發(fā)布時(shí)間：2018-06-02 13:33

  本文選題：氣閥 + 故障診斷　； 參考：《電子科技大學(xué)》2017年碩士論文

【摘要】：隨著科學(xué)技術(shù)的不斷發(fā)展,機(jī)械故障診斷技術(shù)越來(lái)越受到人們的重視。往復(fù)式壓縮機(jī)作為典型的往復(fù)式機(jī)械,其內(nèi)部結(jié)構(gòu)復(fù)雜且激勵(lì)源眾多,傳統(tǒng)的故障診斷技術(shù)已不能滿足工程實(shí)際的需要。貝葉斯網(wǎng)絡(luò)在處理不確定知識(shí)表達(dá)和推理方面具有獨(dú)特的優(yōu)勢(shì),已在語(yǔ)音識(shí)別、圖像處理、金融分析等多個(gè)領(lǐng)域成功應(yīng)用。因此,本文提出了基于貝葉斯網(wǎng)絡(luò)的氣閥故障診斷方法,該方法以氣閥常見(jiàn)故障為對(duì)象,在研究了貝葉斯網(wǎng)絡(luò)相關(guān)理論的基礎(chǔ)上,從不同的角度建立貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)算法,為其在故障診斷中的應(yīng)用提供了有力的證據(jù)。文章在最后重點(diǎn)構(gòu)建了兩類(lèi)貝葉斯分類(lèi)模型,并將其成功應(yīng)用于氣閥故障診斷中。本文具體工作包含以下幾個(gè)方面:1.闡述了貝葉斯網(wǎng)絡(luò)的基本理論,并簡(jiǎn)單介紹了貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)方法、參數(shù)學(xué)習(xí)方法和常見(jiàn)的四種貝葉斯分類(lèi)器。2.針對(duì)氣閥振動(dòng)加速度信號(hào),首先對(duì)原始信號(hào)進(jìn)行小波閾值去噪,并通過(guò)小波包算法提取了各故障特征向量。將特征向量值與類(lèi)變量值組成的樣本進(jìn)行離散化處理,將此作為貝葉斯分類(lèi)器的輸入。3.針對(duì)氣閥常見(jiàn)故障,本文提出了一種BAN分類(lèi)器算法。該算法首先利用遺傳算法和K2算法構(gòu)造屬性節(jié)點(diǎn)之間的網(wǎng)絡(luò)結(jié)構(gòu),然后加入這些節(jié)點(diǎn)的統(tǒng)一父節(jié)點(diǎn)(類(lèi)節(jié)點(diǎn))構(gòu)造出分類(lèi)模型,運(yùn)用貝葉斯估計(jì)算法進(jìn)行參數(shù)學(xué)習(xí)以獲得各節(jié)點(diǎn)對(duì)應(yīng)的條件概率表。根據(jù)測(cè)試樣本集,以條件屬性值作為證據(jù),可求得測(cè)試樣本的后驗(yàn)概率,最大后驗(yàn)概率所對(duì)應(yīng)的類(lèi)標(biāo)簽即作為該樣本的分類(lèi)結(jié)果。4.針對(duì)氣閥常見(jiàn)故障,本文提出了一種GBN分類(lèi)器算法。該算法首先利用CI測(cè)試去除與當(dāng)前節(jié)點(diǎn)變量無(wú)關(guān)的變量,從而縮小了各節(jié)點(diǎn)的初始候選父節(jié)點(diǎn)集合的范圍;通過(guò)貪心算法不斷更新各節(jié)點(diǎn)的候選父節(jié)點(diǎn),最終獲得所求的分類(lèi)模型。本文利用稀疏分?jǐn)?shù)的方法進(jìn)行故障特征選擇,提取不同數(shù)量的特征集合,并利用GBN分類(lèi)器進(jìn)行分類(lèi)預(yù)測(cè)。實(shí)驗(yàn)結(jié)果表明,通過(guò)該特征選擇方法可以有效地提高氣閥故障診斷正確率和減少計(jì)算的復(fù)雜度。5.總結(jié)了全文,并提出了下一步的研究方向。
[Abstract]:With the development of science and technology, people pay more and more attention to mechanical fault diagnosis technology. As a typical reciprocating machine, the reciprocating compressor has complex internal structure and numerous excitation sources. The traditional fault diagnosis technology can not meet the practical needs of engineering. Bayesian network has a unique advantage in dealing with uncertain knowledge representation and reasoning, and has been successfully applied in speech recognition, image processing, financial analysis and other fields. Therefore, this paper presents a method of valve fault diagnosis based on Bayesian network. This method takes common faults of air valve as an object, and establishes Bayesian network learning algorithm from different angles on the basis of studying relevant theory of Bayesian network. It provides strong evidence for its application in fault diagnosis. Finally, two kinds of Bayesian classification models are constructed and successfully applied to valve fault diagnosis. The specific work of this paper includes the following aspects: 1. The basic theory of Bayesian network is expounded, and the learning methods of Bayesian network structure, parameter learning and four kinds of Bayesian classifiers. For the vibration acceleration signal of the valve, the original signal is firstly de-noised by wavelet threshold, and each fault eigenvector is extracted by wavelet packet algorithm. The sample composed of eigenvector value and class variable value is discretized as the input of Bayesian classifier. In this paper, a BAN classifier algorithm is proposed for the common faults of the valve. Firstly, the network structure between attribute nodes is constructed by genetic algorithm and K2 algorithm, and then the classification model is constructed by adding the unified parent nodes (class nodes) of these nodes. Bayesian estimation algorithm is used for parameter learning to obtain conditional probability tables corresponding to each node. According to the test sample set, the posteriori probability of the test sample can be obtained by taking the conditional attribute value as the evidence. The class label corresponding to the maximum posteriori probability is regarded as the classification result of the sample. In this paper, a GBN classifier algorithm is proposed for the common faults of the valve. Firstly, the CI test is used to remove the variables independent of the current node variables, which reduces the range of the initial candidate parent node set of each node, and updates the candidate parent nodes of each node through greedy algorithm. Finally, the desired classification model is obtained. In this paper, the method of sparse fraction is used for fault feature selection, and different number of feature sets are extracted, and GBN classifier is used for classification and prediction. The experimental results show that this method can effectively improve the accuracy of gas valve fault diagnosis and reduce the computational complexity of .5. This paper summarizes the full text and puts forward the next research direction.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：TH45;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 石新發(fā);劉東風(fēng);周志才;楊琨;;基于PSO聚類(lèi)和特征貢獻(xiàn)度的油液監(jiān)測(cè)信息特征選擇方法[J];潤(rùn)滑與密封;2016年01期

