دانش و فناوری هوافضا

دانش و فناوری هوافضا

تحلیل حساسیت مشخصه‌های ارتعاشی جهت تشخیص موقعیت عیب نابالانسی جرمی پره بالگرد با استفاده از نمودار توزیع وزن‌های شبکه عصبی خود سازمان‌ده

نوع مقاله : مقاله پژوهشی

نویسندگان
1 کارشناسی ارشد، دانشکده مهندسی هوافضا، دانشگاه صنعتی مالک اشتر، تهران
2 استادیار، دانشکده مهندسی هوافضا، دانشگاه صنعتی مالک اشتر، تهران
چکیده
یکی از مباحث مهم و موانع توسعه سیستم­های پایش سلامت وسایل پرنده، حجم بالای داده‌های مورد نیاز جهت صحه‌گذاری و اعتبارسنجی الگوریتم‌ها است. در این پژوهش راهکاری مناسب جهت کاهش تعداد سنسور­ها، حجم داده‌های مورد نیاز و محاسبات در سیستم پایش سلامت روتور اصلی بالگرد ارائه شده است. بدین منظور، با استفاده از شبکه­های عصبی خودسازمان­ده، شیوه­ای جدید جهت تحلیل حساسیت میان مشخصه­های استخراج شده از سیگنال‌های ارتعاشی مدل دینامیکی روتور اصلی بالگرد جهت تقلیل داده‌برداری پیشنهاد شده است. در ابتدا  با استفاده از یک مدل دینامیکی غیرخطی مفصل بالگرد، سیگنال‌های متناظر با 15 حالت نابالانسی جرمی به عنوان گستره‌ای از عیوب روتور شبیه‌سازی گردیده است. سپس، ۱۶ مشخصه تحلیل سیگنال ارتعاشی از شتاب­های خطی و زاویه­ای وارده بر هاب روتور اصلی در حالت دائمی پرواز، از طریق پیش‌پردازش و روابط مربوطه استخراج شده است. در نهایت از طریق یک شبکه عصبی خودسازمان­ده، نمونه­های مختلف بانک اطلاعاتی 96 مشخصه ارتعاشی، خوشه‌بندی گردیده و مشخصه­های مهم و کلیدی جهت استفاده در الگوریتم عیب‌یابی با استفاده از نمودار توزیع وزن مشخصه‌های مختلف معرفی شده است.
کلیدواژه‌ها

عنوان مقاله English

Sensitivity analysis of vibration characteristics for localization of Imbalance fault on the helicopter blade

نویسندگان English

Seyyed Mohammad Mirmohammadi 1
Mostafa Khazaee 2
Amir Mahdi Shahverd 1
1 Master of Science, Faculty of Aerospace, Malek Ashtar University of Technology, Iran
2 Assistant Professor, Faculty of Aerospace, Malek Ashtar University of Technology
چکیده English

One of the important subjects and barriers to the development of health and usage monitoring systems for air vehicles is a large amount of required data for the algorithm validation. In this research, an appropriate solution is proposed to reduce the number of sensors, the volume of data, and the calculations in the helicopter's main rotor health monitoring system. Using the self-organizing neural network, an algorithm is developed for sensitivity analysis between vibration characteristics that are extracted from the rotor sensors to minimize the required data acquisition tests. First, a comprehensive nonlinear dynamic model of a helicopter is used for the simulation of the signals for 15 imbalance faults as an example of rotor faults. Then, 16 vibration characteristics are calculated and extracted from linear and rotational accelerations of the main rotor hub in steady flight conditions. Finally, different samples of 96 characteristics from this dataset are clustered using a self-organizing neural network, and the effective and key characteristics for fault detection are determined.

