روش جدید پایش نوک پره توربین با استفاده از سنسور مایکروویو و الگوریتم کلاسه‌بندی K نزدیک‌ترین همسایه (k-NN)

نوع مقاله : علمی-پژوهشی

نویسندگان

دانشکده مهندسی برق و کامپیوتر - دانشگاه کاشان

چکیده

در این مقاله، یک سنسور مایکروویو باند k برای پایش پره توربین شبیه‌سازی و در نرم افزار CST بهینه‌سازی شده است و با استفاده از یک مدل ساده شده توربین در نرم‌افزار CST اثر قرار دادن سنسور در بدنه توربین بررسی شده است و چنانچه هر تغییر شکل در نوک تیغه و یا جابجایی در فاصله مابین نوک تیغه تا پوسته انجام گردد پارامتر پراکندگی این سنسور تغییر می‌کند و پارامتر پراکندگی بدست آمده از سنسور به عنوان اثر انگشت تیغه توربین تعریف می‌شود. در این مقاله شاخص‌های اندازه‌گیری مبتنی بر پارامترهای پراکندگی میدان نزدیک سنسور مایکروویو بعنوان سیستم تشخیص خرابی نوک تیغه و همچنین الگوریتم کلاسه‌بندی k-NN برای تفسیر پارامترهای پراکندگی قابل اندازه‌گیری به‌منظور تعیین مقدار خرابی بعنوان روشی جدید برای پایش پره توربین ارائه گردیده است. مزیت این روش پایش برخط پره توربین با استخراج کامل شاخص‌های اندازه‌گیری ناشی از پارامترهای پراکندگی یک پره نمونه بوده و نشان داده شده است که روش طبقه‌بندی k-NN دقت قابل قبولی در شناسایی و تعیین مقدار فاصله نوک پره توربین از پوسته و تغییر شکل نوک پره دارد چراکه در این روش درصد خطا می‌تواند به زیر 1.8 درصد برسد.

کلیدواژه‌ها

عنوان مقاله [English]

New Method for Monitoring of Turbine Blade Tip Using Microwave Sensor and k-Nearest Neighbor Classification Algorithm

نویسندگان [English]

  • M. Aslinezhad
  • M. Akhavan Hejazi
Faculty of Electrical and Computer Engineering, University of Kashan, Kashan, Iran
چکیده [English]

In this paper, a K band microwave sensor is simulated to monitoring of turbine blade and is optimized in CST software and And is embedded in the turbine shell and if any change in the tip of the blade or displacement at the tip clearance, the scattering parameters of this sensor is changed and the scattering parameter obtained from the sensor mounted on the crust is defined as the turbine blade fingerprint. In this paper, the measurements indices based on scattering parameters of the near field of microwave sensor as a blade tip failure detector system as well as k-NN classification algorithm for interpreting measurable scattering parameters to determine the failure amount as a new method for monitoring of turbine blade is presented. The advantage of this method is online monitoring of turbine blades with fully extracting the measuring indices due to the scattering parameters of a sample blade and It has been shown that the k-NN classification method has an acceptable accuracy in identifying and determining the amount of tip clearance and the deformation of the blade because the error rate can be reached below 1.8% in this way.

کلیدواژه‌ها [English]

  • Microwave Sensor
  • k-Nearest Neighbor classification
  • Tip Clearance
  • Scattering Parameters

