摘要
电力系统的高可靠性要求诊断系统能及时发现水轮发电机组的故障,并给出调整建议;同时要求诊断系统能根据机组状况给出优化运行方案。传统的基于傅立叶变换的故障诊断方法只能从频率的角度发现机组的故障,不能准确定位机组发生故障的时间及故障发展趋势。
本文以水轮发电机组状态监测与故障诊断方法为研究对象,深入研究了Hilbert-Huang变换理论基础的上,将其引入水轮发电机组故障诊断系统中。该方法首先对机组振动信号进行经验模态分解(EMD)获得固有模态函数(IMF)分量,再经过Hilbert变换获得信号的Hilbert谱,从信号的Hilbert谱中即可发现信号中的异常频率及其发生的时间,从而确定机组的故障和发生时间。
Hilbert-Huang变换的端点效应限制了其应用,本文对端点效应的原理做了详细的分析后提出了两种解决端点效应的方法:可变长极值镜像拓延法避免了镜像闭合拓延法造成数据量庞大的缺点,按照实际情况选取拓延极值长度,取得较好效果;基于最小二乘支持向量机(LS-SVM)的端点拓延方法结合了水轮发电机组暂态数据短的特点和最小二乘支持向量机在小样本下可获得最优解的优点,较好的抑制了端点效应。
信号特征提取方法是故障诊断的难点,本文针对水轮发电机组振动信号的特点,提出两种信号特征提取方法:基于EMD和AR模型的方法从波形入手提取信号特征,该方法将每个固有模态函数(IMF)分量提取为4个参数作为智能识别系统的输入;基于能量的特征提取方法是将每个IMF分量的能量作为智能识别系统的输入。这两种方法可以将信号的特征提取为数值特征,为故障的智能识别奠定了基础。
本文最后将Hilbert-Huang变换应用于实际中,对贵州索风营电站1号机组进行了诊断,分析其性能和振动原因,并尝试将最小二乘支持向量机分类方法应用于水轮发电机组故障智能识别系统,得出相应的结论。结果表明,基于Hilbert-Huang变换和支持向量机的水轮发电机组状态监测与故障诊断方法能对机组性能做出较好的评价,准确定位机组的故障,值得推广应用。
High reliability of electrical power system demands that a fault diagnosis system should find out failures of a water-wheel generator set in time, make a suggestion to correct them and give a optimistic scheme for operating as the states of the generator set. However, the traditional fault diagnosis method based on Fourier transform(FT) can only find failures from frequencies of vibration signals and can not know what time and how the failures will happen.
This thesis investigates methodology of the state monitoring and fault diagnosis of a water-wheel generator set. Firstly the Hilbert-Huang transform is deeply studied. After that, it is applied into a fault diagnosis system of a water-wheel generator set. By this method, signals are decomposed by empirical mode decomposition (EMD) firstly and the intrinsic mode functions (IMFs) are obtained. Then Hilbert spectrum is obtained by Hilbert transform. Abnormal frequencies and their occurring time can be discovered from the Hilbert spectrum. So do the failures of the generator set.
Applications of the Hilbert-Huang transform are restricted because of its point effect. Armed with analyzing the principle of point effect in detail, two methods of dealing with it are presented. The one is an alterable length extremism mirroring extension algorithm. The algorithm does not like the close mirroring extension algonithm which can produce an amount of data. Moreover, it has good effect by taking extension extremism length in the actual condition. The other is a point extension algorithm based on the least square support vector machine. This algorithm makes full use of the character of short transient vibration signal data of the water-wheel generator set and optimal advantage of the least square support vector machine with limited samples. So it can solve the point effect more effectively.
It is difficult to distill signal characters for the fault diagnosis. With the character of vibration signals of a water-wheel generator set, the thesis gives two algorithms to distill signal
charaters. The first algorithm is based on EMD and AR mode to distill signal characters from the wave form. This algorithm takes four parameters as inputs of an intelligent recognizing system from every IMF; while the second algorithm is based on energy and it is to make energy of IMF as inputs of the intelligent recognizing system. Both the algorithms can transform signal characters into digital characters and they are the basis of the fault diagnosis.
At the end of this thesis, Hilbert-Huang transform is used in fault diagnosis system of No.1 water-wheel generator set of SUO FENG YING Its performance and vibration reasons are analyzed. Least square classification vector methane is applied to the fault diagnosis intelligent recognizing system of the water-wheel generator set and results are analyzed. They indicate that state monitoring and fault diagnosis system based on Hilbert-Huang transform and support vector machine can give a good estimate for the performance of water-wheel generator set and locate the failures of the generator set. Thus, it is worth of spreading and application.
