摘要
随着世界范围内石油资源的紧缺,石油运输过程中的安全问题日益引起人们的重视。由于管道老化、打孔盗油等原因,输油管道经常发生泄漏。为了及时发现泄漏,基于负压波、声波、光纤等原理的实时泄漏检测系统被设计和应用。其中基于负压力波信号分析的输油管道泄漏故障诊断方法是目前我国输油管道泄漏检测所用的主要方法。在基于负压波的泄漏诊断理论中,输油管道压力时间序列(Oil Pipeline Press Time Series, OPPTS)的波动一直以来都被认作是随机的,导致微小泄漏无法检测,阻碍了基于动态压力信号的输油管道泄漏故障诊断系统的发展。本文主要以OPPTS作为研究对象,研究了其内部动态特性,探讨了提高基于负压波的泄漏诊断技术整体性能的方法,主要工作如下：
1对OPPTS实测数据集依次利用硬件滤波、滑动均值滤波和小波滤波方法进行顺序滤波处理,为后续的数据分析和应用打下基础。在利用小波方法滤波过程中,通过对实测数据和模拟数据的滤波仿真,对比分析了离散小波、提升小波和非抽样小波处理数据的特点,并且得出利用非抽样小波处理OPPTS能够较好的保存管道内部的动态特性。
2提出了改进的Darbyshire-Broomhead Lyapunov指数谱算法,通过互信息函数确定嵌入延迟,利用伪近邻法(False Nearest Neighbors, FNN)方法确定最佳嵌入维,从而确定了Lyapunov指数的个数,克服了原算法排除可疑指数过程中容易引起的指数个数不确定的缺点。
3为了进一步提高基于压力波的泄漏检测方法的性能,本文首次分析出管道内的油品的压力波动具有混沌特性,为基于压力波的泄漏检测研究提供了一条新的研究途径。根据管道内具有湍流的特点,利用Haykin实测数据分析理论对管道内部流体的特性进行了理论分析,求解和分析了数据集的分形维数,计算Lyapunov指数的计算方法并且对目标数据集的Lyapunov指数进行了估计和分析,评估了数据集的平稳性和非线性,根据结果得到了输油管道压力波动具有混沌特性。
4利用OPPTS的混沌特性,给出了一种基于BP和RBF神经网络OPPTS在线故障诊断方法。该方法利用OPPTS的非线性特性重构相空间,以重构向量作为神经网络模型的输入,在线训练神经网络模型,实现网络模型权值在线调整,从而实现实时对故障信号的检测。分别利用BP网络和RBF网络作为该算法的网络模型,利用OPPTS中的故障数据进行了仿真验证。
5分析了视神经网络的特点和参数之间的关系,利用OPPTS的混沌特性给出了OPPTS故障诊断的视神经网络方法。该方法具有需要先验数据少,处理速度快等优点。分别比较了BP、RBF和视神经网络在处理故障诊断问题上的优缺点,并给出了每种方法的使用场合。
6在对OPPTS理论分析和应用研究的基础上,设计了输油管道故障诊断专家系统。利用本文提出的故障算法作为故障定位方法,再利用模糊推理对检测到的压力故障数据进行分类,从而到达检测泄漏并且定位的目的,通过验证,系统性能具有较大提高。
Oil pipelines often leak because of aging, steal etc, so it is an important problem to detect the leak points on oil transmission pipelines. Many methods based on negative press wave, sound wave and optical fiber are used to find leak of oil pipelines, of which negative press wave is the common method in china. By far fluctuation of oil pipeline press time series (OPPTS) is assumed stochastic or white noise, which hinders the improvement of fault diagnosis system that designed based on pressure fluctuation. In this dissertation, the internal dynamic of pressure fluctuation in oil pipelines is reseached, based on which several new leak-detection motheds is proposed, the main work is as follow:
1 RC-filter, mean-filter and wavelet-filter are used in turn to minish the effect of noise before studying internal dynamic of OPPTS. Filting of disperse wavelet, lifting wavelet and undecimated wavelet is discussed and is simulated separately, the result is the undecimated wavelet is the most fitting method.
2 An improved method of computing the Lyapunov-spectrum based on Darbyshire-Broomhead's arithmetic is given, in which the delay is computed based on mutual-information function, the optional embedding is obtained based on false nearest neighbors (FNN). The improved method can get the number of Lyapunov exponents and can evaluate Lyapunov-spectrum of OPPTS including noise. This method can avoid the step of removing spurious exponents.
