Loading...

Application of artificial neural network to estimate the fatigue life of shot peened Ti-6Al-4V ELI alloy

Yavari, S. A ; Sharif University of Technology

849 Viewed
  1. Type of Document: Article
  2. DOI: 10.1002/9781118013373.ch26
  3. Abstract:
  4. An artificial neural network to predict the fatigue life, residual stress and Almen intensity of shot peened alloy Ti6Al4V ELI was developed. To minimize the prediction error, a feed forward model was used and the neural network was trained with back-propagation learning Algorithm. The results of this investigation show that a neural network with one hidden layer and five neurons in this layer will give the best performance. With this structure the network approaches to the desired error in the least time. Furthermore, it was concluded that there is a good agreement between the experimental data, the predicted values and the well-trained neural network. Therefore, the neural network has a great potential to predict modeling of fatigue life within the range of input parameters (between upper and lower limits of shot peening times) considered
  5. Keywords:
  6. Artificial neural network ; Fatigue life ; Ti6Al4V ELI ; Backpropagation learning algorithm ; Experimental data ; Feed forward ; Hidden layers ; Input parameter ; Lower limits ; Prediction errors ; Ti-6al-4v ; Backpropagation algorithms ; Cerium alloys ; Fatigue of materials ; Forecasting ; Learning algorithms ; Materials science ; Shot peening ; Technology ; Vanadium ; Neural networks
  7. Source: Fatigue of Materials: Advances and Emergences in Understanding, Held During Materials Science and Technology 2010, MS and T'10, 17 October 2010 through 21 October 2010 ; 2010 , Pages 411-417 ; 9780470943182 (ISBN)
  8. URL: http://onlinelibrary.wiley.com/doi/10.1002/9781118013373.ch26/summary