引文
[1] 孙嘉平.做好节能工作促进可持续发展[J].中国电力,2006,39(9):1-6.
[2] 王晓英.电力系统设备状态监测的概念及现状[J].煤炭技术,2004,23(6):41-42.
[3] 陈玉林,陈允平,孙金莉等.电网故障诊断综述[J].中国电力,2006,39(5):27-31.
[4] 吴凡.状态监测和故障诊断技术的现状与展望[J].国外电子测量技术,2006,25(3):5-7.
[5] 盛兆顺,尹琦岭.设备状态监测与故障诊断技术及其应用[M].北京:化学工业出版社,2003:1-30.
[6] 汪军,朱浩.水电机组状态检修的现状和发展趋势[J].水电厂自动化,2005,102(2):14-17.
[7] 何永勇,任继顺,陈伟.水电机组远程状态监测、跟踪分析与故障诊断系统[J].清华大学学报(自然科学版),2006,46(5):629-632.
[8] 桂中华,潘罗平,唐澍.基于Web技术的水电机组远程状态监测研究[J].水电厂自动化,2006,110(10):145-148.
[9] 王建学,王锡凡,冯长有.基于市场公平性的法典机组检修规划[J].电力系统自动化,2006,30(20):15-20.
[10] 彭文季,罗兴镝.基于粗糙集和支持向量机的水电机组振动故障诊断[J].电工技术学报,2006.21(10):117-122.
[11] 李风芝,高建瓴.信息融合理论在水轮发电机组故障诊断中的应用[J].科技情报开发与经济,2006,16(19):154-155.
[12] 彭文季,罗兴铸,赵道利.基于频谱分析与径向基函数网络的水电机组振动故障诊断[J].中国电机工程学报,2006,26(9):155-158.
[13] 周晨赓.基于EMD和BP网络联合的故障诊断技术[D].青岛:中国海洋大学,2003:1-6.
[14] 刘峰.基于神经网络的水轮发电机组振动故障诊断专家系统研究[D].西安:西安理工大学,2003:1-10.
[15] 刘金凤.水轮发电机组振动在线监测与分析系统研究[D].西安:西安理工大学,2004:1-12.
[16] 徐东海.水电机组状态监测及故障诊断研究[D].北京:清华大学,2003:1-8.
[17] 梁武科,赵道利,黄秋红等.基于多传感器信息融合的水轮机导轴承故障诊断方法[J].水力发电学报,2004,23(4):117-121.
[18] 曾海平.基于经验模态分解法的滚动轴承故障诊断系统研究[D].杭州:浙江大学,2005:1-10.
[19] 余涛,王晶.水电机组故障诊断专家系统研究现状与发展前景[J].云南电,1999,27(2):50-53.
[20] 贾嵘,王小宇,蔡振华等.基于最小二乘支持向量机回归的HHT在水轮发电机组故障诊断中的应用[J].中国电机工程学报,2006,26(22):128-133.
[21] 袁静,胡昌华,龙勇等.基于C/S+B/S双模式的分布式远程诊断专家系统[J].计算机工程,2006,32(12):196-198.
[22] 王江萍,宁延平.机械设备故障智能诊断技术水平与发展趋势[J].石油机械,2005,33(8):71-74.
[23] 杨晓萍,南海鹏,张江滨.信息融合技术在水轮发电机组故障诊断中的应用[J].水力发电学报,2004,23(6):111-115.
[24] 杨宇.基于EMD和支持向量机的旋转机械故障诊断方法研究[D].长沙:湖南大学,2005:10-30.
[25] 周晨赓.几种信号分析方法对非线性、非平稳信号分析效果的比较[J].山东电子,2003,4:43-45.
[26] 程军圣.基于Hilbert-Huang变换的旋转机械故障诊断方法研究[D].长沙:湖南大学,2005:15-25.
[27] Huang N E, Zheng S, Steven R L, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proc. R. Soc. London. A, 1998, 454: 903-995.
[28] Kang Huang, Dave Tateh Chang, Thomas Hou. A bridge monitoring method based on vibration characteristics under a transient load[J]. Proceeding of the international symposium of civil engineering in the 21st century, 2000: 563-565.
[29] Qiang G, Xiaojiang M, Haiyong Z. The partial wave method for the analysis of non-stationary signals and its use in machine fault diagnosis[J]. Proceedings of the international symposium on test and measurement, 2001, 2: 1465-1468.
