Monitoring the neural network modelling of wear behaviour of Ti-6Al-4 V reinforced with nano B4C particle. (2021)

• Record Type: Journal Article
• Authors: Ramkumar, T.; Selvakumar, M.; Chandrasekar, P.; Mohanraj, M.; Krishnasharma, R.
• Is Part Of: Materials today. Volume 41:Part 4(2021)
• Page Start: 942
• Page End: 950
• Publication Date: 2021
• Subjects: Ti-6Al-4V -- Boron carbide -- SEM morphology -- Tribology -- ANN -- SWR; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2020.10.921
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: The main objective of the study is to fabricate nano boron carbide (B4 C) reinforced with titanium metal matrix composite (Ti-6Al-4 V) through powder metallurgy route. Composites preforms of Ti-6Al-4 V- (2–10) wt. % of nano boron carbide were fabricated. The characterization of the fabricated samples was preformed through Scanning electron microscope and X-Ray diffraction. Pin-on-disk wear testing machine was used to describe the lubricating wear behavior of the composites by varying loads and sliding distances. The surface morphology of worn out surfaces was also examined. Investigations over basic and functional properties of developed MMC revealed that the addition of nano B4 C decrease the specific wear rate (SWR) and coefficient of friction (CoF). To predict the tribological properties of titanium matrix composites, Artificial Neural Network (ANN) technique was adopted to arrive at optimal values of the input parameters based on the experimental data. The results illustrated that the mathematical models of tribological properties of Ti-6Al-4 V-B4 C are reliable with a less error and high level of accuracy.