發(fā)布時(shí)間：2018-05-25 19:17

  本文選題：軸承 + 聲發(fā)射��； 參考：《沈陽(yáng)工業(yè)大學(xué)》2017年碩士論文

【摘要】：與核能發(fā)電和火力發(fā)電相比,風(fēng)力發(fā)電更綠色環(huán)保、資源充足。隨著風(fēng)力發(fā)電行業(yè)迅猛發(fā)展,風(fēng)機(jī)裝機(jī)量逐年遞增。如何及時(shí)發(fā)現(xiàn)風(fēng)機(jī)故障,準(zhǔn)確判斷故障類型,保證風(fēng)力發(fā)電機(jī)組安全可靠運(yùn)行成為世界各國(guó)主要研究的問(wèn)題。本文以風(fēng)機(jī)軸承為研究對(duì)象,搭建風(fēng)機(jī)軸承故障監(jiān)測(cè)系統(tǒng),利用該系統(tǒng)對(duì)軸承運(yùn)行狀態(tài)進(jìn)行實(shí)時(shí)監(jiān)測(cè)和故障診斷研究。該系統(tǒng)利用光柵傳感器提取軸承聲發(fā)射信號(hào)。當(dāng)軸承發(fā)生故障時(shí),聲發(fā)射現(xiàn)象會(huì)引起軸承表面位移變化;光柵傳感器會(huì)將位移變化量轉(zhuǎn)換成電信號(hào);AD9467采集傳感器輸出的電信號(hào);STM32F429對(duì)信號(hào)進(jìn)行濾波、細(xì)分和故障診斷。故障發(fā)生時(shí),該系統(tǒng)有報(bào)警提示功能。此外,該系統(tǒng)還具有數(shù)據(jù)存儲(chǔ)功能和網(wǎng)絡(luò)傳輸功能。光柵傳感器的分辨力決定了軸承故障聲發(fā)射信號(hào)識(shí)別能力。為提高系統(tǒng)故障診斷的精準(zhǔn)性,本文對(duì)莫爾條紋信號(hào)進(jìn)行高倍細(xì)分。首先,通過(guò)智能小波閾值降噪方法對(duì)信號(hào)進(jìn)行小波分解和降噪。其次,針對(duì)莫爾條紋信號(hào)含直流電平、幅值不等、相位不正交等現(xiàn)象,進(jìn)行莫爾條紋信號(hào)補(bǔ)償可有效提高細(xì)分精度。再次,本文對(duì)基于L-M的BP神經(jīng)網(wǎng)絡(luò)莫爾條紋信號(hào)細(xì)分方法進(jìn)行了深入研究。通過(guò)增加新的判斷條件來(lái)改進(jìn)L-M算法,根據(jù)本次訓(xùn)練結(jié)果誤差和上一次訓(xùn)練結(jié)果誤差關(guān)系可以得到新的權(quán)值。該方法能夠提高神經(jīng)網(wǎng)絡(luò)訓(xùn)練速度和結(jié)果精度。將其結(jié)果與RBF神經(jīng)網(wǎng)絡(luò)莫爾條紋細(xì)分方法所得結(jié)果進(jìn)行對(duì)比,實(shí)驗(yàn)結(jié)果表明,基于改進(jìn)L-M的BP神經(jīng)網(wǎng)絡(luò)莫爾條紋信號(hào)細(xì)分方法速度更快、誤差波動(dòng)范圍更小。然后,對(duì)細(xì)分后得到的位移值做頻譜分析可得不同頻率對(duì)應(yīng)的幅值。最后,通過(guò)比較幅值和軸承臨界故障時(shí)的幅值可以判斷軸承是否有故障。仿真結(jié)果和實(shí)驗(yàn)測(cè)試結(jié)果表明,基于改進(jìn)L-M的BP神經(jīng)網(wǎng)絡(luò)莫爾條紋信號(hào)細(xì)分方法可以實(shí)現(xiàn)20000細(xì)分,分辨力達(dá)到1nm,能夠識(shí)別納米級(jí)軸承裂紋故障的聲發(fā)射信號(hào)。表明光柵傳感器通過(guò)莫爾條紋信號(hào)細(xì)分后可以用于提取軸承故障聲發(fā)射信號(hào),通過(guò)小波神經(jīng)網(wǎng)絡(luò)故障診斷方法能判斷出軸承裂紋故障。
[Abstract]:Compared with nuclear power generation and thermal power generation, wind power generation is greener and more resources. With the rapid development of the wind power generation industry, the volume of wind turbines is increasing year by year. How to find out the blower fault in time, accurately determine the type of fault and ensure the safe and reliable operation of the wind turbine is the main problem in the world. This paper is based on the wind turbine shaft. As the research object, a fault monitoring system for the bearing of the fan is built, and the system is used to monitor and diagnose the bearing state of the bearing in real time. The system uses a grating sensor to extract the acoustic emission signal of the bearing. When the bearing occurs, the acoustic emission will cause the change of the displacement of the bearing surface, and the grating sensor will change the displacement. The electrical signal is converted into an electrical signal; AD9467 takes the electrical signal output by the sensor; STM32F429 filters, subdivides and diagnoses the signal. When the fault occurs, the system has alarm and prompt function. In addition, the system also has data storage function and network transmission function. The resolution of the grating sensor determines the identification of the acoustic emission signal of the bearing fault. In order to improve the accuracy of the system fault diagnosis, the moire stripe signal is subdivided in high times. First, wavelet decomposition and noise reduction are carried out by the intelligent wavelet threshold denoising method. Secondly, the moire fringe signal compensation can be effectively proposed for the moire fringe signal containing the DC level, the amplitude is unequal and the phase is not orthogonal. Thirdly, the L-M based BP neural network Moire stripe signal subdivision method is deeply studied in this paper. By adding new judgment conditions to improve the L-M algorithm, new weights can be obtained according to the error of this training result and the error relationship of the previous training results. This method can improve the training speed of neural network and the training speed of neural network. The result is compared with the results obtained from the RBF neural network moire fringe subdivision method. The experimental results show that the moire fringe signal subdivision method based on the improved L-M neural network is faster and the range of error fluctuation is smaller. Then, the spectrum analysis of the displacement values obtained after the subdivision can be obtained with the corresponding amplitude of different frequencies. Finally, by comparing the amplitude and the amplitude of the critical fault of the bearing, the fault of the bearing can be judged. The simulation results and the experimental test results show that the 20000 subdivision method based on the improved L-M BP neural network moire fringe signal subdivision can be realized and the resolution can reach 1nm. After subdivision of the moire fringe signal, the light grating sensor can be used to extract the acoustic emission signal of the bearing fault, and the fault of the bearing crack can be judged by the wavelet neural network fault diagnosis method.
【學(xué)位授予單位】：沈陽(yáng)工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TM614;TP212

