發(fā)布時間：2018-01-25 17:09

  本文關(guān)鍵詞： 故障診斷 多Agent系統(tǒng)(MAS) 協(xié)作機(jī)制 合同網(wǎng)協(xié)議 自適應(yīng)模型　出處：《太原理工大學(xué)》2011年碩士論文　論文類型：學(xué)位論文

【摘要】：隨著現(xiàn)代工業(yè)的迅速發(fā)展,機(jī)械設(shè)備的規(guī)模越來越龐大,自動化程度越來越高,集成化管理方式也越來越普遍,一旦設(shè)備出現(xiàn)問題將會帶來重大的事故和巨大的財產(chǎn)損失。傳統(tǒng)的采用簡單儀器和人工經(jīng)驗(yàn)的方法己不能滿足現(xiàn)代復(fù)雜設(shè)備的故障診斷。近年來,機(jī)械故障診斷技術(shù)在國內(nèi)外受到高度的重視,在機(jī)械學(xué)、通信學(xué)、計算機(jī)學(xué)和人工智能等科學(xué)的基礎(chǔ)上迅速發(fā)展成為一門新興學(xué)科。利用智能系統(tǒng)對設(shè)備進(jìn)行故障診斷,及時發(fā)現(xiàn)故障,以保障關(guān)鍵設(shè)備的正常運(yùn)行具有重大的意義。 MAS(多Agent系統(tǒng))作為一種良好的解決分布式問題的技術(shù),其方法和理論在很多領(lǐng)域都有廣泛應(yīng)用。針對現(xiàn)代機(jī)械故障診斷系統(tǒng)的復(fù)雜性、分布性和動態(tài)性,MAS能利用模塊化的設(shè)計思想和并行的分布式處理技術(shù),將復(fù)雜的系統(tǒng)分解成相對獨(dú)立的子系統(tǒng),而后通過各Agent的交互和協(xié)作共同完成相對復(fù)雜的任務(wù)。當(dāng)然,復(fù)雜機(jī)電設(shè)備診斷的過程中會出現(xiàn)大量新的信息和知識,面對動態(tài)的診斷環(huán)境,MAS故障診斷系統(tǒng)必須能適應(yīng)其周圍環(huán)境,根據(jù)不同的診斷對象構(gòu)建相應(yīng)的模型。因此,研究自適應(yīng)的診斷模型有著很重要的理論和現(xiàn)實(shí)意義。 一個好的多Agent系統(tǒng),必須有良好的協(xié)作機(jī)制的支持。多Agent間的協(xié)作問題研究是伴隨著多Agent系統(tǒng)的出現(xiàn)就產(chǎn)生的。協(xié)作不僅能使整個系統(tǒng)解決問題的能力得到提高,而且增加了多Agent系統(tǒng)的靈活性。針對系統(tǒng)的分布性特征,本文選擇了基于合同網(wǎng)的協(xié)作機(jī)制,并且在傳統(tǒng)合同網(wǎng)的基礎(chǔ)上,提出了一種改進(jìn)的合同網(wǎng)模型PC-CNP (Postpone Commitement-Contract Net Protocol,推遲確認(rèn)的合同網(wǎng)協(xié)議),改善了傳統(tǒng)合同網(wǎng)在資源分配和通信問題上缺陷。實(shí)驗(yàn)證明,在基于PC-CNP的協(xié)作機(jī)制下,任務(wù)完成效率明顯高于基于傳統(tǒng)合同網(wǎng)的機(jī)制。 本文以某大型選煤廠的復(fù)雜機(jī)電設(shè)備為背景,建立了基于MAS的故障診斷自適應(yīng)模型AMFD (Adaptive Model in Fault Diagnosis)。該模型的層次結(jié)構(gòu)與復(fù)雜機(jī)電設(shè)備的層次化組織特點(diǎn)相匹配,同時具有分布性和自適應(yīng)性,能夠根據(jù)診斷對象的變化,通過在拓?fù)浣Y(jié)構(gòu)、Agent組織、診斷流程和知識領(lǐng)域方面的重構(gòu),從而得到優(yōu)化的診斷系統(tǒng)。為了規(guī)范系統(tǒng)的描述,本文采用BNF(巴科斯范式)形式化語言對該AMFD的結(jié)構(gòu)組成等方面進(jìn)行了形式化定義。最后,在JADE平臺上實(shí)現(xiàn)了AMFD的原型系統(tǒng),其中,其動態(tài)的知識管理和層次化的體系結(jié)構(gòu)使增強(qiáng)了系統(tǒng)可擴(kuò)展性和可伸縮性。
[Abstract]:With the rapid development of modern industry, machinery and equipment more and more large scale, more and more high degree of automation, integrated management is becoming more and more popular, once the equipment problems will lead to major accidents and huge property losses. Methods using simple instrument and artificial experience of the traditional can not meet the modern fault diagnosis of complex equipment in recent years, machinery fault diagnosis technology has been highly valued at home and abroad in mechanics, communication science, computer science and artificial intelligence based on the rapid development of science has become a new subject. Fault diagnosis of equipment based on intelligent system, timely detection of failure, to guarantee the normal operation of the key equipment is of great significance.
MAS (multi Agent system) as a good solution to the problem of distributed technology, its theories and methods are widely used in many fields. Because of the complexity of modern mechanical fault diagnosis system, distributed and dynamic, MAS can use the modular design method and parallel distributed processing technology, the complex the system is decomposed into relatively independent subsystems, and then through the interaction and collaboration of each Agent to complete complicated tasks. Of course, the emergence of a large number of new information and knowledge will be the process of complex electromechanical equipment diagnosis, diagnosis in the dynamic environment, the MAS fault diagnosis system must be able to adapt to the surrounding environment, according to the corresponding model the different diagnosis target construction. Therefore, there is an important theoretical and practical significance to study the adaptive diagnosis model.
A good multi Agent system, there must be a good mechanism for collaboration support. The research collaboration between multi Agent is accompanied by the emergence of multi Agent system is generated. The cooperation ability can not only make the whole system to solve the problem is improved, but also increase the flexibility of the multi Agent system. According to the characteristics of distribution system in this paper, the coordination mechanism based on contract net, and based on the traditional contract net, proposes an improved contract net model (PC-CNP Postpone Commitement-Contract Net Protocol contract net protocol, delayed confirmation) to improve the traditional contract net, in resource allocation and communication problems on defects. The experimental results show that based on the the coordination mechanism of PC-CNP, task completion rate was significantly higher than that of the traditional mechanism based on contract net.
Based on the background of complex electromechanical equipment of a large coal preparation plant, established the fault diagnosis model based on adaptive AMFD MAS (Adaptive Model in Fault Diagnosis). The characteristics of hierarchical organization hierarchical structure of the model and the complex electromechanical equipment matching, which has distributed and adaptive, can according to the change of the diagnosis object, through in the topology, Agent, reconstruction of diagnosis process and knowledge, in order to get the diagnosis system optimization. In order to standardize the description of the system, this paper uses BNF (Backus paradigm) formal language for the formal definition of the AMFD structure. Finally, a prototype system of AMFD based on JADE based on the knowledge management and hierarchical structure of the dynamic enhances the expansibility and scalability.

