{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T14:02:07Z","timestamp":1779890527916,"version":"3.53.1"},"reference-count":0,"publisher":"Latvia University of Life Sciences and Technologies, Faculty of Engineering and Information Technologies","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,21]]},"abstract":"<jats:p>Drilling tools operating under extreme conditions face high temperatures, pressure, abrasive wear, and corrosion, leading to rapid wear and failure. Traditional hard alloys, such as those containing 85% tungsten carbide and 15% cobalt, often fail under such stresses, increasing equipment replacement costs and reducing drilling efficiency. To address this issue, machine learning methods were employed to develop new alloys with enhanced properties. Data on the composition and properties of various hard alloys, including elemental percentages, mechanical properties, and test results, were collected and preprocessed by removing outliers and missing values, normalizing, and encoding categorical variables. Gradient boosting (XGBoost) and convolutional neural networks were used to predict alloy properties, with XGBoost achieving a mean absolute error of 0.03 for hardness prediction and 95% accuracy for abrasion rate classification. Based on model predictions, two alloys were proposed: the first containing 88% tungsten carbide, 10% cobalt, and 2% titanium carbide, exhibiting a hardness of 88 HRA, tensile strength of 1700 MPa, and abrasion rate of 0.05 g\u00b7h-1  the second containing 90% tungsten carbide, 8% cobalt, and 2% titanium carbide, demonstrating superior properties with a hardness of 90 HRA, tensile strength of 1900 MPa, and abrasion rate of 0.03 g\u00b7h-1. These alloys outperform traditional compositions in wear resistance, strength, and durability. Implementing these alloys in drilling tools is expected to extend tool life by 15% under high\u2013temperature and high\u2013pressure conditions, reducing equipment replacement costs and improving the drilling efficiency. This study demonstrates that machine learning not only accelerates the development of new materials but also enhances their properties, offering new opportunities to improve efficiency and reduce costs in the oil and gas industry.   <\/jats:p>","DOI":"10.22616\/erdev.2025.24.tf110","type":"proceedings-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T11:42:07Z","timestamp":1748605327000},"source":"Crossref","is-referenced-by-count":3,"title":["Development and optimization of hard alloy compositions for rock destruction"],"prefix":"10.22616","volume":"24","author":[{"given":"Oleksandr","family":"Pashchenko","sequence":"first","affiliation":[{"name":"Dnipro University of Technology, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oleksandr","family":"Kamyshatskyi","sequence":"additional","affiliation":[{"name":"Ukrainian State University of Science and Technologies, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elmira","family":"Omirzakova","sequence":"additional","affiliation":[{"name":"Dnipro University of Technology, Ukraine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Ratova","sequence":"additional","affiliation":[{"name":"Satbayev University, Kazakhstan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9905","published-online":{"date-parts":[[2025,5,21]]},"event":{"name":"24th International Scientific Conference Engineering for Rural Development","acronym":"ERDev2025"},"container-title":["Engineering for Rural Development","24th International Scientific Conference Engineering for Rural Development Proceedings"],"original-title":[],"link":[{"URL":"https:\/\/www.iitf.lbtu.lv\/conference\/proceedings2025\/Papers\/TF110.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T12:06:00Z","timestamp":1748606760000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.iitf.lbtu.lv\/conference\/proceedings2025\/Papers\/TF110.pdf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":0,"URL":"https:\/\/doi.org\/10.22616\/erdev.2025.24.tf110","relation":{},"ISSN":["1691-5976"],"issn-type":[{"value":"1691-5976","type":"print"}],"subject":[],"published":{"date-parts":[[2025,5,21]]}}}