A neural network model to predict low cycle fatigue life of nitrogen-alloyed 316L stainless steel

Modelling and Process Analysis of Resistance Spot Welding On Aluminium Alloy AA6063 T6 Sheets Used In Transportation Applications

“…The underlying trend of the data set presented will be captured by the ANN in the form of a complex nonlinear relationship between the input parameters and output variable [7]. The ANNs characteristics make them suitable for modelling the strength of a RSW joint and therefore it was used as the modelling tool in this research.…”

“…The imitation of behaviour of the biological nervous system is being done by the ANNs. They are capable of mapping non-linear and complex systems in which there are limitations in the regression methods, because of their parallel, distributed and adaptive processing [6,7]. A technique based on ANN to model gas metal arc welding parameters was presented by Ates [8].…”

Application of Artificial Neural Networks in the Estimation of Mechanical Properties of Materials

“…This is a potential problem with the use of powerful non-linear regression methods in neural network modeling. An over-trained model tends to remember the relationship between input and output variables and therefore lacks generalization capability (Mathew et al, 2008). During the training session, the network weights are continuously adjusted until the difference between the predicted output and experimental value is minimized, i.e.…”

Fatigue Life Assessment of Selected Engineering Materials Based on Modified Low-Cycle Fatigue Test

“…The results of some studies prove a classic approach to the determination of fatigue characteristics when based on HCF and LCF tests. In recent years, studies have also appeared that attempt a different approach to the determination of the fatigue life of materials/products [10,11], including those based on hardness testing [12] or applying the idea of neural networks [13,14].…”