Thermal error modeling of machine tool spindle through an ensemble approach

Abstract

Thermal error compensation of machine tool is cost-effective than other methods. Towards this, data-driven machine learning (ML) algorithms have been used to produce accurate prediction models. However, ML models have limitations, such as overfitting, requiring large data etc. In present work, a hybrid model is proposed by exploiting the linear regression (LR), support vector machine (SVM), neural network (NN), and decision tree (DT) models. For this purpose, the optimum weights to each constituent model is identified by cosine similarity maximization. The developed models are validated against the experimental data. The prediction results with optimized weight are compared with equal weights and the root means square error (RMSE) for both methods are 1.8879 and 2.8978, respectively. The RMSE shows that the hybrid model produces good accuracy for both small and large data sets compared to individual models.