A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very co...A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。展开更多
基金Funding from the Key Research and development plan of Shaanxi Province"Research on key problems of surface finishing for Aerospace Fastener"(2023-YBGY-386).
文摘A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。
