The coke reactivity index (CRI) significantly impacts metallurgical coke quality, influencing blast furnace efficiency and environmental emissions. This study focusses on leveraging advanced machine learning algorithms to predict CRI based on key input features such as volatile matter, sulphur (%), ash (%), maximum fluidity (ddpm), plastic thickness (mm) and basicity index. A comprehensive dataset of 636 coal samples from diverse origins, measured according to ASTM standards, was analysed. Rigorous preprocessing, including outlier detection using the random forest algorithm, ensured data reliability. Predictive modeling employed random forest in combination with five metaheuristic optimisation algorithms, including particle swarm optimisation (PSO), genetic algorithm (GA) and grey wolf optimiser (GWO), with k-fold cross-validation to ensure robustness. Evaluation metrics such as R2, MSE and AARE% demonstrated RF-PSO's superiority, achieving R2 of 0.846 and the lowest AARE% during testing, coupled with a significant reduction in computational runtime. SHAP analysis revealed volatile matter as the most critical feature affecting CRI. These findings underline the potential of hybrid machine learning models to enhance predictive accuracy and operational efficiency in industrial coke production.
YuZZhaoJMarkovV,et al.Effects of hydrogen addition on ignition characteristics and engine performance of ammonia-hydrogen blended fuel: a kinetic analysis. Int J Hydrogen Energy2024; 87: 722–735.
2.
Khezerlooe-ye AghdamSMoslemizadehAMadaniM, et al.Mechanistic assessment of Seidlitzia Rosmarinus-derived surfactant for restraining shale hydration: a comprehensive experimental investigation. Chem Eng Res Des2019; 147: 570–578.
3.
Khezerloo-ye AghdamSKazemiAAhmadiM. Theoretical and experimental study of fine migration during low-salinity water flooding: effect of brine composition on interparticle forces. SPE Reservoir Eval Eng2023; 26: 228–243.
4.
ZhuBZhuYYangJ, et al.New potassium sodium niobate single crystal with thickness-independent high-performance for photoacoustic angiography of atherosclerotic lesion. Sci Rep2016; 6: 39679.
5.
GanatTKhezerloo-yeSAlrumahM, et al.Effect of metal oxide nanoparticles on the properties of nanocomposite gels for water shutoff applications: a review. Arab J Sci Eng2025.
6.
WuHLiAZhangH, et al.Microbial mechanisms for higher hydrogen production in anaerobic digestion at constant temperature versus gradient heating. Microbiome2024; 12: 170.
7.
YaoYLuoYLiT, et al.Using the properties of soil to speed up the start-up process, enhance process stability, and improve the methane content and yield of solid-state anaerobic digestion of alkaline-pretreated poplar processing residues. Biotechnol Biofuels2015; 7: 160.
8.
GaoJWuYShenT. Experimental comparisons of hypothesis test and moving average based combustion phase controllers. ISA Trans2016; 65: 504–515.
9.
XieJWenMDingP, et al.One-dimensional consolidation analysis of layered unsaturated soils: an improved model integrating interfacial flow and air contact resistance effects. Comput Geotech2024; 176: 106791.
10.
NiuXMaNBuZ, et al.Thermodynamic analysis of supercritical Brayton cycles using CO2-based binary mixtures for solar power tower system application. Energy2022; 254: 124286.
11.
YaoYZhouJAnL, et al.Role of soil in improving process performance and methane yield of anaerobic digestion with corn straw as substrate. Energy2018; 151: 998–1006.
12.
ZhuB-PTangZZhaoL-H, et al.Synthesis of Mg[Ti2]O4 by spark plasma sintering. Mater Lett2007; 61: 578–581.
13.
NorthLBlackmoreKNesbittK,et al.Models of coke quality prediction and the relationships to input variables: a review. Fuel2018; 219: 446–466.
14.
QiuLDengYFWangF, et al.A review on biochar-mediated anaerobic digestion with enhanced methane recovery. Renewable Sustainable Energy Rev2019; 115: 109373.
15.
XuJFanLChenC, et al.Study on fuel injection stability improvement in marine low-speed dual-fuel engines. Appl Therm Eng2024; 253: 123729.
16.
YaoYBergeronADDavaritouchaeeM. Methane recovery from anaerobic digestion of urea-pretreated wheat straw. Renewable Energy2018; 115: 139–148.
17.
AgarwalS, et al.Prediction of coke CSR using time series model in Coke Plant. Opsearch2021: 1–22.
18.
