نویسندگان
چکیده
هدف اصلی این مقاله، ارائة روشی مبتنی بر شبکة عصبی هوشمند همراه با شبیهسازی دینامیکی برپایة تحلیلهای ریاضی برای عیبیابی موتور سوخت مایعی است که امکان وجود اختلال در سامانة دادهبرداری آن وجود دارد. عیب، به شکل وقوع گرفتگی در مسیرهای متفاوت موتور و اختلال در سامانة دادهبرداری به صورت وجود اغتشاش در اندازهگیری یک پارامتر خروجی از موتور مدل میشود. نقطة کلیدی این طرح، بهکارگیریشبکههای عصبی موازی چند لایة «پیشخور» در تشخیص محل وقوع و میزان عیب،با استفاده از پارامترهای خروجی سامانة دادهبرداری معیوب است. شبیهسازی دینامیکی موتور انجام شده است تا بهوسیلة آن بتوان به دادههای مورد نیاز برای آموزش شبکة عصبی دست یافت. از یک الگوریتم فیلترینگ برای شناسایی و حذف داده اغتشاشی استفاده شده است. الگوریتم، ماتریس دادة تشکیل شده را به عنوان ورودی برای شبکة عصبی در نظر میگیرد که با دادههایی از همان جنس آموزش دیده است. روش عیبیابی مورد نظر، بهوسیلة دادههای آزمایشگاهی یک موتور سوخت مایع اعتبارسنجی شده است.
کلیدواژهها
عنوان مقاله [English]
Neural Network Based Diagnostic Indication of a Liquid Propellant Engine with Faulty Data Collection System
نویسندگان [English]
- S. Khodadadiyan
- R. Farokhi
- D. Ramesh
چکیده [English]
The aim of the paper is to describe a methodology of damage detection in the liquid propellant engine which is based on artificial neural networks in combination with stochastic analysis. It is assumed that the liquid propellant engine have faulty data collection system. Then a filtering algorithm for elimination perturbation data has been applied .The damage is defined as fuel and oxidizer channels clogging up. The key stone of the method is feed-forward multi layer network with back propagation algorithm. It is impossible to obtain appropriate training set for real engine, therefore stochastic analysis using mathematical model is carried out and dynamic simulation is made to get training set virtually. Engine channels clogging up leads to unwanted variation of pressure, flow rate of oxidizer and fuel and other main parameters of engine. Then variations considered as best input data for damage detection. The methodology was carried out using laboratory test.
کلیدواژهها [English]
- Diagnostic indication
- Neural Network
- Liquid Propellant Engine
- Faulty data collection system
- Yam L.H., Yan Y.J. and Jiang J.S., “Vibration-Based Damage Detection for Composite Structures Using Wavelet Transform and Neural Network Identification,” Composite Structures, Vol. 60, Issue 4, 2003, pp. 403-412.
- Hua, Y.F., Bing, L.H. and Jin, T.G., “Application of Neural Network Ensemble for Structural Damage Detection,” Journal of Jilin University (Engineering and Technology Edition), 37, Issue 2, 2007, pp. 438-441.
- Wu, J.D. and Chan, J.J., “Faulted Gear Identification of a Rotating Machinery Based on Wavelet Transform and Artificial Neural Network,” Expert Systems with Applications, 36, Issue 5, 2009, pp. 8862–8875.
- Rajakarunakaran, S., Venkumar, P., Devaraj, D. and Surya Prakasa Rao K., “Artificial Neural Network Approach for Fault Detection in Rotary System,” Artificial Neural Network Approach for Fault Detection in Rotary, 8, Issue 1, 2008, pp. 740–748.
- Wu, J.D., Huang, C.K., Chang,Y.W. and Shiao, Y.J., “Fault Diagnosis for Internal Combustion Engines using Intake Manifold Pressure and Artificial Neural Network,” Expert Systems with Applications, Vol. 37, Issue 2, 2010, pp. 949-958.
- Talebi, H.A., “A Recurrent Neural-Network-Based Sensor and Actuator Fault Detection and Isolation for Nonlinear Subsystem,” IEEE Transactions on Neural Networks, Vol. 20, Issue 1, 2009, pp. 45 – 60.
- Dervilis, N., Barthorpe, R.J., Antoniadou, I., Staszewski, W.J. and Worden, K., “Damage Detection in Carbon Composite Material Typical of Wind Turbine Blades Using Auto-Associative Neural Networks,” (Proceedings Paper), Health Monitoring of Structural and Biological Systems, 8348, 2012.
- Farrokhi, R. and Ramesh, D., “Nonlinear Dynamic Simulation of Liquid Propellant Engine with Four Combustion Chamber,” 15th International Conference of Mechanical Engineering, Amirkabir University, Tehran, 2007.
- Manfletti, Ch., “Transient Simulation of Liquid Rocket Engines: A Step Towards a More Educated Propellant Choice between Kerosene and Methane,” 2nd International Conference on Green Propellants for Space Propulsion, Cagliari, Sardinia, Italy, ESA, 2004.
- Beliaev, Chevanov, V., Chervakov, V., “Mathematical Modeling of Operating Process of Liquid Propellant Rocket Engines”, In Russian, 1999.
- Ramesh D., Aminpour M., “Nonlinear Dynamic Simulation of Liquid Propellant Engine,” 2nd International Conference of Aerospace Engineering,
- Kurkova, V., “Kolmogorov’s Theorem and Multilayer Neural Networks”, Neural Networks, Vol. 5, No. 3, 1992, 501–506.
- Snorek, M., Neural Networks and Neurocomputers, Vydavatelstvi, CVUT, Prague, Czech Republic, 2002.
- Singh, V., Gupta, I. and Gupta, H.O., “ANN-Based Estimator for Distillation Using Levenberg-Marquardt Approach,” Engineering Applications of Artificial Intelligence 20, 2007, pp. 249–259.