CNC screw life prediction based on DFNN performance model

After considering a variety of factors to the performance degradation of screw-nut pair, a novel performance degradation model based on dynamic fuzzy neural network (DFNN) was proposed to predict screw life in this paper. The model can assessed the life of Roller Lead Screw-nut pair of the CNC feed drive system effectively, and can resolved the problems of screw life changing with the machining conditions which impacted the CNC performance. The vibration signals from screw pair parts were processed by analyzing the empirical mode decomposition (EMD) algorithm, time-series features extracted from vibration signals defined as the DFNN input vector, and the rated life under different machining condition used to be the expectancy life. Finally, a physical model of the actual residual life about screw was built, and the online prediction of screw life was achieved. The experimental results show that the model can accurately predict the dynamic life of the screw. It is conducive to the active maintenance of screw.