Artificial neural networks-based J-integral prediction for cracked bodies under elasto-plastic deformation state –monotonic loading. (February 2023)

• Record Type: Journal Article
• Authors: Mortazavi, S.N.S.; Ince, A.
• Is Part Of: International journal of fatigue. Volume 167:Part A(2023)
• Publication Date: 2023-02
• Subjects: Fatigue cracks -- Crack growth-integral -- Artificial neural networks -- Finite element method; Materials -- Fatigue -- Periodicals; Materials -- Fatigue; Periodicals; 620.1122
• DOI: 10.1016/j.ijfatigue.2022.107311
• Languages: English
• ISSNs: 0142-1123

Abstract

Highlights: Artificial neural network model(s) are developed to predict elastic–plastic deformation fields around a crack tip. Input datasets for developed models are based on elastic deformation fields. Predicted elasto-plastic deformation fields are used for J-integral calculations. Non-linear finite element analysis data of a stainless steel (SS304) cracked body is used for models' verification. The proposed modeling approach provides efficient and accurate predictions. Abstract: Artificial neural networks (ANNs) integrated with a finite element (FE)-based equivalent domain integral method are developed to compute J -integral at the vicinity of crack tips through a time-efficient approach. Robust ANN models are trained to establish nonlinear relationships between FE predicted elastic and elasto-plastic stress, strain, and displacement fields of stainless steel (SS304). Subsequently, elastic–plastic J -integral can be determined by using only elastic FE analysis solution rather than computationally expensive elasto-plastic FE analysis solution. The results show that well-trained ANN models can efficiently and accurately determine J -integral around the crack tips on the basis of numerical elastic FE analysis solution.