3 To improve the performance of leak detection system based on OPPTS, the possibility of existing chaotic characters is validated using the method of nonlinear analysis. Experimental data sets of OPPTS are studied on which phase spaces are reconstructed, fractal dimensions and Lyapunov exponents are computed, the stationarity and nonlinearity are validated. By the analysis of the results, the rigorous chaotic characters in OPPTS are found, that is a theoretical basis for the correlative investigation based on pressure time series of oil pipelines.
4 An on-line fault-detection method of BP and RBF based on chaos for OPPTS is proposed. After reconstructing phase-space by OPPTS and using vectors of reconstruction as the input of neutral network model, this proposed method can real-time modify the parameters of model by training the model on-line. Then the default and even little fault can be diagnosed by the error between real-time data and the predicted value of neural network model. Experiential datasets of OPPTS are simulated by the proposed method.
5 Another on-line fault-detection method of retina neural network based on chaos for OPPTS is proposed and the model of retina neural network is given also. This mothod has the excellences of needing little data and faster speed. Then the comparation and the situation of the methods based on BP, RBF and retina neural network is analysed.
6 A leak diagnosis expert system of oil pipeline is desgined, which classes the fault data of OPPTS by fuzzy reasoning and finds fault point of OPPTS by on-line fault-detection method. The expert system has the better result than the old one by simulation,.
引文
1.唐东林,陈才和,崔宇明,宁春梅,何仕刚.海底管道缺陷在线智能检测机器人[J].传感技术学报,2005,18(4)：818-821.
2. Takeda Minkov D, Shoji Y, Lee T. Estimating the sizes of surface cracks based on hall element measurements of the leakage magnetic field and a dipole model of a crack [J]. Applied Physics A:Materials Science and Processing,2002,74(2):169-176.
3. Mandache C, Clapham L. A model for magnetic flux leakage signal predictions [J]. Canada J Phys D:App Phys,2003,36:2427-2431.
4. Coughlin C R, Clapham L, Atherton D L. Effects of stress on MFL responses from elongated corrosion pits in pipeline steel [J]. NDT & E International,2000,33: 181-188.
5. Afzal M, Polikar R, Udpa L, Udpa S. Adaptive noise cancellation schemes for magnetic flux leakage signals obtained from gas pipeline inspection [C].2001 IEEE international conference (ICASSP'01),2001,6:3389-3392.
6. Park G S, Park E S. Improvement of the sensor system in magnetic flux leakage type nondest ructive testing (NDT) [J]. IEEE transactions on magnetics,2002,38: 1277-1280.
7. Forster. New findings in the field of nondestructive magnetic leakage field inspection [J]. NDT international,1986,19:3-14.
8.王瑞利,李斌,高强.漏磁检测与超声波检测技术应用比较[J].管道技术与设备,2006,5：15-17.
9. Okamoto J, Adamowski J C et al. Autonomous system for oil pipelines inspection [J]. Mechatronics,1999,9:731-743.
10.戴波,张慧平等.多通道超声系统在管道内检测中的应用[J].控制工程,2007,14(4)：451-454.
11.唐建,戴波,蒋力培,邓双成.长输管道超声波内检测功能机系统研制[J].北京石油化工学院学报,2006,14(2)：37-40.
12. Murayama R, Makiyama S, Kodama M, Taniguchi Y. Development of an ultrasonic inspection robot using an electromagnetic acoustic transducer for a Lamb wave and an SH-plate wave [J]. Ultrasonics,2004,42:825-829.
13. Zhang Y W, Yan G Z. In-pipe inspection robot with active pipe-diameter adaptability and automatic tractive force adjusting [J]. Mechanism and machine theory,2007,42: 1618-1631.
14. Gunarathne G P P, Qureshi Y. A novel technique for dynamic alignment of ultrasonic transducers in real-time non-destructive testing [C]. IEEE instrumentation and measurement technology conference,2003:1137-1142.
15.冯健.流体输送管道泄漏智能诊断与定位方法的研究[D].沈阳：东北大学,2004.
16. Liou J C P. Pipeline leak detection based on mass balance [C]. Proceedings of the international conference on pipeline infrastructure Ⅱ,1993,175-188.
