SHAP-based interpretation of an XGBoost model in the prediction of grindability of coals and their blends

References

• Ananda Babu, K., A. Lawrence, and P. Sivashanmugam. 2018. Grindability studies on blended coals of high-ash Indian coals with low-ash imported coals. International Journal of Coal Preparation and Utilization 38 (8):433–42. doi:10.1080/19392699.2017.1281254.
   Web of Science ®Google Scholar
• Bagherieh, A. H., J. C. Hower, A. R. Bagherieh, and E. Jorjani. 2008. Studies of the relationship between petrography and grindability for Kentucky coals using artificial neural network. International Journal of Coal Geology 73 (2):130–38. doi:10.1016/j.coal.2007.04.002.
   Web of Science ®Google Scholar
• Carpenter, A. M. 1995. Coal blending for power stations. IEACR-81. IEA Coal Research, London, United Kingdom.
   Google Scholar
• Chelgani, S. C., J. C. Hower, E. Jorjani, S. Mesroghli, and A. H. Bagherieh. 2008. Prediction of coal grindability based on petrography, proximate and ultimate analysis using multiple regression and artificial neural network models. Fuel Processing Technology 89 (1):13–20. doi:10.1016/j.fuproc.2007.06.004.
   Web of Science ®Google Scholar
• Chen, T., and C. Guestrin. 2016. Xgboost: A scalable tree boosting system. In KDD ‘16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–94. New York, United States: Association for Computing Machinery. doi: 10.1145/2939672.2939785.
   Google Scholar
• Conroy, A. 1991. Grinding behaviour of hard coals. Combustion News; (Australia) November: 1–4.
   Google Scholar
• Conroy, A. 1994. Impact of coal quality on grinding characteristics. Combustion News; (Australia) August: 1–3.
   Google Scholar
• Dindarloo, S., J. C. Hower, A. Bagherieh, and A. S. Trimble. 2016. Fundamental evaluation of petrographic effects on coal grindability by seasonal autoregressive integrated moving average (SARIMA). International Journal of Mineral Processing 154:94–99. doi:10.1016/j.minpro.2016.07.005.
   Web of Science ®Google Scholar
• Dube, R., C. Gillum, K. Toupin, and J. Erickson. 2000. Unique boiler design flexibility for a wide range of coal properties for cgesj san jose guatemala project. Presented at Power-Gen 2000 International, Orlando, Florida, Nov. 14–16.
   Google Scholar
• Friedman, J. H. 2001. Greedy function approximation: A gradient boosting machine. The Annals of Statistics 29 (5):1189–232. doi:10.1214/aos/1013203451.
   Web of Science ®Google Scholar
• Hower, J. C. 1988. Additivity of Hardgrove grindability: A case study. Journal of Coal Quality 7:68.
   Google Scholar
• Hower, J. C. 1998. Interrelationship of coal grinding properties and coal petrology. Mining, Metallurgy & Exploration 15 (3):1–16. doi:10.1007/BF03403218.
   Google Scholar
• Hower, J. C. 2006. Discussion: Li et al., Prediction of grindability with multivariable regression and neural network in Chinese coal. Fuel 85. doi:10.1016/j.fuel.2005.11.011.
   Web of Science ®Google Scholar
• Hower, J. C., and C. F. Eble. 1996. Coal quality and coal utilization. Energy Miner. Div. Hourglass 30 (7):1–8.
   Google Scholar
• Idris, A., Z. Man, A. Bustam, N. E. Rabat, F. Uddin, and H. Abdul Mannan. 2019. Grindability and abrasive behavior of coal blends: Analysis and prediction. International Journal of Coal Preparation and Utilization 1–27. doi:10.1080/19392699.2019.1694009.
   Web of Science ®Google Scholar
• Jorjani, E., J. C. Hower, S. C. Chelgani, M. A. Shirazi, and S. Mesroghli. 2008. Studies of relationship between petrography and elemental analysis with grindability for Kentucky coals. Fuel 87 (6):707–13. doi:10.1016/j.fuel.2007.05.044.
   Web of Science ®Google Scholar
• Krevelen, D. W., Van, and J. Schuyer. 1957. Coal science: Aspects of coal constitution. Elsevier. Amsterdam, Netherlands.
   Google Scholar
• Li, P., X. Youhui, Y. Dunxi, and S. Xuexin. 2005. Prediction of grindability with multivariable regression and neural network in Chinese coal. Fuel 84 (18):2384–88. doi:10.1016/j.fuel.2005.04.016.
   Web of Science ®Google Scholar
• Lundberg, S., and S. I. Lee. 2017. A unified approach to interpreting model predictions, Vol. arXipreprint arXi, 1705.07874. Conference: NIPS. Long Beach Convention and Entertainment Center, Long Beach, California, United States.
   Google Scholar
• Marsland, S. 2015. Machine learning: An algorithmic perspective. 2nd ed. Boca Raton, USA: CRC press. Taylor & Francis Inc.
   Google Scholar
• Matin, S. S., J. C. Hower, L. Farahzadi, and S. C. Chelgani. 2016. Explaining relationships among various coal analyses with coal grindability index by random forest. International Journal of Mineral Processing 155:140–46. doi:10.1016/j.minpro.2016.08.015.
   Web of Science ®Google Scholar
• Mielecki, T. 1971. Wiadomości o badaniu i własnościach węgla [studies on coal examination and properties]. Katowice, Poland: Silesia Publishing House.