کلیدواژه‌ها English

Health Monitoring
Neural Network
Signal Processing
Sensitivity Analysis
Characteristics Signal
[1] A. Andrew and H. Azzam , Effects of Helicopter Main Rotor Faults on Fuselage Vibration Modes, in AIAA /AHS/ASC Structures, 1991.
[2] A. Andrew, The Use of Infield Data and Math Dynamic Models to Evaluate Diagnostic Strategies for Main Rotor Systems Faults, in ASCE/AHS/ASC Structures, 1991. 
[3] H. Azzam, R. Callan and A. Andrew, The Implementation of a Pattern Recognition Technique to Classify Main Rotor System Faults, AIAA/ASME Adaptive Structures Forum 1991.
[4] R. Ganguli,  I. Chopra, and D. Haas, Formulation of a rotor-system damage detection methodology, In AIAA/ASME/ASCE/AHS/ASC Structures and AIAA/ASME Adaptive Structures Forum, New Orleans, 1995.
[5] R. Ganguli,  I. Chopra, and D. Haas, Detection of helicopter rotor system simulated faults using neural networks, Journal of the american helicopter society , 1997.
[6] J. Pouradier and M. Trouvé, An Assessment of Eurocopter Experience in HUMS Development and Support, Proceedings of the 57th AHS International Annual Forum, 2001.
[7] H. Decker, Gear Crack Detection using Tooth Analysis, Proceedings of the th Meeting of the Society for MFPT,2002.
[8] Yang, M., I. Chopra, and D. Haas, Rotor System Health Monitoring Using Coupled Rotor-Fuselage Vibration Analysis, Annual Forum Proceedigns - American Helicopter Society, 2000.
[9] P. J. Dempsey and A. A. Afjeh,  Integrating Oil Debris and Vibration Gear Damage Measurement Technologies Using Fuzzy Logic, Journal of the American Helicopter Society, 2004.
[10] S. Maley, J. Plets, and N. D. Phan, US Navy Roadmap to Structural Health and Usage Monitoring-The Present and Future, Annual Forum Proceedings-American Helicopter Society, INC, 2007.
[11] L. Andrew, C. Cheung, and M. Martinez, Use of artificial neural networks for helicopter load monitoring, in In Proc. 7th DSTO Int. Conf. on Health & Usage Monitoring,2011.
[12] Q. Xin, J. Qi, D. Theilliol, Y. Zhang, J. Han, D. Song, and C. Hua, A review on fault diagnosis and fault tolerant control methods for single-rotor aerial vehicles, Journal of Intelligent & Robotic Systems,2014.
[13] D. Mylaraswamy, B. Xu, P. Dietrich and A. Murugan, Case Studies: Big Data Analytics for System Health Monitoring, in In Proceedings on the International Conference on Artificial Intelligence (ICAI), 2014.
[14] H. Azzam and  J. McFeat, Development, validation, verification and certification of structural health monitoring systems for military aircraft, MASAAG, 2016.
[15] X. Liqing, Z. Cheng, H. Yan, G. Yunan and F. Haiyan, A frame design of helicopter health monitoring and diagnosis system based on testability, in Prognostics and System Health Management Conference  2017.
[16] C. V. Garzón, G. B. Moncayo, D. H. Alcántara, J. C. T. Martínez and R. M. Menendez, Towards an automatic system to spindle fault detection, in IFAC International Federation of Automatic Control, 2018.
[17] J. Serafini, G. Bernardini, R. Porcelli and P. Masarati, In-flight health monitoring of helicopter blades via differential analysis, Aerospace Science and Technology, 2019.
[18] A. Mauricio, L. Zhou, D. Mba and K. Gryllias, Vibration based condition monitoring of helicopter gearboxes based on cyclostationary analysis, Turbomachinery Technical Conference and Exposition, 2019.
[19] Z. He, H. Shao, X. Zhong, Y. Yang and J. Cheng, An intelligent fault diagnosis method for rotor-bearing system using small labeled infrared thermal images and enhanced CNN transferred from CAE, Elsevier, Advanced Engineering, 2020.
[20] H. Li, G. Feng, D. Zhen and F. Gu, A normalized frequency-domain energy operator for broken rotor bar fault diagnosis‏, IEEE Transactions on Instrumentation and Measurement,2020.
[21] M. Aleksey and D. Pavel, The Demonstrator of Structural Health Monitoring System of Helicopter Composite Blades, in ICSI The 4th International Conference on Structural Integrity, 2021 .
[22] R. C. Cristobal, S. Andrew and F. Arturo, Experimental assessment of a broadband vibration and acoustice mission sensor for rotorcraft transmission monitoring, in 7th European Conference of the Prognostics and Health Management Society, 2022.
[23] J. Leoni, F. Zinnari, E. Villa, M. Tanelli and A. Baldi, Flight regimes recognition in actual operating conditions: A functional data analysis approach, ELSEVIER, no. Engineering Applications of Artificial Intelligence, 2022.
[24] E. Gildish, M. Grebshtein, Y, Aperstein, A. Kushnirski and I. Makienko,  Helicopter Bolt Loosening Monitoring using Vibrations and Machine Learning, in 7th European Conference of the Prognostics and Health Management Society, 2022.
[25] J.J. Howlett, UH-60A black hawk engineering simulation program. volume 1: Mathematical Model, NASA Ames Research Center, 1981.
[26] Tamayo. Sergio, "Design of fault tolerant control system for individual blade control helicopters" (2011). Graduate Theses,
[27] Cluster with Self-Organizing Map Neural Network 1994-2016.