17. Chaudry M C. Applied hydraulic transients [M]. New York:Van Nostrand Reinhold Press,1987.
18. American Petroleum Institute (API). Computational pipeline monitoring [M], New York:API Publication 1130,1995,10-17.
19. Fur Z. Leakerkennung und-lokalisierung bei pipelines durch on-line korrelation mit einem prozebrechner[J], regelungstechnik,1977,3(1):69-100.
20. Dennis W H. Real-time transient model for batch tracking, line balance and leak detection [J], Journal of canadian petroleum,1981,10(1-9):46-52.
21. Muggleton J M et al. Wave number prediction of waves in buried pipes for water leak detection [J]. Journal of sound and vibration,2003,249(5):939-954.
22. Borener S S, Patterson T. Remote control spill reduction technology:a survey and analysis of applications for liquid pipeline systems [M]. U.S. Department of transportation, Volpe National Transportations Systems Center,1995.
23.何存富,杭利军,吴斌.分布式光纤传感技术在管道泄漏检测中的应用[J].传感器与微系统,2006,5(9)：8-14.
24. Reber K, Beller M, Willems H, Barbian O A. A new generation of ultrasonic in-line inspection tools for detecting, sizing and locating metal loss and cracks in transmission pipelines [J]. IEEE ultrasonics symposium,2002:665-671.
25. Barnoski M K, Jensen S M. Fiber waveguides:a novel technique for investigating attenuation characteristics [J]. Applied Optics,1976,15 (9):2112-2115.
26.李炜,朱芸.长输管线泄漏检测与定位方法分析[J].天然气工业,2005,25(6)：105-109.
27. Liou J C P, Hall R J, Mcmahon M C. Hazardous liquid leak detection techniques and processes [C]. Report of U.S. department of transportation research and special programs administration office of pipeline safety, Washington,2003.
28. Sandberg C. The application of a continuous leak detection system to pipeline and associated equipment [J]. IEEE Transaction on industry applications,1989,25 (5):906-909.
29. Kantz H, Schareiber T. Nonlinear time series analysis [M]. Cambridge, Cambridge university press,1997.
30.刘文广等。输油管道泄漏监测系统灵敏度的影响因素[J].油气田地面工程,2004,23(6)：32.
31. Hilario M, Kalousis A, Pellegrini C, Midler M. Processing and classification of protein mass spectra [J]. Mass Spectrom Rev,2006,25:409-449.
32. Shin H, Mutlu M, Koomen J M, Markey M K. Parametric power spectral density analysis of noise from instrumentation in MALDI TOF mass spectrometry [J]. Cancer informatics,2006,3:317-328.
33. Krutchinsky A N, Chait B T. On the nature of the chemical noise in MALDI mass spectra [J]. J. Am Soc Mass Spectrom,2002,13:129-134.
34. Kwon D, Vannucci M, Song J J, Jeong J, Pfeiffer R M. A novel wavelet-based thresholding method for the pre-processing of mass spectrometry data that accounts for heterogeneous noise [J]. Proteomics 2008,8:3019-3029.
35. Coombes K R, Tsavachidis S et al. Improved peak detection and quantification of mass spectrometry data acquired from surface-enhanced laser desorption and ionization by denoising spectra with the undecimated discrete wavelet transform [J]. Proteomics 2005,5:4107-4117.
36. Qu Y, Adam B L et al. Data reduction using a discrete wavelet transform in discriminant analysis of very high dimensionality data [J]. Biometrics 2003,59: 143-151.
37. Li T Y, Yorke J A. Period three implies chaos[J]. Amer Math Monthly,1975,82: 985-992,
38.吴彤.非线性动力学混沌理论方法及其意义[J].清华大学学报(哲学社会科学版),2000,15(3)：72-79.
39.利昂·格拉斯,迈克尔·C·麦基,潘涛等译.从摆钟到混沌—生命的节律[M].1994,上海：上海远东出版社.
40.刘华杰.混沌语义学与哲学[M].1998,长沙：湖南教育出版社.
41.扎奥丁.萨德尔,孙文龙译.视读混沌学[M].2007,合肥：安徽文艺出版社.
42.王海生等.基于小波分析的输油管道泄漏检测[J],信息与控制,2002,31(5)： 456-460.
43.张东领,王树青,张敏.热输油管道泄漏定位技术研究[J].石油学报,2007,28(1)：131-133.
44.叶昊,王桂增,方崇智.小波变换在故障检测中的应用[J].自动化学报,1997,23(6)：736-741.
