Publication Type : Book Chapter
Publisher : Progress in Computing, Analytics and Networking, Advances in Intelligent Systems and Computing, Springer Verlag
Source : Progress in Computing, Analytics and Networking, Advances in Intelligent Systems and Computing, Springer Verlag, Volume 710, p.559-571 (2018)
ISBN : 9789811078705
Keywords : Adaptive neuro-fuzzy inference system, Ageing time, Artificial neural network modeling, Computer circuits, Copper alloys, Forecasting, Fuzzy inference, Fuzzy logic, Fuzzy neural networks, Fuzzy systems, Hardness, Neural networks, Nickel alloys, regression, Regression analysis, Soft computing, Soft computing models, Spinodal alloy, Statistical regression, Statistical regression model, Ternary alloys, Tin alloys, Wear of materials
Campus : Coimbatore
School : School of Engineering
Department : Mechanical Engineering
Year : 2018
Abstract : Castings of Copper–Nickel–Tin alloy were produced by varying the composition of Ni and Sn. The cast specimens were subjected to homogenization and solution treatment. The specimens were characterized for microstructure, hardness and subjected to adhesive wear test. Statistical regression model, artificial neural network model and Sugeno fuzzy model were developed to predict the hardness and wear rate of the alloy based on %Ni, %Sn and ageing time of the specimens. As Sugeno Fuzzy logic model uses adaptive neuro-fuzzy inference system, an integration of neural networks and fuzzy logic principles, the prediction efficiency was higher than statistical regression and artificial neural network model. The interaction effect of %Ni, %Sn and ageing time on the hardness and wear rate of the specimens were analysed using the Sugeno Fuzzy model. © Springer Nature Singapore Pte Ltd. 2018.
Cite this Research Publication : Dr. Ilangovan S., Vaira Vignesh R., Dr. Padmanaban R., and Dr. Gokulachandran J., “Comparison of statistical and soft computing models for predicting hardness and wear rate of Cu-Ni-Sn alloy”, in Progress in Computing, Analytics and Networking, Advances in Intelligent Systems and Computing, vol. 710, , Ed. Springer Verlag, 2018, pp. 559-571.