Prediction of the peak load and absorbed energy of dynamic brittle fracture using an improved artificial neural network

Abstract

In this paper, a robust technique is presented to predict the peak load and crack initiation energy of dynamic brittle fracture in X70 steel pipes using an improved artificial neural network (IANN). The main objective is to investigate the behaviour of API X70 steel based on two experimental tests, namely Drop Weight Tear Test (DWTT) and the Charpy V-notch impact (CVN), for steel pipe specimens. The mechanical properties in the brittle fracture behaviour of API X70 steel pipes are predicted utilizing numerical approaches with different crack lengths. Next, to simulate the impact of API X70 steel pipes at lower temperatures through a numerical approach, a cohesive approach using the extended Finite Element Method (XFEM) is used. The data obtained are used as input for the proposed IANN using Balancing Composite Motion Optimization (BCMO), Particle Swarm Optimization (PSO) and Jaya optimization algorithms, to predict the peak load values and crack initiation energy of dynamic brittle fractures in API X70 steel with different crack lengths. The results show the effectiveness of ANN-PSO and ANN-BCMO based on the convergence of the results and the accuracy of the prediction of the peak load and crack initiation energy.