پیش‌بینی عمر مفید باقیمانده موتورهای توربین‌ گاز به روش دسته‌بندی سنی و بررسی مقاوم بودن روش پیشنهادی در شرایط کمبود داده

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، دانشکده مکانیک، دانشگاه شریف، تهران، ایران

2 استاد، دانشکده مکانیک، دانشگاه شریف، تهران، ایران

چکیده

روش‌های داده-پایه برای پیش‌بینی عمر، معمولاً نیازمند مقدار زیادی داده برای دستیابی به عملکرد مطلوب می‌باشند. لذا عملکرد آن‌ها به‌طور معمول برای مقادیر کم داده‌های آموزش مطلوب نمی‌باشد. روش پیش‌بینی به کمک دسته‌بندی سنی حجم داده‌های آموزش را از طریق بازتولید مجموعه اولیه داده‌ها افزایش می‌دهد، لذا این روش می‌تواند در مواردی که داده‌های آموزش اندک می‌باشد، استفاده شود. همچنین، ساختار پیشنهادی می‌تواند با بسیاری از روش‌های پیش‌بینی، ترکیب و دقت آن‌ها را به‌طور قابل توجهی بهبود ببخشد. در این مقاله، ساختار مدل پیش‌بینی عمر پیشنهادی شرح و اثربخشی آن برای پیش‌بینی در یک مطالعه موردی در موتورهای توربین گاز بررسی شده است. در بخش نخست، داده‌های کافی برای آموزش در دسترس بوده و نتایج آن با بهترین مقالات ارائه شده بر روی داده‌های مشابه مقایسه شده است. در بخش دوم، مقاوم بودن روش پیشنهادی در شرایط حجم داده‌های آموزش محدود بررسی شده است. در این قسمت خطای پیش‌بینی عمر برای موارد مختلف با حجم محدود داده‌های آموزش مقایسه شده است. نتایج این تحقیق اولاً بهره‌وری روش پیشنهادی را در مقایسه با سایر رویکردهای موجود نشان می‌دهد، و دوم مقاوم بودن روش را (در شرایط داده‌های محدود) نشان می‌دهد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Age-Based Clustering Prognostics of Gas Turbines and Evaluation of the Proposed Method Robustness in Data Deficient Conditions

نویسندگان [English]

  • ali mahmoodian 1
  • mohamad durali 2
  • mahmud saadat 2
1 PhD candidate, Mechanical Engineering, Sharif University of tech
2 Professor, Mechanical Engineering, Sharif University of tech
چکیده [English]

The acceptable performance of the data-driven prognostics methods usually requires a large amount of data, therefore the performance usually is not desirable for small amount of data. The age clustering method multiplies the volume of the train data through observing data at multiple points. The advantage of the method is that it can be used for learning from a small set of data. The proposed approach is integratable with existing prediction methods and improves the accuracy of their result significantly. In this article, the ABC prognosis framework is described, its effectiveness for prognosis in normal conditions is illustrated in a case study on turbofan engines and a comparison with existing results on the same data is made. The paper continues with a study on the robustness of the proposed method under limited data conditions. The prognosis accuracy is compared for the case study in various conditions of available train data. The results emphasize (1) the efficiency of the method compared to other existing approaches in normally rich data condition and (2) the robustness of the results under limited data condition.

کلیدواژه‌ها [English]

