<span style="font-size:15.0pt;font-family: "Times New Roman";mso-fareast-font-family:"Times New Roman";mso-bidi-font-family: "Times New Roman";mso-ansi-language:EN-US;mso-fareast-language:EN-US; mso-bidi-language:AR-SA;mso-bidi-font-weight:bold" lang="EN-US">Prediction of effect of MoS₂ content on wear behavior of sintered Cu-Sn composite using Taguchi analysis and artificial neural network</span>

Abstract

<span style="font-size:9.0pt;mso-bidi-font-size: 10.0pt;mso-bidi-font-weight:bold;mso-bidi-font-style:italic" lang="EN-US">The present investigation aims to develop MoS₂ added, self lubricated copper-tin hybrid composite with different weight fractions of MoS₂ and characterize tribological properties. In order to evaluate the behavior of composites satisfying multiple performance measures, Taguchi approach has been adopted. <span style="font-size:9.0pt;mso-bidi-font-size: 10.0pt;mso-bidi-font-style:italic" lang="EN-US">An orthogonal array and an analysis of variance are employed to the influence of parameters like as wt% of MoS₂, load, sliding speed and sliding distance on dry sliding wear of the composites. Results show that sliding distance has the highest influence followed by a load and reinforcement. Confirmation tests are carried out to verify the experimental results. The morphology of the worn-out surfaces is examined to understand the wear mechanisms.<span style="mso-bidi-font-weight:bold"> The responses have been predicted using both Artificial Neural Network (ANN) and Taguchi method so that a comparative evaluation can be made. From this study, it is concluded that neural network predicts the responses more accurately than Taguchi prediction.

</span></span></span>