2 文志誠(chéng);曹春麗;周浩;;基于樸素貝葉斯分類(lèi)器的網(wǎng)絡(luò)安全態(tài)勢(shì)評(píng)估方法[J];計(jì)算機(jī)應(yīng)用;2015年08期

3 趙海洋;徐敏強(qiáng);王金東;;有理Hermite插值局部均值分解方法及其往復(fù)壓縮機(jī)故障診斷應(yīng)用[J];機(jī)械工程學(xué)報(bào);2015年01期

4 王金東;代梅;夏法鋒;趙海峰;;基于EMD信息熵和支持向量機(jī)的往復(fù)壓縮機(jī)軸承故障診斷[J];流體機(jī)械;2014年07期

5 吳光文;王昌明;包建東;陳勇;胡揚(yáng)坡;;基于自適應(yīng)閾值函數(shù)的小波閾值去噪方法[J];電子與信息學(xué)報(bào);2014年06期

6 姚成玉;陳東寧;王斌;;基于T-S故障樹(shù)和貝葉斯網(wǎng)絡(luò)的模糊可靠性評(píng)估方法[J];機(jī)械工程學(xué)報(bào);2014年02期

7 胡云安;劉振;宋瑞華;史建國(guó);;爬山法與模式蟻群法混合的貝葉斯優(yōu)化算法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年05期

8 馬晉;江志農(nóng);高金吉;;基于活塞桿軸心位置軌跡的往復(fù)壓縮機(jī)故障診斷技術(shù)研究[J];振動(dòng)工程學(xué)報(bào);2012年04期

9 唐友福;劉樹(shù)林;劉穎慧;姜銳紅;;基于非線性復(fù)雜測(cè)度的往復(fù)壓縮機(jī)故障診斷[J];機(jī)械工程學(xué)報(bào);2012年03期

10 陳曉曦;王延杰;劉戀;;小波閾值去噪法的深入研究[J];激光與紅外;2012年01期

相關(guān)博士學(xué)位論文 前2條

1 劉華文;基于信息熵的特征選擇算法研究[D];吉林大學(xué);2010年

2 蔣良孝;樸素貝葉斯分類(lèi)器及其改進(jìn)算法研究[D];中國(guó)地質(zhì)大學(xué);2009年

相關(guān)碩士學(xué)位論文 前5條

1 馬明;貝葉斯網(wǎng)絡(luò)算法研究及應(yīng)用[D];燕山大學(xué);2014年

2 呂健健;基于貝葉斯網(wǎng)絡(luò)的駕駛員疲勞評(píng)估方法研究[D];大連理工大學(xué);2013年

3 沈佳杰;基于改進(jìn)混合進(jìn)化算法的貝葉斯網(wǎng)絡(luò)結(jié)構(gòu)學(xué)習(xí)[D];浙江大學(xué);2013年

4 祝世豐;貝葉斯網(wǎng)絡(luò)分類(lèi)模型研究及其在小樣本故障診斷中的應(yīng)用[D];哈爾濱工業(yè)大學(xué);2009年

5 李欣;自適應(yīng)遺傳算法的改進(jìn)與研究[D];南京信息工程大學(xué);2008年

，

本文編號(hào)：1968942