【摘要】：自動(dòng)化和智能化是當(dāng)今工業(yè)系統(tǒng)的發(fā)展趨勢,而系統(tǒng)的穩(wěn)定性是自動(dòng)化和智能化實(shí)現(xiàn)的前提。永磁同步電機(jī)(Permanent Magnet Synchronous Motor,PMSM)同時(shí)具有高效率、高功率密度以及強(qiáng)魯棒性等性能,現(xiàn)代化工業(yè)領(lǐng)域已離不開PMSM的應(yīng)用,尤其是在精密控制領(lǐng)域的應(yīng)用。當(dāng)電機(jī)發(fā)生故障而未能及時(shí)發(fā)現(xiàn)處理時(shí),輕則電機(jī)本身損傷,重則損壞整個(gè)電機(jī)設(shè)備造成巨大的經(jīng)濟(jì)損失,因此對PMSM故障診斷的研究十分有必要,具有重大意義。而PMSM故障中最為常見的故障分別是驅(qū)動(dòng)系統(tǒng)開路和定子匝間短路故障。本文采用群智能優(yōu)化算法對PMSM驅(qū)動(dòng)系統(tǒng)開路進(jìn)行和PMSM定子匝間短路故障進(jìn)行診斷研究。首先,本文在矢量控制的基礎(chǔ)上,建立PMSM靜態(tài)坐標(biāo)下數(shù)學(xué)模型和dq軸數(shù)學(xué)模型,介紹電機(jī)的矢量變換原理,然后分別分析PMSM驅(qū)動(dòng)系統(tǒng)開路和定子匝間短路故障狀態(tài)下的數(shù)學(xué)模型。然后針對PMSM驅(qū)動(dòng)系統(tǒng)開路故障,提出一種基于自適應(yīng)二階粒子群算法(Self-adaptive SECond-order Particle Swarm Optimization,SASECPSO)的改進(jìn)極限學(xué)習(xí)機(jī)(Improved Extreme Learning Machine,IELM)算法。該SASECPSO算法采用自適應(yīng)慣性權(quán)重策略及線性變化認(rèn)知系數(shù)方法,提高二階粒子群算法(SECond-order Particle Swarm Optimization,SECPSO)的收斂速度和收斂精度。此外,運(yùn)用SASECPSO算法同時(shí)對極限學(xué)習(xí)機(jī)的輸入權(quán)值和隱含層閾值參數(shù)優(yōu)化,可提高極限學(xué)習(xí)機(jī)算法在PMSM故障中的識(shí)別率。以電機(jī)轉(zhuǎn)速和ABC相電流作為多源樣本數(shù)據(jù),多組實(shí)驗(yàn)證明IELM算法相對于其他算法具有較高的診斷精度。最后針對PMSM常見的匝間短路故障,利用能量頻譜分析提取特征向量,采用自適應(yīng)動(dòng)態(tài)貓群算法(ADAptive dynamic Cat Swarm Optimization,ADACSO)優(yōu)化SVM的懲罰因子和核函數(shù)參數(shù),隨后將優(yōu)化后的SVM用于電機(jī)故障診斷。以小波能量頻譜得到的特征向量作為SVM算法的樣本數(shù)據(jù)來進(jìn)行仿真實(shí)驗(yàn),結(jié)果表明,相對于其他優(yōu)化算法,采用ADACSO優(yōu)化SVM參數(shù)能夠使SVM在PMSM故障診斷中具有更高的診斷精度和準(zhǔn)確率。
[Abstract]:Automation and intelligence are the development trend of industrial system, and the stability of system is the premise of automation and intelligent realization. Permanent magnet synchronous motor (Permanent Magnet Synchronous Motor,PMSM) has high efficiency, high power density and strong robustness at the same time. Modern industry has been inseparable from the application of PMSM, especially in the field of precision control. When the motor fails to find and deal with the fault in time, the light motor itself will be damaged, and the heavy motor equipment will be damaged. Therefore, the study of PMSM fault diagnosis is very necessary and has great significance. The most common faults in PMSM are open circuit fault of drive system and short circuit fault of stator turn. In this paper, the open circuit of PMSM drive system and the fault diagnosis of PMSM stator inter-turn short circuit are studied by using swarm intelligence optimization algorithm. Firstly, on the basis of vector control, the mathematical model and dq axis mathematical model under PMSM static coordinate are established, and the vector transformation principle of motor is introduced. Then the mathematical models of PMSM drive system under open circuit and stator interturn short circuit are analyzed respectively. Then an improved extreme learning machine (Improved Extreme Learning Machine,IELM) algorithm based on adaptive second-order particle swarm optimization (Self-adaptive SECond-order Particle Swarm Optimization,SASECPSO) is proposed for the open circuit fault of PMSM drive system. The SASECPSO algorithm adopts adaptive inertial weight strategy and linear varying cognitive coefficient method to improve the convergence speed and accuracy of the second-order particle swarm optimization (SECond-order Particle Swarm Optimization,SECPSO) algorithm. In addition, using SASECPSO algorithm to optimize the input weights of LLM and threshold parameters of hidden layer at the same time, the recognition rate of LLM algorithm in PMSM fault can be improved. The speed of motor and the phase current of ABC are used as multi-source sample data. Many experiments show that the IELM algorithm has higher diagnostic accuracy than other algorithms. Finally, for the common inter-turn short circuit faults in PMSM, the eigenvector is extracted by energy spectrum analysis, and the penalty factor and kernel function parameters of SVM are optimized by adaptive dynamic cat swarm algorithm (ADAptive dynamic Cat Swarm Optimization,ADACSO). Then the optimized SVM is used in motor fault diagnosis. Using the eigenvector obtained from wavelet energy spectrum as the sample data of SVM algorithm, the simulation results show that, compared with other optimization algorithms, Using ADACSO to optimize SVM parameters can make SVM have higher diagnostic accuracy and accuracy in PMSM fault diagnosis.
【學(xué)位授予單位】：江南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP18;TM341

