Abstract
Wear tests are essential in the design of parts intended to work in environments that subject a part to high wear. Wear tests involve high cost and lengthy experiments, and require special test equipment. The use of machine learning algorithms for wear loss quantity predictions is a potentially effective means to eliminate the disadvantages of experimental methods such as cost, labor, and time. In this study, wear loss data of AISI 1020 steel coated by using a plasma transfer arc welding (PTAW) method with FeCrC, FeW, and FeB powders mixed in different ratios were obtained experimentally by some of the researchers in our group. The mechanical properties of the coating layers were detected by microhardness measurements and dry sliding wear tests. The wear tests were performed at three different loads (19.62, 39.24, and 58.86 N) over a sliding distance of 900 m. In this study, models have been developed by using four different machine learning algorithms (an artificial neural network (ANN), extreme learning machine (ELM), kernel-based extreme learning machine (KELM), and weighted extreme learning machine (WELM)) on the data set obtained from the wear test experiments. The R2 value was calculated as 0.9729 in the model designed with WELM, which obtained the best performance [with 11among the models evaluated.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Holmberg K, Erdemir A. Influence of tribology on global energy consumption, costs and emissions. Friction5(3): 263–284 (2017)
Khadem M, Penkov O V, Yang H K, Kim D E. Tribology of multilayer coatings for wear reduction: A review. Friction5(3): 248–262 (2017)
Luo W, Selvadurai U, Tillmann W. Effect of residual stress on the wear resistance of thermal spray coatings. J Therm Spray Technol25(1-2): 321–330 (2016)
Paul T, Alavi S H, Biswas S, Harimkar S P. Microstructure and wear behavior of laser clad multi-layered Fe-based amorphous coatings on steel substrates. Lasers Manuf Mater Process2(4): 231–241 (2015)
Azimi G, Shamanian M. Effect of silicon content on the microstructure and properties of Fe-Cr-C hardfacing alloys. J Mater Sci45(3): 842–849 (2010)
Zahiri R, Sundaramoorthy R, Lysz P, Subramanian C. Hardfacing using ferro-alloy powder mixtures by submerged arc welding. Surf Coat Technol260: 220–229 (2014)
Fan C, Chen M C, Chang C M, Wu W T. Microstructure change caused by (Cr,Fe)23C6 carbides in high chromium Fe-Cr-C hardfacing alloys. Surf Coat Technol201(3-4): 908–912 (2006)
Yang J, Hou X R, Zhang P, Zhou Y F, Yang Y L, Ren X J, Yang Q X. Mechanical properties of the hypereutectoid Fe-Cr-C hardfacing coatings with different nano-Y2O3 additives and the mechanism analysis. Mater Sci Eng: A655: 346–354 (2016)
Zhou Y F, Qin G K, Jiang P J, Wang S F, Qi X W, Xing X L, Yang Q X. Dry sliding wear behavior of (Cr,Fe)7C3-γ(Cr,Fe) metal matrix composite (MMC) coatings: The influence of high volume fraction (Cr,Fe)7C3 carbide. Tribol Lett66(3): 108 (2018)
Durmuş H, Çömez N, Gül C, Yurddaşkal M, Yurddaşkal M. Wear performance of Fe-Cr-CB hardfacing coatings: Dry sand/rubber wheel test and ball-on-disc test. Int J Refract Met Hard Mater77: 37–43 (2018)
Yilmaz S O, Özenbaş M, Yaz M. FeCrC, FeW, and NiAl modified iron-based alloy coating deposited by plasma transferred arc process. Mater Manuf Processes26(5): 722–731 (2011)
Teker T, Karataş S, Yilmaz S O. Microstructure and wear properties of AISI 1020 steel surface modified by HARDOX 450 and FeB powder mixture. Prot Met Phys Chem Surf50(1): 94–103 (2014)
Masanta M, Shariff S M, Choudhury A R. Evaluation of modulus of elasticity, nano-hardness and fracture toughness of TiB2-TiC-Al2O3 composite coating developed by SHS and laser cladding. Mater Sci Eng: A528(16-17): 5327–5335 (2011)
Eroglu M. Boride coatings on steel using shielded metal arc welding electrode: Microstructure and hardness. Surf Coat Technol203(16): 2229–2235 (2009)
Reinaldo P R, D’Oliveira A S C M. NiCrSiB coatings deposited by plasma transferred arc on different steel substrates. J Mater Eng Perform22(2): 590–597 (2013)
Hou Q Y, Gao J S, Zhou F. Microstructure and wear characteristics of cobalt-based alloy deposited by plasma transferred arc weld surfacing. Surf Coat Technol194(2-3): 238–243 (2005)
Liu Y F, Han J M, Li R H, Li W J, Xu X Y, Wang J H, Yang S Z. Microstructure and dry-sliding wear resistance of PTA clad (Cr, Fe)7C3/γ-Fe ceramal composite coating. Appl Surf Sci252(20): 7539–7544 (2006)
Ozel S, Kurt B, Somunkiran I, Orhan N. Microstructural characteristic of NiTi coating on stainless steel by plasma transferred arc process. Surf Coat Technol202(15): 3633–3637 (2008)
