Detecting preload degradation of a ball screw feed system using high-frequency reconstruction and support vector machine

Abstract

Ball screws need to be applied with different preloads in most applications, however, very few studies had paid attention to preload detection, which is one of the most common failure modes of ball screws. To detect the preload of a ball screw, we propose a novel approach using vibration signals and ensemble empirical mode decomposition (EEMD) combined with linear discriminant analysis (LDA) and a support vector machine (SVM). The vibration signals under different preloads are obtained for the same ball screw through degradation experiments, and decomposed and reconstructed by EEMD. Statistical features are extracted from the reconstructed signals in the time and frequency domains. Linear discriminant analysis is used to reduce the dimensionality of the original feature space. Finally, the preload can be identified by the SVM, in which the identification accuracy can be higher than 90%. Further analysis showed that the high-frequency signal has a stronger correlation with preload degradation than the low-frequency signal, and the proposed method can be more effective than other existing methods, especially when the degradation of preload is more than 300N.