Tribological Parameters Optimization of AZ31-SiC Composite Using Whale Optimization Algorithm

Kumar, Kothuri Chenchu Kishor; Kumar, Bandalamudi Raghu; Rao, N. Mohan

doi:10.1007/s11665-022-07570-1

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multi-objective optimization algorithm for solving engineering problems by using an Ant lion optimizing algorithm was reported [23]. Optimization of AZ31-SiC Composite using a whale optimization algorithm, particle swarm optimization, and fire fly algorithm [24]. Few attempts have been made to forecast magnesium-based composites' wear and coefficient of friction.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network Modeling of Tribological Parameters Optimization of AZ31-SiC Metal Matrix Composite

Kishor Kumar,

Raghu Kumar,

Mohan Rao

2023

Applied Engineering Letters

View full text Add to dashboard Cite

This paper focuses on modeling the tribological properties of AZ31-SiC composite using an artificial neural network (ANN) fabricated through the stir casting method. The twenty-seven tests were performed with three loads (10 N, 15 N, and 20 N), three sliding speeds (0.5 m/s, 1.0 m/s, and 1.5 m/s), and three sliding distances (500 m, 750 m, and 1000 m) on wear testing machine and are used in the formation of training sets of ANN. Using the wear test data, Taguchi, Analysis of Variance (ANOVA), and regression analysis were carried out to determine the effect of the control parameters on the wear and coefficient of friction (COF). The experimental results demonstrate that the wear rate increases with an increase in load and distance and decreases with an increase in velocity. In addition, an alternative method is proposed to predict the wear and COF using ANN modeling with single and multi-hidden layer techniques. With good training, ANN gives accurate and close results to the experimental results. The results obtained using ANN modeling have a percentage of error of 4.71% and 5.79% for wear and COF respectively, when compared to experimental values. This prediction process saves time and costs for the manufacturer.

show abstract

Section: Introductionmentioning

confidence: 99%