本文關(guān)鍵詞：面向電網(wǎng)故障診斷的BP神經(jīng)網(wǎng)絡(luò)優(yōu)化算法研究　出處：《昆明理工大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： BP神經(jīng)網(wǎng)絡(luò) 螢火蟲(chóng)算法 變步長(zhǎng)因子 電網(wǎng)故障診斷 隱層節(jié)點(diǎn)數(shù)

【摘要】：隨著經(jīng)濟(jì)的蓬勃發(fā)展,我國(guó)的電力行業(yè)發(fā)展向著更大容量、自動(dòng)化水平更高的方向轉(zhuǎn)變。對(duì)于電網(wǎng)運(yùn)行穩(wěn)定性的要求越來(lái)越高,電網(wǎng)運(yùn)行中出現(xiàn)的故障給供電公司以及用戶(hù)帶來(lái)了巨大的損失。為了減少電網(wǎng)的故障時(shí)間,同時(shí)加強(qiáng)電網(wǎng)供電的可靠性,電網(wǎng)在發(fā)生故障后,應(yīng)該準(zhǔn)確及時(shí)地發(fā)現(xiàn)故障位置,隔離故障元件,消除故障隱患,從而提升系統(tǒng)的安全可靠性,同時(shí)采取相應(yīng)的辦法恢復(fù)電網(wǎng)運(yùn)行。BP神經(jīng)網(wǎng)絡(luò)是目前應(yīng)用于電網(wǎng)故障診斷中最廣泛的神經(jīng)網(wǎng)絡(luò)模型之一,BP神經(jīng)網(wǎng)絡(luò)具有良好的自學(xué)習(xí)能力以及自適應(yīng)和泛化能力,但是BP神經(jīng)網(wǎng)絡(luò)算法是基于梯度的方法,存在運(yùn)算過(guò)程中容易陷入局部極小值的不足,同時(shí)當(dāng)學(xué)習(xí)樣本數(shù)目比較多、輸入與輸出關(guān)系比較復(fù)雜的時(shí)候,網(wǎng)絡(luò)會(huì)出現(xiàn)收斂速度緩慢,收斂精度不高,甚至不收斂的問(wèn)題。螢火蟲(chóng)算法具有全局尋優(yōu)能力,利用螢火蟲(chóng)優(yōu)化BP神經(jīng)網(wǎng)絡(luò)中的初始權(quán)值閾值,可以避免BP神經(jīng)網(wǎng)絡(luò)陷入局部極小的問(wèn)題,有效地提高故障診斷的準(zhǔn)確性。但是,傳統(tǒng)的螢火蟲(chóng)算法本身也有缺陷,在全局尋優(yōu)的過(guò)程中,容易得到局部最優(yōu)解,出現(xiàn)“早熟”的問(wèn)題。為了提高螢火蟲(chóng)算法的全局尋優(yōu)能力,克服“早熟”問(wèn)題。我們?cè)趥鹘y(tǒng)螢火蟲(chóng)算法的基礎(chǔ)上引入了變步長(zhǎng)因子,當(dāng)螢火蟲(chóng)個(gè)體在感知范圍內(nèi)沒(méi)有找到優(yōu)秀個(gè)體時(shí),通過(guò)移動(dòng)一個(gè)步長(zhǎng),從而改變鄰域范圍,在新范圍內(nèi)尋找局部最優(yōu)。從而提高了算法的全局尋優(yōu)能力。本論文提出了改進(jìn)螢火蟲(chóng)算法優(yōu)化BP神經(jīng)網(wǎng)絡(luò)。當(dāng)螢火蟲(chóng)個(gè)體在感知范圍內(nèi)沒(méi)有發(fā)現(xiàn)優(yōu)秀個(gè)體時(shí),通過(guò)引入變步長(zhǎng)因子,隨機(jī)移動(dòng)一個(gè)步長(zhǎng),更新鄰域半徑,從而提高了算法的局部尋優(yōu)能力。進(jìn)而提高了全局尋優(yōu)能力。將結(jié)合后的算法應(yīng)用于電網(wǎng)區(qū)域的故障診斷,得到了較好的診斷效果。
[Abstract]:With the vigorous development of economy, China's power industry development toward larger capacity, higher automation level change direction. And the increasingly high demand for the stability of power grid, the fault occurred in power grid operation has brought huge losses to the power supply companies and users. In order to reduce the fault time of the grid, while enhancing the reliability of power supply the grid after a failure, should be timely and accurately find the fault location, fault isolation components, the failure to eliminate hidden dangers, so as to enhance the safety and reliability of the system, and take corresponding measures to restore the electric network running.BP neural network is one of the neural network model for fault diagnosis of the most widely used BP neural network with self adaptive learning ability and generalization ability and good, but the BP neural network algorithm is based on the gradient method, the operation process is easy to fall into existence Local minimum problem, at the same time when the number of samples to learn more, when the relationship between input and output is more complex, the network will appear slow convergence speed, convergence precision is not high, even no convergence problem. Firefly algorithm has the ability of global optimization, the initial weights and threshold using the firefly to optimize the BP neural network. To avoid the BP neural network into local minima problems, effectively improve the accuracy of fault diagnosis. However, the traditional firefly algorithm itself has a flaw in the global optimization process, easy to get the local optimal solution, the premature problem. In order to improve the global searching ability of the firefly algorithm, overcome the "premature" problem. We introduce a variable step size based on traditional firefly algorithm, when the firefly individual did not find the best individual in the perception range, by moving a step to Change the neighborhood range, find the local optima in the new range. In order to improve the ability of global optimization of the algorithm. This paper presents the improvement of firefly algorithm to optimize BP neural network. When the firefly individual found no outstanding individuals in the perception range, the variable step factor, random moving one step update neighborhood radius thus, to improve the local searching ability of the algorithm. And then improve the ability of global optimization. The fault diagnosis combined algorithm is applied to the regional power grid, get a good diagnosis effect.

