基于集成学习算法的尾气处理装置SO2排放预测模型

Sulfur dioxide emissions predictive model of tail gas treatment unit based on ensemble learning algorithm

关键词:  天然气净化  硫磺回收  尾气处理  二氧化硫排放  预测模型  集成学习算法

Key words:  natural gas purification  sulfur recovery  tail gas treatment  sulfur dioxide emission  prediction model  ensemble learning algorithm

摘要:

目的 精确预测天然气净化厂尾气处理装置烟气中二氧化硫（SO₂）排放质量浓度。方法 利用某天然气净化厂2018—2023年每小时44 000条尾气处理日报数据构建数据集，进行数据处理，并利用重要性分析方法提取27个重要特征。针对烟气中SO₂排放质量浓度的预测任务，采用了随机森林（Random Forest）、梯度提升（Gradient Boost）和极值梯度提升（XGBoost）3种集成学习算法，以及基于径向基（RBF）内核的支持向量机（SVM）替代仿真模型进行建模。结果 3种集成学习模型比SVM单模型的预测效果更为精准，而Random Forest模型展现出最佳性能，决定系数为0.89，均方误差为1 250.59，相对于8 800个真实测试集样本数据，其预测偏差为9.86%，相比于Random Forest模型（数据未处理），其决定系数提高了61.82%。结论 Random Forest模型在准确预测尾气处理装置SO₂排放质量浓度方面具有实际生产应用价值，可为后续尾气处理装置的工艺参数优化提供可靠的模型支持。

Abstract:

Objective The aim is to accurately predict the emission mass concentration of sulfur dioxide (SO₂) in the flue gas of the tail gas treatment unit of natural gas purification plants. Method The data set was constructed using 44 000 hourly tail gas treatment daily report data from a natural gas purification plant from 2018 to 2023. Data processing was conducted, and 27 important features were extracted using importance analysis methods. Aiming at the prediction task of SO₂ emission mass concentration in flue gas, three ensemble learning algorithms—namely, Random Forest, Gradient Boost, and XGBoost—and a Support Vector Machine (SVM) based on a Radial Basis Function (RBF) kernel were used to model the process instead of simulation models. Result The prediction accuracy of the three ensemble learning models was higher than the SVM single model. Among them, the Random Forest model exhibited the best performance, with a coefficient of determination of 0.89 and a mean square error of 1 250.59. Relative to a data set containing 8 800 real test set samples, its prediction deviation was 9.86%. Compared to the Random Forest model without data treatment, its coefficient of determination increased by 61.82%. Conclusion The Random Forest model has practical production application value in accurately predicting SO₂ emission mass concentration of the tail gas treatment unit and can provide reliable model support for the subsequent process parameter optimization of the tail gas treatment unit.