Prediction of curing process for thermosetting prepreg compression molding process based on machine learning

Abstract

In the curing process of thermosetting prepreg compression molding (PCM), the distribution of the temperature field and the curing degree field have an important influence on the performance of composites. Therefore, the establishment of method to accurately predict the temperature difference and the degree of cure (DoC) difference during the curing process is significance for improving the performance of composites. In this paper, three kinds of machine learning models are studied: back propagation (BP) neural network, genetic algorithm‐back propagation (GA‐BP) neural network, radial basis function (RBF) neural network, then predictive models based on finite element method (FEM) and machine learning models are proposed. In the double‐dwell curing curve, six typical parameters are selected as inputs; the maximum value of temperature, the maximum value of temperature overshoot, the maximum DoC difference, the curing time, these four parameters during the curing process are selected as outputs, then the rapid predictive model is established. Within the value range of the process parameters, the Latin hypercube sampling (LHS) method is used to select 100 sets of sample points, and after training on three predictive models, comparison, and verification are carried out. The results show that the predictive effect of the RBF model is the best. In these three models, the RBF model is more suitable for the performance prediction of composites PCM. In this article, the research provides the basis for the performance prediction of composites and the multiobjective optimization of the curing process.

Composite component incremental consolidation for fiber waviness inhibition and its effect on damage progression of curved beams

“…Fiber reinforced polymer composites have gained increasing popularity as primary structural materials in aerospace over last decades due to their lightweight, high mechanical strength, and excellent high-temperature resistance. [1,2] Many high performance composite components are manufactured by stacking prepreg plies onto a rigid mold and then curing the preform in an autoclave.…”

“…Fiber reinforced polymer composites have gained increasing popularity as primary structural materials in aerospace over last decades due to their lightweight, high mechanical strength, and excellent high‐temperature resistance. [ 1,2 ] Many high performance composite components are manufactured by stacking prepreg plies onto a rigid mold and then curing the preform in an autoclave. The processing of flat or low curvature thin composite component is generally not problematic, but severe fiber waviness defects often occur at sharp corners of thick component, [ 3–5 ] where the mechanical strength is also the weakest during service.…”

Review of curing deformation control methods for carbon fiber reinforced resin composites

“…Residual stress and shape deformation caused by the process are the main challenges in the fabrication of composite materials, which seriously limit the rapid development of CFRP composites, and must be considered in the design of composite structures. In order to reduce the residual stress inside the structural parts, not only the curing process of resin was studied, [13][14][15] but also the mechanism and influencing factors of CFRP curing distortion were explored by many scientists. [16][17][18][19] Wucher et al 20 developed a computational mold compensation strategy to compensate the cure-induced distortions of the curved C-Spar.…”

Theory‐guided machine learning for optimal autoclave co‐curing of sandwich composite structures

“…ML methods are also used to predict the temperature differences and the degree of cure during compression molding of thermosetting prepregs. Hou et al [ 18 ] trained several ML algorithms on a data set produced by FE simulations of the process in order to provide a tool with low computational cost for the prediction of the effect of several process parameters on the outcome of the compression molding process. The accuracy of the predictions by their ML tools was affected by the availability of limited data set.…”