Optimization of Variable-depth Pocketed and Bionic Textured Pad Thrust Bearing using Machine Learning Models and Genetic Algorithm

Surface texture is employed to improve the performance behaviours of fluid film bearings. In this paper, an attempt has been made to investigate the influence of different types of texture on the pad surface. Three configurations have been considered, namely, bionic texture inspired by honeycomb structure, variable depth pocket and combination of bionic texture and variable depth pocket. Performance parameters, minimum film thickness and coefficient of friction have been computed at different operating conditions. Due to large number of possible cases, prediction of performance behaviours have been made employing different machine learning models. Lastly, Genetic Algorithms is employed to find the optimized configuration at different operating conditions with fitness evaluation based on prediction model. Optimized texture/pocket yields substantial improvement in minimum film thickness and considerable reduction in coefficient of friction. The optimized values are then compared with computed valued yielding less than 4% error and verified successfully with the help of pin on disc apparatus.