【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TP183;TM711

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 顧雪平,張文勤,高曙,楊以涵;基于神經(jīng)網(wǎng)絡(luò)和元件關(guān)聯(lián)分析的電網(wǎng)故障診斷[J];華北電力大學(xué)學(xué)報(bào);1999年02期

2 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

3 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

4 畢天姝,倪以信,吳復(fù)立,楊奇遜;基于新型神經(jīng)網(wǎng)絡(luò)的電網(wǎng)故障診斷方法[J];中國(guó)電機(jī)工程學(xué)報(bào);2002年02期

5 陳丙珍;人工神經(jīng)網(wǎng)絡(luò)在過(guò)程工業(yè)中的應(yīng)用[J];中國(guó)有色金屬學(xué)報(bào);2004年S1期

6 周明,任建文,李庚銀,徐開(kāi)理;基于模糊推理的分布式電力系統(tǒng)故障診斷專(zhuān)家系統(tǒng)[J];電力系統(tǒng)自動(dòng)化;2001年24期

7 王建元,紀(jì)延超;Petri網(wǎng)絡(luò)在變壓器故障診斷中的應(yīng)用[J];電網(wǎng)技術(shù);2002年08期

8 朱大奇;人工神經(jīng)網(wǎng)絡(luò)研究現(xiàn)狀及其展望[J];江南大學(xué)學(xué)報(bào);2004年01期

9 王宜懷,王林;基于人工神經(jīng)網(wǎng)絡(luò)的非線(xiàn)性回歸[J];計(jì)算機(jī)工程與應(yīng)用;2004年12期

10 趙龍文,侯義斌;多Agent系統(tǒng)及其組織結(jié)構(gòu)[J];計(jì)算機(jī)應(yīng)用研究;2000年07期

相關(guān)博士學(xué)位論文 前1條

1 黃平;粒子群算法改進(jìn)及其在電力系統(tǒng)的應(yīng)用[D];華南理工大學(xué);2012年

相關(guān)碩士學(xué)位論文 前6條

1 武偉;人工神經(jīng)網(wǎng)絡(luò)的范疇解釋及其應(yīng)用[D];南京大學(xué);2016年

2 張瑞冬;基于模糊神經(jīng)網(wǎng)絡(luò)的短期電力負(fù)荷預(yù)測(cè)[D];廣西師范大學(xué);2015年

3 馬彥追;螢火蟲(chóng)算法的改進(jìn)及其應(yīng)用研究[D];廣西民族大學(xué);2014年

4 姜明佐;基于云模型改進(jìn)的遺傳算法研究[D];遼寧師范大學(xué);2013年

5 劉天舒;BP神經(jīng)網(wǎng)絡(luò)的改進(jìn)研究及應(yīng)用[D];東北農(nóng)業(yè)大學(xué);2011年

6 黃麗;BP神經(jīng)網(wǎng)絡(luò)算法改進(jìn)及應(yīng)用研究[D];重慶師范大學(xué);2008年

，

本文編號(hào)：1382652