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 朱群;尹忠剛;張延慶;鐘彥儒;;基于粒子群優(yōu)化算法的永磁同步電機(jī)H_∞速度觀測器[J];西安理工大學(xué)學(xué)報(bào);2016年02期

2 陸慧娟;魏莎莎;宋夫華;高波涌;;一種Fibonacci優(yōu)化理論的改進(jìn)ELM分類方法[J];小型微型計(jì)算機(jī)系統(tǒng);2015年12期

3 肖漢;付俊芳;蔡大泉;周建中;肖劍;付文龍;;基于群智能加權(quán)核聚類的水電機(jī)組故障診斷[J];振動(dòng).測試與診斷;2015年04期

4 賀彥林;王曉;朱群雄;;基于主成分分析-改進(jìn)的極限學(xué)習(xí)機(jī)方法的精對苯二甲酸醋酸含量軟測量[J];控制理論與應(yīng)用;2015年01期

5 付文龍;周建中;李超順;肖漢;肖劍;朱文龍;;基于模糊K近鄰支持向量數(shù)據(jù)描述的水電機(jī)組振動(dòng)故障診斷研究[J];中國電機(jī)工程學(xué)報(bào);2014年32期

6 史麗萍;王攀攀;胡泳軍;韓麗;;基于骨干微粒群算法和支持向量機(jī)的電機(jī)轉(zhuǎn)子斷條故障診斷[J];電工技術(shù)學(xué)報(bào);2014年01期

7 尹剛;張英堂;李志寧;任國全;孫宜權(quán);;自適應(yīng)集成極限學(xué)習(xí)機(jī)在故障診斷中的應(yīng)用[J];振動(dòng).測試與診斷;2013年05期

8 吉哲;王修敏;張松濤;;基于BP神經(jīng)網(wǎng)絡(luò)的艦船電機(jī)故障診斷[J];電機(jī)與控制應(yīng)用;2013年07期

9 謝輔雯;;蟻群優(yōu)化BP神經(jīng)網(wǎng)絡(luò)的電機(jī)故障診斷設(shè)計(jì)與實(shí)現(xiàn)[J];制造業(yè)自動(dòng)化;2012年10期

10 李彬;李貽斌;;基于ELM學(xué)習(xí)算法的混沌時(shí)間序列預(yù)測[J];天津大學(xué)學(xué)報(bào);2011年08期

相關(guān)博士學(xué)位論文 前2條

1 馬超;基于元啟發(fā)優(yōu)化極限學(xué)習(xí)機(jī)的分類算法及其應(yīng)用研究[D];吉林大學(xué);2014年

2 程軍;基于生物行為機(jī)制的粒子群算法改進(jìn)及應(yīng)用[D];華南理工大學(xué);2014年

相關(guān)碩士學(xué)位論文 前5條

1 侯雅曉;五相永磁同步電機(jī)系統(tǒng)故障診斷與容錯(cuò)控制技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2016年

2 杜博超;電動(dòng)汽車用永磁同步電機(jī)的故障診斷[D];哈爾濱工業(yè)大學(xué);2011年

3 王胤龍;稀土永磁電機(jī)振動(dòng)故障診斷系統(tǒng)研究[D];沈陽工業(yè)大學(xué);2008年

4 薛麗英;六相永磁同步電機(jī)驅(qū)動(dòng)系統(tǒng)故障診斷與容錯(cuò)的研究[D];西北工業(yè)大學(xué);2006年

5 張敬南;永磁電動(dòng)機(jī)電力推進(jìn)系統(tǒng)故障診斷專家系統(tǒng)技術(shù)研究[D];哈爾濱工程大學(xué);2004年

，

本文編號：2328142