Bearing rings are thin-walled components prone to distortion during quenching. Achieving high-precision distortion control for bearing rings remains a critical challenge in high-precision bearing manufacturing. This paper proposes an AI-driven method for distortion control during bearing ring quenching in mesh-belt furnaces. The primary objective is to identify the optimal reverse motor frequency within the furnace. An experimental database is established using distortion results obtained at different reverse motor frequencies. This database serves as training data for deep learning. Subsequently, a large language model (LLM) employs few-shot learning to optimize and predict the reverse motor frequency influencing bearing quenching distortion. Results demonstrate that the LLM method achieves significantly higher prediction accuracy than traditional machine learning approaches. The optimization outcomes validate the effectiveness of generative AI in optimizing the reverse motor frequency of mesh-belt furnaces and controlling distortion during bearing ring quenching.

Quenching distortion of bearing rings seriously affects their dimensional accuracy and service performance in industrial production. To address this issue, this study proposes a distortion control method for bearing rings during quenching in widely used mesh-belt furnaces, focusing on the effect of motor frequency on the flipping state of bearing rings. Based on the flipping characteristics of the motor-driven mesh belt, a mathematical model was established to quantify the influence of mesh belt motor frequency on the heat transfer boundary conditions of bearing rings. This model was then implemented in the multiphysics coupling simulation software COSMAP to simulate the quenching process of bearing rings under different motor frequencies, thereby clarifying the evolution of heat transfer characteristics and the distortion mechanism induced by motor frequency changes. To verify the model’s reliability, quenching experiments were conducted on GCr15 UC212 bearing rings under nine different motor frequencies. Comparisons between experimental and simulation results validate the model’s accuracy and reliability, and the optimal motor frequency for UC212 bearing ring quenching was predicted. The results also indicate that the proposed heat transfer boundary modeling method is theoretically applicable to bearing rings of different sizes.