Prediction model for spontaneous combustion temperature of coal based on PSO-XGBoost algorithm

• Published in: Scientific reports Vol. 15; no. 1; pp. 2752 - 16
• Main Authors: Zhuo, Hui, Li, Tongren, Lu, Wei, Zhang, Qingsong, Ji, Lingyun, Li, Jinliang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 22.01.2025; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166; 639/4077/4082/4059; Carbon dioxide; Coal; Coal spontaneous combustion; Combustion; Correlation coefficient; Emergency communications systems; Explosions; Feature selection; Humanities and Social Sciences; Methane; multidisciplinary; Particle swarm optimization; Performance assessment; Prediction models; PSO-XGBoost model; Science; Science (multidisciplinary); Tenfold cross-validation; Warning systems; PSO-XGBoost model; Feature selection; Particle swarm optimization; Tenfold cross-validation; Coal spontaneous combustion
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-025-87035-2

The construction of a predictive model that accurately reflects the spontaneous combustion temperature of coal in goaf is fundamental to monitoring and early warning systems for thermodynamic disasters, including coal spontaneous combustion and gas explosions. In this paper, on the basis of programming temperature experiment and industrial analysis, 381 data sets of 9 coal types are established, and feature selection was executed through the utilization of the Pearson correlation coefficient, ultimately identifying O 2 , CO, CO 2 , C 2 H 4 , C 3 H 8 , C 3 H 8 /CH 4 , C 2 H 4 /CH 4 , C 2 H 4 /C 3 H 8 , CO 2 /CO, and CO/O 2 as input indicators for the prediction model. The chosen indicator data were divided into training and testing sets in a 4:1 ratio, the Particle Swarm Optimization (PSO) methodology was applied to optimize the parameters of the XGBoost regressor, and a universal PSO-XGBoost prediction model is proposed. A tenfold cross-validation method was employed to assess performance of PSO-XGBoost, PSO-RF, PSO-SVR, XGBoost, RF, and SVR models separately, the results underscored the superior predictive accuracy, robustness, fault tolerance, and universality of the PSO-XGBoost model.