Litcius/Paper detail

Artificial neural network technique to predict dynamic fracture of particulate composite

Vinod Kushvaha, S. Anand Kumar, Priyanka Madhushri, Aanchna Sharma

2020Journal of Composite Materials63 citationsDOI

Abstract

In this paper, the artificial neural network technique using a multi-layer perceptron feed forward scheme was used to model and predict the mode-I fracture behaviour of particulate polymer composites when subjected to impact loading. A neural network consisting of three-layers was employed to develop the network. Artificial neural network was constructed using six input parameters such as shear wave speed ( C S ), density ( D), elastic modulus ( E d ), longitudinal wave speed ( C L ), volume fraction ( V f ) and time ( t). The influence of input parameters on the output stress intensity factor and crack-initiation fracture toughness were found to be in the order of t > C S > D > E d > C L > V f . The degree of accuracy of prediction was 92.7% for stress intensity factor. In this regard, artificial neural network can be used in the modelling and prediction of fracture behaviour of particulate polymer composites under impact loading.

Topics & Concepts

Materials scienceArtificial neural networkComposite materialFracture toughnessMultilayer perceptronFracture (geology)Composite numberParticulatesPerceptronStress intensity factorFracture mechanicsStructural engineeringComputer scienceArtificial intelligenceEngineeringEcologyBiologyInnovative concrete reinforcement materialsMechanical Behavior of CompositesAsphalt Pavement Performance Evaluation