电煤供应链碳排放分析与预测  

Analysis and Forecast of Carbon Emission in Power-Coal Supply Chain

作　　者：慈铁军[1,2] 马皓璨 杜恒 杨晓宇 陈通 吴自高 CI Tiejun;MA Haocan;DU Heng;YANG Xiaoyu;CHEN Tong;WU Zigao(School of Energy Power and Mechanical Engineering,North China Electric Power University,Baoding 071003,China;Hebei Key Laboratory of Electric Machinery Health Maintenance&Failure Prevention,North China Electric Power University,Baoding 071003,China)

机构地区：[1]华北电力大学能源动力与机械工程学院,河北保定071003 [2]河北省电力机械装备健康维护与失效预防重点实验室(华北电力大学),河北保定071003

出　　处：《电力科学与工程》2021年第9期62-70,共9页Electric Power Science and Engineering

基　　金：国家自然科学基金(51777075)。

摘　　要：为控制温室气体排放,努力实现“30·60目标”,对电煤供应链碳排放进行分析及预测,对指导减少碳排放具有重要意义。首先,采用Petri网理论分析电煤供应链的运行模式,并结合TOPSIS法寻找关键链节点,为后续求取碳排放量打下基础;然后,对各个关键链节点碳排放来源及计算公式进行分析,计算出实际碳排放量;最后,将实际碳排放量及其他影响因素数据输入到GA-BP神经网络,得出预测值,并比较预测值与实际值的误差,说明其准确性。GA-BP神经网络引入遗传算法,克服了BP神经网络收敛速度慢、容易陷入局部最优解的问题。In order to control greenhouse gas emissions and strive to achieve the“30-60 target”,analyzes and forecasts the carbon emissions in power-coal supply chain in order to control carbon emissions more effectively.Firstly,the operation mode of power-coal supply chain was analyzed by Petri net theory,and the key chain nodes were found with TOPSIS method,which laid a foundation for the subsequent calculation of carbon emissions.Then the carbon emission source and calculation formula of each key chain node were analyzed to calculate the actual carbon emission.Finally,the data of actual carbon emissions and other influencing factors are input into GA-BP neural network to obtain the predicted value,and the error between the predicted value and the actual value was compared to demonstrate its accuracy.GA-BP neural network introduced genetic algorithm to overcome the problem of the slow convergence speed and easily falling into local optimal solution.

关 键 词：电煤供应链 PETRI网 碳排放 GA-BP神经网络 

分 类 号：TM46[电气工程—电器]