Please use this identifier to cite or link to this item:
Title: Prediction of tribological characteristics of powder metallurgy Ti and W added low alloy steels using artificial neural network
Authors: Kandavel, Thanjavur Krishnamoorthy
Kumar, Thangaiyan Ashok
Varamban, Emaya
Keywords: Wear;Mass loss;P/M alloy steels;Friction co-efficient;Artificial neural network
Issue Date: Jun-2020
Publisher: NISCAIR-CSIR, India
Abstract: In the present research work, the effects of Titanium (Ti) and Tungsten (W) addition on tribological behavior of powder metallurgy (P/M) Fe-1%C steel have been investigated. The test specimens of plain carbon steel and 1%Ti, 1%W and 1%Ti+1%W added plain carbon steels were used to conduct the wear tests and wear behavior analyses. The optical and SEM images of wear tracks and microstructures of the alloys were obtained and analysed with wear behavior of the alloy steels. Artificial Neural Network (ANN) software was used to check the degree of agreement of test results with predicted values. The experimental results show that Ti and W added alloy steel exhibits excellent wear resistance. The carbides formation due to alloying elements pronounces the wear resistance of the alloy steel. It has been proven that ANN could be used as a tool to predict the wear behavior of the P/M alloy steels by agreement between the predicted and experimental values.
Page(s): 503-517
ISSN: 0975-1017 (Online); 0971-4588 (Print)
Appears in Collections:IJEMS Vol.27(3) [June 2020]

Files in This Item:
File Description SizeFormat 
IJEMS 27(3) 503-517.pdf1.16 MBAdobe PDFView/Open

Items in NOPR are protected by copyright, with all rights reserved, unless otherwise indicated.