Fernandes F, Lopes B, Cavaleiro A, Ramalho A, Loureiro A. Effect of arc current on microstructure and wear characteristics of a Ni-based coating deposited by PTA on gray cast iron. Surf Coat Technol205(16): 4094–4106 (2011)
Veinthal R, Sergejev F, Zikin A, Tarbe R, Hornung J. Abrasive impact wear and surface fatigue wear behaviour of Fe-Cr-C PTA overlays. Wear301(1-2): 102–108 (2013)
Hornung J, Zikin A, Pichelbauer K, Kalin M, Kirchgaßner M. Influence of cooling speed on the microstructure and wear behaviour of hypereutectic Fe-Cr-C hardfacings. Mater Sci Eng: A576: 243–251 (2013)
Gur A K, Ozay C, Orhan A, Buytoz S, Caligulu U, Yigitturk N. Wear properties of Fe-Cr-C and B4C powder coating on AISI 316 stainless steel analyzed by the Taguchi method. Mater Test56(5): 393–398 (2014)
Deng X K, Zhang G J, Wang T, Ren S, Bai Z L, Cao Q. Investigations on microstructure and wear resistance of Fe-Mo alloy coating fabricated by plasma transferred arc cladding. Surf Coat Technol350: 480–487 (2018)
Huang B P, Chen J C, Li Y. Artificial-neural-networksbased surface roughness Pokayoke system for end-milling operations. Neurocomputing71(4-6): 544–549 (2008)
Zhang N, Shetty D. An effective LS-SVM-based approach for surface roughness prediction in machined surfaces. Neurocomputing198: 35–39 (2016)
Khanlou H M, Ang B C, Barzani M M, Silakhori M, Talebian S. Prediction and characterization of surface roughness using sandblasting and acid etching process on new non-toxic titanium biomaterial: Adaptive-network-based fuzzy inference System. Neural Comput Appl26(7): 1751–1761 (2015)
Pal S K, Chakraborty D. Surface roughness prediction in turning using artificial neural network. Neural Comput Appl14(4): 319–324 (2005)
Yu J B. Online tool wear prediction in drilling operations using selective artificial neural network ensemble model. Neural Comput Appl20(4): 473–485 (2011)
Unune D R, Barzani M M, Mohite S S, Mali H S. Fuzzy logic-based model for predicting material removal rate and average surface roughness of machined Nimonic 80A using abrasive-mixed electro-discharge diamond surface grinding. Neural Comput Appl29(9): 647–662 (2018)
Çetinel H, Öztürk H, Çelik E, Karlık B. Artificial neural network-based prediction technique for wear loss quantities in Mo coatings. Wear261(10): 1064–1068 (2006)
Mojena M A R, Roca A S, Zamora R S, Orozco M S, Fals H C, Lima C R C. Neural network analysis for erosive wear of hard coatings deposited by thermal spray: Influence of microstructure and mechanical properties. Wear376-377: 557–565 (2017)
Altay O, Gurgenc T, Ulas M, Özel C. Prediction of wear loss quantities of ferro-alloy coating using different machine learning algorithms. Friction, in press, DOI 10.1007/s40544-018-0249-z.
Gürgenç T, Özel C. Effect of heat input on microstructure, friction and wear properties of Fe-Cr-BC coating on AISI 1020 surface coated by PTA method. Fırat Univ Turkish J Sci Technol12(2): 43–52 (2017)
Teker T, Karataş S, Yilmaz S O. Microstructure and wear properties of FeCrC, FeW and feti modified Iron based alloy coating deposited by PTA process on AISI 430 steel. Arch Metall Mater59(3): 925–933 (2014)
Yüksel N, Şahin S. Wear behavior-hardness-microstructure relation of Fe-Cr-C and Fe-Cr-C-B based hardfacing alloys. Mater Des58: 491–498 (2014)
Özel C, Gürgenç T. Effect of heat input on microstructure, wear and friction behavior of (wt.-%) 50FeCrC-20FeW- 30FeB coating on AISI 1020 produced by using PTA welding. PLoS One13(1): e0190243 (2018)
Esfe M H, Ahangar M R H, Rejvani M, Toghraie D, Hajmohammad M H. Designing an artificial neural network to predict dynamic viscosity of aqueous nanofluid of TiO2 using experimental data. Int Commun Heat Mass Transfer75: 192–196 (2016)
Esfe M H, Wongwises S, Naderi A, Asadi A, Safaei M R, Rostamian H, Dahari M, Karimipour A. Thermal conductivity of Cu/TiO2-water/EG hybrid nanofluid: Experimental data and modeling using artificial neural network and correlation. Int Commun Heat Mass Transfer66: 100–104 (2015)
Açikgenç M, Ulaş M, Alyamaç K E. Using an artificial neural network to predict mix compositions of steel fiberreinforced concrete. Arab J Sci Eng40(2): 407–419 (2015)
Mukherjee A, Biswas S N. Artificial neural networks in prediction of mechanical behavior of concrete at high temperature. Nuclear Eng Des178(1): 1–11 (1997)
Yu X H, Ye C, Xiang L B. Application of artificial neural network in the diagnostic system of osteoporosis. Neurocomputing214: 376–381 (2016)
Simpson P K. Artificial Neural Systems: Foundations, Paradigms, Applications, and Implementations. New York (USA): Pergamon, 1990.
