Machine-learning-assisted prediction of coke strength after reaction for coke plants

Coke strength after reaction (CSR) is a critical parameter in metallurgical applications, and its accurate prediction is essential for optimizing coal blends and coking processes. This research develops a data-driven method to model CSR by eight input variables, including moisture content, volatile matter, ash percentage, sulfur content, maximum fluidity, plastic layer thickness, mean maximum reflectance (MMR), and the basicity index. A dataset comprising 630 coal samples with diverse properties was analyzed using advanced techniques such as Pearson correlation analysis, the Monte Carlo outlier detection technique in data integrity assessment, and machine-learning models with five-fold cross-validation. Multiple algorithms were implemented, including random forests, decision trees, adaptive boosting, convolutional neural networks, support vector regression, multilayer perceptron-artificial neural networks, and an ensemble learning approach, with hyperparameter optimization and evaluation metrics like mean squared error, R2, and mean and average absolute relative error. The random forest model decisively outperformed all other contenders, demonstrating its superior predictive power through consistently high R2 values and minimal error rates. Furthermore, Shapley additive explanations analysis revealed the influence of each input variable, with volatile matter having a predominantly negative effect on CSR, while features like MMR and moisture showed positive correlations. This systematic methodology underscores the importance of robust data assessment and machine-learning models in enhancing predictive accuracy for CSR.

• Publication year

  2025

• Venue

  Energy Exploration & Exploitation

• Publication date

  2025-08-28

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1177/01445987251365291
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Effect of Coal Tar Components and Thermal Polycondensation Conditions on the Formation of Mesophase Pitch

  2025cited by this paper
• Machine learning frameworks to accurately predict coke reactivity index

  2025cited by this paper
• The power of deep learning in simplifying feature selection for hepatocellular carcinoma: a review

  2024cited by this paper
• A systematic review and meta-analysis of machine learning, deep learning, and ensemble learning approaches in predicting EV charging behavior

  2024cited by this paper
• Sustainable Cokemaking Technology: Future Needs for Ironmaking

  2024cited by this paper
• A machine learning and CFD modeling hybrid approach for predicting real-time heat transfer during cokemaking processes

  2024cited by this paper
• Feature reduction for hepatocellular carcinoma prediction using machine learning algorithms

  2024cited by this paper
• The employment of domain adaptation strategy for improving the applicability of neural network-based coke quality prediction for smart cokemaking process

  2024influential reference
• DT-MNLR: a novel hybrid machine learning framework for precise coke strength and reactivity prediction

  2024cited by this paper
• Employing machine learning for enhanced abdominal fat prediction in cavitation post-treatment

  2024cited by this paper
• Optimal Gasoline Price Predictions: Leveraging the ANFIS Regression Model

  2024cited by this paper
• Vacuum pressure swing adsorption intensification by machine learning: Hydrogen production from coke oven gas

  2024cited by this paper
• Revolutionizing core muscle analysis in female sexual dysfunction based on machine learning

  2024cited by this paper
• A novel image expression-driven modeling strategy for coke quality prediction in the smart cokemaking process

  2024influential reference
• Deep regression analysis for enhanced thermal control in photovoltaic energy systems

  2024cited by this paper
• Dependence of CRI and CSR on the Dimensions of Oriented Molecular Domains and the Ash Composition of the Coke

  2023cited by this paper
• Optimizing epileptic seizure recognition performance with feature scaling and dropout layers

  2023cited by this paper
• Co-combustion performances of biomass pyrolysis semi-coke and rapeseed cake: PCA, 2D-COS and full range prediction of M-DAEM via machine learning

  2023cited by this paper
• An application on forecasting for stock market prices: hybrid of some metaheuristic algorithms with multivariate adaptive regression splines

  2023cited by this paper
• Machine learning-based estimation of nano-lubricants viscosity in different operating conditions

  2023cited by this paper
• Predictive Model Based on K-Nearest Neighbor Coupled with the Gray Wolf Optimizer Algorithm (KNN_GWO) for Estimating the Amount of Phenol Adsorption on Powdered Activated Carbon

  2023cited by this paper
• Human Activity Recognition Using an Ensemble Learning Algorithm with Smartphone Sensor Data

  2022cited by this paper
• Modeling subcritical multi-phase flow through surface chokes with new production parameters

  2022cited by this paper
• Thermodynamic Modeling of Saponin Adsorption Behavior on Sandstone Rocks: An Experimental Study

  2022cited by this paper
• Theoretical and Experimental Study of Fine Migration During Low-Salinity Water Flooding: Effect of Brine Composition on Interparticle Forces

  2022cited by this paper
• A Review of Ensemble Learning Algorithms Used in Remote Sensing Applications

  2022cited by this paper
• Rational construction of a fluorescent sensor for simultaneous detection and imaging of hypochlorous acid and peroxynitrite in living cells, tissues and inflammatory rat models.