HouXQiuLLuoS, et al.Chemical constituents and antimicrobial activity of wood vinegars at different pyrolysis temperature ranges obtained from Eucommia ulmoides Olivers branches. RSC Adv2018; 8: 40941–40949.
19.
ZhuB, et al.(100)-Textured KNN-based thick film with enhanced piezoelectric property for intravascular ultrasound imaging. Appl Phys Lett2015; 106.
20.
BaoWLiuHWangF, et al.Keyhole critical failure criteria and variation rule under different thicknesses and multiple materials in K-TIG welding. J Manuf Process2024; 126: 48–59.
21.
GaoJWuYShenT. On-line statistical combustion phase optimization and control of SI gasoline engines. Appl Therm Eng2017; 112: 1396–1407.
22.
ZhuBWangZZhangY, et al.Low temperature fabrication of the giant dielectric material CaCu3Ti4O12 by oxalate coprecipitation method. Mater Chem Phys2009; 113: 746–748.
23.
ZhangMXuY-CWangJ-F, et al.Cold-sprayed Cu matrix composite coatings with core-shell structured Co@ WC reinforcements on Q235 steel. Surf Interf2025; 56: 105577.
24.
ZhiquanY, et al.Prediction model on maximum potential pollution range of debris flows generated in tailings dam break. Electron J Geotech Eng2015; 20: 4363–4369.
25.
FengM, et al.Hyperrectangle embedding for debiased 3D scene graph prediction from RGB sequences. IEEE Trans Pattern Anal Mach Intell2025: 1–16.
26.
YuHWangHLianZ. An assessment of seal ability of tubing threaded connections: A hybrid empirical-numerical method. J Energy Res Technol2022; 145.
27.
FengCFengZMaoR, et al.Prediction of vitrinite reflectance of shale oil reservoirs using nuclear magnetic resonance and conventional log data. Fuel2023; 339: 127422.
28.
SuiXChenQBaiL. Detection algorithm of targets for infrared search system based on area infrared focal plane array under complicated background. Optik (Stuttg)2012; 123: 235–239.
29.
JiRZhaoQZhaoL, et al.Study on high wear resistance surface texture of electrical discharge machining based on a new water-in-oil working fluid. Tribol Int2023; 180: 108218.
30.
GaoJLiuZ. Adaptive estimator for the friction characteristics of the clutch in automatic transmission. In: Proceedings of the 29th Chinese Control Conference, 2010.
31.
ChelganiSCHowerJCHartB. Estimation of free-swelling index based on coal analysis using multivariable regression and artificial neural network. Fuel Process Technol2011; 92: 349–355.
32.
HeYZioEYangZ, et al.A systematic resilience assessment framework for multi-state systems based on physics-informed neural network. Reliab Eng Syst Saf2025; 257: 110866.
33.
ZhangDLiBWeiY, et al.Investigation of injection and flow characteristics in an electronic injector featuring a novel control valve. Energy Convers Manage2025; 327: 119609.
34.
SoltanianMRBemaniAMoeiniF, et al.Data driven simulations for accurately predicting thermodynamic properties of H2 during geological storage. Fuel2024; 362: 130768.
35.
AbdiJHadavimoghaddamFHadipoorM,et al.Modeling of CO2 adsorption capacity by porous metal organic frameworks using advanced decision tree-based models. Sci Rep2021; 11: 24468.
36.
RazaviRBemaniABaghbanA,et al.Modeling of CO2 absorption capabilities of amino acid solutions using a computational scheme. Environ Prog Sustain Energy2020; 39: e13430.
37.
ChenHJBaiJF. A coke quality prediction model based on support vector machine. Adv Mater Res2013; 690–693: 3097–3101.
38.
NorthLBlackmoreKNesbittK,et al.Methods of coke quality prediction: a review. Fuel2018; 219: 426–445.
39.
KangJZhaoLLiW,et al.Artificial neural network model of co-gasification of petroleum coke with coal or biomass in bubbling fluidized bed. Renewable Energy2022; 194: 359–365.
40.
SidorovOYAristovaNA. Simulation of coke quality indicators using artificial neural network. KnE Eng2020: 21–28.
41.
ZhangJWangQGuoW,et al.A support vector machine based prediction on sensitivity to coal ash blast for different degrees of deterioration. J Sens2022; 2022: 7604338.
42.
AstmD, et al.American society for testing and materials (ASTM). American Association of State Highway and Transportation Officials-AASHTO Standards, United States, 1950.
43.
ZhaoLC, et al.Preparation of Cyclocarya paliurus sugar-free jelly. Sci Technol Food Ind2020; 41: 234–239 and 250.
