Development of a Transfer Learning Technique for Rapid Adaptation of Thermal Compensation Models to Long-Term Machine Thermal Behavior Changes
Open Access
Abstract
Structural aging and environmental changes associated with long-term operation can substantially modify the thermal behavior of machine tools, diminishing the accuracy of existing thermal compensation models. Traditional neural network approaches typically necessitate time-consuming and inefficient retraining from scratch for practical adaptation. To address this limitation, this study proposes a parameter-based transfer learning technique to enhance model adaptability under evolving machine tool operating conditions. The method establishes a composite fine-tuning architecture by adding hidden layers and selectively freezing neural network parameters, enabling the rapid adaptation of the pretrained model to new thermal characteristics using limited data. A full-factorial experimental design identified the optimal configuration, comprising (i) structural expansion via an LSTM layer inserted after the hidden layers; (ii) a strategy freezing parameters in all layers; and (iii) training under the selected optimal condition (C9), which reflects machine tool characteristics and environmental temperature variations. The baseline model achieved an RMSE of 3.88 µm. Traditional retraining using the complete dataset and retraining only on C9 yielded RMSE values of 3.21 and 3.84 µm, respectively. In contrast, the optimized transfer learning model trained on C9 achieved an RMSE of 3.47 µm. Experimental results demonstrate that the proposed strategy converges with limited data, reducing the number of datasets from 18 to nine and significantly shortening training time from 18 h 20 min to 30 s. This approach offers an effective solution for sustainable model maintenance and expedited industrial deployment.Keywords
Funding Information
- National Science and Technology Council (NSTC 113-2622-E-194-006)
- Tongtai Machine & Tool Co., Ltd.
This publication has 32 references indexed in Scilit:
- Optimization through classical design of experiments (DOE): An investigation on the performance of different factorial designs for multi-objective optimization of complex systemsJournal of Building Engineering, 2025
- Review of ML and AutoML Solutions to Forecast Time-Series DataArchives of Computational Methods in Engineering, 2022
- Thermal error modeling and compensation based on Gaussian process regression for CNC machine toolsPrecision Engineering, 2022
- Robust modeling method for thermal error of CNC machine tools based on ridge regression algorithmInternational Journal of Machine Tools and Manufacture, 2017
- A review on spindle thermal error compensation in machine toolsInternational Journal of Machine Tools and Manufacture, 2015
- Thermal issues in machine toolsCIRP Annals, 2012
- Machine tool thermal error modeling and prediction by grey neural networkThe International Journal of Advanced Manufacturing Technology, 2011
- Machine tool calibration: Geometric test uncertainty depends on machine tool performancePrecision Engineering, 2009
- Adaptive model estimation of machine-tool thermal errors based on recursive dynamic modeling strategyInternational Journal of Machine Tools and Manufacture, 2005
- Thermal error measurement and modelling in machine tools. Part II. Hybrid Bayesian Network—support vector machine modelInternational Journal of Machine Tools and Manufacture, 2003