مراجع

[1]    Z. Jilong, D. Fajie, Niu. Guangyue, J. Jiajia and L. Jie, “A blade tip timing method based on a microwave sensor,” MDPI Physical Sensors Journal, vol. 17, 11 May 2017.
[2]    V. Naga Bhushana Rao, IN. Niranjan Kumar and K. Bala Prasad, “Failure analysis of gas turbine blades in a gas turbine engine used for marine applications,” International Journal of Engineering, Science and Technology, vol. 6, no. 1, pp. 43-48, 2014.
[3]    R. Dewangan, J. Patel, J. Dubey, P. Kumar Sen and S. K. Bohidar, “Gas turbines blades a critical review of failure on first and second stages,” International Journal of  Mechanical Engineering and Robotics Research, vol. 4, no. 1, January 2015.
[4]    N. singh Grewal, Gas Turbine Engine Performance Deterioration Modelling and Analysis, Ph.D. Thesis, Cranfield Institute of Technology, School of Mechanical Engineering, February 1988.
[5]    N. Goel, A. Kumar, V. Narasimhan, A. Nayak, and A. Srivastava, “Health risk assessment and prognosis of gas turbine blades by simulation and statistical methods,”  Conference on Electrical and Computer engineering, Canadian, pp. 1087–1091, 2008.
[6]    M. R. Woike, J. W. Roeder, C. E. Hughes, and T. J. Bencic, “Testing of a microwave blade tip clearance sensor at the NASA Glenn research center,” 47th AIAA Aerospace Sciences Meeting, Orlando, Florida, 5-8 January, 2009.
[7]    A. Dutta, Shivangi and J. Valarmathi, “Blade tip clearance measurement using microwave sensing system,” International Journal of Recent advances in Mechanical Engineering (IJMECH), vol. 4, no. 2, 2015.
[8] مریم دهقانی و مرتضی خرّم کشکولی، »تشخیص، شناسایی و جداسازی عیب توربین گاز پالایشگاه دوم پارس جنوبی با استفاده از روشهای ترکیبی داده‌کاوی،means-k ، تحلیل مؤلفه‌های اصلی (PCA) و ماشین بردار پشتیبان(SVM) »، مجله علمی پژوهشی مهندسی برق دانشگاه تبریز، دوره 47،شماره2 ، صفحه 515-501، 1396.
[9]     T. Arthur Holst, Analysis of spatial filtering in phase-based microwave measurements of turbine Blade Tips, M.S. Thesis, Academic Faculty by Georgia Institute of Technology, August 2005.
[10]     A. Schicht, K. Huber, A. Ziroff, M. Willsch and L. Schmidt, “Absolute phase-based distance measurement for industrial monitoring systems,” IEEE Sensor Journal, vol. 9, no. 9, September 2009.
[11]     Z. Li, C. Soutis, A. Haigh,  R. Sloan,  A. Gibson and  N.  Karimian, “Microwave imaging for delamination detection in T- joints of wind turbine composite blades,” in 46th European Microwave IEEE Conference, pp. 1235 – 1238, 2016.
[12]     J. Geisheimer, S. Billington, T. Holst and D. Burgess, “Performance testing of a microwave tip clearance sensor,” in Proceedings of the AIAA Joint Propulsion Conference, Tucson, AZ, USA, 10–13 July 2005.
[13]     Alexander, M. Mikhail and B. Maksim, “Microwave blade tip clearance measurements principles, current practices and future opportunities,” Turbine Technical Conference and Exposition, Copenhagen, Denmark, June 2012.
[14]     M. Violetti, Q. Xu, O. Hochreutiner and A.K.  Skrivervik, “New microwave sensor for on-line blade tip timingin gas and steam turbines,” in Proceedings of the Asia-Pacific Microwave Conference, Taiwan, pp. 1055–1057, December 2012.
[15]     M. Violetti, J.F. Zurcher, J. Geisheimer and A.K. Skrivervik, “Design of antenna based sensors for blade tip clearance measurement in gas turbines,” in IEEE Conference, Barcelona, Spain ,pp. 1-4, 2010.
[16]     Y. Han, C. Zhong, X. Zhu and J. Zhe, “Online monitoring of dynamic tip clearance of turbine blades in high temperature environments,” in Measurement Science and Technology, vol. 29, pp. 1-13, 26 February 2018.
[17]     J. Miguel, J. Zubia and G. Aranguren, “Architecture for Measuring Blade Tip Clearance and Time of Arrival with Multiple Sensors in Airplane Engines,” International Journal of Aerospace Engineering, vol. 2018, May 2018.
[18]     D. Zhai, M. Xie, J. Yuan and S. Liu, “Application of high level synthesis in the blade tip clearance measurement system,” in IEEE BioMedical Engineering and Informatics Conferences, pp. 1-5, 2018.
