Determination of Residual Stress and Strain-Hardening Exponent Using Artificial Neural Networks

Chun Ping Guan; Hong Ping Jin

doi:10.4028/www.scientific.net/AMR.472-475.332

Paper Titles

Preparation of Ni-Base Alloy Coatings on Monel Alloy by Laser Cladding
p.313

Registration of 3-D Shape with Free-Form Surface Using Imageware and Genetic Algorithm
p.317

Fabrication of Semisolid Billets of Hypereutectic Al-Si Alloy by Severe Plastic Deformation and Remelting
p.323

Granite Step Gauge: A New Device for Error Measurement on CNC Machine Tools
p.328

Determination of Residual Stress and Strain-Hardening Exponent Using Artificial Neural Networks
p.332

Study Effect of Deflection on the Progress of Cracking in Aluminum with Different Heat Treatment
p.336

Control, Effection and Analysis of Voltage during Dielectric Barrier Discharges Plasma Surface Treated Carbon Fibers
p.342

Analytical Study on Mechanism of Electrolysis and Plasma Polishing
p.350

Elimination Technology of the Iron Dissolved in Flux Solution of Hot Dip Galvanizing Process
p.354

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 472-475Determination of Residual Stress and...

Determination of Residual Stress and Strain-Hardening Exponent Using Artificial Neural Networks

Abstract:

Through dimensional analysis of indentation parameters in this study, we propose an artificial neural network (ANN) model to extract the residual stress and strain-hardening exponent based on spherical indentation. The relationships between indentation parameters and the residual stress and material properties are numerically calibrated through training and validation of the ANN model. They enable the direct mapping of the characteristics of the indentation parameters to the residual stress and the elastic-plastic material properties. The proposed ANN model can be used to quickly and effectively determine the residual stress and strain-hardening exponent.