本文選題：變槳系統(tǒng) + SCADA數(shù)據(jù)��； 參考：《北京交通大學(xué)》2017年碩士論文

【摘要】：風(fēng)能作為一種潔凈、無污染的綠色能源,已成為可再生能源利用的主力軍。然而,高達(dá)25%～30%的運行和維護成本嚴(yán)重制約著風(fēng)電行業(yè)的發(fā)展。同時,隨著我國近10年風(fēng)電技術(shù)的迅速發(fā)展,大型風(fēng)場的SCADA(Supervisory Control And Data Acquisition,數(shù)據(jù)采集與監(jiān)視控制)系統(tǒng)積累了大量歷史數(shù)據(jù),且運行中的風(fēng)電機組也每時每刻都在產(chǎn)生實時數(shù)據(jù)。這些數(shù)據(jù)蘊含著與風(fēng)機運行和設(shè)備狀態(tài)有關(guān)的豐富信息。如何利用這些閑置的SCADA數(shù)據(jù)進(jìn)行風(fēng)機運行狀態(tài)的評估與預(yù)測,無疑具有重要的現(xiàn)實意義和學(xué)術(shù)價值。因此,本文針對這一問題展開如下研究:1.基于SCADA數(shù)據(jù)的變槳系統(tǒng)狀態(tài)特征參數(shù)提取方法研究。在深入研究變槳系統(tǒng)結(jié)構(gòu)和故障機理的基礎(chǔ)上,結(jié)合某風(fēng)場級綜合監(jiān)測系統(tǒng),采用ReliefF算法和互信息技術(shù)挖掘其SCADA數(shù)據(jù)中與變槳系統(tǒng)運行狀態(tài)相關(guān)的特征參數(shù)。定性和定量仿真測試表明,ReliefF算法與采用互信息技術(shù)及不進(jìn)行數(shù)據(jù)預(yù)處理方法(即將所有故障參數(shù)都作為模型輸入)相比,訓(xùn)練速度更快,故障分類準(zhǔn)確率更高。2.基于ReliefF算法提取的變槳系統(tǒng)預(yù)處理數(shù)據(jù),探討支持向量回歸預(yù)測(SVR)模型參數(shù)尋優(yōu)及應(yīng)用于變槳系統(tǒng)的狀態(tài)評估及預(yù)測問題。首先采用交叉驗證法和網(wǎng)格搜索法(CV)進(jìn)行SVR模型參數(shù)的尋優(yōu)。然后,將功率輸出作為SVR模型的決策參數(shù),建立SVR回歸預(yù)測模型。針對隨機干擾因素,采用滑動窗口殘差估計方法分析預(yù)測模型的殘差趨勢,進(jìn)而評估變槳系統(tǒng)運行狀態(tài)。與神經(jīng)網(wǎng)絡(luò)的對比實驗表明,本文所建SVR模型具有較好的狀態(tài)評估與預(yù)測能力。3.基于小世界鄰域粒子群優(yōu)化支持向量機(SWPSO-SVR)的變槳系統(tǒng)狀態(tài)評估與預(yù)測模型研究。由于CV參數(shù)尋優(yōu)方法存在計算量大,效率和精度低的缺點,在數(shù)據(jù)量大的情況下,所建SVR模型不利于實際應(yīng)用。因此本文進(jìn)一步探討SVR參數(shù)尋優(yōu)問題,提出SWPSO-SVR改進(jìn)算法。對比CV-SVR算法可知,SWPSO-SVR算法具有精度高、收斂速度快、不易陷入局部極小值等優(yōu)點。結(jié)合某風(fēng)場SCADA數(shù)據(jù)測試分析,驗證了改進(jìn)模型用于變槳系統(tǒng)狀態(tài)評估與預(yù)測的有效性和實用性。4.變槳系統(tǒng)運行狀態(tài)監(jiān)測方法工程應(yīng)用系統(tǒng)研究。應(yīng)用Matlab軟件中的GUI開發(fā)可與綜合監(jiān)控系統(tǒng)連接的交互式平臺,以拓展綜合監(jiān)控系統(tǒng)變槳系統(tǒng)故障預(yù)測與報警的功能,為變槳系統(tǒng)的安全運行維護提供決策支持。綜上,風(fēng)場SCADA數(shù)據(jù)蘊含著豐富的運行狀態(tài)信息,通過分析其數(shù)據(jù)變化規(guī)律,可評估和預(yù)測變槳系統(tǒng)的健康運行狀態(tài)。本文研究具有一定的經(jīng)濟性和實用性,可實現(xiàn)變槳系統(tǒng)在線早期故障預(yù)警的目的。
[Abstract]:As a clean and clean green energy, wind energy has become the main force of renewable energy utilization. However, up to 25% of the operating and maintenance costs seriously restrict the development of wind power industry. At the same time, with the rapid development of wind power technology in China in the past 10 years, the SCADA(Supervisory Control And Data requirement (data acquisition and Monitoring Control) system of large wind field has accumulated a large amount of historical data, and the running wind turbine is producing real-time data every moment. These data contain rich information about fan operation and equipment status. How to use these idle SCADA data to evaluate and predict the running state of fan is undoubtedly of great practical significance and academic value. Therefore, this paper focuses on this problem as follows: 1. Research on extraction method of State characteristic parameters of variable Propeller system based on SCADA data. On the basis of deep research on the structure and fault mechanism of the variable propeller system, the ReliefF algorithm and mutual information technology are used to mine the characteristic parameters related to the running state of the variable propeller system