   Google Scholar
• Miroshnichenko, D. V., N. A. Desna, V. V. Koval, and S. V. Fatenko. 2019. Hardgrove grindability of coal. Part 1. Correlations with composition, structure, and properties. Coke and Chemistry 62 (1):1–4. doi:10.3103/S1068364X19010058.
   Web of Science ®Google Scholar
• Miroshnichenko, V. V., S. V. Koval, Fatenko, Y. V. Nikolaichuk, and S. V. Fatenko. 2020. Crushing properties of coal 2. Binary coal blends. Coke and Chemistry 63 (11):513–18. doi:10.3103/S1068364X20110046.
   Web of Science ®Google Scholar
• Mitchell, G. D. 2005. Coal and organic petrology laboratories. The Pennsylvania State University, Coal Utilization in the Steel Industry. Pennsylvania, United States.
   Google Scholar
• Molnar, C. 2020. Interpretable machine learning. Lulu. com. https://christophm.github.io/interpretable-ml-book/
   Google Scholar
• Natekin, A., and A. Knoll. 2013. Gradient boosting machines, a tutorial. Frontiers in Neurorobotics 7:21. doi:10.3389/fnbot.2013.00021.
   PubMed Web of Science ®Google Scholar
• Özbayoğlu, G. A., M. Özbayoğlu, and M. E. Özbayoğlu. 2008. Estimation of Hardgrove grindability index of Turkish coals by neural networks. International Journal of Mineral Processing 85 (4):93–100. doi:10.1016/j.minpro.2007.08.003.
   Google Scholar
• Rejdak, M., and R. Wasielewski. 2015. Mechanical compaction of coking coals for carbonization in stamp-charging coke oven batteries. Physicochemical Problems of Mineral Processing 51 (1):151–61. doi:10.5277/ppmp150114.
   Web of Science ®Google Scholar
• Rejdak, M., T. Micorek, and J. C. Hower. 2018. Influence of selected factors of polish coking coals on the Hardgrove Grindability Index (HGI). International Journal of Coal Preparation and Utilization 1–14. doi:10.1080/19392699.2018.1526790.
   Google Scholar
• Ribeiro, M. T., S. Singh, and C. Guestrin. 2016. “ Why should i trust you?” Explaining the predictions of any classifier. In KDD ‘16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–44. New York, United States: Association for Computing Machinery.
   Google Scholar
• Róg, L. 2007. Czynniki wpływające na podatność przemiałową węgli kamiennych [Factors influencing the grindability of hard coals]. Prace Naukowe GIG, Górnictwo I Srodowisko 3:39–53.
   Google Scholar
• Rubiera, F., A. Arenillas, E. Fuente, N. Miles, and J. J. Pis. 1999. Effect of the grinding behaviour of coal blends on coal utilisation for combustion. Powder Technology 105 (1–3):351–56. doi:10.1016/S0032-5910(99)00158-8.
   Web of Science ®Google Scholar
• Sengupta, A. N. 2002. An assessment of grindability index of coal. Fuel Processing Technology 76 (1):1–10. doi:10.1016/S0378-3820(01)00236-3.
   Web of Science ®Google Scholar
• Shapley, L. S. 1953. A value for n-person games. Contributions to the Theory of Games 2 (28):307–17.
   Google Scholar
• Speight, J. 2015. Handbook of coal analysis. 2nd ed. Hoboken, New Jersey: John Wiley & Sons.
   Google Scholar
• Tichánek, F. 2008. Contribution to determination of coal grindability using hardgrove method. GeoScience Engineering LIV:27–32.
   Google Scholar
• Tillman, D., D. Duong, and N. S. Harding. 2012. Solid fuel blending: Principles, practices, and problems. 1st ed. Waltham, Massachusetts: Butterworth-Heinemann/Elsevier.
   Google Scholar
• Tora, B., P. Fecko, A. Nowak, and Z. Tajchman. 2010. Badanie zależności podatności na mielenie od wybranych parametrów węgla kamiennego [Investigation on dependence of grindability on chosen parameters of hard coal]. Górnictwo I Geoinzynieria 34:285–92.
   Google Scholar
• Trimble, A. S., and J. C. Hower. 2003. Studies of the relationship between coal petrology and grinding properties. International Journal of Coal Geology 54 (3–4):253–60. doi:10.1016/S0166-5162(03)00039-9.
   Web of Science ®Google Scholar
• Ural, S., and M. Akyıldız. 2004. Studies of the relationship between mineral matter and grinding properties for low-rank coals. International Journal of Coal Geology 60 (1):81–84. doi:10.1016/j.coal.2004.07.001.
   Web of Science ®Google Scholar
• Vuthaluru, H. B., R. J. Brooke, D. K. Zhang, and H. M. Yan. 2003. Effects of moisture and coal blending on hardgrove grindability index of Western Australian coal. Fuel Processing Technology 81 (1):67–76. doi:10.1016/S0378-3820(03)00044-4.
   Web of Science ®Google Scholar
• Wang, C. A., Y. Liu, X. Zhang, and D. Che. 2011. A study on coal properties and combustion characteristics of blended coals in northwestern China. Energy & Fuels 25 (8):3634–45. doi:10.1021/ef200686d.
   Web of Science ®Google Scholar
• Williams, O., C. Eastwick, S. Kingman, D. Giddings, S. Lormor, and E. Lester. 2015. Investigation into the applicability of Bond Work Index (BWI) and Hardgrove Grindability Index (HGI) tests for several biomasses compared to Colombian La Loma coal. Fuel 158:379–87. doi:10.1016/j.fuel.2015.05.027.
   Web of Science ®Google Scholar