本文選題：大數(shù)據(jù)　切入點(diǎn)：Spark　出處：《華北電力大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：近年來,隨著風(fēng)力發(fā)電的迅猛發(fā)展,越來越多的風(fēng)電場(chǎng)相繼建成,大量的風(fēng)電機(jī)組投入到運(yùn)行當(dāng)中。由于風(fēng)電場(chǎng)通常選址在戈壁等地區(qū),導(dǎo)致風(fēng)電機(jī)組常年處于極其惡劣的環(huán)境中工作,極易出現(xiàn)運(yùn)行故障。其中,齒輪箱是整個(gè)風(fēng)電機(jī)組發(fā)生故障概率最高的部件,據(jù)統(tǒng)計(jì),風(fēng)電機(jī)組60%以上的故障都發(fā)生于齒輪箱部位。因此迅速、準(zhǔn)確地對(duì)齒輪箱故障進(jìn)行診斷,對(duì)降低風(fēng)電場(chǎng)的運(yùn)維成本、提高風(fēng)電場(chǎng)的經(jīng)濟(jì)效益、提高風(fēng)電機(jī)組運(yùn)行的可靠性具有重要意義。隨著信息采集系統(tǒng)的快速發(fā)展和廣泛應(yīng)用,風(fēng)電機(jī)組狀態(tài)監(jiān)測(cè)的廣度和深度不斷加強(qiáng),生成的數(shù)據(jù)呈海量特征。如何對(duì)這些不斷增長的海量狀態(tài)監(jiān)測(cè)數(shù)據(jù)進(jìn)行處理,對(duì)所發(fā)生故障進(jìn)行快速、準(zhǔn)確地診斷成為了重要的課題。在此背景下,本文對(duì)上述問題展開研究。首先,為了提高故障診斷的準(zhǔn)確度,本文給出了一種基于人工蜂群優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的算法。將人工蜂群算法引入到傳統(tǒng)的BP神經(jīng)網(wǎng)絡(luò)中,利用人工蜂群的全局搜索能力改善BP神經(jīng)網(wǎng)絡(luò)對(duì)于初始參數(shù)敏感的缺陷。其次,針對(duì)傳統(tǒng)基于梯度下降法的BP神經(jīng)網(wǎng)絡(luò)算法執(zhí)行效率低的不足,以及故障診斷的實(shí)際應(yīng)用場(chǎng)景,本文將極限學(xué)習(xí)機(jī)算法引入到齒輪箱的故障診斷領(lǐng)域,并利用螢火蟲算法對(duì)其進(jìn)行優(yōu)化,同時(shí)也針對(duì)螢火蟲算法的“早熟”、“震蕩”等缺陷進(jìn)行改進(jìn),提高故障診斷的精度。最后,在Spark平臺(tái)上實(shí)現(xiàn)了以上兩種故障診斷模型的并行化設(shè)計(jì),提高其處理海量數(shù)據(jù)的能力。最后,進(jìn)行實(shí)驗(yàn)測(cè)試。選用某風(fēng)電場(chǎng)實(shí)際運(yùn)行數(shù)據(jù),在實(shí)驗(yàn)室搭建的具有8個(gè)節(jié)點(diǎn)的云計(jì)算集群上對(duì)本文設(shè)計(jì)的兩種故障診斷模型進(jìn)行性能測(cè)試,并與傳統(tǒng)故障診斷算法進(jìn)行對(duì)比。實(shí)驗(yàn)結(jié)果表明,相對(duì)于傳統(tǒng)故障診斷算法,本文給出的算法均具有更高的故障診斷精度,證明了設(shè)計(jì)的算法的有效性和良好的并行性能。
[Abstract]:In recent years, with the rapid development of wind power, more and more wind farms have been built and a large number of wind turbines have been put into operation. It causes wind turbine to work in an extremely bad environment all year round, so it is easy to run malfunction. Among them, gearbox is the component with the highest probability of failure, according to statistics, The faults above 60% of the wind turbine unit occur in the gearbox position. Therefore, the diagnosis of the gearbox fault quickly and accurately will reduce the operation and maintenance cost of the wind farm and increase the economic benefit of the wind farm. It is of great significance to improve the reliability of wind turbine operation. With the rapid development and wide application of information collection system, the breadth and depth of wind turbine condition monitoring are continuously strengthened. How to deal with these growing mass state monitoring data and diagnose the faults quickly and accurately has become an important issue. First of all, in order to improve the accuracy of fault diagnosis, a BP neural network algorithm based on artificial beecolony optimization is presented in this paper. The artificial bee colony algorithm is introduced into the traditional BP neural network. The global searching ability of artificial bee colony is used to improve the defect of BP neural network which is sensitive to the initial parameters. Secondly, the shortcomings of the traditional BP neural network algorithm based on gradient descent method and the practical application of fault diagnosis are pointed out. In this paper, the extreme learning machine algorithm is introduced into the field of gearbox fault diagnosis, and the firefly algorithm is used to optimize it. At the same time, the "precocity" and "oscillation" of the firefly algorithm are improved. Finally, the parallel design of the above two fault diagnosis models is implemented on the Spark platform to improve their ability to deal with massive data. Finally, the experimental tests are carried out, and the actual operation data of a certain wind farm are selected. The performance of the two fault diagnosis models designed in this paper is tested on the cloud computing cluster with eight nodes built in the laboratory, and compared with the traditional fault diagnosis algorithm. The experimental results show that compared with the traditional fault diagnosis algorithm, the performance of the two fault diagnosis models is compared with that of the traditional fault diagnosis algorithm. The algorithm presented in this paper has higher fault diagnosis accuracy, and proves the effectiveness and good parallel performance of the proposed algorithm.
【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP18;TM315

