基于改进符号有向图的电站热力系统故障诊断方法研究.pdfVIP

25 卷 23 期 中 国 电 机 工 程 学 报 Vol.25 No.23 Dec. 2005 2005 年12 月 Proceedings of the CSEE 2005 Chin.Soc.for Elec.Eng. 文章编号：0258-8013 (2005) 23-0124-05 中图分类号：TK267 文献标识码：A 学科分类号：47020 基于改进SDG的电站热力系统故障诊断方法研究 曹文亮，王兵树，马良玉，张 冀，高建强 （华北电力大学控制科学与工程学院，河北省保定市 071003 ） RESEARCH ON FAULT DIAGNOSIS APPROACH BASED ON THE IMPROVED SIGNED DIRECTED GRAPH FOR THE POWER PLANT THERMAL SYSTEM CAO Wen-liang，WANG Bing-shu，MA Liang-yu，ZHANG Ji，GAO Jian-qiang (School of Control Science Engineering , North China Electric Power University, Baoding 071003, Hebei Province,China) ABSTRACT: The Signed Directed Graph (SDG) deep 层知识模型能表达复杂的因果关系，具有包容大规 knowledge model can be used to express the complex cause and 模潜在信息的能力，目前，在流程系统领域是完备 effect relations, and has very large capacity of containing 性较好的一种故障诊断方法。虽然基于SDG 的方法 process potential information, it is a self-contained method to 只是定性的，但在实际的电站热力过程中，操作条 effectively diagnosis system failures, but many limitations [1-3] 件多变，动态特性复杂 ，而只有变量间的定性逻 restrict it applies in fault diagnosis. The shortcoming of single 辑关系保持稳定不变，因而它具有不可比拟的优势。 variable analysis in modifying node state and threshold value 如果和其它方法相结合发挥这一特点，克服其不足 can be avoided by combine the Principal Component Analysis (PCA) with SDG; and the patterns that can not be distinguished 之处，将具有 大的发展前景。 are diagnosed by using the relative gain of corresponding nodes 本文首先从知识表示和处理的角度对SDG传统 to form a qualitative and quantitative model, and then the fault 方法进行了简要的分析。然后针对SDG模型在进行 can be di