【摘要】：車(chē)間調(diào)度問(wèn)題由于其N(xiāo)P-Hard特性，傳統(tǒng)集中式的解決方案由于其求解消耗隨著問(wèn)題規(guī)模的日漸增長(zhǎng)指數(shù)級(jí)上漲而顯得臃腫不堪，而在更切合實(shí)際環(huán)境的柔性制造環(huán)境下更是無(wú)法滿足其復(fù)雜性，動(dòng)態(tài)性，隨機(jī)性的需求。在這樣的背景下，很多學(xué)者都開(kāi)始研究引進(jìn)更適合問(wèn)題模型的基于自治與協(xié)調(diào)的自適應(yīng)系統(tǒng)。本文在結(jié)合分析近代國(guó)內(nèi)外相關(guān)研究成果的基礎(chǔ)上，以具有柔性生產(chǎn)加工的離散作業(yè)制造車(chē)間作為研究對(duì)象，建立了基于Agent單元和合同網(wǎng)協(xié)商機(jī)制的自治與協(xié)商模型，并為系統(tǒng)模型引入了Q-Learn算法和工序價(jià)值評(píng)估算法進(jìn)行局部?jī)?yōu)化，為柔性車(chē)間調(diào)度問(wèn)題提供了有效實(shí)用的解決方案。 本文主要內(nèi)容可概括為： 1．首先針對(duì)柔性車(chē)間調(diào)度問(wèn)題，對(duì)近年來(lái)的相關(guān)研究成果與發(fā)展現(xiàn)狀進(jìn)行簡(jiǎn)單概括與分析，進(jìn)而提出本文研究的出發(fā)點(diǎn)與意義。 2．針對(duì)問(wèn)題的復(fù)雜性、不確定性、多約束多資源互相協(xié)調(diào)的特點(diǎn)，提出以復(fù)雜適應(yīng)系統(tǒng)（CAS）理論為基礎(chǔ)，Agent為基本單元，基于合同網(wǎng)協(xié)商機(jī)制的柔性車(chē)間調(diào)度問(wèn)題的實(shí)時(shí)調(diào)度框架模型。對(duì)系統(tǒng)框架進(jìn)行利弊分析，指出系統(tǒng)骨架的合同網(wǎng)缺乏優(yōu)化和動(dòng)態(tài)學(xué)習(xí)的問(wèn)題。 3．將Q-Learn強(qiáng)化學(xué)習(xí)算法引進(jìn)系統(tǒng)模型中的標(biāo)書(shū)評(píng)估決策，并根據(jù)算法的具體要求對(duì)Q-Learn算法的模型進(jìn)行了詳細(xì)定義和描述，賦予合同網(wǎng)協(xié)議動(dòng)態(tài)智能學(xué)習(xí)能力。 4．在標(biāo)書(shū)評(píng)估過(guò)程中提出了工序價(jià)值的概念，將系統(tǒng)目標(biāo)量化為“價(jià)值”的形式附加到子任務(wù)中，對(duì)系統(tǒng)進(jìn)行局部?jī)?yōu)化。 5．最后，使用Java+Swarm+Matlab工具，設(shè)計(jì)和開(kāi)發(fā)了綜合的仿真系統(tǒng)，對(duì)文中的設(shè)計(jì)與觀點(diǎn)進(jìn)行仿真測(cè)試，為該理論在問(wèn)題的實(shí)際應(yīng)用上做出可行性嘗試。本文對(duì)解決柔性制造環(huán)境下的車(chē)間調(diào)度問(wèn)題提出了一個(gè)合理的通過(guò)仿真證明其可行性的基于Agent的自治與協(xié)商調(diào)度方案，在一定程度上推動(dòng)了該方向?qū)?wèn)題的求解研究。
[Abstract]:Because of its characteristic of NP-Hard, the traditional centralized solution of job shop scheduling problem appears to be bloated because of its solution consumption increasing exponentially with the increasing scale of the problem. And in the more practical environment of flexible manufacturing environment is not able to meet its complexity, dynamic, random needs. In this context, many scholars have begun to study the introduction of adaptive systems based on autonomy and coordination that are more suitable for problem models. Based on the analysis of relevant research results at home and abroad in modern times, this paper takes the discrete job shop with flexible production and processing as the research object, and establishes the autonomy and negotiation model based on Agent unit and contract net negotiation mechanism. The Q-Learn algorithm and the process value evaluation algorithm are introduced to the system model for local optimization, which provides an effective and practical solution for the flexible job shop scheduling problem. The main contents of this paper can be summarized as follows: 1. Firstly, this paper summarizes and analyzes the related research results and development status in recent years, and then puts forward the starting point and significance of this study. 2. 2. In view of the complexity, uncertainty, multi-constraint and multi-resource coordination of the problem, this paper proposes a complex adaptive system based on (CAS) theory and Agent as the basic unit. A real-time scheduling framework model for flexible job shop scheduling problem based on contract net negotiation mechanism. This paper analyzes the advantages and disadvantages of the system framework and points out the lack of optimization and dynamic learning of the contract network of the system skeleton. 3. The Q-Learn reinforcement learning algorithm is introduced into the bidding evaluation decision of the system model, and the model of the Q-Learn algorithm is defined and described in detail according to the specific requirements of the algorithm, which endows the contract net protocol with dynamic intelligent learning ability. 4. In the process of bid evaluation, the concept of process value is put forward, and the system objective is quantified as "value", which is attached to the sub-task, and the system is locally optimized. 5. Finally, a comprehensive simulation system is designed and developed by using Java Swarm Matlab tool. The design and viewpoint of this paper are simulated and tested, which makes a feasible attempt for the practical application of the theory. In this paper, a reasonable Agent based autonomy and negotiation scheduling scheme is proposed to solve the job shop scheduling problem in flexible manufacturing environment, which is proved to be feasible by simulation. To some extent, it promotes the research of solving the problem in this direction.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類(lèi)號(hào)】：TH186;N945.12