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 丁旭;李彬華;楊曉晗;;一種基于FPGA的光柵信號(hào)細(xì)分方法[J];傳感技術(shù)學(xué)報(bào);2016年06期

2 劉小康;陳自然;王先全;鄭方燕;;空間精密位移信號(hào)軟細(xì)分方法研究[J];儀器儀表學(xué)報(bào);2016年03期

3 高旭;萬(wàn)秋華;盧新然;杜穎財(cái);陳偉;;莫爾條紋光電信號(hào)自動(dòng)補(bǔ)償系統(tǒng)[J];紅外與激光工程;2016年02期

4 馮濟(jì)琴;劉浩;陳自然;鄭方燕;;基于域變換和灰色預(yù)測(cè)的光柵信號(hào)軟細(xì)分方法[J];儀器儀表學(xué)報(bào);2016年02期

5 李紅延;周云龍;田峰;李松;孫天寶;;一種新的小波自適應(yīng)閾值函數(shù)振動(dòng)信號(hào)去噪算法[J];儀器儀表學(xué)報(bào);2015年10期

6 郭雨梅;盧弘博;;光柵莫爾條紋信號(hào)非正弦性誤差修正[J];沈陽(yáng)工業(yè)大學(xué)學(xué)報(bào);2015年06期

7 范國(guó)鵬;周莉;殷明;李振華;蔣濤;周文慶;;基于時(shí)空轉(zhuǎn)換法的正弦波光柵尺位移測(cè)量系統(tǒng)設(shè)計(jì)[J];傳感技術(shù)學(xué)報(bào);2015年09期

8 左洋;龍科慧;劉金國(guó);劉兵;周磊;喬克;;非均勻采樣莫爾條紋信號(hào)的分析與處理[J];光學(xué)精密工程;2015年04期

9 張曉濤;唐力偉;王平;鄧士杰;;軸承故障聲發(fā)射信號(hào)多頻帶共振解調(diào)方法[J];振動(dòng).測(cè)試與診斷;2015年02期

10 郭福平;段志宏;孫志偉;;基于包絡(luò)譜分析的滾動(dòng)軸承滾動(dòng)體故障聲發(fā)射診斷研究[J];組合機(jī)床與自動(dòng)化加工技術(shù);2015年02期

，

本文編號(hào)：1934363