NGSAII-GPR模型在碳排放短期预测中的应用

The Application of NGSA II-GPR Model in Short-Term Carbon Emission Forecasting

针对于采矿过程中以电机为研究对象的碳排放来源的复杂性以及其影响因素的多样性引起的碳排放短期预测精度不高的问题,结合灰色理论提出一种基于NGSAII-GPR模型的铅锌矿采矿过程碳排放预测方法。首先,对碳排放来源及其影响因素进行分析,采用灰色理论进行聚类分析以归并同类因素;其次,根据灰色关联性分析得到主要影响因素;最后,为解决超参数优化确定问题,将带精英策略的非支配排序遗传算法(NGSAII)引入到高斯过程回归(GPR)模型,提出了一种基于NGSAII-GPR的预测模型。经实验证明,相较于其他超参数优化确定方法,NGSAII能更好地对超参数进行优化确定,且相较于其他常规预测模型,NGSAII-GPR能更精确的预测铅锌矿采矿过程的碳排放量,其预测误差更小。

Considering the low forecasting accuracy problem caused by the complexity of the carbon emission sources from the motor and the diversity of its impacts during the lead-zinc mine mining process, a carbon emission forecasting method for lead-zinc mine mining process is proposed based on improved Gaussian process regression model combined with the grey theory. Firstly, the sources of carbon emission and their impacts are analyzed and the grey theory is used to cluster and merge the similar impacts. Then, the grey relational analysis is applied to obtain the main impacts. Finally, In order to solve the problem of hyperparameter optimization, the non-dominated sorting genetic algorithm (NGSA II) with elite strategy (NGSA II) is introduced into the Gauss process regression (GPR). Meanwhile the NGSAII-GPR Model is proposed. The result shows that NGSA II can better optimize the hyperparameter when compared with other methods. In addition NGSAII-GPR Model can be used to forecast the short-term carbon emission of lead-zinc mine mining process with high accuracy and minimum error compared with other forecasting models.