Optimization of tribological behaviour of TiO2 nanoparticles reinforced AA7178 alloy matrix using ANN and Taguchi's methodology. (1st June 2022)

• Record Type: Journal Article
• Authors: Bharat, Nikhil; Bose, P S C
• Is Part Of: Surface topography. Volume 10:Number 2(2022)
• Publication Date: 2022-06-01
• Subjects: AA7178 -- wear -- ANN -- taguchi -- optimization; Surfaces (Physics) -- Periodicals; Surfaces (Physics) -- Measurement -- Periodicals; 530.417
• DOI: 10.1088/2051-672X/ac7a55
• Languages: English
• ISSNs: 2051-672X

Abstract

Abstract: The investigation of tribological behaviour of AA7178 base alloy matrix reinforced with varying weight percentage of nano TiO2 particles (0, 1, 2 and 3%) using artificial neural network (ANN) and Taguchi is presented in this paper. Scanning Electron Microscope(SEM) with Energy Dispersive Spectroscopy (EDAX) was used to study the microstructural as well as wear behaviour of the nanocomposite. SEM images confirm that abrasive and adhesive wear was responsible for the worn-out surface. ANN with the Taguchi model was used to obtain the best input process parameters (sliding speed, distance, load and weight percentage) to minimize the output values (Coefficient of friction and wear rate). The coefficient of friction and wear rate were mainly affected from the weight percentage of nano TiO2 by 60.95% and 57.33%, respectively. The efficiency of ANN model was better compared to Taguchi model.