A Machine Learning Model to Detect Flow Disturbances during Manufacturing of Composites by Liquid Moulding

Abstract

In this work, a supervised machine learning (ML) model was developed to detect flow disturbances caused by the presence of a dissimilar material region in liquid moulding manufacturing of composites. The machine learning model was designed to predict the position, size and relative permeability of an embedded rectangular dissimilar material region through use of only the signals corresponding to an array of pressure sensors evenly distributed on the mould surface. The burden of experimental tests required to train in an efficient manner such predictive models is so high that favours its substitution with synthetically-generated simulation datasets. A regression model based on the use of convolutional neural networks (CNN) was developed and trained with data generated from mould-filling simulations carried out through use of OpenFoam as numerical solver. The evolution of the pressure sensors through the filling time was stored and used as grey-level images containing information regarding the pressure, the sensor location within the mould and filling time. The trained CNN model was able to recognise the presence of a dissimilar material region from the data used as inputs, meeting accuracy expectation in terms of detection. The purpose of this work was to establish a general framework for fully-synthetic-trained machine learning models to address the occurrence of manufacturing disturbances without placing emphasis on its performance, robustness and optimization. Accuracy and model robustness were also addressed in the paper. The effect of noise signals, pressure sensor network size, presence of different shape dissimilar regions, among others, were analysed in detail. The ability of ML models to examine and overcome complex physical and engineering problems such as defects produced during manufacturing of materials and parts is particularly innovative and highly aligned with Industry 4.0 concepts.

PermeabilityNets: Comparing Neural Network Architectures on a Sequence-to-Instance Task in CFRP Manufacturing

“…For 2-dimensional flow (as addressed in the work at hand), the planar, anisotropic permeability tensor is set up as follows: The permeability x and y direction is shown by k x and k y , whereas k xy describes the dependency of the flow in one main direction on a pressure gradient in the other main direction. Gonzales et al [7] used CNNs to detect changes in the flow front from pressure sensors to be able to detect changes in permeability. They use the data of whole recorded runs, but can only detect single, rectangular changes in permeability.…”

Graphene nanoparticles as data generating digital materials in industry 4.0

“…Other than the calibration models, AI tools can be easily employed for detection, inspection and monitoring tasks 134 . These tasks may include detection of resin race-tracking in molds 135 , flow disturbances 136 , and unfilled zones formation 137 during the filling stage of an LCM process as well as inspection of broken-filaments during fiber production 138 . Novel AI-based methods for the inspection of the Automated Fiber Placement (AFP) process have also been presented by several researchers [139][140][141][142][143] .…”

The intersection of damage evaluation of fiber-reinforced composite materials with machine learning: A review

“…[139][140][141] Since damage mechanisms are known to form during the manufacturing process of composites, studies have examined their presence to identify potential regions of discontinuity and anomalies in the production of a composite part. Gonza´lez and Ferna´ndez-Le on 142 detected dissimilar materials during the production of liquid molded composites using a convolutional neural network architecture. Stieber et al 143 detected the occurrence of dry spots in resin transfer molding of CFRP laminates.…”