Optimization of hybrid aluminum composites wear using Taguchi method and artificial neural network

Abstract

Purpose This research aims to describe the influence of weight per cent of graphite (Gr), applied load and sliding speed on the wear behavior of aluminum (Al) alloy A356 reinforced with silicon carbide (SiC) (10 Wt.%) and Gr (1 Wt.% and 5 Wt.%) particles. The objective is to analyze the effect of the aforementioned parameters on a specific wear rate. Design/methodology/approach These hybrid composites are obtained by means of the compo-casting process. Tribological analyses were conducted on block-on-disc tribometer at three different loads (10, 20 and 30 N) and three different sliding speeds (0.25, 0.5 and 1 m/s), at the sliding distance of 900 m, in dry sliding wear conditions. Optimization of the tribological behavior was conducted via the Taguchi method, and ANOVA was used for the analysis of the specific wear rate. Confirmation tests are used to foresee and check the experimental results. Examined samples were analyzed via a scanning electron microscope (SEM). Regression models for predicting specific wear rate were developed with Taguchi and ANN (artificial neural network) methods. Findings The biggest impact on value of specific wear rate has the load (43.006%), while the impact of Wt.% Gr (31.514%) was less. After comparison of the results, i.e. regression models, for predicting the specific wear rate, it was observed that ANN was more efficient than the Taguchi method. The specific wear rate of Al alloy A356 with SiC (10 Wt.%) and Gr (1 Wt.% and 5 Wt.%) decreases with a decrease in the load and weight per cent of Gr-reinforcing material, as well as with a decrease in sliding speed. Originality/value The results obtained in this paper using the Taguchi method and the ANN method are useful for improving and further investigating the wear behavior of the SiC- and Gr-reinforced Al alloy A356.

Determination of tribological properties of aluminum cylinder by application of Taguchi method and ANN-based model

“…Validation of the results is carried out in parallel, using the ANN-based model. As a basis for modeling and calibration of the model, some of the available scientific results in this field are used [34][35][36][37].…”

Tribological characteristics of Al/SiC/Gr hybrid composites

“…1. The effect of load on the wear rate of the Al/SiC/Gr composites with different wt % of the SiC particles and fixed 1 wt % Gr [13,[19][20]. From diagram in Figure 2, one can notice that the friction coefficient increases with the load increase, as well as with the SiC particles volume share increase.…”

Optimization of Parameters of a Planetary Gearbox Using the Taguchi-Grey Relational Analysis

“…The (S/N) ratios, which are log functions of a desired output, serve as the objective functions for optimization, help in the data analysis and prediction of the optimum results. There are three types of the (S/N) ratio analyses that are generally applicable: the-higher-the-better, the-nominal-the-better and thelower-the-better [7]. In this study, the higher-the-better quality characteristics has been used for calculating the (S/N) ratio for the Grey grade of the responses.…”

“…The (S/N) ratio is the objective function for optimization and with the use of a logarithmic function it helps in data analysis and in prediction of the optimal results. In this paper, the-higher-the-better quality characteristics was used for calculating the (S/N) ratios of the responses [5], [6], [7]. In this way, the multiple response problems are converted into a single response problem.…”

“…The Taguchi method is a well-known optimization method, which is used in a variety of applications [5], [6]. Application of this method ensures savings in labor and time costs, with simultaneously examining several parameters in several experimental conditions, providing the quantitative information, [7], [8]. Limitation of the Taguchi method is that it can only be applied to solve individual objective problems and cannot be used for problems with multiple objectives optimization, especially when there are different performance characteristics needed.…”