in its SCADA data, combined with the integrated monitoring system of a certain wind field. The qualitative and quantitative simulation results show that the algorithm has higher training speed and higher fault classification accuracy than using mutual information technology and data preprocessing method (that is, using all fault parameters as model input). Based on the preprocessing data of variable propeller system extracted by ReliefF algorithm, the parameter optimization of support vector regression prediction (SVR) model and its application to the condition evaluation and prediction of variable propeller system are discussed. First, cross validation method and grid search method are used to optimize the parameters of SVR model. Then, the power output is taken as the decision parameter of the SVR model, and the SVR regression prediction model is established. Aiming at the random disturbance factors, the residual trend of the prediction model is analyzed by using the sliding window residual estimation method, and then the running state of the propeller system is evaluated. The comparison experiment with neural network shows that the proposed SVR model has a good capability of state evaluation and prediction. Research on the State Evaluation and Prediction Model of variable Propeller system based on Small-world Neighbourhood Particle Swarm Optimization support Vector Machine (SWPSO-SVR). Because the CV parameter optimization method has the disadvantages of large calculation, low efficiency and precision, the established SVR model is unfavorable for practical application in the case of large amount of data. Therefore, this paper further discusses the optimization problem of SVR parameters, and proposes an improved SWPSO-SVR algorithm. Compared with the CV-SVR algorithm, the SWPSO-SVR algorithm has the advantages of high accuracy, fast convergence speed and difficulty in falling into local minima. The effectiveness and practicability of the improved model for the state evaluation and prediction of a variable propeller system are verified by combining the SCADA data of a certain wind field. Research on Engineering Application system of variable Propeller system running condition Monitoring method. The interactive platform which can be connected with the integrated monitoring system is developed by using the GUI of Matlab software to expand the function of fault prediction and alarm of the integrated monitoring system and to provide decision support for the safe operation and maintenance of the variable propeller system. In a word, the wind field SCADA data contain abundant information of running state. By analyzing the variation law of the data, the healthy running state of the variable propeller system can be evaluated and predicted. The research in this paper has certain economy and practicability, and can realize the purpose of on-line early fault warning of the variable propeller system.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TM315

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 肖成;劉作軍;張磊;;基于SCADA系統(tǒng)的風(fēng)電變槳故障預(yù)測方法研究[J];可再生能源;2017年02期

