Temperature measurement point optimization and experimental research for bi-rotary milling head of five-axis CNC machine tool

Thermal deformation is the main factor affecting machining accuracy of bi-rotary milling head. To accurately determine temperature-sensitive points head to suppress thermal deformation, this paper adopts back propagation (BP) neural network sensitivity analysis method with improved connection weights optimize temperature measurement points. The results are subjected randomized mean value processing reduce randomness initialization prediction model. number reduced from 15 4. Taking 5AS01 direct-drive as an example, a thermal-structural coupling model established analyze its characteristics. capillary copper tube cooling suppression experiment arranged according position experimental show that can simultaneously error in X- and Z-directions by about 58%, providing basis for improve accuracy.