A Rolling Bearing Condition Assessment Method Driven by Data-Model

Rolling bearings are critical components in the operation of machinery, and their performance directly affects the safety and stability of the entire system. However, the challenge lies in the difficulty of accurately capturing the wear process of rolling bearings, making it hard for traditional models to predict their actual operating conditions accurately. To overcome this problem, this study introduces a new data-model driven approach to assess the health of rolling element bearings. This new method first utilizes deep learning technology to build an advanced network model aimed at deeply analyzing and extracting key information during the bearing degradation process. By effectively integrating this key information, this paper construct an index system that accurately reflects the degradation trend of the bearings. Subsequently, the method employs stochastic process theory to establish a mathematical model of rolling bearing degradation, providing a detailed description of the degradation process. Finally, the previously constructed degradation indicators are input into this model to predict the remaining useful life of the bearings and assess their overall operating condition. This innovative assessment method allows for more precise monitoring and management of the health status of rolling bearings, providing strong technical support for equipment maintenance and fault prevention.