Optimization of wear performance of plain bearings based on BOA-BP algorithm

Abstract

Reducing frictional wear is of great significance to extend the working life of components and improve the efficiency of components. Based on ANSYS finite element software, this paper focuses on the study of the influence of working condition parameters on the wear performance of the sliding bearing, and integrates the advantages of BOA optimization algorithm and BP neural network, and designs the BOA-BP improved optimization algorithm with fast convergence speed, higher model accuracy, and strong adaptability to achieve the optimal prediction of wear quantity through BOA-BP algorithm. The results show that the wear amount increases linearly with the increase of rotational speed, and increases and then decreases with the increase of load and temperature. Surface stress shows an increasing trend with the increase of rotational speed and load; with the increase of temperature, the contact surface stress shows a trend of decreasing and then increasing. The influence of working condition parameters on the amount of wear is as follows: rotational speed V > load F > (rotational speed V × load F) > (rotational speed V × temperature T) > (load F × temperature T) > temperature T. The influence of working condition parameters on the surface stress is as follows: rotational speed V > (load F × temperature T) > load F > temperature T. The optimum working condition operating parameters of the QAL9-4 are as follows: rotational speed of 60 rad/min, load of 30 N. Temperature of 250°C. The contact surface stresses under this working condition firstly decrease, The optimal operating parameters of QAL9-4 are: rotational speed 60rad/min, load 30N, temperature 250°C, minimum wear under this operating condition is 123.7831mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , and minimum surface stress is 0.0012246MPa. This study is of great significance for the selection of the operating environment of the robotic arm and the prediction of the service life of the sliding bearings.