Gaussian Process Regression-Based Optimization of Helical Gear Tooth Surface Modification for Misalignment Tolerance

This study presents a data-driven framework for determining the optimal gear tooth surface modification (crowning) to improve tolerance to angular misalignment (in-plane and out-of-plane). A nonlinear tooth contact analysis (TCA) model was employed to accurately predict the contact path evolution of meshing gears under different combinations of tooth modification amounts and misalignment angles. An accurate dataset consisting of 530 simulated helical gear meshing configurations was generated. Based on these simulation results, a Gaussian Process Regression (Kriging) surrogate model was developed to establish the relationship between tooth modification, misalignment parameters, and contact behavior. The validated surrogate model enables rapid prediction of gear contact characteristics and interpolation within the design space, thereby supporting efficient surrogate-assisted design exploration without requiring repeated computationally intensive TCA simulations. The proposed framework identifies the minimum modification required to maintain acceptable contact conditions, and provides an efficient tool for improving misalignment tolerance and supporting robust gear design.