Machine learning frameworks to accurately predict coke reactivity index
Precisely forecasting coke reactivity index (CRI) plays a critical role in the metallurgical industry, as it enables optimization of coke quality, leading to cost-effective production and efficient resource utilization. In this research, several machine learning predictive models based on extra tree...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-05-01
|
| Series: | Energy Exploration & Exploitation |
| Online Access: | https://doi.org/10.1177/01445987251318353 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849691786126032896 |
|---|---|
| author | Ayat Hussein Adhab Morug Salih Mahdi Krunal Vaghela Anupam Yadav Jayaprakash B Mayank Kundlas Ankur Srivastava Jayant Jagtap Aseel Salah Mansoor Usama Kadem Radi Nasr Saadoun Abd Samim Sherzod |
| author_facet | Ayat Hussein Adhab Morug Salih Mahdi Krunal Vaghela Anupam Yadav Jayaprakash B Mayank Kundlas Ankur Srivastava Jayant Jagtap Aseel Salah Mansoor Usama Kadem Radi Nasr Saadoun Abd Samim Sherzod |
| author_sort | Ayat Hussein Adhab |
| collection | DOAJ |
| description | Precisely forecasting coke reactivity index (CRI) plays a critical role in the metallurgical industry, as it enables optimization of coke quality, leading to cost-effective production and efficient resource utilization. In this research, several machine learning predictive models based on extra trees, decision tree, support vector machine, random forest, multilayer perceptron artificial neural network, K-nearest neighbors, convolutional neural network, ensemble learning, and adaptive boosting using a dataset gathered from a coke plant are developed to predict CRI. To minimize overfitting in each algorithm, K-fold cross-validation methodology is employed during the training phase. The efficacy of each algorithm is visually represented through graphical methods and quantitatively evaluated using performance metrics. The findings indicate that maximum fluidity and mean maximum reflectance (MMR) exhibit a direct correlation with CRI while being indirectly relevant to moisture content, ash content, sulfur content, basicity index, plastic layer thickness, and MMR. Among the various predictive models evaluated, the random forest model emerged as the most accurate tool, according to the performance metrics of R -squared, mean square error, and average absolute relative error (%), with numerical values of 0.958, 3.718, and 2.545%, respectively, for the total datapoints. The developed tool can be easily used to accurately estimate CRI without needing experimental or field data reliably. |
| format | Article |
| id | doaj-art-e4759fefa78948218232bb95a181cfdc |
| institution | DOAJ |
| issn | 0144-5987 2048-4054 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Energy Exploration & Exploitation |
| spelling | doaj-art-e4759fefa78948218232bb95a181cfdc2025-08-20T03:20:55ZengSAGE PublishingEnergy Exploration & Exploitation0144-59872048-40542025-05-014310.1177/01445987251318353Machine learning frameworks to accurately predict coke reactivity indexAyat Hussein Adhab0Morug Salih Mahdi1Krunal Vaghela2Anupam Yadav3Jayaprakash B4Mayank Kundlas5Ankur Srivastava6Jayant Jagtap7Aseel Salah Mansoor8Usama Kadem Radi9Nasr Saadoun Abd10Samim Sherzod11 Department of Pharmacy, , Karbala, Karbala, Iraq College of MLT, Ahl Al Bayt University, Karbala, Karbala, Iraq Marwadi University Research Center, Department of Computer Engineering, Faculty of Engineering & Technology, , Rajkot, Gujarat, India Department of Computer Engineering and Application, GLA University Mathura, India Department of Computer Science & IT, School of Sciences, JAIN (Deemed to be University), Bangalore, Karnataka, India Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, , Rajpura, Punjab, India Department of CSE, Chandigarh Engineering College, Chandigarh Group of Colleges-Jhanjeri, Mohali, Punjab, India Department of Computing Science and Artificial Intelligence, NIMS Institute of Engineering & Technology, NIMS University Rajasthan, Jaipur, Rajasthan, India Pharmacy College, Gilgamesh Ahliya University, Baghdad, Baghdad, Iraq Collage of Pharmacy, , Dhi Qar, Iraq Medical Technical College, , Baghdad, Baghdad, Iraq Faculty of Engineering, , Nangarhar, AfghanistanPrecisely forecasting coke reactivity index (CRI) plays a critical role in the metallurgical industry, as it enables optimization of coke quality, leading to cost-effective production and efficient resource utilization. In this research, several machine learning predictive models based on extra trees, decision tree, support vector machine, random forest, multilayer perceptron artificial neural network, K-nearest neighbors, convolutional neural network, ensemble learning, and adaptive boosting using a dataset gathered from a coke plant are developed to predict CRI. To minimize overfitting in each algorithm, K-fold cross-validation methodology is employed during the training phase. The efficacy of each algorithm is visually represented through graphical methods and quantitatively evaluated using performance metrics. The findings indicate that maximum fluidity and mean maximum reflectance (MMR) exhibit a direct correlation with CRI while being indirectly relevant to moisture content, ash content, sulfur content, basicity index, plastic layer thickness, and MMR. Among the various predictive models evaluated, the random forest model emerged as the most accurate tool, according to the performance metrics of R -squared, mean square error, and average absolute relative error (%), with numerical values of 0.958, 3.718, and 2.545%, respectively, for the total datapoints. The developed tool can be easily used to accurately estimate CRI without needing experimental or field data reliably.https://doi.org/10.1177/01445987251318353 |
| spellingShingle | Ayat Hussein Adhab Morug Salih Mahdi Krunal Vaghela Anupam Yadav Jayaprakash B Mayank Kundlas Ankur Srivastava Jayant Jagtap Aseel Salah Mansoor Usama Kadem Radi Nasr Saadoun Abd Samim Sherzod Machine learning frameworks to accurately predict coke reactivity index Energy Exploration & Exploitation |
| title | Machine learning frameworks to accurately predict coke reactivity index |
| title_full | Machine learning frameworks to accurately predict coke reactivity index |
| title_fullStr | Machine learning frameworks to accurately predict coke reactivity index |
| title_full_unstemmed | Machine learning frameworks to accurately predict coke reactivity index |
| title_short | Machine learning frameworks to accurately predict coke reactivity index |
| title_sort | machine learning frameworks to accurately predict coke reactivity index |
| url | https://doi.org/10.1177/01445987251318353 |
| work_keys_str_mv | AT ayathusseinadhab machinelearningframeworkstoaccuratelypredictcokereactivityindex AT morugsalihmahdi machinelearningframeworkstoaccuratelypredictcokereactivityindex AT krunalvaghela machinelearningframeworkstoaccuratelypredictcokereactivityindex AT anupamyadav machinelearningframeworkstoaccuratelypredictcokereactivityindex AT jayaprakashb machinelearningframeworkstoaccuratelypredictcokereactivityindex AT mayankkundlas machinelearningframeworkstoaccuratelypredictcokereactivityindex AT ankursrivastava machinelearningframeworkstoaccuratelypredictcokereactivityindex AT jayantjagtap machinelearningframeworkstoaccuratelypredictcokereactivityindex AT aseelsalahmansoor machinelearningframeworkstoaccuratelypredictcokereactivityindex AT usamakademradi machinelearningframeworkstoaccuratelypredictcokereactivityindex AT nasrsaadounabd machinelearningframeworkstoaccuratelypredictcokereactivityindex AT samimsherzod machinelearningframeworkstoaccuratelypredictcokereactivityindex |