45.王立宁,李健,靳世久.热输原油管道瞬态压力波法泄漏点定位研究[J].石油学报,2000,21(4)：93-96.
46.沈功田,李光海,景为科,左延田.埋地管道泄漏监测检测技术[J].无损检测,2006,(5)：267-271.
47. Mears M N.Real world applications of pipeline leak detection [C]. Proceedings of the international conference on pipeline infrastructure Ⅱ,1993,189-209, San Antonio, Texas.
48.王立坤,赵晋云,付松广,谭东杰,李健,靳世久.基于神经网路的管道泄漏声波信号特征识别[J].仪器仪表学报,2006,27(6)：2247-2249.
49.崔谦,靳世久等.基于序贯检验的管道泄漏检测方法[J].石油学报,2005,26(4)：123-126.
50. Zhang X J. Statistical leak detection in gas and liquid pipelines [J]. Pipes and pipelines international,1993,38 (4):26-29.
51. Feng J, Zhang H G. Diagnosis and localization of pipeline leak based on fuzzy decision-making method [J]. ACTA Automatica SINICA,2005,31(3):484-490.
52. Donoho D L, Johnstone I M. Ideal spatial adaptation by wavelet shrinkage [M]. Biometrika,1994,81:425-455.
53. Donoho D L, Johnstone I M. Adapting to unknown smoothness via wavelet shrinkage via wavelet shrinkage [M]. JASA,1995,90(432):1200-1224.
54. Randolph T W, Yasui Y. Multiscale processing of mass spectrometry data [J]. Biometrics 2006,62,589-597.
55. Chen S, Hong D, Shyr Y. Wavelet-based procedures for proteomic mass spectrometry data processing[J]. Comput Stat Data An,2007,52:211-220.
56. Er M J, Sia A M. Adaptive noise cancellation using dynamic fuzzy neural networks algorithm [C]. Proceedings 15th of IFAC World Congress, Barcelona, Spain 2002.
57. Vorobyov S A, Cichocki A. Adaptive noise cancellation for multi-sensory signals [J]. Fluction and noise letters,2001,1(1):13-24.
58. Er M J, Wu S Q. A fast learning algorithm for parsimonious fuzzy neural systems [J]. Fuzzy sets and systems,126(3):61-75.
59. Cichocki A, Vorobyov S A, Rutkowski T. Nonlinear interference cancellation using neural networks [C]. Proc. Int. Symposium on nonlinear theory and its applications, Hawaii,1999:875-878.
60. Elliott R J. Filtering with a small non-linear term in the signal [J]. Syst Control Lett, 1990,15:81-90.
61. Yaesh I, Shaked U. Min-max Kalman filtering [J]. Syst Control Lett,2004,53: 217-228.
62. Sweldens W. The lifting scheme:A new philosophy in biorthogonal wavelet constructions [J]. Proc SPIE,1995,2659:68-79.
63. Daubechies I, Sweldens W. Factoring wavelet transforms into lifting steps [J]. Fourier Anal Appl,1998,4(3):247-269.
64. Sweldens W. The lifting scheme:a construction of second generation wavelets [J]. SI AM J Math Anal,1997,29 (02):511-546.
65. Sweldens W. The lifting scheme:A custom-design construction of biorthogonal wavelets [J]. Appl Comput Harmon Anal,1996,3(2):186-200.
66. Starck J L, Fadili J., Murtagh F. The undecimated wavelet decomposition and its reconstruction [J]. IEEE transactions on image processing,2007,16(2):297-309.
67. Antoine J P, Murenzi R. Two dimensional wavelet analysis in image processing [J]. Phys. Mag.,1994,16:105-134.
68. Stefano D A., White P R., White P R. Noise reduction in spine videofluoroscopic images using the undecimated wavelet transform [J]. Computerized medical imaging and graphics,2004,28:453-459.
69. Gyaourova A, Kamath R, Fodor I K. Undecimated wavelet transforms for image de-noising [C]. Technical report, Lawrence Livermore national laboratory, UCRL-ID-150931,2002.
70. Dutilleux P. An implementation of the "algorithme a trous" to compute the wavelet transform [J]. In wavelets:time-frequency methods and phase-space, New York, Springer-Verlag,1989:298-304.
71.飞思科技产品研发中心.小波分析理论与MATLAB7实现.北京：电子工业出版社,2005.
