Artificial neural network (ANN) prediction of compressive strength of VARTM processed polymer composites

Abstract

A three layer feed forward artificial neural network (ANN) model having three input neurons, one output neuron and two hidden neurons was developed to predict the ply-lay up compressive strength of VARTM processed E-glass/ polyester composites. The composites were manufactured using fabric preforms consolidated with 0, 3 and 6 wt.% of thermoplastic binder. The learning of ANN was accomplished by a backpropagation algorithm. A good agreement between the measured and the predicted values was obtained. Testing of the model was done within low average error levels of 3.28%. Furthermore, the predictions of ANN model were compared with those obtained from a multi-linear regression (MLR) model. It was found that ANN model has better predictions than MLR model for the experimental data. Also, the ANN model was subjected to a sensitivity analysis to obtain its response. As a result, the ANN model was found to have an ability to yield a desired level of ply-lay up compressive strength values for the composites processed with the addition of the thermoplastic binder.

Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood

“…These techniques have been widely used to solve a wide variety of problems regarding the strength of materials in many engineering fields. The following literature lists some of ANN and MLR applications in predicting strength properties of various materials [9,11,[14][15][16][17][18]. These modeling approaches have been also employed for predicting strength properties of wood and wood products.…”

On the Robustness of Forward and Inverse Artificial Neural Networks for the Simulation of Ethylene/1‐Butene Copolymerization

“…This approach may be used to solve highly nonlinear and complex problem by finding the optimum learning patterns of relationship between input and output variables . ANN models have been applied in various polymer applications as a predictive model for polymer properties and polymerization kinetics …”

Yield Estimation and Clustering of Chickpea Genotypes Using Soft Computing Techniques

“…The ANN modeling is typically applied when the process under interest is too complex or unknown to be modeled statistically. The ANN is especially useful in modeling complex nonlinear, multidimensional functional relationships (Seyhan et al, 2005; Tompos et al, 2007).…”

“…The ANN offers a distinct advantage over statistical models (i.e., mechanistic and empirical models) because of the elegance by which the technique can be implemented, and because no a priori assumptions about the shape of the fitting functions have to be made (Seyhan et al, 2005). ANN models do not depend on assumptions about functional form, probability distribution or smoothness, and have been proven to be universal approximators (Mittal and Zhang, 2000).…”

“…One of the characteristics of ANN is its ability to learn the relationship between dependent and independent variables through the data itself rather than assuming the functional form of the relationship (Mittal and Zhang, 2000). Learning is a data‐driven self‐adaptive process by which experience arising from exposure to measurements of empirical phenomena is converted to knowledge, embodied in internal parameter weights of the network (Seyhan et al, 2005). This could help overcome the lack of knowledge about the crop growth process.…”