[19]     L. Jiang, C. Xue, J. Cui, M. Yu, X. Pu and J. Shi, “Research recognition of aircraft engine abnormal state,”  in IEEE Control and Decision Conference, China, May 2015.
[20]     M. Violetti, A.K. Skrivervik, Q. Xu, J. Geisheimer and G. Egger, Device and Method for Monitoring Rotor Blades of a Turbine, European Patent Application no. 11181622, Sept. 16, 2011.
[21]     R. Szczepanik, R. Przysowa, J. Spychala, E. Rokicki, K. Kamierczak and P. Majewski, Thermal Power Plants:  Application of Blade Tip Sensors to Blade Vibration Monitoring in Gas Turbines, Poland Air Force Institute of Technology, InTech, pp. 145-175, 2012.
[22]     A.K. Zimmer, Investigation of the Impact of Turbine Blade Geometry on Near-field Microwave Blade Tip Time of Arrival Measurements, M.S Thesis, Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology, December 2008.
[23]     P. Wade, W1GHZ Online Microwave AntennaBook, Available:http://www.w1ghz.org/antbook/contents.htm/Understanding Circular Waveguide Experimentally, Jan/Feb 2001.
[24]     P.A. Rizzi, Microwave engineering passive circuits, Microwave resonator and filters, Latest Edition, PHI Learning, pp. 427-438, 2004.
[25]     J.G. Pollock, Analysis and Design of A New Class of Miniaturized Circular Waveguides Containing Anisotropic Metamaterial Liners, Ph.D. Thesis, Department of electrical and computer engineering university of Alberta, 2016.
[26]     W.W.S. Lee and E.K.N. Yung, “The input impedance of a coaxial line fed probe in a cylindrical waveguide” IEEE Transactions on Microwave Theory and Techniques, vol. 42, no. 8, August 1994.
[27]     X. Li and Y. Jiang, Design of a Cylindrical Cavity Resonator for Measurements of Electrical Properties of Dielectric Materials, Master Thesis, University of Gavle, Department of Technology, September, 2010.
[28]     D. M. Pozar, Microwave Network Analysis: in Microwave Engineering, 3rd edn, Wesley Publishing, pp. 220-240, 2005.
[29]     Maier, C. Leonard, Field Strength Measurements in Resonant Cavities, Research Laboratory of Electronics, Massachusetts Institute of Technology, Technical Report No.143, November 1949.
[30]     L.J. Wang, X.L. Wang and Q. C. Chen, “GA-based feature subset clustering for combination of multiple nearest neighbors classifiers,” in Machine Learning and Cybernetics Conference, Guangzhou, China, vol. 5, pp. 2982–2987, see also pp. 18–21, August 2005.
[31]     T. M. Cover and P.E. Hart, “Nearest neighbor pattern classification,” IEEE Transactions on Information Theory, vol. 13, no. 1, pp. 21–27, 1967.
[32]     B. K. Panigrahi, V. R. Pandi, “Optimal feature selection for classification of power quality disturbances using wavelet packet-based fuzzy k-nearest neighbour algorithm,” IET Gener. Transm & Distribution Journal, vol. 3, no. 3, pp. 296–306, 2009.
[33]   مهرداد حیدری ارجلو، سید قدرت‌الله سیف‌السادات و مرتضی رزاز،» یک روش هوشمند تشخیص جزیره در شبکه توزیع دارای تولیدات پراکنده مبتنی بر تبدیل موجک و –k نزدیک‌ترین همسایگی(KNN)»، مجله علمی پژوهشی مهندسی برق دانشگاه تبریز، دوره 43، شماره1 ، صفحه 26-15، 1392.
[34]     P. Parveen and B. Thuraisingham, “Face recognition using multiple classifiers,” in Conference on Tools with Artificial Intelligence, Arlington, Virginia, pp. 179-186, 2006.
[35]     S.A. Dudani, “The distance-weighted k-nearest-neighbor rule,”  IEEE Transactions on Systems, vol. SMC-6, no. 4, pp. 325–327, April 1976.
[36]     L. J. Wang, X. L. Wang and Q. C. Chen, “Combination of multiple k-NNCS by fuzzy integral,” in Conference on Machine Learning and Cybernetics, pp. 1774–1778, August 2006.
[37]     M.A. Hejazi, G.B. Gharehpetian, G. Moradi, H.A. Alehosseini and M. Mohammadi, ”Online monitoring of transformer winding axial displacement and its extent using scattering parameters and k-nearest neighbour method,” IET Gen. Trans& Distribution Journal, vol. 5, no. 8, pp. 824 - 832, , August 2011.

فایل ها

هم رسانی

ارجاع به این مقاله

آمار