A Study on fatigue Damage Model using Neural Networks in 2024-T3 aluminium alloy

신경회로망을 이용한 Al 2024-T3합금의 피로손상모델에 관한 연구

To estimate crack growth rate and cycle ratio uniquely, many investigators have developed various kinds of mechanical parameters and theories. But, these have produced local solution space through single parameter. Neural Networks can perform pattern classification using several input and output parameters. Fatigue damage model by neural networks was used to recognize the relation between da/dN N/Nf, and half-value breadth ratio B/BO0, fractal dimension Df and fracture mechanical parameters in 2024-T3 ability to predict both crack growth rate da/dN and cycle ratio N/Nf within engineering estimated mean error (5%).