Neural networks with NARX structure for material lifetime assessment application

Abstract

In the present paper, neural networks (NN) with non-linear auto-regressive exogenous inputs (NARX) structure is developed and further applied for material lifetime assessment application. Rational of the use of the NARX structure in the application was emphasized and linked to the concept of constant life diagram (CLD), the well known concept in fatigue of material analysis and design. Fatigue life assessment was then performed and realized as one-step ahead prediction with respect to each stress level corresponding to stress ratio values arranged in such a way that transition took place from a fatigue region to another one in the CLD. As a result, material lifetime assessment can be fashioned for a wide spectrum of loading in an efficient manner. The simulation results for different materials and loading situations are presented and discussed.