  • Prognosis and health management
  • Reliability
  • Limited data
  • Remaining useful life estimation
[1] E. khavasi, S. Nasiri, Analysis and Simulation of Surge phenomena in the axial Compressor of GE-frame 6 gas Turbine, Amirkabir Journal of Mechanical Engineering, online published (2019) (in persian).
 [2] R. Jiang, C. Huang, Predicting distribution of time to degradation limit using a weighted approach, Journal of Mechanical Science and Technology, 32(11) (2018) 5133-5138 (in Persian) .
[3] R. Bannazadeh, R. M, A. M., Failure Analysis of a Gas Turbine Blade Made of Inconel 738LC Super Alloy, Amirkabir Journal of Mechanical Engineering, 50 (2018) 103-112.
[4] D. Kwon, J. Yoon, A model-based prognostic approach to predict interconnect failure using impedance analysis, Journal of Mechanical Science and Technology, 30(10) (2016) 4447-4452.
[5] D. An, J.H. Choi, K. N, Prediction of remaining useful life under different conditions using accelerated life testing data, Journal of Mechanical Science and Technology, 32 (2018) 2497-2507.
[6] F.O. Heimes, Recurrent neural networks for remaining useful life estimation, international conference on prognostics and health management (IEEE),  (2008) 1-6.
[7] J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, D. Siegel, Prognostics and health management design for rotary machinery systems-Reviews, methodology and applications, Mechanical systems and signal processing, 42 (2014) 20.
[8] S.M. Raghavan, A. Palatel, J. Simon, Health Assessment of Gas Turbine Compressor Using Process History Based Modelling Approach, ASME 2015 Gas Turbine India Conference (pp. V001T08A001-V001T08A001). American Society of Mechanical Engineers.,  (2015).
[9] M. Garsia A. Munoz, A. Sola, Hybrid model-based fault detection and diagnosis for the axial flow compressor of a combined-cycle power plant, Journal of Engineering for Gas Turbines and Power, 135 (2013).
[10] R. Sekhon, Real Time Prognostic Strategies Application to Gas Turbines, Clemson university Technical Report (2007).
[11] P. Baraldi, F. Cadini, F. Mangili, E. Zio, Model-based and data-driven prognostics under different available information, Probabilistic Engineering Mechanics, 32 (2013) 66-79.
[12] Y.G. Li, P. Nilkitsaranont, Gas turbine performance prognostic for condition-based maintenance, Applied energy, 86 (2009) 2152-2161.
[13] F. Lu, J. Wu, J. Huang, X. Qiu, Aircraft engine degradation prognostics based on logistic regression and novel OS-ELM algorithm, Aerospace Science and Technology,  (2019) 661-671.
[14] D. An, N.H. Kim, J.H. Choi, Statistical aspects in neural network for the purpose of prognostics, . Journal of Mechanical Science and Technology, 29 (2015) 1369-1375.
[15] W. Zhao, A Probabilistic Approach for Prognostics of Complex Rotary Machinery Systems, Doctoral dissertation, University of Cincinnati,  (2015).
[16] J. Son, S. Zhou, C. Sankavaram, X. Du, Y. Zhang, Remaining useful life prediction based on noisy condition monitoring signals using constrained Kalman filter, Reliability Engineering & System Safety, 152 (2016) 38-50.
[17] O.N. Diallo, A data analytics approach to gas turbine prognostics and health management, Doctoral dissertation, Georgia Institute of Technology,  (2010).
[18] M. Daigle, S. Sankararaman, Predicting remaining driving time and distance of a planetary rover under uncertainty, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, 2 (2016).
[19] W. Caesarendra, W. , A. , B.S. Yang, Combination of probability approach and support vector machine towards machine health prognostics, Probabilistic Engineering Mechanics, 26 (2011) 165-173.
[20] H.Z. Huang, H.K. Wang, Y.F. Li, L. Zhang, Z. Liu, Support vector machine based estimation of remaining useful life: current research status and future trends, Journal of Mechanical Science and Technology,  (2015) 151-163.
[21] F. Lu, J. Wu, J. Huang, X. Qiu, Aircraft engine degradation prognostics based on logistic regression and novel OS-ELM algorithm, Aerospace Science and Technology, 84 (2019) 661-671.
