用深度强化学习优化注塑参数，兼顾质量与利润。
DRL-Based Injection Molding Process Parameter Optimization for Adaptive and Profitable Production
- 用DRL同时优化产品质量和生产利润，考虑材料、模具磨损等成本。
- 相比遗传算法，推理速度提升135倍，实时性更强。
- 适合需要动态调整的智能工厂，尤其关注成本效益的制造场景。
注塑成型仍是现代制造的核心工艺，但在动态环境与经济条件下，平衡产品品质与利润的参数优化仍具挑战。本文提出一种基于深度强化学习（DRL）的实时优化框架，将产品质量与利润纳入统一控制目标。构建利润函数，涵盖树脂、模具磨损及电价（含分时定价）成本。采用代理模型预测产品质量与周期时间，利用软演员-评论家（SAC）与近端策略优化（PPO）算法实现高效离线训练。实验表明，该框架能动态适应季节与运营变化，持续保证产品品质并最大化利润。相比传统遗传算法，DRL模型在经济性能相当的前提下，推理速度提升高达135倍，适用于实时应用。其可扩展性与适应性凸显了其在智能制造中作为数据驱动决策基础的巨大潜力。
原文摘要 · Abstract (English)
Plastic injection molding remains essential to modern manufacturing. However, optimizing process parameters to balance product quality and profitability under dynamic environmental and economic conditions remains a persistent challenge. This study presents a novel deep reinforcement learning (DRL)-based framework for real-time process optimization in injection molding, integrating product quality and profitability into the control objective. A profit function was developed to reflect real-world manufacturing costs, incorporating resin, mold wear, and electricity prices, including time-of-use variations. Surrogate models were constructed to predict product quality and cycle time, enabling efficient offline training of DRL agents using soft actor-critic (SAC) and proximal policy optimization (PPO) algorithms. Experimental results demonstrate that the proposed DRL framework can dynamically adapt to seasonal and operational variations, consistently maintaining product quality while maximizing profit. Compared to traditional optimization methods such as genetic algorithms, the DRL models achieved comparable economic performance with up to 135x faster inference speeds, making them well-suited for real-time applications. The framework's scalability and adaptability highlight its potential as a foundation for intelligent, data-driven decision-making in modern manufacturing environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。