Loading...

Application of artificial neural network to predict the effects of severe shot peening on properties of low carbon steel

Maleki, E ; Sharif University of Technology | 2016

383 Viewed
  1. Type of Document: Article
  2. DOI: 10.1007/978-981-10-1082-8_5
  3. Publisher: Springer Verlag , 2016
  4. Abstract:
  5. Mechanical failures in most cases originate from the exterior layers of the components. It is considerably effective to apply methods and treatments capable to improve the mechanical properties on component’s surface. Surface nanocrystallization produced by severe plastic deformation (SPD) processes such as severe shot peening (SSP) is increasingly considered in the recent years. However, artificial intelligence systems such as artificial neural network (ANN) as an efficient approach instead of costly and time consuming experiments is widely employed to predict and optimize the science and engineering problems in the last decade. In the present study the application of ANN in predicting of SSP effective parameters has been investigated and evaluated. The Back propagation (BP) error algorithm is used to network’s training. In order to train the ANN, experimental tests on AISI 1017 mild steel specimens were conducted and the data was gathered. Testing of the ANN is carried out using experimental data not used during training. Almen intensity, residual stress, crystallite size, full width at half maximum (FWHM) and hardness were modeled. Different networks with different inputs are developed for modeling of each mentioned parameters. The Almen intensity, hardness, crystallite size, FWHM and residual stress have least mean error respectively for the accomplished modeling. The comparison of obtained results of ANN’s response and experimental values indicates that the networks are tuned well and the ANN can be used to predict the SSP effective parameters and it can be an alternative way for calculating of parameters of this process
  6. Keywords:
  7. Artificial neural network ; Back propagation error ; Modeling ; Nanocrystallization ; Severe shot peening
  8. Source: Advanced Structured Materials ; Volume 61 , 2016 , Pages 45-60 ; 18698433 (ISSN)
  9. URL: https://link.springer.com/chapter/10.1007%2F978-981-10-1082-8_5