Application of Adaptive Neuro-Fuzzy Inference Systems Technique for Modeling of Postweld Heat Treatment Process of Pressure Vessel Steel ASTM A516 Grade 70
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32794
Application of Adaptive Neuro-Fuzzy Inference Systems Technique for Modeling of Postweld Heat Treatment Process of Pressure Vessel Steel ASTM A516 Grade 70

Authors: Omar Al Denali, Abdelaziz Badi

Abstract:

The ASTM A516 Grade 70 steel is a suitable material used for the fabrication of boiler pressure vessels working in moderate and lower temperature services, and it has good weldability and excellent notch toughness. The post-weld heat treatment (PWHT) or stress-relieving heat treatment has significant effects on avoiding the martensite transformation and resulting in high hardness, which can lead to cracking in the heat-affected zone (HAZ). An adaptive neuro-fuzzy inference system (ANFIS) was implemented to predict the material tensile strength of PWHT experiments. The ANFIS models presented excellent predictions, and the comparison was carried out based on the mean absolute percentage error between the predicted values and the experimental values. The ANFIS model gave a Mean Absolute Percentage Error of 0.556%, which confirms the high accuracy of the model.

Keywords: Prediction, post-weld heat treatment, adaptive neuro-fuzzy inference system, ANFIS, mean absolute percentage error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 305

References:


[1] W. H. Kearns, Welding Handbook Metals and Their Weldability, American Welding Society, Miami, Fla, USA, 7th edition, 1982
[2] H. Granjon, Fundamentals of Welding Metallurgy, Abington Publishing, Cambridge, UK, 1991.
[3] G. Özkan, M. İnal, Comparison of neural network application for fuzzy and ANFIS approaches for multi-criteria decision making problems, Appl. Soft Comput. 24 (2014) 232–238.
[4] S. Kar, et al., Applications of neuro fuzzy systems: a brief review and future outline, Appl. Soft Comput. 15 (2014) 243–259.
[5] Nazari A and Riahi S. Computer-aided prediction of physical and mechanical properties of high strength cementitious composite containing Cr2O3 nanoparticles. Nano. 2010; 5(5):301-318. http://dx.doi.org/10.1142/S1793292010002219
[6] Jaya N. Sahu; Application of Response Surface Methodology for Modeling of Postweld Heat Treatment Process in a Pressure Vessel Steel ASTM A516 Grade 70, The Scientific World Journal Volume 2015, Article ID 318475, 8 pages http://dx.doi.org/10.1155/2015/318475.
[7] Ambrogio, G.; Filice, L.; Shivpuri, R.; Umbrello, D. Application of NN technique for predicting the in-depth residual stresses during hard machining of AISI 52100 steel. Int. J. Mater. Form. 2008, 1, 39–45 (CrossRef)
[8] Mia, M.; Królczyk, G.; Maruda, R.; Wojciechowski, S. Intelligent Optimization of Hard-Turning Parameters Using Evolutionary Algorithms for Smart Manufacturing. Materials 2019, 12, 879 (CrossRef)