本文關(guān)鍵詞：基于貝葉斯網(wǎng)的電力系統(tǒng)故障診斷方法研究　出處：《西南交通大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 故障診斷 故障隔離 貝葉斯模型 容錯(cuò)性 電力系統(tǒng)

【摘要】：目前信息技術(shù)和通信技術(shù)得以高度發(fā)展,隨著數(shù)字化變電站以及智能二次設(shè)備的更新?lián)Q代,二次側(cè)信息實(shí)現(xiàn)高度共享和集成,電網(wǎng)故障診斷具備充實(shí)的數(shù)據(jù)基礎(chǔ)。90年代初至今,我國(guó)的專家學(xué)者對(duì)電力系統(tǒng)故障診斷做了大量的研究。但是目前只有少數(shù)基于模式識(shí)別、規(guī)則挖掘的方法用于電網(wǎng)故障診斷。研究以解決實(shí)際工程問(wèn)題為目標(biāo)的故障診斷方法具有重要的研究意義。貝葉斯網(wǎng)絡(luò)理論是公認(rèn)具有優(yōu)異容錯(cuò)能力的模式識(shí)別方法。貝葉斯模型的構(gòu)造對(duì)故障診斷效果有很大的影響。傳統(tǒng)面向元件建模的貝葉斯故障診斷模型結(jié)構(gòu)相對(duì)固定,節(jié)點(diǎn)之間的連接方式不夠合理,貝葉斯網(wǎng)的計(jì)算結(jié)果過(guò)于依賴保護(hù)節(jié)點(diǎn)。另外獲取先驗(yàn)概率的困難阻礙了貝葉斯方法應(yīng)用到實(shí)際故障診斷。本文針對(duì)故障區(qū)域判斷和貝葉斯模型進(jìn)行了改進(jìn)研究。提出一種基于故障隔離的貝葉斯故障診斷算法,在連接方式上將保護(hù)和斷路器節(jié)點(diǎn)分開(kāi),實(shí)現(xiàn)模型對(duì)保護(hù)和斷路器信息的綜合利用。模型去除了元件節(jié)點(diǎn)的先驗(yàn)概率,只需要獲得保護(hù)和斷路器的條件概率以及節(jié)點(diǎn)證據(jù)值就可以進(jìn)行故障診斷。由于保護(hù)和斷路器的條件概率對(duì)應(yīng)的事件屬于小概率事件,不會(huì)因?yàn)楦怕实淖兓绊懺\斷結(jié)果。因此典型的保護(hù)和斷路器條件概率即可滿足貝葉斯建模的需求。通過(guò)對(duì)斷路器和保護(hù)分層處理,簡(jiǎn)化了貝葉斯模型的構(gòu)造,并使貝葉斯模型能夠兼容含有失靈保護(hù)的元件。同時(shí)本文利用簡(jiǎn)單的時(shí)序處理,配合斷路器分層進(jìn)一步減少可疑元件的數(shù)量,提高了故障診斷的效率。算法模型的有效性通過(guò)電網(wǎng)實(shí)際算例和典型電網(wǎng)仿真算例進(jìn)行了驗(yàn)證。對(duì)于故障診斷算法的容錯(cuò)能力,大部分的研究只停留在特殊算例的描述上,無(wú)法量化算法的容錯(cuò)性能,不同算法之間難以進(jìn)行橫向比較。本文提出了兩個(gè)指標(biāo)用來(lái)評(píng)價(jià)故障診斷算法的容錯(cuò)能力。并對(duì)傳統(tǒng)貝葉斯模型和基于故障隔離的貝葉斯模型進(jìn)行了仿真對(duì)比。結(jié)果表明基于故障隔離的貝葉斯模型具有更高的容錯(cuò)性。
[Abstract]:At present, information technology and communication technology is highly developed, with two digital substation equipment and intelligent upgrading, two side information to achieve a high degree of sharing and integration of power grid fault diagnosis have so far full data base.90 in the early 1990s, experts and scholars in China have done a lot of research on Fault Diagnosis of power system. But at present only a method based on pattern recognition, rules for power system fault diagnosis. Have important significance to study the fault diagnosis method to solve practical engineering problems as the goal. Bias network theory, the pattern recognition method is recognized with excellent fault tolerance. Constructing the Bias model has a great influence on the effect of fault diagnosis. Fault diagnosis of Bias model the structure of the traditional component oriented modeling is relatively fixed, connections between nodes is not reasonable, the calculation of Bias The result is too dependent on the protection of nodes. In addition to obtaining the prior probability difficultieshinder the Bias method is applied to the actual fault diagnosis. This paper studies the fault area and determine the improved Bias model was proposed. A fault diagnosis algorithm based on Bias fault isolation, the connection mode of general protection and circuit breaker node separately, realize the comprehensive utilization of the model the information of protections and circuit breakers. The prior probability model of removing element nodes, only need to obtain protection and circuit breaker condition probability and node values could be evidence for fault diagnosis. Because the protection of circuit breakers and the conditional probability of the corresponding event belongs to a small probability event, not because the probability changes affect the diagnosis results. Therefore typical protection and circuit breaker condition probability can meet the demand. The Bias model of circuit breaker and protection layer, simplified The Bias model, and Bias model can be compatible with failure protection components. At the same time with the application of time series processing simple, hierarchical tie breaker further reduce the number of suspicious components, improve the efficiency of fault diagnosis. The effectiveness of the algorithm model through practical examples and typical power grid simulation examples. For fault tolerance and fault diagnosis algorithm, most of the research is only in the special case description, not fault-tolerant performance quantization algorithm, difficult to compare between different algorithms. This paper proposes a fault tolerance of two indexes for evaluating the fault diagnosis algorithm. And the traditional Bias model and Bias model based on fault isolation the simulation results show that the Bias model. Based on the fault isolation has a higher fault tolerance.