72. Starck J L, Elad M, Donoho D L. Redundant multiscale transforms and their application for morphological component analysis [J]. J. Adv. Imag. Elect. Phys.,2004, 132:287-348.
73. Starck J L, Murtagh F. Astronomical image and data analysis [M]. New York: Springer-Verlag,2002.
74. Shensa M J. Discrete wavelet transforms:Wedding the a trous and Mallat algorithms [J]. IEEE Trans Signal Process,1992,40(10):2464-2482.
75. Cvetkovic Z, Vetterli M. Oversampled filter banks [J]. IEEE Trans Signal Process, 1998 46(5):1245-1255.
76. Genovesio, Olivo-Marin J C. Tracking fluorescent spots in biological video microscopy [J]. In three-dimensional and multidimensional microscopy:image acquisition and processing X, Bellingham, WA:SPIE,2003,4964:98-105.
77. Burt P J, Adelson A E. The Laplacian pyramid as a compact image code [J]. IEEE Trans Commun,1983,31(4):532-540.
78. Haykin S. Adaptive Filter Theory (Fourth Edition) [M].北京,电子工业出版社,2002.
79. Packard N H, Crutchfield P, Farmer J D, Shaw R S. Geometry from a time series [J]. Phys Rev Lett,1980,45(9):712-716.
80. Takens F. Detecting strange attractors in turbulence [J]. Lecture notes in mathematics, 1981,898:366-381.
81. Sauer T, Yorke J A, Casdagli M. Embedology dynamical systems and turbulence [J]. J Stat Phys,1991,65:579-616.
82. Gao C H, Qian J X. Evidence of chaotic behavior in noise from industrial process [J]. IEEE transactions on signal processing,2007,55(6):2877-2844.
83. Abarbanel H D. Analaysis of observed chaotic data [J]. Springer-Verlag, New York, 1996.
84. Cao L Y. Practival method for determining the minimum embedding dimension of a scalar time series [J]. Physica D,1997,110:43-50.
85.甘建超.混沌信号处理在雷达和通信对抗中的应用[D].成都：电子科技大学,2004.
86.林嘉宇,黄芝平.语音信号相空间重构中时间延迟选择的改进的平均位移法[J].国防科技大学学报,1999,21(3)：62-65.
87.林嘉宇,黄芝平,王跃科,沈振康.语音信号相空间重构中时间延迟选择-复自相关法[J].信号处理,1999,15(3)：220-225.
88.田玉楚.混沌时间序列的时滞判断[J].物理学报,1997,46(3)：442-447.
89. Abarbanel H D I, Masuda N, Rabinovich M I, Turner E. Distribution of mutual information [J]. Physics letters A,2001,281 (5-6),369-373.
90. Frazer A M, Swinney H L, Independent coordinates in strange attractors from mutual information [J]. Phys Rev A,1986, (33):1134-1140.
91. Kraskov A, Stogbauer H, Grassberger P. Estimating mutual information [J]. Physical review E,2004,69(9):Art. No. o66138 Part 2.
92. Luis A A. A nonlinear correlation function for selecting the delay time in dynamical reconstructions [J]. Physics letters A,1995,203:88-94.
93. Abarbanel H D L Analysis of observed chaotic data [M]. Springer-Verlag, New York, 1996.
94. Kennel M B, Brown R, Abarbanel H D L Determining embedding dimension for phase-space reconstruction using a geometrical construction [J]. Phys Rev A, Gen Phys,1992,45(6):3403-3411.
95. Broomhead D S, King G E. Extracting qualitative dynamics from experimental data [J]. Physica D,1986 (20):217-236.
96.韩敏.混沌时间序列预测理论与方法[M].北京：中国水利水电出版社,2007.
97. Haykin S, Puthusserypady S. Chaotic dynamics of sea clutter [J]. Chaos,1997,7: 777-802.
98. Haykin S, Puthusserypady著.祝明波译.海杂波的混沌动态特性[M].国防工业出版社,北京,2006.
99. Varadan V, Leung H, and Bosse E. Dynamical model reconstruction and accurate prediction of power-pool time series [J]. IEEE transactions on instrumentation and measurement,2006,55(1):327-336.
100. AntzHolger. a robust method to estimate themaximal lyapunov exponent [J]. Phys Lett A,1994,185:77-879.
101. Eckmann J P, Kamphorst S O, Ruelle D et al. Lyapunov exponents from time series [J]. Physical review A,1986,34(6):4971-4979.
