This paper presents crack growth analysis approach on the basis of neural networks, a branch of cognitive science to high temperature low cycle fatigue that shows strong nonlinearity in material behavior. As the number of data patterns on crack growth increase, pattern classification occurs well and two point representation scheme with gradient of crack growth curve simulates crack growth rate better than one point representation scheme. Optimal number of learning data exists and excessive number of learning data increases estimated mean error with remarkable learning time J-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).
Jo, Seok-Su ; Ju, Won-Sik 2000. "A Study on Fatigue Crack Growth and Life Modeling using Backpropagation Neural Networks" 大韓機械學會論文集. Transactions of the Korean Society of Mechanical Engineers. A. A, 24(3): 634~644
2000. "A Study on the Prediction of Fatigue Life in 2024-T3 Aluminium using X-ray Half-Value Breadth" 한국정밀공학회지 = Journal of the Korean Society of Precision Engineering, 17(1): 145~152
2001. "A Study of Fatigue Damage Model using Neural Networks in 2024-T3 Aluminium Alloy" 한국공작기계학회논문집 = Transactions of the Korean society of machine tool engineers, 10(4): 14~21
Kim, Cheol ; Yang, Won-Ho ; Heo, Sung-Pil ; Chung, Ki-Hyun 2002. "Prediction for the Error due to Role Eccentricity in Hole-drilling Method Using Backpropagation Neural Network" 大韓機械學會論文集. Transactions of the Korean Society of Mechanical Engineers. A. A, 26(3): 436~444
2005. "" Journal of mechanical science and technology, 19(7): 1393~1404