인공지능형 네트워크를 이용한 재료거동모델링에 관한 연구 = A Study on Material Modelling using Artificial Intelligent Networks

다국어 초록 (Multilingual Abstract)

Backpropagation neural networks performs computer simulations that have the potential to find the same patterns that fatigue practitioners recognize to relate experimental results to fatigue life prediction. This potential was used to construct neural networks to recognize the relation between X-ray diffraction half-value breadth ratio B/Bo, fractal dimension D_f, stress amplitude Δσ, main crack length α, (Δσ/σ_ys)^ma^n and da/dN, N/N_f for Al 2024-T3 alloy. Learning and generalization of neural networks was optimized by floating rate method. This study shows that neural networks has ability to predict fatigue crack growth rate and life on data of unlearned experimental condition.

목차 (Table of Contents)

• 1. 서론
• 2. 신경회로만을 이용한 피로손상 모델링
• 2.1 역전파 신경회로망
• 2.2 신경회로망을 이용한 피로손상 모델링
• 2.3 학습에 미치는 각 파라미터의 영향
• 3. 피로손상파측모델링 결과 및.2찰
• 4. 결과