102. Ramazanetal G. An algorithm for the N-Lyapunov exponents of an N-dimensional unknown dynamical system [J]. Phys D,1992,599:142-1571.
103. FroylandJan. lyapunov exponent spectra for the lorenz model [J]. Phys Rev A,1984,29: 2928-2931.
104. Darbyshire A G., Broomhead D S. Robust estimation of tangent maps and liapunov spectra [J]. Physica D,1996,89:287-305.
105. Banbrook M, Ushaw G, McLaughlin S. How to extract lyapunov exponents from short and noisy time series [J]. IEEE transactions on signal processing,1997,45(5): 1378-1382.
106. Grassberger P, Procaccia I. Characterization of strange attractors [J]. Phys Rev Lett, 1983,50(5):346-349.
107. Grassberger P, Procaccia I. Measuring the strangeness of strange attractors [J]. Physica D,1983,9:189-208.
108. Schouten J C, Takens F, Bleek V D C M. Estimation of the dimension of a noisy attractor [J]. Physical review E,1994,50:1851-1861.
109. Schouten J C, Takens F, Bleek V D C M. Maximum likelihood estimation of the entropy of an attractor [J]. Physical review E 1994,49 126-129.
110. Lai Y C et al. Correlation-dimension and autocorrelation fluctuations in epileptic seizure dynamics [J]. Phys Rev E,2002,3:1-5.
111. Nolte G, Ziehe A, Miiller K R. Noise robust estimates of correlation dimension and K2-entropy [J]. Phys Rev E,2001,64:1-10.
112. Corana A. Adaptive box-assisted algorithm for correlation-dimension estimation [J]. Phys Rev E,2000,62:7872-7881.
113. Kim H S, Eykholt R, Salas J D. Delay time window and plateau onset of the correlation dimension for small data sets [J]. Phys Rev E,1998,58:5676-5882.
114. Hegger R, Kantz H, Olbrich E. Correlation dimension of intermittent signals [J]. Phys Rev E,1997,56:199-203.
115. Frank M, Keller G, Sporer R. Practical implementation of error estimation for the correlation dimension [J]. Phys Rev E,1996,53:5831-5836.
116. Ding M Z, Grebogi C, Ott E, Sauer T, Yorke J A. Plateau onset for correlation dimension:When does it occur [J]? Phys Rev Lett,1993,70:3872-3875.
117. Farrell M E, Passamante A., Hediger T. Comparing a nearest-neighbor estimator of local attractor dimensions for noisy data to the correlation dimension [J]. Phys Rev A, 1990,41(12):6591-6595.
118. Theiler J, Eubank S et al. Testing for nonlinearity in time series:The method of surrogate data [J]. Physica D,1992,58(1-4):77-94.
119.宋爱军,韩雷.热超声键合换能系统动力学特性的非线性检验[J].物理学报,2007,56(7)：3821-3825.
120. Barnett A G and Wolff R C A time-domain test for some types of nonlinearity [J]. IEEE transactions on signal processing,2005,53(1):26-33.
121. Thornhill N F. Finding the source of nonlinearity in a process with plant-wide oscillation [J]. IEEE transactions on control systems technology,2005,13(3):434-443.
122.李锬,齐中英.沪铜、天然橡胶期货价格时间序列的非线性检验[J].哈尔滨工业大学学报,2005,7(5)：81-84.
123. Grassberger P. An optimized box-assisted algorithm for fractal dimensions [J]. Physics letters A,1990,148:63-68.
124. Muller K R, Mika S et al. An introduction to kernel-based learning algorithms [J]. IEEE Transaction on neural networks,2001,12(2):181-201.
125. Hay kin S, Principe J. Making sense of a complex world [J]. IEEE signal processing magazine,1998,15(3):66-68.
126.万毅.基于RBFNN的接触网系统可靠性设计方法研究[D].成都：西南交通大学,2006.
127.蔡自兴 徐光佑.人工智能及其应用[M].北京：清华大学出版社,2004.
128. Chen Z Q, He J F, Yuan Z Z. An adaptive identification and control scheme using radial basis function networks [J]. System Engineering and Electronics,1999,10(1):54-61.
129.行鸿彦,徐伟.混沌背景中微弱信号检测的神经网络方法[J].物理学报,2007,56(7)：3771-3776.
