A novel fault early warning method for mechanical equipment based on improved MSET and CCPR

Abstract

Prompt fault early warning is a significant approach to improve the reliability of mechanical equipment. An abnormal state recognition method based on improved multivariate state estimation technology (MSET) and control chart pattern recognition (CCPR) is proposed. First, the health data band (HDB) of equipment is established through a k-nearest neighbor algorithm. Meanwhile, a dynamic memory matrix construction approach based on a clustering algorithm is presented to improve the calculation efficiency of MSET. The CCPR is integrated to reduce limitations such as artificial interference in the traditional threshold method of fault early warning. The proposed method is applied into two cases of rolling bearing and control moment gyro so as to compare its performance with other MSET modeling methods. According to the results, the proposed method can detect equipment abnormalities hours to weeks in advance, and significantly reduce the false alarm rate and calculation time.