[30] Gravier B M, Pelstring J A. An assessment of the application of the Hilbert spectrum to the fatigue analysis of marine risers[J]. Proceedings of the international offshore and polar engineering conference, 2001, 2: 268-275.
[31] Loh CH, Wu T C, HuangN E. Application of the empirical mode decomposition-Hilbert spectrum method to identify near-fault ground-motion characteristics and structural responses[J]. BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA, 2001, 91(5): 1339-1357.
[32] Zhang Haiyong, Ma Xiaojiang, Gaiqiang. Wigner-Ville distribution based on intrinsic mode function[J]. Pro. OfICR, Beijing, 2001: 1015-1017.
[33] Timashcv SA, Shalin MG. Precise analysis of non-stationary vibration processes using the Hilbert transform[J]. ACSIM 2000 Proceeding, 2000, 395-404.
[34] 钟佑明.希尔伯特-黄变换局瞬信号分析理论的研究[D].重庆:重庆大学,2002:16-30.
[35] 陈忠,郑时雄.基于经验模式分解(EMD)的齿轮箱齿轮故障诊断技术研究[J].振动工程学报,2003,16(2):229-232.
[36] 杨世锡,胡劲松,吴昭同等.旋转机械振动信号基于EMD的希尔伯特变换和小波变换时频分析比较[J].中国电机工程学报,2003,23(6):102-107.
[37] 贾嵘,王小宇,张丽等.基于EMD和AR模型的水轮机尾水管动态特征信息提取[J].电力系统自动化,2006,30(22):77-80.
[38] B Boashash. Estimating and interpreting the instantaneous frequency of a signal-part1: fundamentals[J]. Proc.IEEE, 1992,80(4): 520-538.
[39] L.科恩.时一频分析[M].第一版(白局宪译).西安:西安交通大学出版社,2000:20-50.
[40] 高云超.希尔伯特-黄变换方法的仿真研究[D].哈尔滨:哈尔滨工程大学,2005:14-32.
[41] Huang N E, Wu M C. A confidence limit for empirical mode decomposition and Hilbert spectral analysis[J]. Proc. R. Soc. London, Ser.A, 2003, 459: 2317-2345.
[42] Wu Z, Huang N E. A study of the characteristics of white noise using the empirical mode decomposition method[J]. Proceedings of the Royal Society of London, Series A, 2004, 460: 1597-1611.
[43] Gloersen P, Huang N E. Comparison of interannual intrinsic modes in hemispheric sea ice covers and other geophysical parameterS[J]. IEEE Transactions on Geoscience and Remote Sensing, 2003, 41(5): 1062-1074.
[44] Huang N E, Wu M L. Application of Hilbert-Huang transform to non-stationary financial time series analysis[J]. Applied Stochastic Models in Business and Industry, 2003, 19(6): 245-268.
[45] 熊学军,郭炳火,胡筱敏等.EMD方法和Hilbert谱分析法的应用与探讨[J].黄渤海海洋,2002,20(2):12-21.
[46] 钟佑明,秦树人,汤宝平.Hilbert-Huang变换中的理论研究[J].振动与冲击,2002,21(4):13-17.
[47] 王波,杨洪耕.电力系统电压短期扰动的三角模态检测方法[J].电工技术学报,2005,20(11):101-105.
[48] 程军圣,于德介,杨宇.EMD方法在转子局部碰摩故障诊断中的应用[J].振动、测试与诊断,2006,26(1):24-27.
[49] 李天云,赵妍,季小慧等.HHT方法在电力系统故障信号分析中的应用[J].电工技术学报,2005,20(6):87-91.
[50] 任达千,吴昭同,杨世锡.基于HHT的转子扭振估计方法研究[J].汽轮机技术,2005,47(6):430-432.
[51] 胡劲松,杨世锡.基于HHT的转子横向裂纹故障诊断[J].动力工程,2004,24(2):218-221.
[52] 胡劲松,杨世锡.基于EMD和HT的旋转机械振动信号时频分析[J].振动、测试与诊断,2004,24(2):106-110.
[53] 盖广洪.基于经验模态分解的转子启动波德图绘制[J].机械科学与技术,2006,25(1):9-11.
[54] 牛发亮,黄进,杨家强等.基于感应电机启动电磁转矩Hilbert-Huang变换的转子断条故障诊断[J].中国电机工程学报,2005,25(11):107-112.
