本文選題：轉(zhuǎn)子系統(tǒng) + 信息熵�。� 參考：《蘭州理工大學(xué)》2013年碩士論文

【摘要】：旋轉(zhuǎn)機(jī)械是工業(yè)部門中應(yīng)用最為廣泛的一類機(jī)械設(shè)備,其核心部件為轉(zhuǎn)子-軸承系統(tǒng)。利用振動(dòng)信號(hào)對轉(zhuǎn)子-軸承系統(tǒng)的運(yùn)行進(jìn)行實(shí)時(shí)監(jiān)測、分析與診斷,是保證旋轉(zhuǎn)機(jī)械穩(wěn)定、高效運(yùn)作的重要措施。但隨著旋轉(zhuǎn)機(jī)械設(shè)備結(jié)構(gòu)的大型化和工作環(huán)境的復(fù)雜化,傳統(tǒng)的故障診斷方法已不能滿足現(xiàn)代轉(zhuǎn)子系統(tǒng)故障分類的需求,故智能故障分類方法在轉(zhuǎn)子故障診斷研究中占有愈加重要的地位。然而,現(xiàn)有的智能故障分類方法很難解決通用性與高效性之間的矛盾,且在處理異常故障時(shí)還存在諸多問題。基于此,本研究以轉(zhuǎn)子試驗(yàn)臺(tái)模擬的故障數(shù)據(jù)為研究對象,借鑒生物免疫調(diào)節(jié)理論,研究了免疫陰性選擇算法在轉(zhuǎn)子故障數(shù)據(jù)分類中的應(yīng)用。并且采用信息熵方法來定量的對故障信息進(jìn)行特征提取,進(jìn)而對數(shù)據(jù)進(jìn)行了歸一化處理,最后設(shè)計(jì)了適合典型轉(zhuǎn)子故障識(shí)別的分類器。開展的具體研究工作與獲得的研究結(jié)論如下： 1)在轉(zhuǎn)子實(shí)驗(yàn)臺(tái)上模擬了四種典型故障,分析了四種故障的機(jī)理。在此基礎(chǔ)上分析了信號(hào)在時(shí)域的奇異譜熵、頻域的功率譜熵、時(shí)頻域的小波能譜熵和小波空間譜熵,并計(jì)算了四種故障信號(hào)的熵帶,以四類譜熵為原始數(shù)據(jù),對數(shù)據(jù)進(jìn)行歸一化處理,并建立了訓(xùn)練樣本集和測試樣本集。 2)分析了Forrest陰性選擇算法、RNS算法與V-detector算法產(chǎn)生檢測器的優(yōu)缺點(diǎn),進(jìn)而對V-detector算法產(chǎn)生檢測器階段進(jìn)行了兩方面的改進(jìn)：①改變接受和拒絕零假設(shè)的條件,使生成檢測器的數(shù)目與預(yù)期覆蓋率沒有直接關(guān)系,在覆蓋率提高時(shí),檢測器數(shù)目沒有明顯增加；②對生成的檢測器集進(jìn)行優(yōu)化,使檢測器間的重疊覆蓋現(xiàn)象得到改善,且實(shí)現(xiàn)了降低“黑洞的數(shù)目”的目的。 3)針對V-detector算法在檢測階段只能識(shí)別自我和非我的缺陷,借鑒SVM中“有向無環(huán)圖分類法(directed acyclic gragh)",設(shè)計(jì)出能夠識(shí)別多種轉(zhuǎn)子故障的分類器,并對比了改進(jìn)后V-detector算法與V-detector算法的分類效果,表明前者的分類效果更優(yōu)。 4)基于改進(jìn)后V-detector算法流程,開發(fā)了一套基于MATLAB GUI的轉(zhuǎn)子故障數(shù)據(jù)分類系統(tǒng)。此系統(tǒng)由三個(gè)子系統(tǒng)組成。子系統(tǒng)一：實(shí)現(xiàn)對振動(dòng)信號(hào)的消噪分析,頻譜分析,軸心軌跡分析等；子系統(tǒng)二：實(shí)現(xiàn)熵值數(shù)據(jù)的歸一化；子系統(tǒng)三：實(shí)現(xiàn)兩種算法分類的效果對比。在轉(zhuǎn)子實(shí)驗(yàn)臺(tái)上的應(yīng)用效果理想。 研究表明,免疫陰性選擇算法作為人工免疫算法的核心算法,其在故障診斷辨識(shí)中的應(yīng)用具有很大的研究空間和研究價(jià)值,該算法的思想為提高智能故障診斷質(zhì)量提供了新思想和新方法。
[Abstract]:Rotating machinery is the most widely used type of mechanical equipment in the industrial sector, its core component is rotor-bearing system. Using vibration signals to monitor, analyze and diagnose the rotor-bearing system in real time is an important measure to ensure the stable and efficient operation of the rotating machinery. However, with the large-scale structure of rotating machinery and complicated working environment, the traditional fault diagnosis method can not meet the needs of modern rotor system fault classification. Therefore, intelligent fault classification plays an increasingly important role in rotor fault diagnosis. However, the existing intelligent fault classification methods are difficult to solve the contradiction between universality and efficiency, and there are still many problems in dealing with abnormal faults. Based on this, the application of immune negative selection algorithm in rotor fault data classification is studied based on the theory of biological immune regulation. And the information entropy method is used to quantitatively extract the fault information, and then the data is normalized. Finally, a classifier suitable for the typical rotor fault identification is designed. The specific research work carried out and the conclusions obtained are as follows: 1) four typical faults are simulated on the rotor test bench, and the mechanism of the four faults is analyzed. On this basis, the singular spectral entropy in time domain, power spectral entropy in frequency domain, wavelet spectrum entropy in time-frequency domain and wavelet space spectral entropy in time-frequency domain are analyzed. The entropy bands of four kinds of fault signals are calculated, and the four kinds of spectral entropy are taken as the original data. The data is normalized and the training sample set and the test sample set are established. 2) the advantages and disadvantages of Forrest negative selection algorithm and V-detector algorithm generation detector are analyzed, and then two improvements are made to the stage of V-detector algorithm generating detector: 1, which changes the condition of accepting and rejecting zero hypothesis. The number of generated detectors is not directly related to the expected coverage. When the coverage increases, the number of detectors is not significantly increased and the generated detector sets are optimized, so that the overlap coverage between detectors is improved. The aim of reducing the number of black holes is achieved. 3) aiming at the defect that V-detector algorithm can only recognize self and non-self in detection stage, a classifier which can identify many kinds of rotor faults is designed by referring to "directed acyclic graghs" in SVM. The classification effect of the improved V-detector algorithm and the V-detector algorithm is compared, which shows that the former has better classification effect. 4) based on the improved V-detector algorithm, a rotor fault data classification system based on MATLAB GUI is developed. The system consists of three subsystems. Subsystem 1: noise reduction analysis of vibration signal, spectrum analysis, axis trajectory analysis, etc.; Subsystem 2: normalization of entropy data; Subsystem 3: comparison of the results of the two algorithms. The application effect on the rotor test bench is ideal. The research shows that the immune negative selection algorithm is the core algorithm of artificial immune algorithm, and its application in fault diagnosis and identification has great research space and research value. The idea of this algorithm provides a new idea and method for improving the quality of intelligent fault diagnosis.
【學(xué)位授予單位】：蘭州理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號(hào)】：TH165.3;TP311.13

