Bearing faults diagnosis using envelope analysis and 1D Convolutional neural network

Due to the importance of rolling bearings as one of the most widely used industrial machinery elements. Therefore, the development of a method to monitor the condition of bearing is very important. This work presents a novel method to classify the bearing faults by using an envelope analysis and 1D-CNN. Firstly, envelope analysis is used as a method for pre-processing by calculating the envelope spectrum of the raw vibration data. Secondly, a 1D-CNN is used as a classifier to diagnose the bearing faults. The proposed method is tested on the CWRU dataset from bearings under different rotating speeds. Results of the case study show that the proposed method can achieve a testing accuracy of 99.85 %