[55] 冯志鹏,褚福磊.基于Hilbert-Huang变换的水轮机非平稳压力脉动信号分析[J].中国电机工程学报,2005,25(10):111-115.
[56] Vladimir N.Vapnik.统计学习理论的本质[M].第一版(张学工译).北京:清华大学出版社,2000.1-240.
[57] 赵冲冲.基于支持向量机的旋转机械故障[D].西安:西北工业大学,2003:1-50.
[58] 邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[MI.第一版.北京:科学出版社,2004:1-300.
[59] Nello Cristianini,John Shawe-Taylor.支持向量机导论[M].第一版(李国正,王猛,曾华军译).北京:电子工业出版社,2004:1-100.
[60] 范昕伟.支持向量机算法的研究及其应用[D].杭州:浙江大学,2003:15-30.
[61] 孙宗海.支持向量机及其在控制中的应用研究[D].杭州:浙江大学,2003:17-33.
[62] 孙德山.支持向量机分类与回归方法研究[D].长沙:中南大学,2004:22-40.
[63] 张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[64] 曾嵘.支持向量机在设备故障诊断中的应用研究[D].长沙:中南大学,2005:15-40.
[65] 黄勇,郑春颖,宋忠虎.多分类支持向量机算法综述[J].计算技术与自动化,2005,24(4):62-63.
[66] 赵晶,张旭东,高隽.基于支持向量机的多类形状识别系统[J].合肥工业大学学报(自然科学版),2004,27(1):23-26.
[67] 萧嵘,孙晨,王继成等.一种具有容噪性能的SVM多值分类器[J].计算机研究与发展,2000,37(9):1071-1075.
[68] 刘志刚,李德仁,秦前清等.支持向量机在多类分类问题中的推广[J].计算机工程与应用,2004,7:10-13.
[69] 孙即祥.现代模式多类识别[M].长沙:国防科技大学出版社,2002.1-50.
[70] 文明,方凯,汪方斌等.一种基于SVM的多类判别算法[J].工业仪表与自动化装置,2006,6:6-8.
[71] Platt J, Cristianini N, Shawe-Taylor J. Large Margin DAG's for Multiclass Classification[J]. Advances in Neural Information Processing Systems, 2000: 547-553.
[72] 余艳芳,高大启.一种改进的最小二乘支持向量机及其应用[J].计算机工程与科学,2006,28(2):69-71.
[73] Francesseo Masulli, Giorgio Valentini. Comparing decomposition methods for classification[J]. Fourth international conference on knowledge-based intelligent engineering, Systems and technologies, 2000: 788-792.
[74] Dietterich T G, Bakiri O. Solving Multiclass learning problems via Error-Correcting Output Codes[J]. Journal of Arti-ficial intelligence research, 1995, (2): 263-286.
[75] 潘明清.基于支持向量机的机械故障模式分类研究[D].杭州:浙江大学,2005:15-30.
[76] 杨琦.支持向量机在液压系统故障诊断中的应用研究[D].大连:大连海事学院,2005:10-31.
[77] Suykens J A K, De Brabanter J, Lukas L, et al. Weighted least squares support vector machines: robustness and sparse approximation[J]. Neurocomputing, 2002, 48(1-4): 85-105.
[78] Suykens J A K., Vandewalle J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3): 293-300.
[79] Suykens J A K., Vandewalle J, De Moor B. Optimal control by least squares support vector machines[J]. Neural Networks, 2001, (14): 23-35.
[80] 许亚洲.基于最小二乘支持向量机的数控机床热误差建模的研究[D].杭州:浙江大学,2006:9-41.
[81] 黄大吉,赵进平,苏纪兰.希尔伯特-黄变换的端点拓延[J].海洋学报,2003,25(1):1-11。
[82] 陈忠,郑时熊.EMD信号分析方法边缘效应分析[J].数据采集与处理,2003,18(1):114-118.
[83] 盖强,马孝江,张海勇.一种消除局域波法中边界效应的新方法[J].大连理工大学学报,2002,42(1):115-117.
[84] 刘慧婷,张曼,程家兴.基于多项式拟合算法的EMD端点问题的处理[J].计算机工程与应用,2004,40(16):84-86.
[85] 张郁山,梁建文,胡肆贤.应用自回归模型处理EMD方法中的边界问题[J].自然科学进展,2003,13(10):1054-1059.
[86] 邓拥军,王伟,钱成春等.EMD方法及Hilbert变换中边界问题的处理[J].科学通报,2001,46(3):257-263.