Modeling of Wear Performance of Si3N4-hBN Composite Using Artificial Neural Network (ANN)

Bhalerao, Yogesh Jayant ORCID: https://orcid.org/0000-0002-0743-8633 (2016) Modeling of Wear Performance of Si3N4-hBN Composite Using Artificial Neural Network (ANN). Artificial Intelligent Systems and Machine Learning, 8 (2). pp. 57-61.

Full text not available from this repository.

Abstract

Wear particles generated due to rolling/sliding motion between artificial joint leads to joint failure, which need to be minimised to extend the joint life. Silicon nitride (Si3N4) is non-oxide ceramic suggested as a new alternative for hip/knee joint replacement. Hexagonal Boron Nitride (hBN) is suggested as a solid additive lubricant to improve the wear performance of Si3N4. In this paper attempt has been made to evaluate the optimum proportion of % hBN in Si3N4 to minimise wear volume loss (WVL) against alumina (Al2O3) counterface. The experiments were conducted according to Design of Experiments (DoE) – Taguchi method and using the experimental results artificial neural network (ANN) trained and simulated for the different condition to predict wear volume loss in the Si3N4-hBN composite. Taguchi method presents 15N load and 8% hBN to minimise WVL of Si3N4. To confirm these levels, trained ANN simulated to validate the control parameters suggested by Taguchi method.

Item Type: Article
Faculty \ School: Faculty of Science > School of Engineering (former - to 2024)
UEA Research Groups: Faculty of Science > Research Groups > Materials, Manufacturing & Process Modelling
Related URLs:
Depositing User: LivePure Connector
Date Deposited: 14 Jan 2020 05:00
Last Modified: 07 Nov 2024 12:41
URI: https://ueaeprints.uea.ac.uk/id/eprint/73611
DOI:

Actions (login required)

View Item View Item