Fault detection of bearings based on wavelet scattering and machine learning
MEI Na
YAN Bingzheng
Abstract：Bearing condition monitoring and fault diagnosis are essential for the stability and reliability of medical devices.In response to issues such as reliance on manual experience,low detection efficiency,and accuracy in bearing fault detection,a bearing fault detection model based on wavelet scattering and support vector machine is proposed.Firstly,the original vibration signal is preprocessed,and a wavelet scattering network is constructed.Cross validation and grid search algorithm are used to train the SVM model,which can determine the fault type and size at different speed.To verify the performance of the model,ex-periments are conducted using a bearing dataset collected by Case Western Reserve University.The results show that the model can achieve an accuracy rate of 100%in detecting fault positions and fault sizes.The model demonstrates excellent accuracy and stability,and provides a new approach for automatic bearing fault detection.
Keywords：fault detectionrolling bearingwavelet scatteringmachine learningSVM
Publication Date：2025-08-01
Online Publishing Date：2026-08-28(First online date of this platform, not the publication date of the document)
Pages：11( 516-526 )