基于贝叶斯优化支持向量回归的煤自燃温度预测模型

打开文本图片集

中图分类号：TD752 文献标志码：A  文章编号：1671−251X（2025）07−0036−09

Abstract：To address the issue that traditional coal spontaneous combustion temperature prediction models do notconsider multicollinearity between indicator gasesand temperature dataand have insuficient prediction accuracy，a coal spontaneous combustion temperature prediction model using Support Vector Regresson （SVR） with hyperparameters optimized by Bayesian Optimization （BO），abbreviated as BO-SVR，was proposed.A programmed heating experiment of coal spontaneous combustion was conducted to collct and process the generated indicator gas data. Spearman correlation analysis was used to select indicator gases with strong correlation to coal temperatureand analyze themulticolinearityamong the amountsof the generated indicator gases.Principal component analysis was performedon the selected indicator gases to resolve multicolinearity and reduce dimensionality simultaneously.Five-fold cross-validation was used todivide the training set and testset. The performance of the BO-SVR model was quantitatively evaluated in comparison with SVR，Particle Swarm Optimization SVR （PSO-SVR），and Genetic Algorithm-Optimized SVR （GA-SVR） models using Mean Absolute Error （MAE）， Root Mean Square Error （RMSE）， and Coefficient of Determination （R2） .Results showed that the MAEof the BO-SVR model decreased by 74.2% 2 36.7% and 10.2% compared with the other three models， respectively; the RMSE decreased by 71.9% 33.3% ，and 11.4% ， respectively; and the R2 reached 0.9885，which was higher than other models. Paralel experiments were conducted using bituminous coal samples from Shanxi Coal Import and Export Group Hequ Jiuxian Open-pit Coal Industry Co.， Ltd. The results showed that the BOSVRmodelhadanMAEof 4.9279∘C ，anRMSEof 6.4899°C ，and an R2 of 0.9853 onthe new dataset，which was highly consistent with the prediction results of the original dataset.This indicates that the BO-SVR model has good generalization ability，prediction accuracy，and robustnes，contributing to improving the accuracy of coal spontaneous combustion temperature prediction.

Key words： coal spontaneous combustion; Bayesian optimization; support vector regression; indicator gas; prediction model

0引言

煤自燃灾害作为煤炭安全生产的核心威胁之_[1-2]，不仅会造成煤炭资源的严重浪费，还可能引发火灾、爆炸等灾难性事故[3]。（剩余13987字）