Rolling bearing fault classification method based on data simulation collaborative drive and transfer learning

The simulation data is complete, but the measured data is unbalanced or missing, which makes it difficult to apply the data-driven model. In addition, there are many adjustable hyperparameters and artificially adjusted random factors in the data-driven model, which leads to the final result of the model. Insufficient precision. Therefore, this paper proposes a rolling bearing fault image recognition method based on hyperparameter optimization and transfer learning.First, build a simulation model to generate some samples, and then screen the network through noise resistance, select a network with strong robustness, and then input the network with strong noise resistance with simulation data. In this paper, AlexNet depth volume is selected. A neural network is integrated and the model is tuned through hyperparameter optimization techniques. Finally, this paper constructs a model by migrating the evaluation model from the simulation domain to the measured data domain through feature projection to make up for the scarcity of samples. It is verified by experiments that the actual measurement data of rolling bearing faults from Case Western Reserve University is used, and the overall accuracy of the model is improved by means of the hyperparameter optimization method. In addition, this paper also uses transfer learning and feature projection methods to solve the problem of scarcity of measured fault samples, and has a good transfer effect and high accuracy after transfer. The above results have verified the improvement effect and good noise immunity of the above method.