  2022cited by this paper
• Gas-oil gravity drainage mechanism in fractured oil reservoirs: surrogate model development and sensitivity analysis

  2022cited by this paper
• Advanced Feature-Selection-Based Hybrid Ensemble Learning Algorithms for Network Intrusion Detection Systems

  2022cited by this paper
• Lung cancer prediction model using ensemble learning techniques and a systematic review analysis

  2022cited by this paper
• A comparative analysis of K-Nearest Neighbour, Genetic, Support Vector Machine, Decision Tree, and Long Short Term Memory algorithms in machine learning

  2022cited by this paper
• Thermodynamic analysis of supercritical Brayton cycles using CO2-based binary mixtures for solar power tower system application

  2022cited by this paper
• Co-pyrolytic interactions, kinetics and products of biomass pyrolysis coke and rapeseed cake: Machine learning, DAEM and 2D-COS analysis

  2022cited by this paper
• Optimization of High-Speed Channel for Signal Integrity With Deep Genetic Algorithm

  2022cited by this paper
• Design optimization of cement grouting material based on adaptive boosting algorithm and simplicial homology global optimization

  2022cited by this paper
• A Survey on ensemble learning under the era of deep learning

  2021cited by this paper
• Prediction of Gray-King coke type from radical concentration and basic properties of coal blends

  2021cited by this paper
• Modeling apparent viscosity of waxy crude oils doped with polymeric wax inhibitors

  2021cited by this paper
• Line Chart Understanding with Convolutional Neural Network

  2021cited by this paper
• Prediction of coke CSR using time series model in Coke Plant

  2021cited by this paper
• Stamp-Charged Coke-Making Technology—The Effect of Charge Density and the Addition of Semi-Soft Coals on the Structural, Textural and Quality Parameters of Coke

  2021cited by this paper
• Hybrid computing models to predict oil formation volume factor using multilayer perceptron algorithm

  2021cited by this paper
• Comparison of Random Forest and Gradient Boosting Machine Models for Predicting Demolition Waste Based on Small Datasets and Categorical Variables

  2021cited by this paper
• RBF neural network modeling approach using PCA based LM-GA optimization for coke furnace system

  2021cited by this paper
• Classification of ECG beats using optimized decision tree and adaptive boosted optimized decision tree

  2021cited by this paper
• Topic Extraction and Interactive Knowledge Graphs for Learning Resources

  2021cited by this paper
• Adaptive neuro-fuzzy algorithm applied to predict and control multi-phase flow rates through wellhead chokes

  2020cited by this paper
• Optimization of the Random Forest Algorithm

  2020cited by this paper
• A Monte Carlo-Based Outlier Diagnosis Method for Sensitivity Analysis

  2020cited by this paper
• Reliable Accuracy Estimates from k-Fold Cross Validation

  2020cited by this paper
• Life cycle assessment of sintering process for carbon footprint and cost reduction: A comparative study for coke and biomass-derived sintering process

  2020cited by this paper
• Mechanistic assessment of Seidlitzia Rosmarinus-derived surfactant for restraining shale hydration: A comprehensive experimental investigation

  2019cited by this paper
• Predicting asphaltene precipitation during titration of diluted crude oil with paraffin using artificial neural network (ANN)

  2019cited by this paper
• The linear random forest algorithm and its advantages in machine learning assisted logging regression modeling

  2019cited by this paper
• An MLP-ANN-based approach for assessing nitrate contamination

  2019cited by this paper
• Molecular dynamics simulation of aluminum inhibited leaching during ion-adsorbed type rare earth ore leaching process

  2019cited by this paper
• A new model for predicting asphaltene precipitation of diluted crude oil by implementing LSSVM-CSA algorithm

  2019cited by this paper
• Intelligent interpolation by Monte Carlo machine learning

  2018cited by this paper
• Multiple predicting K-fold cross-validation for model selection

  2018cited by this paper
• Extending MLP ANN hyper-parameters Optimization by using Genetic Algorithm

  2018cited by this paper
• Evaluation of Convolutional Neural Network Architectures for Chart Image Classification

  2018cited by this paper
• A review on deep convolutional neural networks

  2017cited by this paper
• Fast monostatic scattering analysis based on Bayesian compressive sensing

  2017cited by this paper
• Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review

  2017cited by this paper
• Random Forest.

  2017cited by this paper
• Evolving ANFIS model to estimate density of bitumen-tetradecane mixtures

  2017cited by this paper
• A new testing and evaluating method of cokes with greatly varied CRI and CSR

  2016influential reference
• Improvement on enhanced Monte-Carlo outlier detection method

  2016cited by this paper
• Outlier Detection by means of Monte Carlo Estimation including resistant Scale Estimation

  2015cited by this paper
• Novel time domain integral equation method hybridized with the macromodels of circuits

  2015cited by this paper
• A framework for making maintenance decisions for oil and gas drilling and production equipment

  2015cited by this paper
• Ash basicity and the coke characteristics CRI and CSR: A review

  2014cited by this paper
• Evaluation of MLP-ANN Training Algorithms for Modeling Soil Pore-Water Pressure Responses to Rainfall

  2013cited by this paper
• 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

  2012cited by this paper
• Diagnosing multiple faults in oil rig motor pumps using support vector machine classifier ensembles

  2011cited by this paper
• Near-infrared (NIR) spectroscopy for motor oil classification: From discriminant analysis to support vector machines

  2011cited by this paper
• Overview of use of decision tree algorithms in machine learning

  2011cited by this paper
• Fast and Sensitive LC-DAD-ESI/MS Method for Analysis of Saikosaponins c, a, and d from the Roots of Bupleurum Falcatum (Sandaochaihu)

  2011cited by this paper
• Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation

  2010cited by this paper
• Modifying CRI and CSR values of coke

  2010cited by this paper
• Coke Reactivity under Blast Furnace Conditions and in the CSR/CRI Test

  2009influential reference
• Forecasting PVT properties of crude oil systems based on support vector machines modeling scheme

  2009cited by this paper
• Outlier detection in near-infrared spectroscopic analysis by using Monte Carlo cross-validation

  2008cited by this paper
• Energy

  2007cited by this paper
• Fast Monte Carlo reliability evaluation using support vector machine

  2002cited by this paper

• No citing papers are available for this paper.