【摘要】：傳統(tǒng)的風(fēng)機(jī)故障預(yù)警一般通過(guò)設(shè)定單一變量的恒定預(yù)警閾值來(lái)實(shí)現(xiàn),但在實(shí)際復(fù)雜工況下,這種方法易導(dǎo)致故障誤報(bào)、不報(bào)或預(yù)留排查時(shí)間不足。在不同的環(huán)境溫度下,風(fēng)機(jī)的運(yùn)行狀況不完全相同,并網(wǎng)發(fā)電量、并網(wǎng)功率、各部件溫度也不盡相同,僅依靠恒定預(yù)警值無(wú)法滿足復(fù)雜多變的工況下的預(yù)警要求。針對(duì)此問(wèn)題,本文提出一種基于大數(shù)據(jù)分析的風(fēng)機(jī)群落中異常風(fēng)機(jī)的識(shí)別和故障預(yù)警方法。通過(guò)對(duì)河北赤沽地區(qū)某大型風(fēng)電場(chǎng)中所有風(fēng)機(jī)運(yùn)行狀況的研究,并結(jié)合現(xiàn)場(chǎng)SCADA系統(tǒng)中相關(guān)歷史數(shù)據(jù)的整理分析,采用聚類(lèi)分析的方法對(duì)風(fēng)場(chǎng)中運(yùn)行工況相似的風(fēng)機(jī)進(jìn)行群落劃分。采用統(tǒng)計(jì)學(xué)原理,對(duì)每一個(gè)群落中風(fēng)機(jī)溫度類(lèi)參數(shù)進(jìn)行箱式分布,依據(jù)箱式圖中離群點(diǎn)的分布特性識(shí)別出群落中表現(xiàn)為離群特性的風(fēng)機(jī)。在此基礎(chǔ)上采用顯著性差異分析方法對(duì)離群風(fēng)機(jī)進(jìn)行異常顯著性判斷,識(shí)別出異常運(yùn)行的離群風(fēng)機(jī)。為排除偶然因素造成的干擾,采用滑動(dòng)窗口異常率統(tǒng)計(jì)分析方法消除風(fēng)電機(jī)組奇異點(diǎn)的干擾,實(shí)現(xiàn)了風(fēng)機(jī)群落中異常風(fēng)機(jī)的識(shí)別。在hadoop大數(shù)據(jù)分析平臺(tái)中采用“分布式存儲(chǔ)、并行式計(jì)算”的方法對(duì)整個(gè)風(fēng)場(chǎng)進(jìn)行分析,實(shí)現(xiàn)所有群落中異常風(fēng)機(jī)地識(shí)別。為進(jìn)一步預(yù)測(cè)異常風(fēng)機(jī)的變化特性,采用線性回歸分析方法對(duì)異常風(fēng)機(jī)正常歷史數(shù)據(jù)進(jìn)行建模,采用實(shí)時(shí)數(shù)據(jù)對(duì)模型進(jìn)行殘差預(yù)測(cè)。結(jié)合現(xiàn)場(chǎng)經(jīng)驗(yàn)設(shè)置合理的預(yù)測(cè)殘差預(yù)警閾值,從而實(shí)現(xiàn)異常風(fēng)機(jī)的故障預(yù)警。
[Abstract]:The traditional fan fault early warning is usually realized by setting a constant early warning threshold of a single variable, but under the actual complex working conditions, this method is easy to lead to false alarm of the fault, and there is not enough time to report or reserve the check. At different ambient temperatures, the operation status of the fan is not exactly the same, grid-connected power, the temperature of each component is not the same, only rely on constant early warning value can not meet the requirements of early warning under complex and changeable working conditions. In order to solve this problem, this paper presents a method of identification and fault early warning of abnormal fans in fan community based on big data analysis. Based on the study of the operation status of all the fans in a large wind farm in Chigu area of Hebei Province, and combined with the collation and analysis of the relevant historical data in the field SCADA system, the fan community with similar operating conditions in the wind field is divided by cluster analysis. Based on the statistical principle, the fan temperature parameters in each community are distributed in the box, and the fans with outlier characteristics in the community are identified according to the distribution characteristics of the outliers in the box diagram. On this basis, the significance difference analysis method is used to judge the abnormal significance of the outlier fan, and the abnormal operation of the outlier fan is identified. In order to eliminate the interference caused by accidental factors, the statistical analysis method of abnormal rate of sliding window is used to eliminate the interference of singularity of wind turbine, and the identification of abnormal fan in fan community is realized. In hadoop big data analysis platform, the method of "distributed storage and parallel calculation" is used to analyze the whole wind field, and the identification of abnormal fan in all communities is realized. In order to further predict the variation characteristics of abnormal fan, linear regression analysis method is used to model the normal history data of abnormal fan, and real-time data are used to predict the residual error of the model. Combined with the field experience, a reasonable prediction residual early warning threshold is set to realize the fault early warning of abnormal fan.
【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(lèi)號(hào)】：TP311.13;TM614

