發(fā)布時(shí)間：2018-10-25 14:29

【摘要】：在國(guó)內(nèi)外油田生產(chǎn)過(guò)程中,機(jī)械采油仍然占有很大一部分。在整個(gè)機(jī)械采油中抽油機(jī)等采油設(shè)備對(duì)于油田的生產(chǎn)非常重要。由于抽油機(jī)大多是在野外工作,長(zhǎng)期處在高溫度、高載荷等惡劣的環(huán)境中,而且抽油機(jī)的井下工況也是極其復(fù)雜,導(dǎo)致抽油機(jī)經(jīng)常出現(xiàn)故障。抽油機(jī)的故障所造成的經(jīng)濟(jì)損失是極其巨大的,因此需要對(duì)抽油機(jī)的工況進(jìn)行故障診斷�；�于人工智能的機(jī)器學(xué)習(xí)方法能夠構(gòu)造多類分類學(xué)習(xí)模型并進(jìn)行故障診斷,已成為當(dāng)前研究的熱點(diǎn)之一。因此本文提出一種基于螢火蟲(chóng)優(yōu)化支持向量機(jī)的抽油機(jī)工況故障診斷方法,主要內(nèi)容如下:首先,針對(duì)當(dāng)前油田生產(chǎn)所遇到的問(wèn)題設(shè)計(jì)了抽油機(jī)工況診斷系統(tǒng)整體結(jié)構(gòu)框架。研究了理論示功圖形成原理以及部分典型的故障示功圖特征,并對(duì)示功圖進(jìn)行預(yù)處理,示功圖的處理方式包括圖像的灰度化、濾波、圖像二值化以及邊緣檢測(cè)等,將示功圖轉(zhuǎn)化為邊界最大區(qū)域填充的圖像。其次,針對(duì)Hu矩特征值包含的信息不全面的問(wèn)題,采用基于小波變換和矩特征相結(jié)合的小波不變矩方法來(lái)提取抽油機(jī)的示功圖特征值。由于小波變換抗干擾性強(qiáng)以及反映局部信息的能力,因此采用小波不變矩對(duì)抽油機(jī)示功圖進(jìn)行局部和全局的特征提取,進(jìn)而建立典型示功圖樣本庫(kù)。再次,深入分析了支持向量機(jī)算法,支持向量機(jī)參數(shù)的選擇及參數(shù)組合(懲罰因子c與核函數(shù)參數(shù)σ)會(huì)影響其分類精度,本文將引入螢火蟲(chóng)算法對(duì)其優(yōu)化。為避免傳統(tǒng)的螢火蟲(chóng)算法易出現(xiàn)局部最優(yōu)解,特對(duì)其進(jìn)行改進(jìn),將改進(jìn)后的螢火蟲(chóng)算法應(yīng)用到支持向量機(jī)的參數(shù)選擇上,通過(guò)與改進(jìn)粒子算法優(yōu)化支持向量機(jī)以及傳統(tǒng)螢火蟲(chóng)優(yōu)化支持向量機(jī)相比較,基于螢火蟲(chóng)優(yōu)化的支持向量機(jī)的分類效果有了很大的提高。最后,將改進(jìn)后螢火蟲(chóng)算法優(yōu)化的支持向量機(jī)應(yīng)用到抽油機(jī)工況故障診斷中,建立支持向量機(jī)故障診斷模型。將測(cè)試數(shù)據(jù)輸入到診斷模型中進(jìn)行試驗(yàn),實(shí)驗(yàn)結(jié)果表明基于改進(jìn)螢火蟲(chóng)優(yōu)化的支持向量機(jī)故障診斷方法具有較高的分類準(zhǔn)確度。通過(guò)上述理論研究后,本文采用C#編程語(yǔ)言與ORACLE數(shù)據(jù)庫(kù)相結(jié)合設(shè)計(jì)了抽油機(jī)工況故障診斷系統(tǒng),并對(duì)其進(jìn)行現(xiàn)場(chǎng)測(cè)試。測(cè)試結(jié)果表明,系統(tǒng)可以運(yùn)行穩(wěn)定,診斷結(jié)果準(zhǔn)確。
[Abstract]:In the production process of oil fields at home and abroad, mechanical oil production still occupies a large part. Oil extraction equipment such as pumping unit is very important to the production of oil field. Because the pumping unit mostly works in the field for a long time in the bad environment such as high temperature high load and so on and the downhole working condition of the pumping unit is extremely complex resulting in the pumping unit often appear malfunction. The economic losses caused by the faults of pumping units are extremely huge, so it is necessary to diagnose the working conditions of pumping units. The machine learning method based on artificial intelligence can construct multi-class classification learning model and make fault diagnosis, which has become one of the hot research topics. Therefore, this paper presents a fault diagnosis method of pumping unit based on firefly optimized support vector machine. The main contents are as follows: firstly, the whole structure framework of pumping unit condition diagnosis system is designed to solve the problems encountered in oil field production. This paper studies the formation principle of theoretical indicator diagram and some typical fault indicator diagram features, and preprocesses the indicator diagram, which includes image grayscale, filtering, image binarization and edge detection, etc. Convert the indicator diagram into an image filled with the maximum boundary area. Secondly, in order to solve the problem of incomplete information contained in Hu moment eigenvalue, wavelet invariant moment method based on wavelet transform and moment feature is used to extract the eigenvalue of indicator diagram of pumping unit. Because wavelet transform has strong anti-interference and the ability to reflect local information, wavelet invariant moment is used to extract the local and global features of the indicator diagram of pumping unit, and then the sample library of typical indicator graph is established. Thirdly, the support vector machine (SVM) algorithm is deeply analyzed. The selection and combination of SVM parameters (penalty factor c and kernel function parameter 蟽) will affect the classification accuracy. In this paper, the firefly algorithm is introduced to optimize the SVM. In order to avoid the local optimal solution of the traditional firefly algorithm, the improved firefly algorithm is applied to the parameter selection of support vector machine. Compared with the improved particle algorithm optimization support vector machine and the traditional firefly optimization support vector machine, the classification effect of the support vector machine based on the firefly optimization has been greatly improved. Finally, the support vector machine (SVM) optimized by the improved firefly algorithm is applied to the fault diagnosis of pumping unit, and the fault diagnosis model of SVM is established. The experimental results show that the SVM fault diagnosis method based on improved firefly optimization has high classification accuracy. After the above theoretical research, this paper uses C # programming language and ORACLE database to design the pumping unit working condition fault diagnosis system, and carries on the field test to it. The test results show that the system can run stably and the diagnosis result is accurate.
【學(xué)位授予單位】：東北石油大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TE933.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳德勝;張國(guó)梁;;我國(guó)石油產(chǎn)業(yè)發(fā)展現(xiàn)狀與趨勢(shì)分析[J];節(jié)能與環(huán)保;2016年10期

