Online Gate-Driven Flow Control in Resin Transfer Moulding Using a Neural-Network Surrogate
Abstract
In resin transfer moulding, complete saturation of the fibre preform is necessary before the resin front reaches the outlet vent(s), to prevent dry-spot formation. In practice, the flow front rarely advances uniformly due to race-tracking effects. We propose a combined estimation and control strategy to address this issue. We use pressure-sensor data collected during filling to estimate the unknown race-tracking strengths via an iterated extended Kalman filter, and to simultaneously optimise auxiliary gate pressures to prevent the resin from arriving at the vent before complete saturation occurs. To make this approach feasible in real time, we replace the expensive finite element-control volume model with neural network surrogate models. The Bayesian approximation error framework is used to account for the discrepancy between the surrogates and the original model. To make the training of the surrogates feasible with time-dependent control actions, we prove that the flow-front geometry depends only on the time-averaged gate pressures. We demonstrate the methodology on a representative forked geometry, showing that the combined estimation-and-control framework can substantially reduce the number of unfilled nodes at the end of filling compared with an uncontrolled baseline. However, the level of improvement depends strongly on the location and number of auxiliary gates.
Related
- The Interference-Conjugate Transform: The Tightest Interference-Linear Surrogate for Power Control, Scheduling and Beamforming in Wireless Networks
- Online Individualized Treatment Selection under Partial Feedback: False Discovery Control and Minimax Optimality
- Predictive Online Disturbance-Action Control for Linear Dynamical Systems
- Optimal Regret for Online Storage Control via Cumulative Policies
- Online Control of the Family-wise Error Rate (FWER) for Multi-stage Platform Trials
BibTeX
@misc{wright2026online,
title = {{Online Gate-Driven Flow Control in Resin Transfer Moulding Using a Neural-Network Surrogate}},
author = {Nicholas Wright and Oliver Maclaren and Piaras Kelly and Suresh Advani and Ruanui Nicholson},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.29521},
eprint = {2608.29521},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.29521},
}
RIS
TY - UNPB
TI - Online Gate-Driven Flow Control in Resin Transfer Moulding Using a Neural-Network Surrogate
AU - Nicholas Wright
AU - Oliver Maclaren
AU - Piaras Kelly
AU - Suresh Advani
AU - Ruanui Nicholson
PY - 2026
DA - 2026/08/30
PB - arXiv
DO - 10.48550/arxiv.2608.29521
UR - https://arxiv.org/abs/2608.29521
AB - In resin transfer moulding, complete saturation of the fibre preform is necessary before the resin front reaches the outlet vent(s), to prevent dry-spot formation. In practice, the flow front rarely advances uniformly due to race-tracking effects. We propose a combined estimation and control strategy to address this issue. We use pressure-sensor data collected during filling to estimate the unknown race-tracking strengths via an iterated extended Kalman filter, and to simultaneously optimise auxiliary gate pressures to prevent the resin from arriving at the vent before complete saturation occurs. To make this approach feasible in real time, we replace the expensive finite element-control volume model with neural network surrogate models. The Bayesian approximation error framework is used to account for the discrepancy between the surrogates and the original model. To make the training of the surrogates feasible with time-dependent control actions, we prove that the flow-front geometry depends only on the time-averaged gate pressures. We demonstrate the methodology on a representative forked geometry, showing that the combined estimation-and-control framework can substantially reduce the number of unfilled nodes at the end of filling compared with an uncontrolled baseline. However, the level of improvement depends strongly on the location and number of auxiliary gates.
ER -