A novel inverse method for Advanced monitoring of lubrication conditions in sliding bearings through adaptive genetic algorithm

Abstract

This study introduces an inverse lubrication analysis (ILA) method, a novel approach for simulating the lubrication state of sliding bearings under various load conditions. By integrating experimental pressure data from sliding bearings with an adaptive genetic optimization algorithm, this method precisely calculates the eccentricity, attitude angle, and global pressure distribution of the lubrication film. Unlike traditional forward lubrication analysis (FLA) methods, which indirectly estimate the lubrication film status through loads, the ILA method utilizes direct pressure measurements, ensuring accurate and timely raw data for inverse calculations. This approach rapidly and accurately converts measured data into key parameters, closely aligning simulation results with experimental data. The lubrication states of the experimental sliding bearing under loads of 100 N, 200 N, 300 N, and 400 N were successfully predicted, highlighting the method’s reliability in real-world applications. This study provides a new approach and perspective for health monitoring and fault diagnosis of sliding bearings, especially under extreme conditions.