摘要
针对铝型材生产过程中能耗较大，传统人工采集能耗数据频率低，采集速度慢等问题，该文提出一种铝型材熔铸炉生产实时能耗监测及能耗预测系统。该系统一方面使用基于zigbee协议的无线传输通讯方式将生产现场电表、燃气表与交换机相连接，并通过网络接口数据发送至服务器，实现对生产能耗数据的实时监测；另一方面采用回归型支持向量机对历史生产数据进行学习，得到预测能耗模型，用于对当前生产能耗数据预测，及时发现生产中的能源损失、生产参数不当等异常现象。
Energy consumption of Production process of aluminum is greatly, and traditional manual energy consumption data collection frequency is inefficiently. In order to solve these problems, this paper proposes an energy consumption monitoring and prediction system on aluminum furnace production. A wireless communication based on ZigBee protocol is used to connect field meter, gas meter and switches, and energy consumption data are sent to server through network interface to achieve real-time monitoring of the production energy consumption data; on the other hand, using historical production data to train regression support vector machine, then the trained SVM model of energy consumption is used for energy consumption prediction. The ex-perimental result shows that our system can find the production of energy loss, improper production parameters of abnormal phe-nomenon and etc.
作者
罗铭强
梁鹏
LUO Ming-qiang, LIANG Peng （1.Xingfa Aluminum Holdings Limited, Foshan 528061,China; 2.School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China）
出处
《电脑知识与技术》
2014年第10期6767-6770,共4页
Computer Knowledge and Technology
基金
国家科技支撑计划课题（2012BAF12810）
广东省教育部产学研结合项目（20128010500027）
关键词
能耗预测
实时能耗监测
回归型支持向量机
Energy consumption prediction
Real-time Energy consumption monitoring
Regression Support Vector Machine