【學(xué)位授予單位】：太原理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2011
【分類號】：TH165.3

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 吳泉源,王懷民;銀河分布計算環(huán)境[J];軟件學(xué)報;1997年10期

2 許六一;李建璜;胡柏青;覃方君;;一種改進(jìn)的CBR故障診斷方法研究[J];微計算機(jī)信息;2007年07期

3 程顯毅,石純一;分布式人工智能測試床[J];小型微型計算機(jī)系統(tǒng);2001年01期

4 陳浩;景寧;李軍;唐宇;;基于外包合同網(wǎng)的自治電磁探測衛(wèi)星群任務(wù)規(guī)劃[J];宇航學(xué)報;2009年06期

5 王娜,梁禹;基于神經(jīng)網(wǎng)絡(luò)與D-S證據(jù)理論的故障診斷[J];儀器儀表學(xué)報;2005年S1期

6 熊詩波;大型復(fù)雜機(jī)械系統(tǒng)的狀態(tài)監(jiān)測和故障診斷[J];振動.測試與診斷;2000年04期

7 吳偉蔚,楊叔子,吳今培;故障診斷Agent研究[J];振動工程學(xué)報;2000年03期

8 陳真勇,何永勇,褚福磊,黃靖遠(yuǎn);多Agent故障診斷原型系統(tǒng)研究[J];中國機(jī)械工程;2002年13期

相關(guān)博士學(xué)位論文 前5條

1 李偉;基于免疫機(jī)理的可重構(gòu)診斷系統(tǒng)研究[D];重慶大學(xué);2005年

2 孫紅巖;大型旋轉(zhuǎn)機(jī)械智能診斷多Agent系統(tǒng)的研究[D];重慶大學(xué);2007年

3 馬巧云;基于多Agent系統(tǒng)的動態(tài)任務(wù)分配研究[D];華中科技大學(xué);2006年

4 周桂紅;基于多Agent的數(shù)控機(jī)床遠(yuǎn)程故障診斷系統(tǒng)研究[D];吉林大學(xué);2008年

5 劉美容;基于遺傳算法、小波與神經(jīng)網(wǎng)絡(luò)的模擬電路故障診斷方法[D];湖南大學(xué);2009年

相關(guān)碩士學(xué)位論文 前3條

1 徐燕妮;基于合同網(wǎng)協(xié)議的多Agent協(xié)作技術(shù)研究[D];山東科技大學(xué);2006年

2 雷燕;基于合同網(wǎng)的多Agent協(xié)作技術(shù)在車間調(diào)度中的應(yīng)用研究[D];武漢理工大學(xué);2009年

3 高飛燕;基于擴(kuò)展合同網(wǎng)的多Agent任務(wù)分配機(jī)制的研究[D];大連海事大學(xué);2009年

，

本文編號：1463269