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 譚躍進(jìn),鄧宏鐘;復(fù)雜適應(yīng)系統(tǒng)理論及其應(yīng)用研究[J];系統(tǒng)工程;2001年05期

2 黃炳強(qiáng);曹廣益;王占全;;強(qiáng)化學(xué)習(xí)原理、算法及應(yīng)用[J];河北工業(yè)大學(xué)學(xué)報(bào);2006年06期

3 馬鑫;梁艷春;;基于GPGP協(xié)同機(jī)制的多Agent車(chē)間調(diào)度方法研究[J];計(jì)算機(jī)研究與發(fā)展;2008年03期

4 胡舜耕;張莉;鐘義信;;多Agent系統(tǒng)的理論、技術(shù)及其應(yīng)用[J];計(jì)算機(jī)科學(xué);1999年09期

5 張�？�,史忠植;動(dòng)態(tài)合同網(wǎng)協(xié)議[J];計(jì)算機(jī)工程;2004年21期

6 楊萍;孫延明;劉小龍;車(chē)蘭秀;;基于細(xì)菌覓食趨化算子的PSO算法[J];計(jì)算機(jī)應(yīng)用研究;2011年10期

7 高陽(yáng),陳世福,陸鑫;強(qiáng)化學(xué)習(xí)研究綜述[J];自動(dòng)化學(xué)報(bào);2004年01期

8 熊銳,吳澄;車(chē)間生產(chǎn)調(diào)度問(wèn)題的技術(shù)現(xiàn)狀與發(fā)展趨勢(shì)[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);1998年10期

9 劉大有,楊鯤,陳建中;Agent研究現(xiàn)狀與發(fā)展趨勢(shì)[J];軟件學(xué)報(bào);2000年03期

10 李冬梅,陳衛(wèi)東,席裕庚;基于強(qiáng)化學(xué)習(xí)的多機(jī)器人合作行為獲取[J];上海交通大學(xué)學(xué)報(bào);2005年08期

相關(guān)博士學(xué)位論文 前2條

1 鞠全勇;智能制造系統(tǒng)生產(chǎn)計(jì)劃與車(chē)間調(diào)度的研究[D];南京航空航天大學(xué);2007年

2 王世進(jìn);基于自治與協(xié)商機(jī)制的柔性制造車(chē)間智能調(diào)度技術(shù)研究[D];上海交通大學(xué);2008年

相關(guān)碩士學(xué)位論文 前1條

1 王雪輝;基于多智能體的車(chē)間調(diào)度系統(tǒng)的研究[D];河北工業(yè)大學(xué);2005年

，

本文編號(hào)：2362739