Abstract
The current work mainly focused on predicting the wear performance of modified ZA-27 alloy under dry sliding conditions. The trail runs were conducted with wear parameters such as varying normal loads, sliding speeds and sliding distances. A total of 75 number experiments were conducted to determine the wear loss. Supervised machine learning algorithms such as random forest (RF), Gaussian process regression, k-nearest neighbor, support vector machine and linear regression were used with the experimental results as input data set to predict the wear loss. Results reveal that the performance rate of R2 for training and testing are closely nearer for all constructed models. RF has yielded the superior results in R2, MAE and RMSE among all the constructed models. Wear surface and debris analysis were carried out using SEM micrographs.
Similar content being viewed by others
References
Babic M, Ninkovic R (2004) Zn-Al alloys as tribo materials. Tribol Ind 26(1 & 2):3–7
Prasad BK, Patwardhan AK, Yegneswaran AH (1998) Microstructure and property characterization of a modified zinc-base alloy and comparison with bearing alloys. J Mater Eng Perform 7(1):130–135
Algur V, Kabadi VR, Ganechari SM, Chavan VR (2017) Effect of Mn content on tribological wear behaviour of ZA-27 alloy. Mater Today Proc 4:10927–10934
Algur V, Kabadi VR, Ganechari SM, Sharanabasappa M (2014) Experimental investigation on friction characteristics of modified ZA-27 alloy using Taguchi technique. Int J Mech Eng Robot Res 3(4):24–32
Sevik H (2014) The effect of silver on wear behaviour of zinc-aluminium based ZA-12 alloy produced by gravity casting. Mater Charact 89:81–87
Algur V, Kabadi VR, Sharanabasappa M, Ganechari SM, Shetty PB (2015) Optimization of sliding specific wear and frictional force behaivour of modified ZA-27 alloy using taguchi method. Int J Recent Innov Trends Comput Commun 3(5):2644–2649
Seenappa V, Sharma KV (2011) Characterization of mechanical and micro structural properties of ZA alloys. Int J Eng Sci Technol 3(3):1783–1789
Murphy S, Savaskan T (1984) Comparative wear behavior of Zn-Al based alloys in an automotive engine application. Wear 98:151–161
Li Y, Ngai TL, Xia W, Zhang W (1996) Effects of Mn content on the tribological behaviors of Zn-27% Al-2% Cu alloy. Wear 198:129–135
Choudhury P, Das S, Datta BK (2002) Effect of Ni on the wear behavior of a zinc aluminium alloy. J Mater Sci 37:2103–2107
Savaskan T, Aydmer A (2004) Effect of silicon content on the mechanical and tribological properties of monotectoid- based zinc-aluminium-silicon alloys. Wear 257:377–388
Vencl A, Bobic I, Vucetic F, Bobic B, Kandeva M (2014) The influence of strontium addition on the tribological properties of Zn25Al3Si alloy in boundary lubricated condition. Int Conf Mater Tribol 25:1
Pandey JP, Prasad BK, Yegneswaran AH (1998) Dry sliding wear behaviour of a zinc-based alloy: a comparative study with a leaded-tin bronze. Mater Trans 39(11):1121–1125
Rosenkranz A, Marian M, Profito FJ, Aragon N, Shah R (2020) The use of artificial intelligence in tribology. Lubricants 9(2):1–11
Liu Y, Li HY, Jiang HF, Su XJ (2013) Artificial neural networking modelling to predict hot deformation behaivour of zinc-aluminium alloy. Mater Sci Technol 29(2):184–189
Altay O, Gurgenc T, Ulas M, Ozel C (2020) Prediction of wear loss quantities of ferro-alloy coating using different machine learning algorithms. Friction 8(1):107–114
Moosavin A, Ahmadi H, Tababaeefer A, Khazaee M (2013) Comparison of two classifiers; K-nearest neighbor and artificial neural network, for fault diagnosis on a main engine journal bearing. Shock Vib 20:263–272
Sharanabasappa M, Kabadi VR, Algur V (2015) The effect of pearlite, cementite, and martensite phases on volumetric wear rate of hypereutectoid steel under dry sliding conditions. Int J Metall Mater Sci Eng 5(1):2278–2524
Nagaral M, Deshapande RG, Auradi V, Boppana SB, Dayanand S, Anilkumar MR (2021) Mechanical and wear characterization of ceramic boron carbide reinforced Al2024 alloy metal composites. J Bio- Tribo Corros 7(9):1–2
Al-Nasser AD, Radaideh A (2008) Estimation of simple linear regression model using L ranked set sampling. Int J Open Probl Compt Math 1(1):18–33
Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier, Amsterdam
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Brereton RG, Lloyd GR (2010) Support vector machines for classification and regression. Analyst 135(2):230–267
S Gunn (1998) Support vector machines for classification and regression. ISIS Technical Report. Image speech and intelligent systems group university of Southampton
Zhong Y, Zhao L, Liu Z, Xu Y, Li R (2010) Using a support vector machine method to predict the development indices of very high water cut oilfields. Pet Sci 7:379–384
Hashemitaheri M, Mekarthy SM, Cherukuri H (2020) Prediction of specific cutting forces and maximum tool temperatures in orthogonal machining by support vector and Gaussian process regression methods. Procedia Manuf 48:1000–1008
Kong D, Chen Y, Li N (2018) Gaussian process regression for tool wear prediction. Mech Syst Signal Process 104:556–574
Aye S, Heyns P (2017) An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission. Mech Syst Signal Process 84:485–498
Breiman L (2001) Random forests. Mach Learn 45:5–32
Aydin F, Durgut R (2021) Estimation of wear performance of AZ91alloy under dry sliding conditions using machine learning methods. Trans Nonferrous Met Soc China 31:125–137
James G, Witten D, Hastie T, Tibshirani R (2013) An introduction to statistical learning. Springer Science and Business Media LLC, New York
Bermejo S, Cabestany J (2000) Adaptive soft k-nearest-neighbour classifiers. Pattern Recogn 33:1999–2005
Qiao Q, He H, Yu J, Zhang Y, Qi H (2021) Applicability of machine learning on predicting the mechanochemical wear of the borosilicate and phosphate glass. Wear 476:203721
Imandoust SB, Bolandraftar M (2013) Application of K-nearest neighbour (KNN) approach for predicting economic events: theoretical background. Int J Eng Res Appl 3(5):605–610
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Algur, V., Hulipalled, P., Lokesha, V. et al. Machine Learning Algorithms to Predict Wear Behavior of Modified ZA-27 Alloy Under Varying Operating Parameters. J Bio Tribo Corros 8, 7 (2022). https://doi.org/10.1007/s40735-021-00610-8
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40735-021-00610-8