的振动信号,获取包含轴承状态信息的原始数据。利用信号处理与特征提取技术,从原始振动信号中提取出能够表征轴承磨损状态的关键特征。进一步构建了极限学习机(ELM)作为磨损故障诊断模型,并利用粒子群优化算法(PSO)优化ELM的权重和偏置,以提高模型的诊断精度。实验结果表明,该方法能够有效地从振动信号中识别出发动机轴承的磨损故障,实现高精度的故障诊断,为发动机轴承的维护和管理提供了有力的技术支持。
Aiming at the problem of low accuracy of engine bearing wear fault diagnosis,a research based on vibration signals is carried out.By collecting the vibration signals of the engine bearings during operation,the raw data containing information about the bearing status are obtained.Using signal processing and feature extraction techniques,key features that can characterise the bearing wear state are extracted from the raw vibration signals.The Extreme Learning Machine(ELM)is further constructed as a wear fault diagnosis model,and the particle swarm optimisation(PSO)algorithm is used to optimise the weights and biases of the ELM to improve the diagnostic accuracy of the model.The experimental results show that the method in this paper can effectively identify the wear faults of engine bearings from vibration signals,achieve high-precision fault diagnosis,and provide powerful technical support for the maintenance and management of engine bearings.
作者
罗腾
Luo Teng(Hangzhou Sailunxes Automotive Parts Co.,Ltd.,Hangzhou Zhejiang 311106,,China)
出处
《机械管理开发》
2025年第5期76-78,共3页
Mechanical Management and Development
关键词
振动信号
轴承
故障诊断
磨损
发动机
vibration signal
bearing
fault diagnosis
wear
engine
