本文選題：風(fēng)力發(fā)電機(jī) + 故障診斷��； 參考：《燕山大學(xué)》2015年碩士論文

【摘要】：隨著風(fēng)力發(fā)電產(chǎn)業(yè)的迅猛發(fā)展以及對風(fēng)力發(fā)電機(jī)系統(tǒng)的穩(wěn)定性、易維護(hù)性等方面要求,風(fēng)力發(fā)電機(jī)狀態(tài)監(jiān)測與故障診斷技術(shù)引起了學(xué)術(shù)界和工程界的廣泛關(guān)注。齒輪箱和轉(zhuǎn)子分別作為風(fēng)力發(fā)電機(jī)組的關(guān)鍵部件,其運行狀態(tài)的實時監(jiān)測和準(zhǔn)確分析,對整個風(fēng)力發(fā)電機(jī)的故障診斷和運行維護(hù)均具有重要的意義。當(dāng)前,振動信號分析法是風(fēng)力機(jī)組故障監(jiān)測與診斷的主要方式,但該方法具有設(shè)備成本高、傳感器安裝不便以及受外界干擾較大等弊端。相比而言,定子電流信號分析法具有不易受外界干擾、信號易采集、信噪比高以及可實現(xiàn)在線監(jiān)測等優(yōu)勢,已被國內(nèi)外專家學(xué)者作為風(fēng)力機(jī)組故障診斷的重要手段。因此,本文采用定子電流信號分析法,對風(fēng)力發(fā)電機(jī)的齒輪和轉(zhuǎn)子進(jìn)行故障診斷研究。主要圍繞以下幾方面內(nèi)容展開:(1)詳細(xì)介紹了風(fēng)力發(fā)電機(jī)的系統(tǒng)構(gòu)成和常見故障,重點對發(fā)電機(jī)轉(zhuǎn)子斷條故障機(jī)理和風(fēng)力發(fā)電機(jī)的齒輪故障振動特性及定子電流檢測原理進(jìn)行分析,為下文進(jìn)行風(fēng)力發(fā)電機(jī)的轉(zhuǎn)子斷條故障檢測和齒輪點蝕故障檢測提供依據(jù)。(2)根據(jù)發(fā)電機(jī)轉(zhuǎn)子斷條故障機(jī)理,提出將譜減法引入定子電流頻譜分析中,并與解析小波變換相結(jié)合進(jìn)行轉(zhuǎn)子斷條故障檢測,實現(xiàn)在負(fù)荷突變情況下轉(zhuǎn)子斷條故障的特征提取和故障檢測。通過數(shù)值仿真信號和模型仿真信號來驗證所提方法的有效性。進(jìn)一步引入故障程度因子來量化轉(zhuǎn)子斷條故障程度。(3)根據(jù)風(fēng)力發(fā)電機(jī)齒輪故障定子電流信號特點,本文將基于經(jīng)驗?zāi)B(tài)分解(EMD)和獨立分量分析(Fast ICA)的故障特征提取方法與樣本熵算法相結(jié)合用于齒輪點蝕故障檢測,有效量化齒輪故障特征向量。通過仿真信號分別驗證基于EMD和Fast ICA故障特征提取算法的有效性和樣本熵用于量化時間序列復(fù)雜度的有效性。通過搭建風(fēng)力發(fā)電機(jī)齒輪點蝕故障診斷平臺,在不同的轉(zhuǎn)速條件下,驗證本文所提方法的有效性。
[Abstract]:With the rapid development of wind power generation industry and the requirements of stability and maintainability of wind turbine system, wind turbine condition monitoring and fault diagnosis technology has attracted extensive attention from academia and engineering circles. Gear box and rotor are the key components of wind turbine. The real-time monitoring and accurate analysis of the running state of the gearbox and rotor are of great significance to the fault diagnosis and operation maintenance of the whole wind turbine. At present, vibration signal analysis is the main method of wind turbine fault monitoring and diagnosis, but this method has the disadvantages of high equipment cost, inconvenient installation of sensors and large external interference. In contrast, the stator current signal analysis method has the advantages of easy external interference, easy signal acquisition, high signal-to-noise ratio and on-line monitoring, and has been used as an important means of wind turbine fault diagnosis by experts and scholars at home and abroad. Therefore, the stator current signal analysis method is used to study the fault diagnosis of the gear and rotor of the wind turbine. Focusing on the following aspects: 1) the system structure and common faults of the wind turbine are introduced in detail. The mechanism of broken bar fault of generator rotor, the vibration characteristics of gear fault and the detection principle of stator current of wind turbine are analyzed. This paper provides a basis for rotor broken bar fault detection and gear pitting fault detection of wind turbine. According to the fault mechanism of generator rotor bar breakage, the spectral subtraction method is introduced into stator current spectrum analysis. Combined with the analytic wavelet transform, the fault detection of rotor bar break is carried out, and the feature extraction and fault detection of rotor broken bar fault are realized in the case of sudden change of load. The validity of the proposed method is verified by numerical simulation signal and model simulation signal. Furthermore, the fault degree factor is introduced to quantify the fault degree of rotor broken bar. (3) according to the characteristics of stator current signal of gear fault of wind turbine, In this paper, the method of fault feature extraction based on empirical mode decomposition (EMD) and independent component analysis (ICA) is combined with the sample entropy algorithm for pitting fault detection of gears. The validity of fault feature extraction algorithm based on EMD and Fast ICA and the validity of sample entropy used to quantize the complexity of time series are verified by simulation signals. By setting up a fault diagnosis platform for pitting corrosion of wind turbine gear, the effectiveness of the proposed method is verified under different rotational speed conditions.
【學(xué)位授予單位】：燕山大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2015
【分類號】：TM315

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 王松嶺;許小剛;劉錦廉;戴謙;;基于符號動力學(xué)信息熵與改進(jìn)神經(jīng)網(wǎng)絡(luò)的風(fēng)機(jī)故障診斷研究[J];華北電力大學(xué)學(xué)報(自然科學(xué)版);2013年04期

相關(guān)碩士學(xué)位論文 前1條

1 李海波;大型風(fēng)力發(fā)電機(jī)齒輪箱故障模糊診斷技術(shù)研究[D];沈陽工業(yè)大學(xué);2014年

，

本文編號：1954814