A Comparative Analysis of Machine Learning Techniques for Predicting the Wear Rate of Ceramic Coated Steel

IF 3.4 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

IEEE Access Pub Date : 2024-10-03 DOI:10.1109/ACCESS.2024.3473028

N. Radhika;M. Sabarinathan;S. Sivaraman

{"title":"A Comparative Analysis of Machine Learning Techniques for Predicting the Wear Rate of Ceramic Coated Steel","authors":"N. Radhika;M. Sabarinathan;S. Sivaraman","doi":"10.1109/ACCESS.2024.3473028","DOIUrl":null,"url":null,"abstract":"Ceramic coatings are necessary for steel as they offer resistance to corrosion, high-temperature degradation, and abrasion, thereby enhancing the wear characteristics of steel structures. Evaluating the wear rate of Ceramic-Coated (CC) steels is crucial for enhancing the reliability and longevity of steel components. Various factors such as microstructural features and operating conditions complicate the wear analysis of CC steel. To overcome this obstacle, the present study employs several Machine Learning (ML) models such as Elastic Net Regressor (ENR), Robust Regressor (RR), Extreme Gradient Boosting Regressors (XGBoost), and Bagging Regressor (BR), to predict the wear rate of CC steel. Pearson Correlation Coefficient (PCC) revealed that the hardness of the coating greatly affects the wear rate. Among various ML regressor models, the BR model exhibited the optimum performance with the R2 of 0.93 with ENR, RR, and XGBoost exhibiting lower R2 values of 0.79, 0.84, and 0.89 respectively. Eventually, the BR model is used to predict the wear rate of TiN and Al2O3-coated steel, and the experimental results of the same are compared. The comparison of results revealed an error percentage of ± 7.78% between the experimental and predicted wear rate.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"12 ","pages":"146949-146967"},"PeriodicalIF":3.4000,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10704673","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Access","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10704673/","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Ceramic coatings are necessary for steel as they offer resistance to corrosion, high-temperature degradation, and abrasion, thereby enhancing the wear characteristics of steel structures. Evaluating the wear rate of Ceramic-Coated (CC) steels is crucial for enhancing the reliability and longevity of steel components. Various factors such as microstructural features and operating conditions complicate the wear analysis of CC steel. To overcome this obstacle, the present study employs several Machine Learning (ML) models such as Elastic Net Regressor (ENR), Robust Regressor (RR), Extreme Gradient Boosting Regressors (XGBoost), and Bagging Regressor (BR), to predict the wear rate of CC steel. Pearson Correlation Coefficient (PCC) revealed that the hardness of the coating greatly affects the wear rate. Among various ML regressor models, the BR model exhibited the optimum performance with the R2 of 0.93 with ENR, RR, and XGBoost exhibiting lower R2 values of 0.79, 0.84, and 0.89 respectively. Eventually, the BR model is used to predict the wear rate of TiN and Al2O3-coated steel, and the experimental results of the same are compared. The comparison of results revealed an error percentage of ± 7.78% between the experimental and predicted wear rate.

查看原文本刊更多论文

预测陶瓷涂层钢磨损率的机器学习技术比较分析

陶瓷涂层对钢材来说是必要的，因为它们具有耐腐蚀、耐高温降解和耐磨损的性能，从而提高了钢结构的磨损特性。评估陶瓷涂层（CC）钢的磨损率对于提高钢部件的可靠性和使用寿命至关重要。微观结构特征和操作条件等各种因素使 CC 钢的磨损分析变得复杂。为了克服这一障碍，本研究采用了多种机器学习（ML）模型，如弹性网回归器（ENR）、鲁棒性回归器（RR）、极梯度提升回归器（XGBoost）和袋式回归器（BR），来预测 CC 钢的磨损率。皮尔逊相关系数（PCC）显示，涂层硬度对磨损率有很大影响。在各种 ML 回归模型中，BR 模型表现最佳，R2 为 0.93，ENR、RR 和 XGBoost 的 R2 值较低，分别为 0.79、0.84 和 0.89。最终，BR 模型被用于预测 TiN 和 Al2O3 涂层钢的磨损率，并与实验结果进行了比较。比较结果显示，实验和预测磨损率之间的误差为 ± 7.78%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Access COMPUTER SCIENCE, INFORMATION SYSTEMSENGIN-ENGINEERING, ELECTRICAL & ELECTRONIC

CiteScore

9.80

自引率

7.70%

发文量

6673

审稿时长

6 weeks

期刊介绍： IEEE Access® is a multidisciplinary, open access (OA), applications-oriented, all-electronic archival journal that continuously presents the results of original research or development across all of IEEE''s fields of interest. IEEE Access will publish articles that are of high interest to readers, original, technically correct, and clearly presented. Supported by author publication charges (APC), its hallmarks are a rapid peer review and publication process with open access to all readers. Unlike IEEE''s traditional Transactions or Journals, reviews are "binary", in that reviewers will either Accept or Reject an article in the form it is submitted in order to achieve rapid turnaround. Especially encouraged are submissions on: Multidisciplinary topics, or applications-oriented articles and negative results that do not fit within the scope of IEEE''s traditional journals. Practical articles discussing new experiments or measurement techniques, interesting solutions to engineering. Development of new or improved fabrication or manufacturing techniques. Reviews or survey articles of new or evolving fields oriented to assist others in understanding the new area.