Carbon Emission Prediction Method of Steel(Blast Furnace)Industry Based on Ensemble Learning
The steel industry is a typical industry with high energy consumption and amplified carbon emissions.China's steel industry is one of the industries with the highest carbon emissions in the world.At present,due to the lack of monitoring data,there is little research on predic-ting carbon emissions of steel industry enterprises.To effectively address this issue,a carbon emission prediction method for the steel(blast furnace)industry based on ensemble learning is proposed.It selects electricity consumption with good measurement methods as the influencing factor of carbon emissions,and combines blast furnace and electric arc furnace processes to adopt three machine learning models,namely Back Propagation(BP)neural network,Support Vector Machine,and Random Forest.These models have broad application prospects in the field of machine learning.Using Shapley ensemble learning method for carbon emission prediction.The effectiveness and accuracy of the proposed carbon emission prediction model for the steel industry based on electricity consumption input have been verified through simulation experi-ments.This result can provide scientific basis for steel industry enterprises in emission reduction and resource optimization.
BP neural networksupport vector machinerandom foreststeel(blast furnace)industrysteel(blast furnace)industry
万方数据
维普
