决策树ID3算法在RH-KTB真空系统故障诊断中的应用  

Diagnosis of RH-KTB Vacuum System Based on Decision Tree ID3 Theory

作　　者：王庆[1] 巴德纯[1] 王晓冬[1] 靳雨菲[2] 

机构地区：[1]东北大学机械工程与自动化学院,辽宁沈阳110004 [2]宝钢集团股份有限公司宝山钢铁股份有限公司,上海201900

出　　处：《钢铁研究学报》2006年第4期59-62,共4页Journal of Iron and Steel Research

基　　金：教育部博士基金资助项目(2000014520);辽宁省科技基金重点资助项目(9910200102)

摘　　要：介绍了RH-KTB炉外精炼真空抽气系统的工作原理和故障特点。该系统的故障诊断应能从大量数据中快速提取征兆并及时诊断,且有一定的自学习能力。为此,采用一种以实例为基础的归纳学习算法即ID3算法进行故障诊断。ID3算法有一定的自学习、自组织能力,适用于复杂系统的智能诊断。通过讨论分析了ID3算法的特点和作用。RH-KTB vacuum system is used in secondary steelmaking. The basic principle and faults of RH-KTB are introduced. It is important for intelligent fault diagnosis to mined symptoms quickly and diagnose timely with selfstudy function. An example of induction ID3 algorithm is presented. The algorithm has self-study and self-organizing ability and is fit for intelligent diagnosis of complicated system. It was proved through the example that the proposed algorithm can be used for fault diagnosis of RH-KTB vacuum system. The characteristics and function of ID3 algorithm is analyzed.

关 键 词：决策树 真空 智能 故障诊断 

分 类 号：TF769.4[冶金工程—钢铁冶金]