2 黃廷輝;伊凱;王玉良;崔更申;;螢火蟲(chóng)算法優(yōu)化神經(jīng)網(wǎng)絡(luò)的無(wú)線傳感器網(wǎng)絡(luò)數(shù)據(jù)融合[J];儀表技術(shù)與傳感器;2016年07期

3 田夢(mèng)楚;薄煜明;陳志敏;吳盤(pán)龍;趙高鵬;;螢火蟲(chóng)算法智能優(yōu)化粒子濾波[J];自動(dòng)化學(xué)報(bào);2016年01期

4 張龍濤;孫玉秋;;一種圖像增強(qiáng)的混合算法研究[J];長(zhǎng)江大學(xué)學(xué)報(bào)(自科版);2015年25期

5 田中大;李樹(shù)江;王艷紅;高憲文;;基于小波變換的風(fēng)電場(chǎng)短期風(fēng)速組合預(yù)測(cè)[J];電工技術(shù)學(xué)報(bào);2015年09期

6 陳琦;丁麗娜;;基于STM32和GPRS的無(wú)線油井監(jiān)控器[J];微型機(jī)與應(yīng)用;2015年06期

7 譚笑;陜梅辰;徐小力;馬超;智玉杰;;基于示功圖分形盒維數(shù)的無(wú)桿抽油機(jī)故障診斷方法研究[J];機(jī)床與液壓;2014年17期

8 丁漪;李訓(xùn)銘;;示功圖特征提取選擇在油井故障診斷中的研究應(yīng)用[J];電子設(shè)計(jì)工程;2014年17期

9 蔣煜琪;谷兆貴;史旺旺;;基于ZigBee和GPRS的多通訊功能無(wú)線測(cè)控系統(tǒng)[J];機(jī)電工程;2014年06期

10 董立功;;我國(guó)石油供需及發(fā)展趨勢(shì)分析[J];中國(guó)石油和化工標(biāo)準(zhǔn)與質(zhì)量;2014年05期

相關(guān)碩士學(xué)位論文 前5條

1 王曉菡;用于工況診斷的示功圖特征提取方法研究[D];中國(guó)石油大學(xué);2011年

2 劉欽;油井遠(yuǎn)程自動(dòng)監(jiān)測(cè)與工況分析技術(shù)應(yīng)用研究[D];中國(guó)石油大學(xué);2009年

3 劉煒;基于支持向量機(jī)的抽油機(jī)示功圖工況判別[D];西安理工大學(xué);2009年

4 張沖;油田抽油機(jī)運(yùn)行狀態(tài)遠(yuǎn)程監(jiān)測(cè)系統(tǒng)研制[D];哈爾濱工業(yè)大學(xué);2008年

5 孫玉龍;分層有桿抽油系統(tǒng)井下故障診斷技術(shù)[D];浙江大學(xué);2001年

，

本文編號(hào)：2293968