A Comprehensive Approach for Thermal Error Model Optimization for ANN-Based Real-Time Error Compensation in CNC Machine Tools

Abstract

Thermally induced errors play a critical role in the control of machining accuracy. They can account for as much as 70% of dimensional errors in produced parts. Since thermal errors cannot totally be eliminated at the design phase, errors compensation appears to be the most economical solution. Accurate and efficient modeling of the thermally induced errors is an essential part of the error compensation process. This paper presents a comprehensive approach for thermal error modeling optimization. The proposed optimization method is based on multiple temperature measurements, Taguchi’s orthogonal arrays, various statistical tools and artificial neural networks to provide cost effective selection of appropriate temperature variables and modeling conditions as well as to achieve robust and accurate thermal error models. The proposed approach can be effectively and advantageously used for real-time thermal error compensation since it presents the benefit of straightforward application, reduced modeling time and uncertainty. The experimental results on a CNC turning center confirm the feasibility and efficiency of the proposed optimization method and show that the resultant model can accurately predict the time-variant thermal error components under various operating conditions.