Reinforcement Learning-based Automatic Tuning Method and Application of Injection Molding Process Parameters

The optimization of injection molding process parameters is crucial in contemporary manufacturing, as it affects not only product quality but also production costs and efficiency. Traditional manual tuning methods rely on trial and error, leading to extended production cycles and increased costs. To address this, reinforcement learning (RL) technology is applied, for the first time, to the tuning of injection molding process parameters, proposing a novel automatic tuning algorithm based on RL for injection molding process parameters. The paper first models the injection molding process parameter tuning problem as a sequential decision-making problem and designs a customized Markov Decision Process model. Subsequently, a model-free RL method is proposed, implementing the automatic selection of injection molding process parameters based on the Q-learning algorithm. Compared with traditional methods, this algorithm can automatically explore and optimize process parameter configurations in dynamically changing production environments. Finally, the feasibility and effectiveness of the proposed method are experimentally validated, demonstrating significant application potential.