Momeni E, Armaghani D J, Hajihassani M, Amin M F M. Prediction of uniaxial compressive strength of rock samples using hybrid particle swarm optimization-based artificial neural networks. Measurement60: 50–63 (2015)
Dreyfus G. Neural Networks: Methodology and Applications. Berlin (Germany): Springer Science & Business Media, 2005.
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: Theory and applications. Neurocomputing70(1-3): 489–501 (2006)
Bilhan O, Emiroglu M E, Miller C J, Ulas M. The evaluation of the effect of nappe breakers on the discharge capacity of trapezoidal labyrinth weirs by ELM and SVR approaches. Flow Meas Instrum64: 71–82 (2018)
Huang W M, Li N, Lin Z P, Huang G B, Zong W W, Zhou J Y, Duan Y P. Liver tumor detection and segmentation using kernel-based extreme learning machine. In Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan, 2013: 3662–3665.
Yang Z, Ce L, Lian L. Electricity price forecasting by a hybrid model, combining wavelet transform, ARMA and kernel-based extreme learning machine methods. Appl Energy190: 291–305 (2017)
Altay O, Ulas M. The use of kernel-based extreme learning machine and well-known classification algorithms for fall detection. In Advances in Computer Communication and Computational Sciences. Bhatia S K, Tiwari S, Mishra K K, Trivedi M C, Eds. Singapore: Springer, 2019: 147–155.
Wang X Z. International journal of machine learning and cybernetics. Int J Mach Learn Cybern1(1-4):1–2 (2010).
Huang G B, Zhou H M, Ding X J, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst, Man, Cybern, Part B (Cybern)42(2): 513–529 (2012)
Frénay B, Verleysen M. Using SVMs with randomised feature spaces: An extreme learning approach. In Proceedings of the 18th ESANN, Bruges, Belgium: 2010.
Frénay B, Verleysen M. Parameter-insensitive kernel in extreme learning for non-linear support vector regression. Neurocomputing74(16): 2526–2531 (2011)
Huang G B, Wang D H, Lan Y. Extreme learning machines: A survey. Int J Mach Learn Cybern2(2): 107–122 (2011)
Zong W W, Huang G B, Chen Y Q. Weighted extreme learning machine for imbalance learning. Neurocomputing101: 229–242 (2013)
Deng W Y, Zheng Q H, Chen L. Regularized extreme learning machine. In Proceedings of 2009 IEEE Symposium on Computational Intelligence and Data Mining, Nashville, USA, 2009: 389–395.
Altay O, Ulas M. Location determination by processing signal strength of Wi-Fi routers in the indoor environment with linear discriminant classifier. In Proceedings of the 6th International Symposium on Digital Forensic and Security (ISDFS), Antalya, Turkey, 2018: 1–4.
Hyndman R J, Koehler A B. Another look at measures of forecast accuracy. Int J Forecast22(4): 679–688 (2006)
Author information
Authors and Affiliations
Corresponding author
Additional information
Mustafa ULAS. He is an assistant professor in Department of the Software Engineering, Firat University, Turkey. He received his B.S. degree in 2003 and the Ph.D. degree in Electric and Electronics Engineering Department in Firat University, Turkey, 2011. From 2004 to 2012, he worked as a lecturer and a software developer in the Department of Informatics. He was vice president of Computer Center and Department of Informatics from 2008 to 2012, Turkey. He worked in the University of Michigan, USA, as a visitor researcher in 2013. He has studied on data mining, machine learning algorithms, big data, and augmented reality.
Osman ALTAY. He received his B.S. degree in Department of Electronic Computer Education of Selcuk University, Turkey, in 2011. Currently, he is continuing his Ph.D. in software engineering at Firat University, Turkey. He is a research assistant at the Department of Software Engineering, Manisa Celal Bayar University, Turkey. His research interests include data mining, bioinformatics, machine learning, and data science.
Turan GURGENC. He received his Ph.D. degree in mechanical engineering from Firat University, Turkey, in 2017. He is a research assistant in Automotive Engineering Department, Firat University, Turkey. His research interests include surface coating, wear analysis, sintering, manufacturing, and computational intelligence.
Cihan ÖZEL. He received his Ph.D. degree in mechanical engineering from Firat University, Turkey, in 2000. He is currently an associate professor in Mechanical Engineering Department, Firat University, Turkey. His research interests cover CNC machining, surface coating, wear, and manufacturing.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Ulas, M., Altay, O., Gurgenc, T. et al. A new approach for prediction of the wear loss of PTA surface coatings using artificial neural network and basic, kernel-based, and weighted extreme learning machine. Friction 8, 1102–1116 (2020). https://doi.org/10.1007/s40544-017-0340-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40544-017-0340-0