【摘要】：風(fēng)電機(jī)組運(yùn)行環(huán)境惡劣,受氣候等多種不確定因素的影響,容易出現(xiàn)性能與狀態(tài)劣化。關(guān)鍵部件一旦失效,檢修時間較長,增加風(fēng)電場的運(yùn)維成本。軸承作為風(fēng)電機(jī)組中關(guān)鍵的部件,其運(yùn)行狀況對整臺設(shè)備的可靠性具有重要的影響。本文基于風(fēng)電機(jī)組的監(jiān)控與數(shù)據(jù)采集(Supervisory Control And Data Acquisition,SCADA)系統(tǒng)運(yùn)行數(shù)據(jù),從健康評估模型和劣化趨勢預(yù)測兩方面展開對軸承的狀態(tài)的研究。建立軸承健康評估模型和趨勢預(yù)測模型。本文以風(fēng)電機(jī)組軸承溫度為研究對象,考慮軸承溫度受風(fēng)速和功率的影響,以Bin方法進(jìn)行劃分工況,利用相對評價(jià)標(biāo)準(zhǔn)遴選軸承各工況的健康狀態(tài)樣本集;利用最小二乘擬合健康樣本數(shù)據(jù),形成軸承溫度健康狀態(tài)評估模型,在此基礎(chǔ)之上,結(jié)合實(shí)際運(yùn)行狀態(tài)的上下閾值,引入劣化度概念。考慮到風(fēng)電機(jī)組軸承劣化趨勢非線性的問題,進(jìn)一步應(yīng)用時間序列神經(jīng)網(wǎng)絡(luò),建立風(fēng)電機(jī)組軸承的劣化趨勢預(yù)測模型。以風(fēng)電場實(shí)際數(shù)據(jù)為例,對模型進(jìn)行驗(yàn)證并與其它模型進(jìn)行比較。應(yīng)用前面建立模型評估時,還存在風(fēng)電機(jī)組軸承劣化趨勢非穩(wěn)定性的問題,這將會影響預(yù)測結(jié)果。于是在預(yù)測之前,應(yīng)用EEMD(Ensemble Empirical Mode Decomposition)方法,將具有非平穩(wěn)性特性的劣化趨勢分解為一系列相對平穩(wěn)的分量,利用時間序列神經(jīng)網(wǎng)絡(luò)對各分量開展預(yù)測,將所有分量的預(yù)測結(jié)果疊加得到最終的預(yù)測結(jié)果。研究結(jié)果表明,對于非線性數(shù)據(jù),時間序列神經(jīng)網(wǎng)絡(luò)預(yù)測模型更具有一定的優(yōu)勢,精度得到提高,通常能滿足風(fēng)電機(jī)組軸承對監(jiān)測參數(shù)的需求,對發(fā)現(xiàn)早期機(jī)組潛在的故障具有很好的實(shí)用性。對于具有較強(qiáng)非線性和非穩(wěn)定的時間序列,本文的組合預(yù)測模型能更有效地跟蹤風(fēng)機(jī)軸承健康狀態(tài)劣化趨勢,且能明顯提高預(yù)測的精度。
[Abstract]:Because of the bad operating environment and the influence of many uncertain factors such as climate, wind turbine is prone to performance and condition deterioration. Once the key components fail, the overhaul time is longer, which increases the cost of operation and maintenance of wind farm. As a key component of wind turbine, the operation condition of bearing has an important influence on the reliability of the whole equipment. In this paper, based on the monitoring and data collection of wind turbine, the operation data of (Supervisory Control And Data requirement SCADA system is collected, and the research on the state of bearing is carried out from two aspects: health assessment model and deterioration trend prediction. Establish bearing health assessment model and trend prediction model. In this paper, bearing temperature of wind turbine unit is taken as research object, bearing temperature is affected by wind speed and power, working conditions are divided by Bin method, and healthy state sample set of each condition of bearing is selected by relative evaluation standard. Based on the least square fitting of health sample data, an evaluation model of bearing temperature health state is established. Based on this model, the concept of deterioration degree is introduced in combination with the upper and lower threshold of actual operation state. Considering the nonlinear problem of bearing deterioration trend of wind turbine, a prediction model of wind turbine bearing deterioration trend is established by using time series neural network. Taking the actual data of wind farm as an example, the model is verified and compared with other models. The instability of bearing deterioration trend of wind turbine is also existed when the model is used to evaluate the model, which will affect the prediction results. Before prediction, EEMD (Ensemble Empirical Mode Decomposition) method is used to decompose the deterioration trend with non-stationary property into a series of relatively stationary components, and the time series neural network is used to predict each component. The final prediction results are obtained by superposing the prediction results of all components. The research results show that the time series neural network prediction model has some advantages and the accuracy is improved for nonlinear data, and it can usually meet the needs of the monitoring parameters of wind turbine bearings. It has good practicability to discover the potential fault of the early generation unit. For the time series with strong nonlinearity and instability, the combined prediction model in this paper can more effectively track the trend of deterioration of the health state of fan bearings, and can obviously improve the accuracy of prediction.
【學(xué)位授予單位】：華北電力大學(xué)(北京)
【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 胡姚剛;李輝;廖興林;宋二兵;歐陽海黎;劉志祥;;風(fēng)電軸承性能退化建模及其實(shí)時剩余壽命預(yù)測[J];中國電機(jī)工程學(xué)報(bào);2016年06期