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 洪征;吳禮發(fā);王元元;;應(yīng)用改進(jìn)的V-detector算法檢測蠕蟲[J];北京郵電大學(xué)學(xué)報(bào);2007年02期

2 楊江云,李蓓智,楊建國,毛志敏;人工免疫機(jī)理在故障診斷中的應(yīng)用[J];東華大學(xué)學(xué)報(bào)(自然科學(xué)版);2004年01期

3 王艷;陳歡歡;沈毅;;有向無環(huán)圖的多類支持向量機(jī)分類算法[J];電機(jī)與控制學(xué)報(bào);2011年04期

4 朱大奇,于盛林;電子電路故障診斷的神經(jīng)網(wǎng)絡(luò)數(shù)據(jù)融合算法[J];東南大學(xué)學(xué)報(bào)(自然科學(xué)版);2001年06期

5 劉樹林;叢蕊;冷建成;王金東;孟慶武;;基于人工免疫系統(tǒng)的設(shè)備在線自主故障診斷策略[J];大慶石油學(xué)院學(xué)報(bào);2005年06期

6 韓中合;王峰;郝曉冬;劉帥;;基于人工免疫算法的機(jī)組振動(dòng)故障診斷方法[J];華北電力大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年03期

7 劉占生;竇唯;王曉偉;趙廣;;基于人工免疫的直升機(jī)傳動(dòng)系統(tǒng)在線異常監(jiān)測方法[J];航空學(xué)報(bào);2007年03期

8 晏義威;張鳳斌;楊曉君;;基于改進(jìn)的可變半徑檢測器實(shí)值否定選擇算法[J];哈爾濱理工大學(xué)學(xué)報(bào);2009年02期

9 班凌瀟;陳新軒;;基于模糊理論的機(jī)械設(shè)備故障診斷方法[J];建設(shè)機(jī)械技術(shù)與管理;2006年05期

10 林圣;何正友;錢清泉;;基于人工免疫算法的輸電線路故障類型識(shí)別新方法[J];電力系統(tǒng)保護(hù)與控制;2011年11期

相關(guān)博士學(xué)位論文 前1條

1 徐銳;人工免疫算法優(yōu)化及其應(yīng)用研究[D];上海大學(xué);2009年

相關(guān)碩士學(xué)位論文 前7條

1 霍天龍;基于支持向量機(jī)的轉(zhuǎn)子系統(tǒng)故障診斷方法研究[D];蘭州理工大學(xué);2011年

2 侯永強(qiáng);旋轉(zhuǎn)機(jī)械轉(zhuǎn)子系統(tǒng)故障診斷方法的應(yīng)用研究[D];大連理工大學(xué);2006年

3 胡軍輝;基于譜熵的故障特征提取與數(shù)據(jù)挖掘技術(shù)研究[D];西北工業(yè)大學(xué);2007年

4 竇遠(yuǎn);旋轉(zhuǎn)機(jī)械故障特征提取技術(shù)及其系統(tǒng)研制[D];北京化工大學(xué);2009年

5 賈超;基于人工免疫算法的電機(jī)故障診斷系統(tǒng)研究[D];武漢理工大學(xué);2010年

6 張弛;旋轉(zhuǎn)機(jī)械典型故障特征提取方法研究[D];北京化工大學(xué);2010年

7 楊娟;轉(zhuǎn)子故障信號(hào)的量化特征提取方法研究[D];蘭州理工大學(xué);2010年

，

本文編號(hào)：1826940