130. Hosoyal T, Baccusl S A, Meister M. Dynamic predictive coding by the retina [J]. Nature,2005,436:71-77.
131. Dong D W, Atick J J. Statistics of natural time-varying images [J]. Network,1995,6: 345-358.
132. Field D J. Relations between the statistics of natural images and the response properties of cortical cells [J]. Journal of the optical society of America A:optics, image science, and vision,1987,4(12):2379-2394.
133. Srinivasan M V, Laughlin S B, Dubs A. Predictive coding:a fresh view of inhibition in the retina [J]. Proceedings of the royal society of London,1982, Series B,216: 427-459.
134. Chichilnisky E J. A simple white noise analysis of neuronal light responses [J]. Network,2001,12:199-213.
135. Kuffler S W. Discharge patterns and functional organization of mammalian retina [J]. Neurophysiol,1953,16:37-68.
136. Barlow H B. Summation and inhibition in the frog's retina [J]. Physiol,1953,119: 69-88.
137. Meister M, Berry M J. The neural code of the retina [J]. Neuron,1999,22:435-450.
138. Barlow H B In Sensory Communication [M]. Cambridge:MIT Press,1961.
139. Van Hateren J H. Real and optimal neural images in early vision [J]. Nature,1992,360: 68-70.
140. Atick J J, Redlich A N. What does the retina know about natural scenes [J]? Neural comput,1992,4:196-210.
141. Haggett S J, Chu D F, Marshall I W. Evolving a dynamic predictive coding mechanism for novelty detection [J]. Knowledge-based systems,2008,21(3):217-224.
142.张军峰,胡寿松.基于一种新型聚类算法的RBF神经网络混沌时间序列预测[J],物理学报,2007,56(2)：713-719.
143. Borgnea Y A L,Santinib S, Bontempia G. Adaptive model selection for time series prediction in wireless sensor networks [J]. Signal processing,2007,87:3010-3020.
144.李士勇.模糊控制、神经控制和智能控制论[M].哈尔滨：哈尔滨工业大学出版社,2004.
145. Silva H V, Morooka C K et al. Leak detection in petroleum pipelines using a fuzzy system [J]. Journal of Petroleum Science and Engineering,2005,49:223-238.
146.边肇祺,张学工.模式识别[M].北京：清华大学出版社,2004.
147. Hu J Q, Zhang L B, Wang Z H, Liang W. The application of integrated diagnosis database technology in safety management of oil pipeline and transferring pump units [M]. Journal of loss prevention in the process industries,2008, In Press.
148. Chang X G, Lilly J H. Evolutionary design of a fuzzy classifier from data [J]. IEEE transactions on systems, man, and cybernetics—Part B:cybernetics,2004,34(4): 1894-1906.
149. Lee H J, Park D Y, Ahn B S, Park Y M. A fuzzy expert system for the integrated fault diagnosis [J]. IEEE transactions on power delivery,2000,15(2):833-838.
150. El-Shal S M, Morris A S. A fuzzy expert system for fault detection in statistical process control of industrial processes [J]. IEEE transactions on systems, man, and cybernetics-part C:applications and reviews,2000,30(2):281-289.
151. Kim K H, Park J K, Hwang K J, Kim S H. Implementation of hybrid short-term load forecasting system using artificial neural networks and fuzzy expert systems [J]. IEEE transactions on power systems,1995,10(3):1534-1539.
152. Stroppiana D, Boschetti M, Brivio P A, Carrara P, Bordogna G. A fuzzy anomaly indicator for environmental monitoring at continental scale [J]. Ecological indicators, 2009,9:92-106.
153.Azadeh A, Fam I M, Khoshnoud M, Nikafrouz M. Design and implementation of a fuzzy expert system for performance assessment of an integrated health, safety, environment (HSE) and ergonomics system:The case of a gas refinery [J]. Information sciences 2008,178:4280-4300.
154. Lopez E M, Garcia M, Schuhmacher M, Domingo J L.A fuzzy expert system for soil characterization [J].Environment international,2008,34:950-958.
155. Lin C S, Khan H A, Chang R Y, Wang Y C. A new approach to modeling early warning systems for currency crises:Can a machine-learning fuzzy expert system predict the currency crises effectively [J]? Journal of international money and finance,2008,27: 1098-1121.
156. Mosqueira-Rey E, Moret-Bonillo V et al. An expert system to achieve fuzzy interpretations of validation data [J]. Expert systems with applications,2008,35: 2089-2106.