2 董興輝;閆慧麗;張曉亮;;基于FDA貢獻(xiàn)圖的風(fēng)電機組變槳系統(tǒng)故障定位[J];可再生能源;2017年01期

3 趙洪山;張健平;王桂蘭;連莎莎;;基于狀態(tài)估計的風(fēng)電機組液壓變槳距系統(tǒng)故障檢測[J];電力系統(tǒng)自動化;2016年22期

4 李輝;胡姚剛;李洋;楊東;梁媛媛;歐陽海黎;蘭涌森;;大功率并網(wǎng)風(fēng)電機組狀態(tài)監(jiān)測與故障診斷研究綜述[J];電力自動化設(shè)備;2016年01期

5 王東;史曉霞;尹交英;;不同核函數(shù)的支持向量機用于空調(diào)負(fù)荷預(yù)測的對比研究[J];電工技術(shù)學(xué)報;2015年S1期

6 郭鵬;王雪茹;;風(fēng)電機組高斯過程回歸塔架振動監(jiān)測研究[J];動力工程學(xué)報;2015年05期

7 王爽心;楊成慧;;基于層連優(yōu)化的新型小世界神經(jīng)網(wǎng)絡(luò)[J];控制與決策;2014年01期

8 梁穎;方瑞明;;基于SCADA和支持向量回歸的風(fēng)電機組狀態(tài)在線評估方法[J];電力系統(tǒng)自動化;2013年14期

9 李輝;楊超;趙斌;唐顯虎;劉行中;;風(fēng)電機組電動變槳系統(tǒng)建模及運行特性評估與測試[J];電力系統(tǒng)自動化;2013年11期

10 謝松汕;許寶杰;吳國新;左云波;;基于狀態(tài)監(jiān)測與故障診斷在風(fēng)電機組上的應(yīng)用分析[J];電子測試;2013年08期

相關(guān)博士學(xué)位論文 前3條

1 顏永龍;風(fēng)電機組運行狀態(tài)評估與短期可靠性預(yù)測方法研究[D];重慶大學(xué);2015年

2 呂寧;基于數(shù)據(jù)驅(qū)動的故障診斷模型及算法研究[D];哈爾濱理工大學(xué);2009年

3 劉靖旭;支持向量回歸的模型選擇及應(yīng)用研究[D];國防科學(xué)技術(shù)大學(xué);2006年

相關(guān)碩士學(xué)位論文 前10條

1 李新麗;大型風(fēng)力發(fā)電機組的故障診斷研究[D];華北電力大學(xué);2016年

2 趙龍;基于NWP和改進(jìn)BP神經(jīng)網(wǎng)絡(luò)的風(fēng)電功率預(yù)測研究[D];北京交通大學(xué);2015年

3 鄒迪;基于狀態(tài)監(jiān)測信息的風(fēng)力發(fā)電機故障預(yù)警與短期可靠性評估研究[D];重慶大學(xué);2014年

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

5 朱雯;風(fēng)電機組運行狀態(tài)監(jiān)測與分析[D];華北電力大學(xué);2013年

6 吳樹梁;兆瓦級風(fēng)電齒輪箱故障監(jiān)測及分析[D];山東大學(xué);2012年

7 李濤;支持向量機在風(fēng)電功率預(yù)測中的應(yīng)用研究[D];北京交通大學(xué);2012年

8 馬楊;風(fēng)電機組的實時可靠性評價及預(yù)測研究[D];華北電力大學(xué);2012年

9 韓敬宇;基于聲發(fā)射技術(shù)的風(fēng)電葉片裂紋無線監(jiān)測系統(tǒng)研究[D];北京化工大學(xué);2010年

10 楊明明;大型風(fēng)電機組故障模式統(tǒng)計分析及故障診斷[D];華北電力大學(xué)（北京）;2009年

，

本文編號：1792735