Thermal Error Modeling of Numerical Control Machine Based on Beetle Antennae Search Back-propagation Neural Networks

Abstract

Thermal errors are one key impact factor on the processing accuracy of numerical control machine. This study targeted at a certain vertical processing center presents a new algorithm for predictive modeling of thermal errors in numerical control machine. This algorithm is founded on back-propagation neural networks (BPNNs) and adopts beetle antennae search (BAS) to find the best weights and thresholds of BPNNs. It avoids the local minimization due to local extremums faced by traditional BPNNs. The intermingling rate and arithmetic computation efficiency of neural network algorithms are further improved. Then, a BAS-BP thermal error prediction model is built with the machine temperature changes and thermal errors as the input data. Compared with conventional BPNNs, the BPNN after particle swarm optimization suggests the convergence rate of BAS-BP is improved by 85%, the leftover mistakes between the genuine information and the anticipated information are under 1 um, and the overall prediction precision is above 90%. Thus, the new model has high precision, high anti-disturbance ability and strong robustness.