44.
ZhuBHanJShiJ, et al.Lift-off PMN–PT thick film for high-frequency ultrasonic biomicroscopy. J Am Ceram Soc2010; 93: 2929–2931.
45.
ZhaoL-CTangMZhangQ-H, et al.Fabrication of a porous metal-organic framework with polar channels for 5-Fu delivery and inhibiting human osteosarcoma cells. J Chem2018; 2018: 1523154.
46.
MohapatraNShreyaKChinmayA. Optimization of the random forest algorithm. Singapore: Springer Singapore, 2020.
47.
JinwuGZhiyuanL. Static output feedback control of the linear system with parameter uncertainties. In: 2010 8th World Congress on Intelligent Control and Automation, 2010.
48.
ZhuB, et al.KNN-based single crystal high frequency transducer for intravascular photoacoustic imaging. In: 2017 IEEE International Ultrasonics Symposium (IUS), 2017.
49.
ShamiTMEl-SalehAAAlswaittiM, et al.Particle swarm optimization: a comprehensive survey. Ieee Access2022; 10: 10031–10061.
50.
GadAG. Particle swarm optimization algorithm and its applications: a systematic review. Arch Comput Methods Eng2022; 29: 2531–2561.
51.
HousseinEHGadAGHussainK,et al.Major advances in particle swarm optimization: theory, analysis, and application. Swarm Evol Comput2021; 63: 100868.
LamboraAGuptaKChopraK. Genetic algorithm – a literature review. IEEE, 2019.
54.
MirjaliliSMirjaliliS. Genetic algorithm. In: Evolutionary algorithms and neural networks: theory and applications. Springer, 2019, pp.43–55.
55.
MathewTV. Genetic algorithm.Report submitted at IIT Bombay, 2012. 53.
56.
MirjaliliSMirjaliliSMLewisA. Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
57.
Al-TashiQ, et al.A review of grey wolf optimizer-based feature selection methods for classification. In: Evolutionary machine learning techniques: algorithms and applications. Springer, 2020, pp.273–286.
58.
MakhadmehSN, et al.Recent advances in grey wolf optimizer, its versions and applications. IEEE Access2023.
59.
MirjaliliSLewisA. The whale optimization algorithm. Adv Eng Softw2016; 95: 51–67.
60.
GharehchopoghFSGholizadehH. A comprehensive survey: whale optimization algorithm and its applications. Swarm Evol Comput2019; 48: 1–24.
GandomiAHYangX-SAlaviAH. Cuckoo search algorithm: a metaheuristic approach to solve structural optimization problems. Eng Comput2013; 29: 17–35.
67.
ValianEMohannaSTavakoliS. Improved cuckoo search algorithm for global optimization. Int J Commun Inf Technol2011; 1: 31–44.
68.
BemaniABaghbanAMosaviA. Estimating CO2-Brine diffusivity using hybrid models of ANFIS and evolutionary algorithms. Eng Appl Comput Fluid Mech2020; 14: 818–834.
69.
DaryasafarAShahbaziK. Prediction of CO2/water/quartz wettability behavior during CO2 storage in deep saline aquifers. Energy Sources Part A2023; 45: 9593–9601.
70.
DaryasafarAKeykhosraviAShahbaziK. Modeling CO2 wettability behavior at the interface of brine/CO2/mineral: application to CO2 geo-sequestration. J Cleaner Prod2019; 239: 118101.
71.
YangZQZhuHL. Study on the effect of carbon nanotubes on the microstructure and anti-carbonation properties of cement-based materials. J Funct Mater2023; 54: 8217–8227.
72.
WangDOu-YangJGuoW, et al.Novel fabrication of PZT thick films by an oil-bath based hydrothermal method. Ceram Int2017; 43: 9573–9576.
73.
YangZZhaoQGanJ, et al.Damage evolution characteristics of siliceous slate with varying initial water content during freeze-thaw cycles. Sci Total Environ2024; 950: 175200.
74.
ZhangH. Relationship of coke reactivity and critical coke properties. Metall Mater Trans B2019; 50: 204–209.
75.
KumarDSaxenaVKTiwariHP, et al.Variability in metallurgical coke reactivity Index (CRI) and coke strength after reaction (CSR): an experimental study. ACS Omega2022; 7: 1703–1711.
76.
PuszSBuszkoR. Reflectance parameters of cokes in relation to their reactivity index (CRI) and the strength after reaction (CSR), from coals of the upper silesian coal basin, Poland. Int J Coal Geol2012; 90–91: 43–49.
