Intelligent Prediction of Wear Loss Based on Ensemble Learning in Dual-Phase Steel
Main Article Content
Abstract
Dual-phase (DP) steels are widely used in the automotive and aerospace sectors for their excellent tensile strength, ductility, and wear resistance. Experimental determination of wear loss is expensive and time-consuming. These limitations can be eliminated by using data-driven machine-learning approaches. The primary purpose of this work is to develop efficient ensemble machine learning (EML) models to make predictions regarding the amount of wear loss experienced by dual-phase steel. Random forest (RF), Ada boost (AdaB), and gradient boost (GB) were used to predict wear-loss quantities. EML models have achieved their intended accuracy through a process of empirical tuning of their parameters using k-fold validation and grid search optimization. GB has outperformed others with the highest model accuracy and the fewest statistically significant errors. As a result, the ELM technique shows great promise in aiding the manufacture of wear-resistant components for a wide range of applications.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
G Britain; Education and research: A Report on the Present Position and Industry’s Needs, Lubrication (Tribology), H.M. Stationary Office, London, 1966.
D Dowson; History of Tribology, 2nd edition, Wiley, 1998.
M Ulas, O Altay, T Gurgenc, C Ozel; A new approach for prediction of the wear loss of PTA surface coatings using artificial network and basic, kernel-based and weighted extreme learning machine, Friction, 8 (2020), 1102-1116.
P I Menezes, M Nosonvsky, S P Ingole, S V Kailas, M R Lovell; Tribology for scientists and engineers, Springer, 2013.
Amit K Gupta, Deep Narayan Mishra; An experimental investigation of the effect of carbon content on the wear behavior of plain carbon steel, IJSR, 2(7) (2013), 222-224.
M Sharanabasappa, V R Kabadi, P B Shetty and Veerabhadrappa Algur; Dry Sliding Wear Behaviour of Hypereutectoid Steel Under the Influence of Microstructures, Sliding speeds, and Normal pressures, Int Journ of Mech Engg & Robot Reser, 4(2) (2015), 1-12.
Etsuo Marui, Norihiko Hasegawa, Hiroki Endo, Katsuhito Tanaka, Taiji Hattori; Research on the wear characteristics of hypereutectoid steel, Wear 205 (1997), 186-199.
X Gao, Z Jiang, D Wei, B Kosasih, S Jiao, D Chen; Dry sliding wear behaviour of full pearlite obtained by cladding low carbon steel to hypoeutectoid steel, Adv Mater Res 1017 (2014), 147-153.
Osman Altay, Turan Gurgenc, Mustafa Ulas, Chian Ozel; Prediction of wear loss quantities of ferroalloy coating using different machine learning algorithms, Friction, 8(1) (2020), 107-114.
S Siqi, Jian Gao, Yue Liu, Yan Zhao, Qu Wu, Wangwei Ju, Chuying Ouyang, Ruijuan Xiao; Multi-scale computation methods: Their applications in lithium-ion battery research and development, Chin, Phys. B 25(1) (2016), 018212.
J.C.A Batista, C. Godoy, A. Matthews; Micro-scale abrasive wear testing of duplex and non-duplex (single-layered) PVD (Ti, Al) N, TiN and Cr–N coatings, Tribology International, 35(2002), 363-372.
Veerabhadrappa Algur, Poornima Hulipalled, V Lokesha, Madeva Nagaral, V Auradi; Machine Learning Algorithms to Predict Wear Behavior Modified ZA-27 Alloy of Under Varying Operating Parameters, Journal of Bio-and Tribo-Corr, 8(1) (2022), 1-10.
K. Tsutsui, H. Terasaki, T. Maemura, K. Hayashi, K. Moriguchi, S. Morito; Microstructural diagram for steel based on crystallography with machine learning, Computational Materials Science 159 (2019), 403-411.
Ling Qiao, Zhonghong Lai, Yong Liu, Aorigele Bao, Jingchuan Zhu; Modelling and prediction of hardness in multi-component alloys: A combined machine learning, first principles and experimental study, Journal of Alloys and Compounds, 5 (2021), 853.
Veerabhadrappa Algur, V. R. Kabadi, S. M. Ganechari, V. R. Chavan; Effect of Mn content on tribological wear behaviour of ZA-27 alloy, Materials today: Proceedings 4 (2017), 10927-10934.
Poornima Hulipalled, Veerabhadrappa Algur, V Lokesha; An Approach of Data Science for the Prediction of Wear Behaviour of Hypereutectoid Steel, Journal of Bio-and Tribo-Corr, 8(1) (2022), 1-10.
Md Syam Hasan, Amir Kordijazi, Pradeep K Rohatgi, Michael Nosonovsky; Tribo informatic modeling of dry friction and wear of aluminum base alloys using machine learning algorithms, Trib Intern, 161 (2021), 1-11.
Fatih Aydin, Rafet Durgut; Estimation of wear performance of AZ91 alloy under dry sliding conditions using machine learning methods, Transc of Nonfer Met Soc of Ch, 31(1) (2021), 125-137.
S Bermejo, J Cabestany; Adaptive soft k-nearest-neighbour classifiers, Pattern Recogn, 33 (2005), 1999.
Li Yang, Abdallah Shami; On hyperparameter optimization of machine learning algorithms: Theory and practice, Neurocomputing, 415 (2020), 295-316.
Poornima Hulipalled, V. Lokesha; Optimized Machine Learning Algorithms to Predict Wear Behavior of Tribo-Informatics, Journal of Robotics and Automation Research, 3 (2022), 316-321.