Error prediction of balancing machine calibration based on machine learning method

This paper proposes a method of compensating for brake disc balance error by using a machine learning algorithm. Automobile brake discs in the production process will inevitably produce unbalance. The unevenness produced by the uneven mass distribution will produce high-frequency vibration in the process of high-speed rotation, which seriously affects the safety of the vehicle and the personal safety of the occupants. The key measure to solve this problem is to correct the unbalance with higher precision before the brake disc leaves the factory. The traditional correction method is to improve the detection accuracy of unbalance to achieve balance accuracy. In this paper, we hope to improve the balance accuracy by compensating for the errors generated in the correction process. We use the random forest model, decision tree model, and support vector machine model to predict the errors of the balancing machine during the calibration process. The main idea is to take the parameters of the brake disc and the features in the milling process as input and the error amplitude as output. The results show that the stochastic forest model has higher prediction accuracy than the decision tree model and support vector machine model. This method can also predict errors from other sources, such as thermal errors.