基于ANN和SVM的轴承剩余使用寿命预测

为了提高现代制造业设备的可靠性和高效性,轴承剩余使用寿命(RUL)的预测已经成为越来越重要的研究方向。提出一种基于人工神经网络(ANN)和支持向量机(SVM)的轴承剩余使用寿命预测方法。该方法首先将获取的18维反映轴承衰退的时域特征和频域特征输入到ANN模型中做特征抽取,再将输出的18维特征向量作为SVM模型的输入,进而对轴承剩余使用寿命进行预测。基于ANN和SVM融合模型方法是结合了ANN基于数据的强大特征学习能力和SVM处理小数据集的优势。运用多组轴承衰退振动信号对模型进行验证,比较实验结果表明,相比于随机森林(RFR)模型、LASSO模型、SVM模型和ANN模型,基于ANN和SVM的轴承剩余使用寿命预测方法具有更高的预测精度。

Bearing Remaining Useful Life Prediction Based on Artificial Neural Network and Support Vector Machine

In order to improve the reliability and efficiency of modern manufacturing equipment,the prediction of bearing remaining useful life(RUL)has become an increasingly important research direction.This paper proposes a bearing remaining useful life prediction method based on artificial neural network(ANN)and support vector machine(SVM).The method firstly inputs the acquired 18-dimensional reflection time domain features and frequency domain features into the ANN model for feature extraction,and then uses the output 18-dimensional feature vector as the input of the SVM model to predict the remaining life of the bearing.Based on the ANN and SVM fusion model approach,this paper combines the powerful data learning capabilities of ANN and the advantages of SVM in processing small data sets.The model is validated by using multiple sets of bearing decay vibration signals.The experimental results show that compared with the random forest model,LASSO model,SVM model and ANN model,the bearing residual life prediction method based on ANN and SVM is higher.The accuracy of the prediction.