The superior multi-functional properties of polymer composites have made them an ideal choice for aerospace, automobile, marine, civil, and many other technologically demanding industries. The increasing demand of these composites calls for an extensive investigation of their physical, chemical and mechanical behavior under different exposure conditions. Machine learning (ML) has been recognized as a powerful predictive tool for data-driven multi-physical modeling, leading to unprecedented insights and exploration of the system properties beyond the capability of traditional computational and experimental analyses. Here we aim to abridge the findings of the large volume of relevant literature and highlight the broad spectrum potential of ML in applications like prediction, optimization, feature identification, uncertainty quantification, reliability and sensitivity analysis along with the framework of different ML algorithms concerning polymer composites. Challenges like the curse of dimensionality, overfitting, noise and mixed variable problems are discussed, including the latest advancements in ML that have the potential to be integrated in the field of polymer composites. Based on the extensive literature survey, a few recommendations on the exploitation of various ML algorithms for addressing different critical problems concerning polymer composites are provided along with insightful perspectives on the potential directions of future research. 

/pdf/advances-in-computational-intelligence-of-polymer-composite-crkooqxw.pdf

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Machine learning prediction of mechanical properties of braided-textile reinforced tubular structures

Vacuum-assisted resin transfer molding (VaRTM) is becoming one of the most robust alternatives for autoclave processes. VaRTM, which applies the resin injection method in a vacuum environment, generally uses fiber reinforcement and a polymer matrix separately in the process. The VaRTM is mainly dominated by the characteristics of constituent materials, such as preform permeability and resin viscosity. Among them, process design with the arrangement of resin inlet/outlet locations is closely related to process defects, and inappropriate inlet/outlet layouts cause voids, etc, which has a decisive effect on quality degradation. Therefore, in this study, a highly curved and twisted spar structure was fabricated by the VaRTM, and both flow simulations using Programs for Applied Mechanics–Resin Transfer Molding software and experimental test parts built with three different inlet/outlet line conditions were performed and compared to predict and improve impregnation quality. There was good agreement between the simulation and built test specimen for the three cases that the shorter inlet and outlet length resulted in improved impregnation quality. It was verified that impregnation and inner quality could be improved through flow simulation analysis during the VaRTM process.

Improvement of impregnation quality on out-of-autoclave processed CFRP aircraft wing spar through resin flow simulation

/pdf/advances-in-computational-intelligence-of-polymer-composite-n9kqvjendh.pdf

Glass fiber-reinforced plastic (GFRP) composites take place in engineering materials owing to their low-weight and high-mechanical properties. In some cases, they need to be shaped by machining before using in industrial applications. However, when these composites are machined, many problems such as bad surface quality, rapid tool wear are encountered. Therefore, optimization of cutting parameters is essential to eliminate or minimize these problems. In this study, GFRP composites were produced by combining polyester matrix material with glass fibers (GF) having 6 mm, 6–12 mm, 12 mm fiber length, and 20%, 25%, 30% fiber ratio by weight. The tensile strengths of these composites were investigated. Turning tests were also performed with cutting speeds of 40, 80, and 120 m/min, feed rates of 0.1, 0.2 and 0.3 mm/rev, and depth of cut of 1, 2, and 3 mm, according to Taguchi L27 standard orthogonal array method. The effect of fiber length and ratio, and cutting parameters on cutting forces and surface roughness were analyzed. As a result of the experiments, it was observed that the reinforced polymer matrix with GF provide to increase the tensile strength. The highest tensile strength was obtained as 55.95 MPa from the composite having a fiber length of 12 mm and a fiber ratio of 25%. Besides, the feed rate was determined as the most effective parameter among the all parameters on both cutting force and surface roughness. Therefore, the feed rate should be chosen low for lower cutting force and surface roughness values.

https://link.springer.com/content/pdf/10.1007/s42452-020-2684-5.pdf

Investigation of mechanical characteristics of GFRP composites produced from chopped glass fiber and application of taguchi methods to turning operations

The present work is aimed at determining mechanical properties of chopped strand glass fiber reinforced composite laminates manufactured based on the design of experiments by resin transfer molding at various injection pressures with 4, 5 and 6 layers. Response surface methodology was implemented to the experimental data for evaluating the effect of number of layers and resin injection pressure on mechanical properties and void content. Teaching learning based optimization (TLBO) has been proposed to predict optimal (maximum) mechanical properties of composite by optimizing the number of layers and injection pressure. Artificial neural network (ANN) with feed forward back propagation algorithm was also used to predict the responses and compare with experimental and TLBO results. It was found that the predicted values of responses from TLBO and ANN are good in agreement with experimental results.

/pdf/modeling-of-glass-fiber-reinforced-composites-for-optimal-519evxxeup.pdf

Modeling of glass fiber reinforced composites for optimal mechanical properties using teaching learning based optimization and artificial neural networks

Flow front velocity of resin plays a key role in yielding better impregnation of fiber reinforcement in resin transfer molding to fabricate quality composites. A video camera was used to capture the patterns of resin flowing below the grid lines drawn on the acrylic sheet of resin transfer mold and also to accurately measure the flow front velocity using an image conversion tool. The effect of flow front velocity, permeability, Reynolds number and void content at five different injection pressures on chopped strand E-glass/polyester composites consisting of 4, 5 and 6 layers has been studied. On the basis of Reynolds number of resin flow and void content present in the composite, optimal injection pressures are suggested for better impregnation of preform. Composites processed at these injection pressures gave superior properties in tension and flexure. Fractured parts of the specimens were examined on Scanning Electron Microscope to explain the causes of superior mechanical properties.

Venkata Ravishankar Dasari

Papers

Modeling of glass fiber reinforced composites for optimal mechanical properties using teaching learning based optimization and artificial neural networks

Determination of flow front velocity and optimal injection pressures for better impregnation of E-glass with polyester in resin transfer mold