基于SSA-RVM的滚动轴承可靠度评估与预测
Evaluation and Prediction of Rolling Bearing Reliability Based on SSA-RVM
高淑芝 1于一凡 2张义民1
作者信息
- 1. 沈阳化工大学装备可靠性研究所,辽宁 沈阳 110142
- 2. 沈阳化工大学信息工程学院,辽宁 沈阳 110142
- 折叠
摘要
为解决滚动轴承运行可靠度预测问题,这里提出了基于麻雀搜索算法-相关向量机的滚动轴承可靠度预测方法.首先对轴承振动信号在时域、频域及时频域构成的维数较高的向量集利用主成分分析算法进行降维;然后将降维后的特征集作为轴承的退化状态特征输入到逻辑回归模型中,进行滚动轴承可靠性评估;然后将轴承的性能退化状态特征作为麻雀搜索算法-相关向量机模型的输入,获取预测结果;最终把结果带入到逻辑回归模型中,预测轴承的运行可靠度.实验结果表明提出的算法在预测滚动轴承运行可靠性中具有明显优势.
Abstract
In order to solve the problem of rolling bearing operation reliability prediction,a rolling bearing reliability prediction method based on sparrow search algorithm and relevance vector machine is proposed in this paper.Firstly,principal component analysis(PCA)was used to reduce the dimensionality of the higher dimensional vector set composed of bearing vibration signals in time domain,frequency domain and time-frequency domain.Then,the feature set after dimensionality reduction was input into the logistic regression model as the degenerate state features of the bearing to evaluate the reliability of the rolling bearing.Then,the performance degradation state characteristics of the bearing were taken as the input of the sparrow search algorithm-relevance vector machine model to obtain the prediction results.Finally,the results are put into the logistic regression model to predict the operating reliability of bearings.Experimental results show that the proposed algorithm has obvious advantages in predicting the operational reliability of rolling bearings.
关键词
机械轴承/可靠性预测/相关向量机/麻雀搜索算法Key words
Mechanical Bearing/Reliability Prediction/Relevance Vector Machine/Sparrow Search Algorithm引用本文复制引用
基金项目
NSFC-国家自然科学重点基金—辽宁联合基金(U1708254)
辽宁省特聘教授项目([2018]3533)
出版年
2024
NETL
NSTL
万方数据