Thermal Error Modelling for the Parallelism Between the Gear Axis and the Z-axis of GMI

Abstract Gear measuring instrument (GMI) is the mainstream equipment for gear measurement. As measurement accuracy of gears improves and GMI gradually used in production, thermal errors are becoming an important factor affecting GMI. In precision gears, parallelism between axis Z-axis major error source. This usually reduced by mechanical adjustment when a assembled. When temperature its environment changes, deformation will lead to new GMI, which further cause this paper, effect studied, model under room was established. First, field were measured; then, TMP grouped using FCM, key selected optimizing group points Pearson correlation coefficient method; finally, established RBF (Radial Basis Function) neural network tested measured data. The experimental results show that predictive can reach 60.89% X direction 82.26% Y direction, indicating good generalization ability robustness. be subsequent compensation.