2 李輝;胡姚剛;李洋;楊東;歐陽海黎;蘭涌森;唐顯虎;;基于溫度特征量的風(fēng)電機(jī)組關(guān)鍵部件劣化漸變概率分析[J];電力自動化設(shè)備;2015年11期

3 王賀;胡志堅(jiān);張翌暉;李晨;楊楠;王戰(zhàn)勝;;基于聚類經(jīng)驗(yàn)?zāi)B(tài)分解和最小二乘支持向量機(jī)的短期風(fēng)速組合預(yù)測[J];電工技術(shù)學(xué)報(bào);2014年04期

4 董玉亮;李亞瓊;曹海斌;何成兵;顧煜炯;;基于運(yùn)行工況辨識的風(fēng)電機(jī)組健康狀態(tài)實(shí)時評價(jià)方法[J];中國電機(jī)工程學(xué)報(bào);2013年11期

5 張小田;鄢盛騰;周雪青;趙洪山;;基于狀態(tài)監(jiān)測的風(fēng)電機(jī)組主軸承早期故障預(yù)測方法[J];廣東電力;2012年11期

6 李方溪;陳桂明;朱露;劉希亮;李勝朝;;基于經(jīng)驗(yàn)?zāi)B(tài)分解與RBF神經(jīng)網(wǎng)絡(luò)的混合預(yù)測[J];振動.測試與診斷;2012年05期

7 周松林;茆美琴;蘇建徽;;基于小波分析與支持向量機(jī)的風(fēng)速預(yù)測[J];太陽能學(xué)報(bào);2012年03期

8 蘇連成;李興林;李小俚;張燕遼;張仰平;;風(fēng)電機(jī)組軸承的狀態(tài)監(jiān)測和故障診斷與運(yùn)行維護(hù)[J];軸承;2012年01期

9 肖文斌;陳進(jìn);周宇;王志陽;趙發(fā)剛;;小波包變換和隱馬爾可夫模型在軸承性能退化評估中的應(yīng)用[J];振動與沖擊;2011年08期

10 張玉;;基于振動幅域參數(shù)指標(biāo)的滾動軸承故障診斷[J];機(jī)械制造與自動化;2011年03期

相關(guān)博士學(xué)位論文 前3條

1 徐東;球軸承疲勞剩余壽命分析與預(yù)測方法研究[D];國防科學(xué)技術(shù)大學(xué);2011年

2 王衍學(xué);機(jī)械故障監(jiān)測診斷的若干新方法及其應(yīng)用研究[D];西安交通大學(xué);2009年

3 熊衛(wèi)華;經(jīng)驗(yàn)?zāi)B(tài)分解方法及其在變壓器狀態(tài)監(jiān)測中的應(yīng)用研究[D];浙江大學(xué);2006年

相關(guān)碩士學(xué)位論文 前6條

1 李卉;基于狀態(tài)監(jiān)測的滾動軸承性能退化評估[D];大連工業(yè)大學(xué);2015年

2 鄭皓;基于多元時間序列的神經(jīng)網(wǎng)絡(luò)短期風(fēng)速預(yù)測模型的研究[D];太原理工大學(xué);2013年

3 李學(xué)偉;基于數(shù)據(jù)挖掘的風(fēng)電機(jī)組狀態(tài)預(yù)測及變槳系統(tǒng)異常識別[D];重慶大學(xué);2012年

4 徐大維;基于時間序列模型的化工設(shè)備狀態(tài)的預(yù)測研究[D];北京化工大學(xué);2009年

5 雷金波;基于邏輯回歸和支持向量機(jī)的設(shè)備狀態(tài)退化評估與趨勢預(yù)測研究[D];上海交通大學(xué);2008年

6 劉穎峰;旋轉(zhuǎn)機(jī)械狀態(tài)監(jiān)測系統(tǒng)的研究與開發(fā)[D];浙江大學(xué);2003年

，

本文編號：2167783