Stacking ensemble transfer learning based thermal displacement prediction system

In the precision machining industry, machine tools are usually affected by various factors during machining, and various machining errors generated accordingly. Where thermal error is one of the most common and difficult to control factors for machine tools. Therefore, in this study, six temperature sensors and an eddy current displacement meter are provided in a machine tool with 4-axis for dataset collection required for the model training, then data are organized and normalized. Next, data are introduced into a variety of learning models and validated by k-Fold cross-validation for predicting those nonlinear factors that affect the errors. At the end, predicted results are summarized and compared to find out the best two model with better predictive performance for pre-trained model of transfer learning. It observes better predicted results from a retraining conducted through applying Multilayer Perceptron (MLP) on these two pre-trained models, wherein MAE value as 0.40, RMSE as 0.52625 and R-2 score as 0.99696 respectively.

Automated summary

In the precision machining industry, thermal error is a common and difficult to control factor for machine tools. This study uses temperature sensors and an eddy current displacement meter to collect data for training models, which are then organized and normalized. Different learning models are used to predict the nonlinear factors that affect the errors, and the best two models with better predictive performance are identified for the pre-trained model of transfer learning. Retraining with Multilayer Perceptron (MLP) on these two models improves the predicted results, with an MAE value of 0.40, RMSE of 0.52625, and R-2 score of 0.99696.