Taguchi approach and decision tree algorithm for prediction of wear rate in zinc oxide-filled AA7075 matrix composites

Alagarsamy, S.V.; Balasundaram, R.; Ravichandran, M.; Mohanavel, V.; Karthick, Alagar; Devi, Sharmila

doi:10.1088/2051-672x/ac0f34

Cited by 17 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, these alloys are made with self or hard ceramic particulates such as ZrO 2 [2], TiC [3], TiB 2 [4], Al 2 O 3 [5], B 4 C [6,7], ZnO [8], Si 3 N 4 [9], and Gr [10] to improve the tribological properties. The development of Al-based composites increases widespread in recent days because of it providing more wear resistance.…”

Section: Introductionmentioning

confidence: 99%

Optimization and Prediction of Tribological Behaviour of Al-Fe-Si Alloy-Based Nanograin-Refined Composites Using Taguchi with Response Surface Methodology

Balaji

Maniarasan

Alagarsamy³

et al. 2022

Journal of Nanomaterials

View full text Add to dashboard Cite

Aluminium matrix composites (AMCs) are broadly used to change the monolithic materials in aviation, automotive, and defense industries owing to their superior characteristics such as specific strength with light weight, greater hardness, good wear resistance, and better thermal properties. This novel work was aimed at estimating the specific wear rate (SWR) of zirconium dioxide- (ZrO2-) filled AA8011 (Al-Fe-Si alloy) matrix composites. A Taguchi method and response surface methodology (RSM) were used to find out the optimum range of control parameters on SWR of proposed composites. The stir casting technique was used to fabricate the composite specimens with varying proportions (5, 10, and 15 wt.%) of ZrO2 particle addition. The wear tests were performed as per L27 orthogonal design by using a pin-on-disk apparatus under dry conditions. For this test, four control parameters such as wt.% of ZrO2, load, disc velocity, and sliding distance each at three levels were selected. Based on the experimental results, 15 wt.% of ZrO2, 29.43 N of load, 0.94 m/s of disc velocity, and 1000 m of sliding distance provide the minimum SWR of the developed composite sample. ANOVA result revealed that the load (49.04%) was the primary dominant factor for affecting the SWR, followed by wt.% of ZrO2 content (29.24%), respectively. Moreover, scanning electron microscopy (SEM) analysis was performed to study the wear mechanism of worn-out surface of the composite test specimens.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization and Prediction of Tribological Behaviour of Al-Fe-Si Alloy-Based Nanograin-Refined Composites Using Taguchi with Response Surface Methodology

Balaji

Maniarasan

Alagarsamy³

et al. 2022

Journal of Nanomaterials

View full text Add to dashboard Cite

show abstract

“…Based on the extensive literature review conducted, it has been understood that many factors independently affect the tribological properties of MMCs in terms of wear rate and coefficient of friction. 31 The parameters and their corresponding levels were selected from the previous studies 32 and these are shown in Table 1. Taguchi methodology is adopted to obtain the optimized parameters, which would result in the lowest wear rate and COF.…”

Section: Experiments and Methodologymentioning

confidence: 99%

Optimization of tribological process parameters of titanium carbide reinforced copper matrix composites

Ravichandran¹,

Alagarsamy²,

Dinakaran³

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part J:

Self Cite

View full text Add to dashboard Cite

Copper (Cu) matrix composites are developed by reinforcing Cu with Titanium Carbide (TiC) powder using the powder metallurgy (PM) method. Pin-on-disc tribo analysis is conducted to evaluate the tribological performance of the developed composites. Moreover, the influence of different parameters such as, concentration (wt.%) of TiC, applied load, sliding velocity and sliding distance on the wear rate and friction coefficient are studied using Taguchi L16 orthogonal array. The main effect plot reveals that the lowest wear rate is obtained at 12 wt.% of TiC, 10 N applied load, 4 m/s sliding velocity and 1750 m sliding distance. Similarly, the lowest friction coefficient is attained at 12 wt.% of TiC, 10 N applied load, 4 m/s sliding velocity and 750 m sliding distance. Analysis of variance (ANOVA) results shows that the wt.% of TiC powder is a more noteworthy parameter for obtaining the lowest wear rate and friction coefficient with a contribution of 94.54% and 94.17%, respectively. A regression model is also developed to predict the friction coefficient and wear rate for the developed composites.

show abstract

“…They compared the output of the predicted values, with original values, revealed good prediction accuracy. Balasundaram et al [22] proposed a step-by-step technique for using the decision tree algorithm to solve a twomachine flow shop scheduling problem. Ramakrishnan and Balasundaram [8] applied regression models to the boronizing process of SS310.…”

Section: Literature Surveymentioning

confidence: 99%

Investigation of surface roughness and material removal rate of WEDM of SS304 using ANOVA and regression models

Srinivasan¹,

Ganesh²,

D³

et al. 2022

Surf. Topogr.: Metrol. Prop.

Self Cite

View full text Add to dashboard Cite

Use of machine learning and artificial intelligence (AI) to analyze the complex interdependencies of production dataset has gained momentum in recent years. Machine learning and predictive algorithms are now used by manufacturers to fine-tune the quality of their products. WEDM of SS304 with process parameters such as pulse-on-time (Ton), pulse-off-time (T off), current (I), and voltage (V) was varied to study the effect of machining parameters such as Material Removal Rate (MRR) and surface roughness. Experiments were planned and executed according to the L’9 orthogonal array. Scanning Electron Microscope (SEM) was utilized to study the machined surface. An analysis of variance (ANOVA) was performed to determine the input and output significance. ANOVA results revealed that V (81.85%) and Toff (77.75 %) for surface roughness. Further to determine the relationship between variables, various regression models based on machine learning was tested. The effectiveness of the regression models were tested. From their output it was concluded that the multilayer perception model had the highest correlation coefficient (0.999) for MRR while for surface roughness it was (0.995).

show abstract

Taguchi approach and decision tree algorithm for prediction of wear rate in zinc oxide-filled AA7075 matrix composites

Cited by 17 publications

References 24 publications

Optimization and Prediction of Tribological Behaviour of Al-Fe-Si Alloy-Based Nanograin-Refined Composites Using Taguchi with Response Surface Methodology

Optimization and Prediction of Tribological Behaviour of Al-Fe-Si Alloy-Based Nanograin-Refined Composites Using Taguchi with Response Surface Methodology

Optimization of tribological process parameters of titanium carbide reinforced copper matrix composites

Investigation of surface roughness and material removal rate of WEDM of SS304 using ANOVA and regression models

Contact Info

Product

Resources

About