水泥工厂电耗预测及优化

Electricity consumption prediction and optimization in cement plants

针对当前水泥工厂面临的高电耗问题,提出了基于支持向量机(SVM)的电耗预测。通过预测未来时刻的电耗,在优化控制上做相应的调整,在不影响生产质量的前提下达到高效生产的目的。首先分析了解水泥的生产工艺及其数据特点,确定影响电耗的关键指标;对于水泥工艺变量存在的滞后性、多工况等难点,在预测模型中加入了自适应的策略;经离线验证并在某水泥现场实施应用了两个月,证实了预测的可靠性,并在节能方面取得了不错的效果。

Aiming at the problem of high power consumption faced by the current cement plants, a power consumption prediction based on support vector machine(SVM) is proposed. By predicting the power consumption in the future, we will make corresponding adjustments in the optimization control, and achieve the goal of efficient production without affecting the production quality. Firstly, in order to determine the key indicators affecting power consumption, the process and data characteristics of the cement production are analyzed.As the variables of cement process has the characteristics of hysteresis and multiple loadcases, an adaptive strategy is added to the prediction model;This method has been applied on a cement sitefor two months,the reliability of the prediction is confirmed and good results are achieved in energy saving.