A DeepBottleneck-1DCNN for Rolling Bearing Fault Diagnosis

Aiming at the problems of low accuracy of the existing fault diagnosis methods for rolling bearings, this paper proposes a rolling bearing fault diagnosis model based on DeepBottleaneck-1D convolutional neural network (DeepBottleaneck-1DCNN). A fault diagnosis program has been designed for the operation history data of the machine, which can achieve real-time data collection and image display functions, and can intuitively reflect the equipment status. During program execution, it has the ability to monitor and diagnose faults in real-time. Simulated, when a potential fault is detected, the machine can automatically stop running and send an alarm, taking timely measures to ensure the safety of personnel and equipment. The experimental results show that the proposed fault diagnosis model can effectively identify multiple types of faults and accurately diagnose faults, with an average accuracy rate of 99.35 %. Compared with existing models, the proposed model has better results, proving the superiority of our model.