【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TM711

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 何小飛;童曉陽(yáng);孫明蔚;;基于貝葉斯網(wǎng)絡(luò)和D-S證據(jù)理論的分布式電網(wǎng)故障診斷[J];電力系統(tǒng)自動(dòng)化;2011年10期

2 張耀天;何正友;趙靜;張鵬;李明;桂建廷;;基于粗糙集理論和樸素貝葉斯網(wǎng)絡(luò)的電網(wǎng)故障診斷方法[J];電網(wǎng)技術(shù);2007年01期

3 王磊;陳青;李天友;高湛軍;李兆飛;;基于網(wǎng)格平臺(tái)的電網(wǎng)故障診斷架構(gòu)[J];電力系統(tǒng)自動(dòng)化;2013年03期

4 宋耐超;陳素霞;;基于粗糙集-貝葉斯的電網(wǎng)故障診斷方法[J];化工自動(dòng)化及儀表;2011年07期

5 馬永杰;;電網(wǎng)故障模型中貝葉斯網(wǎng)絡(luò)和DS證據(jù)理論的應(yīng)用[J];企業(yè)技術(shù)開(kāi)發(fā);2011年03期

6 董海鷹,常弘,白建社,薛鈞義;一種基于Web的多Agent變電站故障診斷方法研究[J];西安交通大學(xué)學(xué)報(bào);2003年02期

7 束洪春,孫向飛,司大軍;基于粗糙集理論的配電網(wǎng)故障診斷研究[J];中國(guó)電機(jī)工程學(xué)報(bào);2001年10期

8 丁劍;白曉民;趙偉;方竹;李再華;仲悟之;;基于復(fù)雜事件處理技術(shù)的電網(wǎng)故障信息分析及診斷方法[J];中國(guó)電機(jī)工程學(xué)報(bào);2007年28期

9 楊健維;何正友;臧天磊;;基于方向性加權(quán)模糊Petri網(wǎng)的電網(wǎng)故障診斷方法[J];中國(guó)電機(jī)工程學(xué)報(bào);2010年34期

10 文福拴，韓禎祥;基于遺傳算法和模擬退火算法的電力系統(tǒng)的故障診斷[J];中國(guó)電機(jī)工程學(xué)報(bào);1994年03期

，

本文編號(hào)：1422692