Application of artificial neural network on wear properties of sinter-forged Fe-C-Mo low alloy steel. (2015)

• Record Type: Journal Article
• Authors: Vijay, D.; Kandavel, T.K.
• Is Part Of: International journal of advanced intelligence paradigms. Volume 7:Number 3/4(2015)
• Page Start: 209
• Page End: 221
• Publication Date: 2015
• Subjects: low alloy steel -- dry sliding wear -- coefficient of friction -- microstructure -- artificial neural networks -- ANNs -- molybdenum -- wear resistance -- microstructure; Artificial intelligence -- Periodicals; Machine theory -- Periodicals; Fuzzy logic -- Periodicals; 006.305
• Languages: English
• ISSNs: 1755-0386

Abstract

Application of artificial neural networks (ANN) in all possible fields is inevitable due to its robustness and simplicity over problem complexity. In this paper, an effort is made to apply ANN for the purpose of fitting and predicting the wear behaviour based on the criteria of various densification levels of molybdenum (2%Mo) alloyed powder metallurgy (P/M) low alloy steel (Fe-0.5%C). The various densities of sintered P/M low alloy steel specimens were subjected to dry sliding wear tests using pin-on-disc tribotester. The results of wear tests were compared, analysed and predicted by applying the ANN technique. It is observed that the ANN predicted values have good agreement with the experimental values. The wear properties of low alloy steel could be predicted on any input parameters level using ANN. The Mo addition has resulted in enhancing the wear resistive property of the plain carbon steel due to its carbides in the microstructure.