[22] D. Simon, A comparison of filtering approaches for aircraft engine health estimation, Aerospace Science and Technology,  (2008) 276-284.
[23] K.T. McClintic, Feature prediction and tracking for monitoring the condition of complex mechanical systems, Doctoral dissertation, Pennsylvania State University,  (1998).
[24] D.C. Swanson, A general prognostic tracking algorithm for predictive maintenance, IEEE Aerospace Conference Proceedings,  (2001) 2971-2977.
[25] F. Lu, H. Ju, J. Huang, An improved extended Kalman filter with inequality constraints for gas turbine engine health monitoring, Aerospace Science and Technology,, (58) (2016) 36-47.
[26] C. Ding, J. Xu, L. Xu, ISHM-based intelligent fusion prognostics for space avionics, Aerospace Science and Technology,, 29 (2013) 200-205.
[27] Goebel K, Saha B, S. A.. A comparison of three data-driven techniques for prognostics. In62nd meeting of the society for machinery failure prevention technology,  (2008) 119-131.
[28] J. Xu, Y. Wang, L. Xu, PHM-oriented integrated fusion prognostics for aircraft engines based on sensor data, IEEE Sensors Journal, 14 (2013) 1124-1132.
[29] R. Salehi, A. Alasty, G.R. Vossoughi, Sliding Mode Observers to Detect and Isolate Faults in a Turbocharged Gasoline Engine, SAE International Journal of Engines, 8 (2015) 399-410.
[30] N. Puggina, M. Venturini, Development of a Statistical Methodology for Gas Turbine Prognostics, ASME 2011 Turbo Expo, Turbine Technical Conference and Exposition, 4 (2011) 981-992.
[31] M. Venturini, D. Therkorn, Application of a statistical methodology for gas turbine degradation prognostics to alstom field data, Journal of Engineering for Gas Turbines and Power,, 135 (2013).
[32] M. Venturini, N. Puggina, Prediction reliability of a statistical methodology for gas turbine prognostics, Journal of Engineering for Gas Turbines and Power, 134 (2012).
[33] Musavi A, R. H., Failure analysis of compressor blades in a gas turbine,  International Power System Conference, 22 (2009) (in Persian).
[34] C.M. Holcomb, Diagnostics and Control of Gas Turbines Through System Identification, Doctoral dissertation, UC San Diego,  (2015).
[35] P. Wang, G. Vachtsevanos, Fault prognostics using dynamic wavelet neural networks, AI EDAM, 15 (2001) 349-365.
[36] R. Yan, R.X. Gao, X. Chen, Wavelets for fault diagnosis of rotary machines: A review with applications, Signal processing, 96 (2014) 1-15.
[37] R. Mao, H. Zhu, L. Zhang, A. Chen, A new method to assist small data set neural network learning, Sixth International Conference on Intelligent Systems Design and Applications 1(2006) 17-22.
[38] R. Moghaddass, M.J. Zuo, An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration process, Reliability Engineering & System Safety,  (2014) 92-104.
[39] Y. Xiang, Y. Liu, Application of inverse first-order reliability method for probabilistic fatigue life prediction, Probabilistic Engineering Mechanics, 26  148-156.
[40] M. Gholamrezaei, K. Ghorbanian, Application of integrated fuzzy logic and neural networks to the performance prediction of axial compressors, Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy, 229 (2015) 928-947.
[41] D. Zhou, H. Zhang, S. Weng, A novel prognostic model of performance degradation trend for power machinery maintenance, Energy, 78 (2014) 740-746.
[42] A. Saxena, K. Goebel, D. Simon, Damage propagation modeling for aircraft engine run-to-failure simulation, international conference on prognostics and health management (IEEE),  (2008  ) 1-9.
[43] E. Ramasso, M. Rombaut, N. Zerhouni, Joint prediction of observations and states in time-series: a partially supervised prognostics approach based on belief functions and KNN, networks,  (2013).
[44] R. Khelif, S. Malinowski, B. Chebel-Morello, N. Zerhouni, RUL prediction based on a new similarity-instance based approach, 23rd International Symposium on Industrial Electronics (ISIE),  (2014) 2463-2468.
