钢铁企业能耗预测系统的设计  

Design of Energy Consumption Prediction System of Iron and Steel Enterprises

作　　者：张全[1] 刘渺[1] 凌振华[1] 高敏[1] 

机构地区：[1]中南大学能源与动力工程学院,湖南长沙410083

出　　处：《冶金动力》2006年第2期67-68,70,共3页Metallurgical Power

摘　　要：基于湘钢历年每月总能耗数据,运用BP神经网络算法建立数学模型,用M ATLAB作为后台数据处理工具,用VB与M ATLAB的混合编程开发了钢铁企业能耗预测系统。预测值与实际能耗量的相对误差很小:最大相对误差为3.016%,最小相对误差仅为0.084%,平均相对误差为1.336%,系统具有较好的预测效果。Based on the monthly energy consumption data of Xiangtan Iron ＆ Steel Co. over the years, a mathematic model is established by the BP neural network algorithm, and MATLAB is used as the tool of background data processing. The prediction system of energy consumption of iron and steel enterprises is developed using VB and MATLAB. There is a small deviation between the predicted energy consumption amount and the practical energy consumption amount： the biggest is 3.016%; the smallest is 0.084%; and the average is 1.336%. The system has a good prediction effect.

关 键 词：神经网络 MATLAB 能耗 预测 系统 

分 类 号：F272.1[经济管理—企业管理]