[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121381-en":3,"doc-seo-121381-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121381,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Predicting the hardgrove grindability index using interpretable decision tree-based machine learning models - Full Length Article","The Hardgrove grindability index (HGI) serves as a key measure of coal grindability, and reliable prediction supports improved production efficiency and economic outcomes in the coal industry. This study predicts HGI for 129 coal samples using six decision tree-based machine learning models, with hyperparameters tuned via Optuna and interpretability assessed through SHAP. The optimized NGBoost model achieves the best test performance (R2=0.9715), with MAE and RMSE of 1.1507 and 1.4735.","Fuel 384 (2025) 133953  \nContents lists available at ScienceDirect  \nFuel  \njournal [homepage: www.elsevier.com/locate/fuel](homepage: www.elsevier.com/locate/fuel)  \n| Full Length Article\u003Cbr>Predicting the hardgrove grindability index using interpretable decision tree-based machine learning models |  |  |  |\n| --- | --- | --- | --- |\n| Yuxin Chen a, Manoj Khandelwal b,*, Moshood Onifade b, Jian Zhou a, Abiodun Ismail Lawal c, Samson Oluwaseyi Badad,*, Bekir Genc e\u003Cbr>a School of Resources and Safety Engineering, Central South University, Changsha 410083, China\u003Cbr>b Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC 3350, Australia c Department of Mining Engineering, Federal University of Technology, Akure, Nigeria\u003Cbr>d School of Chemical and Metallurgy, Faculty of Engineering and the Built Environment, University of the Witwatersrand, Johannesburg, South Africa e School of Mining Engineering, Faculty of Engineering and the Built Environment, University of the Witwatersrand, Johannesburg, South Africa |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Hardgrove grindability index Machine learning Hyperparameter optimization Interpretation analysis NGBoost |  | The Hardgrove grindability index (HGI) is a crucial indicator for assessing the grindability of coal, and accurate prediction of HGI is essential for improving the production efficiency and economic benefits of the coal industry. This study employed six decision tree-based machine learning models to predict the HGI values of 129 coal samples, with hyperparameter optimization performed using Optuna, and model interpretability analyzed using SHapley Additive exPlanations (SHAP). The results showed that the optimized natural gradient boosting (NGBoost) model outperformed all other models, which achieved the highest performance on the test set with a coefficient of determination (R2) of 0.9715, a mean absolute error (MAE) of 1. 1507, and a root mean squared error (RMSE) of 1.4735. SHAP analysis further revealed that volatile matter (VM) contributed the most to the model’s predictions, while pyrite (FeS2) had the least contribution. This study provides an efficient machine learning approach for accurate HGI prediction, offering excellent predictive performance, interpretability, and application value. |  |\n\n1. Introduction  \nCoal still occupies an important position in the global energy structure and plays an irreplaceable role in global energy supply, economic development, and industrial production [24,27,73]. The utilization of coal requires grinding it into fine particles, and the grindability of coal is crucial in coal processing and usage as it directly affects the efficiency of pulverizers, the particle size distribution of coal powder, combustion characteristics, and equipment wear [30,68]. The grindability of coal refers to the ease with which it can be pulverized into fine powder in mechanical equipment, typically measured by the Hardgrove Grindability Index (HGI) [62,72,90]. The HGI is determined by conducting experiments using standardized Hardgrove equipment following a specified procedure [19,22]. A higher HGI value indicates that the coal is easier to pulverize, while a lower value indicates greater difficulty [75].  \nAlthough HGI testing equipment is relatively inexpensive and easy to  \nmaintain, the measurement procedure is quite cumbersome [15,58]. According to the American Society for Testing and Materials (ASTM) International standard procedure[5], each machine can only perform six tests per hour. Additionally, issues such as non-standardized equipment, variations in sample preparation, and the repeatability and reproducibility of the test make determining the HGI value a time-consuming and complex process, posing difficulties for large-scale and high-frequency measurements [70,79]. Therefore, researchers have analyzed large datasets to identify factors affecting the HGI and have empl","cbCaiqM07TDwEibs","https://ap.wps.com/l/cbCaiqM07TDwEibs","pdf",8835399,1,16,"English","en",105,"# Introduction\n## Problem background and importance of HGI\n## Challenges of conventional HGI testing\n## Motivation for machine learning prediction\n# Methods and Modeling\n## Decision tree-based machine learning models\n## Hyperparameter optimization with Optuna\n## Model interpretability with SHAP\n# Results and Discussion\n## Best-performing NGBoost model performance\n## Feature contributions and key drivers of HGI\n# Conclusion and Practical Value","[{\"question\":\"What did SHAP analysis reveal about factors influencing HGI predictions?\",\"answer\":\"SHAP indicated that volatile matter (VM) contributed the most to predictions, while pyrite (FeS2) had the least contribution.\"}]","Predicting the hardgrove grindability index using interpretable decision tree-based machine learning models - Full Length Article | PDF",1785735393,40,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"predicting-the-hardgrove-grindability-index-using-interpretable-decision-tree-based-machine-learning-models-full-length-article","",{"@graph":36,"@context":77},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-the-hardgrove-grindability-index-using-interpretable-decision-tree-based-machine-learning-models-full-length-article/121381/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What did SHAP analysis reveal about factors influencing HGI predictions?","Question",{"text":75,"@type":76},"SHAP indicated that volatile matter (VM) contributed the most to predictions, while pyrite (FeS2) had the least contribution.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":29,"slug":110},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]