Ordinary Differential Equations with Machine Learning for Prediction of Smart Composite Fracture Toughness

Abstract

This work in on the development of an ordinary differential equation (ODE) model coupled with statistical methods for the prediction of fracture toughness of a magnetostrictive, piezoelectric smart self-sensing Fiber Reinforced Polymer (FRP) composite. The smart composite with sensing properties encompasses Terfenol-D alloy nanoparticles and Single Walled Carbon NanoTubes (SWCNT). To explore various configurations the of nanoparticle constituents’ effect on fracture toughness within the FRP composite, the ODE model developed within a finite element analysis (FEA) environment is considered to attain fracture observations across the solution space. The acquired FEA data is then used to feed the machine-learning (ML) algorithms to obtain composite fracture toughness predictions. A comparison and development of artificial neural networks (ANN), decision trees and support vector machines (SVM) models for FRP smart self-sensing composite fracture toughness prediction is done. Qualitative results stating if the sample has fractured or not and quantitative data giving the fracture toughness and strain energy release rate for the smart self-sensing FRP composites is attained. A comparison of all predictions from the developed models for both fracture toughness is corroborated with literature data.