Research on Improved Fault Detection Method of Rolling Bearing Based on Signal Feature Fusion Technology

Abstract

Rolling bearings are the core transmission components of large-scale equipment. Once a fault occurs, the consequences may be catastrophic, posing a serious threat to life and the safety of the property. Aimed at the problem of rolling bearing faults, this paper analyzes the characteristics of different fault signals and proposes a fault diagnosis method based on fuzzy signals. Based on the definition of an incomplete mapping of a new connotation, this paper proposes a fuzzy fault diagnosis method by fuzzy mapping, gives a fuzzy signal processing algorithm, and discusses two judgment principles. Further, it carries out a vibration signal analysis of the rolling bearing. According to the fault diagnosis method in this paper, the fault rolling bearing is diagnosed. The experimental results show that the proposed method can effectively diagnose rolling bearing faults closer to their natural attributes and solves the problem of traditional generator bearing fault diagnosis that requires complex models and poor diagnosis speed. Further, it can be seen that the average time consumption of this method is reduced and the fault recognition accuracy rate is increased. Compared with the existing related methods, this proposed diagnosis method is superior to that of several existing methods. It not only has higher precision, stronger anti-noise capacity, and faster diagnosis speed, but also has lower effective information loss.