2025 International Conference on Equipment Intelligent Operation and Maintenance (ICEIOM2025)

264 / 2025-06-15 18:52:35

Bore Expansion Life Prediction of Gear Interference-Fit in Locomotive Transmission Systems Based on GAN-BP Hybrid Model

interference fit,Plastic Bore Expansion,Damage Evolution Model,Hybrid Model,Service Life Prediction

    In locomotive transmission systems, interference fit between gears and shafts is susceptible to plastic bore expansion due to the coupling effects of dynamic load and residual stresses. This article systematically investigates the coupled influence of interference fit magnitude, residual stresses and dynamic load on the stress distribution within the gear bore. A damage evolution model for plastic bore expansion is established based on plastic fatigue theory. Stress data are acquired through finite element simulation. A hybrid model integrating Generative Adversarial Networks (GAN) and Backpropagation (BP) Neural Networks is proposed to predict the maximum von Mises stress in the gear bore. A service life  prediction system is developed by coupling this hybrid model with the damage evolution model. The results demonstrate that the interference fit range (0.241–0.3 mm) in the gear design satisfies strength requirements, while the maximum relative error of the plastic bore expansion prediction system, comparing measured values, is 5.4%. The proposed system effectively quantifies the evolution of in-service damage. This research provides a robust theoretical and technical foundation for the reliability assessment of locomotive transmission systems.