157. Zaheeruddin, Jain V K. An expert system for predicting the effects of speech interference due to noise pollution on humans using fuzzy approach [J]. Expert systems with applications,2008,35:1978-1988.
158. Dokas L M, Karras D A, Panagiotakopoulos D C. Fault tree analysis and fuzzy expert systems:Early warning and emergency response of landfill operations [J]. Environmental modelling & software,2009,24:8-25.
159. Zeng Q F, Zhang L T et al. Designing expert system for in situ toughened Si3N4 based on adaptive neural fuzzy inference system and genetic algorithms [J]. Materials and design,2009,30:256-259.
160. Sengur A, Turkoglu I. A hybrid method based on artificial immune system and fuzzy k-NN algorithm for diagnosis of heart valve diseases [J]. Expert systems with applications,2008,35:1011-1020.
161.Castanho M J P, Barros L C, Yamakami A, Vendite L L. Fuzzy expert system:An example in prostate cancer [J]. Applied mathematics and computation,2008,202: 78-85.
162. Hadjimichae M. A fuzzy expert system for aviation risk assessment [J]. Expert systems with application,2008, in publishing.
163.Tsipouras M G, Voglis C, Fotiadis D I. A framework for fuzzy expert system creation-application to cardiovascular diseases [J]. IEEE transactions on biomedical engineering,2007,54(11):2089-2103.
164. Giartano J, Riley G. Expert systems, principles and programming [M].Boston:PWS Publishing Company,1998.
165. Liao S H. Expert system methodologies and applications-a decade review from 1995 to 2004 [J]. Expert Syst Appl,2005,28:93-103.
166. Pedrycz W, Oliveira J V D. An algorithmic framework for development and optimization of fuzzy models [J]. Fuzzy sets syst.,1996,80:37-55.
167. Garibalti J M, Ifeachor E I. Application of simulated annealing fuzzy model tuning to umbilical cord acid-base interpretation [J]. IEEE Trans Fuzzy Syst,1999,7(1):72-84.
168. Goletsis Y, Papaloucas C, Fotiadis D I, Likas A, Michalis L K. Automated ischemic beat classification using genetic algorithms and multicriteria decision analysis [J]. IEEE Trans. Biomed. Eng.,2004,51(1):1717-1725.
169. Jang J S R, Sun C T. Neuro-fuzzy modeling and control [C]. Proc.IEEE,1995,83(3): 378-406.
170. Tsoukalas L H, Uhrig R E. Fuzzy and neuralapproaches in engineering [M]. New York: Wiley,1997.
171. Wang L X. A course in fuzzy systems and control [M]. Upper Saddle River, NJ: Prentice-Hall,1997.
172. Duda R O, Hart P E, Hart D G. Pattern classification,2nded [M]. New York:Wiley, 2001.
173.Bazdek J C, Pal S K. Fuzzy models for pattern recognition [M]. New York:IEEE, 1992.
174. Chong E K P, Zak S H. An introduction to optimization [M]. New York:Wiley,2001.
175. Hansen E. Global optimization using interval analysis [M]. New York:Dekker,1992.
176. Kirkpatrick S, Gelatt C D, Vecchi M P. Optimization by simulated annealing [J]. Science,1983,220:671-680.
177.刘金海,张化光,冯健.输油管道时间序列的动态特性研究[J].物理学报,2008,57(11)：6868-6877.
178. Liu Jinhai, Zhang Huaguang, Feng Jian. A New Fault Detection and Diagnosis Method for Oil Pipeline Based on Rough Set and Neural Network [J]. ISNN, Part III, LNCS, 2007 4493:561-569.
179.刘金海,张化光,冯健.长输油管线实时泄漏发现与定位系统设计[J].仪器仪表学报,27(S1)：286-287,2006.
180.刘金海,张化光,冯健,杨东升.一种改进的Lyapunov指数谱算法及应用研究[J].系统仿真学报,已录用.
181.刘金海,张化光,冯健.一种基于混沌特征的输油管道压力时间序列在线故障诊断算法[J].东北大学学报,已录用.
182.刘金海,张化光.混沌系统奇异点检测的神经网络方法研究[J].物理学报,已投.
183.刘金海,张化光.小波滤波方法在实测数据处理中的应用研究[J].仪器仪表学报,已投.
184.刘金海,张化光.一种基于视神经网络的故障诊断算法及应用[J].自动化学报,已投.