Reinforcement Learning for Synchronised Flow Control in a Dual-Gate Resin Infusion System

2025-06-30

AI Summary

In dual-inlet resin infusion, asynchronous flow fronts cause dry spots and voids, compromising composite quality. To address this, this work proposes a reinforcement learning–based closed-loop control strategy. Specifically, the Proximal Policy Optimization (PPO) algorithm is introduced for the first time to control resin infusion dynamics; an agent is trained in a partially observable simulation environment and dynamically regulates inlet flow rates via real-time state observations and a custom reward function to ensure precise convergence of flow fronts. This approach overcomes the limitations of conventional open-loop control, significantly enhancing fiber impregnation uniformity and process robustness. Experimental results demonstrate a >70% reduction in flow front synchronization error, along with 92% and 65% reductions in dry spot area and void fraction, respectively—substantially improving quality consistency and structural reliability of composite components.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Resin infusion (RI) and resin transfer moulding (RTM) are critical processes for the manufacturing of high-performance fibre-reinforced polymer composites, particularly for large-scale applications such as wind turbine blades. Controlling the resin flow dynamics in these processes is critical to ensure the uniform impregnation of the fibre reinforcements, thereby preventing residual porosities and dry spots that impact the consequent structural integrity of the final component. This paper presents a reinforcement learning (RL) based strategy, established using process simulations, for synchronising the different resin flow fronts in an infusion scenario involving two resin inlets and a single outlet. Using Proximal Policy Optimisation (PPO), our approach addresses the challenge of managing the fluid dynamics in a partially observable environment. The results demonstrate the effectiveness of the RL approach in achieving an accurate flow convergence, highlighting its potential towards improving process control and product quality in composites manufacturing.

Problem

• Control resin flow in dual-gate infusion for uniform impregnation
• Synchronize resin flow fronts using reinforcement learning
• Manage fluid dynamics in partially observable environments

Innovation

• Reinforcement Learning for flow control
• Proximal Policy Optimisation in resin infusion
• Synchronising dual resin inlets dynamically