Thermal error prediction model of high-speed motorized spindle based on DELM network optimized by weighted mean of vectors algorithm

Abstract

The thermal error compensation process of high-speed motorized spindle needs to establish an effective prediction model. In this study, firstly, the thermal characteristics of a motorized spindle are tested, and the data at different speeds are obtained. Considering the disadvantage that the number of clusters in traditional clustering methods needs to be specified artificially, particle clustering and grey correlation analysis are selected to optimize the temperature measuring points. Aiming at the influence of data noise and the slow training speed, the depth limit learning machine is used to establish the thermal error prediction model. Considering that the output of deep extreme learning machine (DELM) is easily influenced by random input weights and biases, weighted mean of vectors algorithm (INFO) proposed in 2022 is chosen to optimize the two influencing factors. By establishing the INFO-DELM thermal error prediction model, and using the screened data to train the INDO-DELM model, the final prediction result is obtained. The results show that the accuracy of the INFO-DELM model is improved by 3%–26% compared with the basic DELM model. In addition, the INFO-DELM model shows excellent stability in both forward and backward forecasting, which proves that the model has strong adaptability. The optimization method of measuring points and INFO-DELM model in this paper provide a new idea for the field of thermal error compensation of motorized spindle.