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 呂忠;周強(qiáng);周琨;陳立;申雙葵;;基于遺傳算法改進(jìn)極限學(xué)習(xí)機(jī)的變壓器故障診斷[J];高壓電器;2015年08期

2 謝敏;吳亞雄;閆圓圓;諸言涵;;基于改進(jìn)動(dòng)態(tài)自適應(yīng)模糊Petri網(wǎng)與BP算法的電網(wǎng)故障診斷[J];中國電機(jī)工程學(xué)報(bào);2015年12期

3 夏威;張麟;袁秋實(shí);陳國新;馬松濤;劉涌;李皓巖;;改進(jìn)極限學(xué)習(xí)機(jī)應(yīng)用于電網(wǎng)故障診斷[J];電網(wǎng)與清潔能源;2015年04期

4 向玲;鄢小安;;基于小波包的EITD風(fēng)力發(fā)電機(jī)組齒輪箱故障診斷[J];動(dòng)力工程學(xué)報(bào);2015年03期

5 王軍輝;賈嶸;譚泊;;基于EEMD和模糊C均值聚類的風(fēng)電機(jī)組齒輪箱故障診斷[J];太陽能學(xué)報(bào);2015年02期

6 寇為剛;李永祥;孫艷軍;;電力系統(tǒng)故障診斷的研究現(xiàn)狀與展望綜述[J];自動(dòng)化與儀器儀表;2015年02期

7 黎濤;唐明珠;譚欣星;;基于CLSSVM的風(fēng)電機(jī)組齒輪箱故障診斷[J];可再生能源;2015年02期

8 公茂法;張言攀;柳巖妮;王志文;劉麗娟;;基于BP網(wǎng)絡(luò)算法優(yōu)化模糊Petri網(wǎng)的電力變壓器故障診斷[J];電力系統(tǒng)保護(hù)與控制;2015年03期

9 李巍華;翁勝龍;張紹輝;;一種螢火蟲神經(jīng)網(wǎng)絡(luò)及在軸承故障診斷中的應(yīng)用[J];機(jī)械工程學(xué)報(bào);2015年07期

10 鄭楠;王翔;于浩杰;顏敏;;一種改進(jìn)混沌螢火蟲算法[J];計(jì)算機(jī)仿真;2014年10期

相關(guān)博士學(xué)位論文 前3條

1 馬超;基于元啟發(fā)優(yōu)化極限學(xué)習(xí)機(jī)的分類算法及其應(yīng)用研究[D];吉林大學(xué);2014年

2 李小冬;核極限學(xué)習(xí)機(jī)的理論與算法及其在圖像處理中的應(yīng)用[D];浙江大學(xué);2014年

3 張偉;人工蜂群混合優(yōu)化算法及應(yīng)用研究[D];浙江大學(xué);2014年

相關(guān)碩士學(xué)位論文 前10條

1 李爽;基于Spark的數(shù)據(jù)處理分析系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];北京交通大學(xué);2015年

2 樊嘉麒;基于大數(shù)據(jù)的數(shù)據(jù)挖掘引擎[D];北京郵電大學(xué);2015年

3 梁彥;基于分布式平臺(tái)Spark和YARN的數(shù)據(jù)挖掘算法的并行化研究[D];中山大學(xué);2014年

4 齊昕;風(fēng)電場(chǎng)運(yùn)行數(shù)據(jù)采集和監(jiān)控系統(tǒng)的研究與應(yīng)用[D];華北電力大學(xué);2014年

5 唐振坤;基于Spark的機(jī)器學(xué)習(xí)平臺(tái)設(shè)計(jì)與實(shí)現(xiàn)[D];廈門大學(xué);2014年

6 蔡蕊;基于人工蜂群算法和LSSVM的風(fēng)機(jī)齒輪箱故障診斷[D];華北電力大學(xué);2014年

7 張建美;基于云模型和數(shù)據(jù)挖掘技術(shù)的風(fēng)電機(jī)組故障診斷[D];華北電力大學(xué);2014年

8 劉迎;基于SVM風(fēng)電機(jī)組齒輪箱故障診斷系統(tǒng)研究[D];華北電力大學(xué);2013年

9 彭國華;風(fēng)電機(jī)組齒輪箱在線振動(dòng)監(jiān)測(cè)系統(tǒng)的開發(fā)[D];南京航空航天大學(xué);2013年

10 銀建霞;人工蜂群算法的研究及其應(yīng)用[D];西安電子科技大學(xué);2012年

，

本文編號(hào)：1626762