DRL-Based Injection Molding Process Parameter Optimization for Adaptive and Profitable Production

2025-05-16

AI Summary

To address the challenge of jointly optimizing product quality and profitability in injection molding under dynamic operating conditions and multi-source costs (e.g., resin, mold wear, time-of-use electricity pricing), this paper proposes a real-time profit-driven deep reinforcement learning framework. We innovatively model profitability as a learnable reward function that integrates a surrogate model for quality prediction with a time-of-use electricity-aware profit formulation. A hybrid SAC–PPO policy enables online adaptive decision-making, accommodating both transient process variations and seasonal shifts. Experiments demonstrate that the framework achieves optimal profitability under prescribed yield constraints, with inference speed 135× faster than genetic algorithms—satisfying millisecond-level control requirements in production lines. To the best of our knowledge, this is the first work to realize end-to-end, real-time co-optimization of quality and economic objectives in injection molding processes.

Technology Category

• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

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.

Problem

• Optimizing injection molding parameters for quality and profit
• Adapting to dynamic environmental and economic conditions
• Real-time process optimization using deep reinforcement learning

Innovation

• DRL-based real-time process optimization framework
• Profit function integrating costs and quality
• Surrogate models for efficient offline training