面向吨钢综合能耗预测的基因表达式编程方法

发布时间：2018-02-26 16:14

本文关键词： 综合能耗基因表达式编程预测方法模型　出处：《机械设计与制造》2017年02期 　论文类型：期刊论文

【摘要】：钢铁是国民经济的基础用材,我国吨钢综合能耗仍与发达国家存在较大差距。准确预测吨钢综合能耗,有利于制定节能方针和减少能源浪费。根据我国钢铁工业吨钢综合能耗历史数据,利用基因表达式编程(Gene Expression Programming,GEP)算法,构建吨钢综合能耗预测模型。首先,将吨钢综合能耗进行等间隔时序化、函数表达式符号化,在终端集中添加常量数组;其次,利用选择操作、变异操作、重组操作和移项操作进行遗传操作,获得吨钢综合能耗预测模型。结果表明,基于GEP的预测值与实测值平均误差为0.31,该模型较准确地预测我国钢铁工业吨钢综合能耗发展趋势。
[Abstract]:Iron and steel is the basic material of the national economy, and there is still a big gap between the comprehensive energy consumption of tons of steel in our country and that of developed countries. According to the historical data of comprehensive energy consumption of iron and steel industry in China, gene Expression programming algorithm is used to construct the prediction model of comprehensive energy consumption for tons of steel. The comprehensive energy consumption of tons of steel is sequenced at equal intervals, the function expression is symbolized, and the constant array is added in the terminal set. Secondly, genetic operations are carried out by means of selection operation, variation operation, recombination operation and item shifting operation. The prediction model of comprehensive energy consumption for tons of steel is obtained. The results show that the average error between the predicted value and the measured value based on GEP is 0.31, and the model can accurately predict the development trend of comprehensive energy consumption of tons of steel in China's iron and steel industry.
【作者单位】：武汉科技大学机械自动化学院;德克萨斯A&M大学能源研究所;武汉科技大学汽车与交通工程学院;
【基金】：国家自然科学基金资助项目(51275366,51305311) 教育部博导和博士后科学基金项目(20134219110002,2013M542073) 湖北省教育厅科学研究计划项目(B2013238)
【分类号】：TF087

【相似文献】