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭鵬;姜漫利;李航濤;;基于運(yùn)行數(shù)據(jù)和高斯過(guò)程回歸的風(fēng)電機(jī)組發(fā)電性能分析與監(jiān)測(cè)[J];電力自動(dòng)化設(shè)備;2016年08期

2 魏書(shū)榮;何之倬;唐征歧;周杰;;海上風(fēng)電機(jī)組的在線監(jiān)測(cè)與故障預(yù)警[J];上海電力學(xué)院學(xué)報(bào);2014年06期

3 盧建昌;樊圍國(guó);;大數(shù)據(jù)時(shí)代下數(shù)據(jù)挖掘技術(shù)在電力企業(yè)中的應(yīng)用[J];廣東電力;2014年09期

4 顧煜炯;蘇璐瑋;鐘陽(yáng);徐婷;;基于區(qū)間劃分的風(fēng)電齒輪箱在線故障預(yù)警方法[J];電力科學(xué)與工程;2014年08期

5 孫翔;何文林;邱煒;李晨;;基于顯著性差異的油浸倒置式電流互感器氫氣閾值分析[J];浙江電力;2014年06期

6 李輝;楊超;李學(xué)偉;季海婷;秦星;陳耀君;楊東;唐顯虎;;風(fēng)機(jī)電動(dòng)變槳系統(tǒng)狀態(tài)特征參量挖掘及異常識(shí)別[J];中國(guó)電機(jī)工程學(xué)報(bào);2014年12期

7 童超;郭鵬;;基于特征選擇和BP神經(jīng)網(wǎng)絡(luò)的風(fēng)電機(jī)組故障分類(lèi)監(jiān)測(cè)研究[J];動(dòng)力工程學(xué)報(bào);2014年04期

8 王珊;蘇璐瑋;顧煜炯;楊昆;;變工況特性下的風(fēng)電軸承早期故障診斷方法[J];電力科學(xué)與工程;2014年03期

9 孫建平;朱雯;翟永杰;葛建宏;;基于MSET方法的風(fēng)電機(jī)組齒輪箱預(yù)警仿真研究[J];系統(tǒng)仿真學(xué)報(bào);2013年12期

10 許駿龍;李征;;基于支持向量機(jī)的風(fēng)電機(jī)組故障預(yù)警[J];工業(yè)控制計(jì)算機(jī);2013年08期

相關(guān)碩士學(xué)位論文 前2條

1 張小田;基于回歸分析的風(fēng)機(jī)主要部件的故障預(yù)測(cè)方法研究[D];華北電力大學(xué);2013年

2 李若昭;風(fēng)電機(jī)組綜合性能評(píng)估與運(yùn)行特性分析[D];華北電力大學(xué)（北京）;2009年

，

本文編號(hào)：2507373