[45] E. Ramasso, Investigating computational geometry for failure prognostics, International Journal of Prognostics and Health Management,, 5 (2014).
[46]A, Mahmoodina. M Durali, Saadat M, A Data Driven Prognostics Method for Gas Turbines with Limited Information Using an Age Based Clustering Algorithm, 20th International Conference on Gas Turbines,,  (2018) (in Persian).
[47] M. Tahan, E. Tsoutsanis, M. Muhammad, Z.A. Karim, Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review, Applied energy, 198 (2017) 122-144.
[48] M. Makvandi H , Moradi.S., Crack identification in postbuckled plates using differential quadrature element method and sequential quadratic programming, Amirkabir Journal of Mechanical Engineering, online published (2018).
[49] S.R. Prasad, A.S. Sekhar, Life estimation of shafts using vibration based fatigue analysis, Journal of Mechanical Science and Technology, 32 (2018) 4071-4078.
[50] C. Fisher, N.C. Baines, . Multi-sensor condition monitoring systems for gas turbines, Journal of Condition Monitoring,  (1988) 57-68.
[51] D. Muir, B. Taylor, Oil debris monitoring for aeroderivative gas turbine, ASME Power Division (Publication) PWR,,  (1997).547-553.
[52] M. Behzad, A. Ebrahimi, M. Heydari, M. Asadi, Experimental investigation on the fault diagnosis of permanent magnet DC electromotors, Insight, 55 (2013) 1-8.
[53] M. Behzad, M.R. Hoseini, H. Salmasi, M. Asayesh, Fault Diagnosis In Two Industrial Applications By Vibration Analysis, Proceeding of IMEC 2004,  (2004) 591-603.
[54] M. Behzad, A.R. Bastami, M. Maassoumian, Fault diagnosis of a centrifugal pump by vibration analysis, ASME 7th Biennial Conference on Engineering Systems Design and Analysis (2004) 221-226.
[55] M. Behzad, M. Asoyesh, Steam turbine coupling misalignment detection by vibrational analysis, Journal of Electrical Science and Technology, 13 (2001) 47-53.
[56] A.H. Zamanian, A. Ohadi, 2011, Gear fault diagnosis based on Gaussian correlation of vibrations signals and wavelet coefficients, Applied Soft Computing, 11 (2011) 4807-4819.
[57] N Mahmoodi, Lari H, Using vibrating properties of gas turbines to prevent failure, 15th International Power System Conference,  (1999).
[58] E. Halim, Fault Detection And Diagnosis Of Rotating Machineries, Doctoral dissertation, Alberta university,  (2009).
[59] M. Rezaei, B. .M., M. , Moradi, H. , H. Haddadpour, Modal-based damage identification for the nonlinear model of modern wind turbine blade, Renewable energy,, 94 (2016) 391-409.
[60] E. Mohammadi, M. Montazeri-Gh, Simulation of full and part-load performance deterioration of industrial two-shaft gas turbine, Journal of Engineering for Gas Turbines and Power,, 136 (2014).
[61] B. Zhou, K. Bhimavarapu, . Effect of Condition Monitoring on Risk Mitigation for Steam Turbines in the Forest Products Industry, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B: Mechanical Engineering, 3 (2017).
[62] A Mahmoodian,. M Durali, Saadat M, Investigating Different Structures for Mapping Sensor Information of a Complex Mechanical System to Its Health Status, Proceedings of the 26th ISME Conference,  (2018) 110-114 (in persian)
[63] M Kamari,G Payeganeh., Implementation of Neuro– Fuzzy and Multi-Layer Perceptron System Intelligent Techniques for Main Fault Diagnosis of Rotating Machinery, Amirkabir Journal of Mechanical Engineering, 45 (2013) 105:118
[64] E. Ramasso, A. Saxena, . Review and analysis of algorithmic approaches developed for prognostics on CMAPSS dataset, International Journal of Prognostics and Health Management,,  (2014).
[65] T. Wang, J. Yu, Siegel, J. D. and Lee, A similarity-based prognostics approach for remaining useful life estimation of engineered systems, In 2008 international conference on prognostics and health management,  (2008) 1-6.
[66] K. Javed, R. Gouriveau, N. Zerhouni, Novel failure prognostics approach with dynamic thresholds for machine degradation, In IECON 2013-39th Annual Conference of the IEEE Industrial Electronics Society,  (2013) 4404-4409.