ALGORITHMS FOR DIAGNOSTIC AND PARAMETER OF FAILURES OF CHANNELS OF MEASUREMENT OF TV3-117 AIRCRAFT ENGINE AUTOMATIC CONTROL SYSTEM IN FLIGHT MODES BASED ON NEURAL NETWORK TECHNOLOGIES
DOI:
https://doi.org/10.18372/2306-1472.84.14950Keywords:
aircraft engine, automatic control systems, noisy environments, identification, built-in linear adaptive on-board engine mathematical model, measurement channel, algorithms of fault diagnostics and counteraction, fault detection and isolationAbstract
The solution of the reliability increasing problem of the TV3-117 aircraft engine automatic control system (ACS) through the use of the algorithmic redundancy is offered. The purpose of research is development of algorithms of measuring channels’ fault diagnostics and counteraction for input parameters of linear adaptive on-board engine model (LABEM) built into the ACS. The LABEM basic mathematics is shown. The static model is based on the throttle characteristics of the individual engine. The throttle characteristics was obtained in the acceptance tests or "race" in the operation after the service. The lower level dynamic linear mathematical model of a gas-turbine engine is obtained by state space method. The technical and theoretical difficulties of practical implementation of algorithmic reservation by the model are associated with the high dimensionality of the engine state space, that are significantly higher than the dimension of the vector of parameters measured on board. There is a problem of identification of sensor fault with subsequent replacement of the value by modeling information. The necessity of fault detection and isolation algorithms in is justified. To improve the reliability of the fuel circuit input information the Kalman-filtering algorithms with integrated fault detection and isolation logic for the measuring channels are used. The fault detection and isolation algorithms for sensors’ channels measurement in dosing needle loop based on Kalman filters were described. The algorithms are based on the calculation of the fault signature as weighted sum of the squares of residuals (WSSR), which is compared with the selected threshold value. The practice results of engines’ stand tests and MatLab simulation showed the high reliability and quality of TV3-117 aircraft engine ACS based on proposed algorithms.
References
Panov V. (2014). “Auto-tuning of real-time dynamic gas turbine models”, Proceedings of ASME Turbo Expo 2014: Turbine Technical Conference and Exposition, June 16–20, 2014. 10 p.
Kong Ch., Kang M., Koh S. and Park G. (2013). “A study on practical condition monitoring system for 2-spool Turbofan Engine using artificial intelligent algorithms”, American Institute of Aeronautics and Astronautics, 9 p.
Malloy D.J., Webb A.T. and Kidman D. (2002). “Propulsion System Ground and Flight Test Analysis Using Modeling and Simulation”, Proceedings of ASME Turbo-Expo 2002, June 03–06, 2002, 2002. 8 p.
Zhernakov, S. (2007). “Neural network technology for diagnosing the technical condition of aircraft engines”, Information Technology, no. 8, pp. 22–29. (in Russian)
Vladov S., Shmelov Yu., Kotliarov K., Hrybanova S., Husarova O., Derevyanko I. and Chyzhova L., (2019). “Onboard parameter identification method of the TV3-117 aircraft engine of the neural network technologies”, Transactions of Kremenchuk Mykhailo Ostrohradskyi National University, issue 5/2019 (118), pp. 90–96.
Kuznetsova T., Avgustinovich V. and Iakushev A. (2014). “The statistical analysis of processes in aircraft engine control systems with on-board mathematical models”, Scientific and Technical Volga region Bulletin, 2014, no. 35, pp. 236–238. (in Russian)
Kuznetsova T., Gubarev E. and Likhacheva Iu. (2014). “The optimal filtering algorithms in tasks of automatic control aircraft engine parameters’ identification”, Information-measuring and Control Systems, vol. 12, no. 9, pp. 12–20. (in Russian)
Kobayashi T. and Simon D.L. (2003). “Application of a bank of Kalman filters for aircraft engine fault diagnostics”, Proceedings of ASME Turbo Expo 2003, 10 p.
Kobayashi T. and Simon D.L., (2008). “Aircraft Engine On-Line Diagnostics Through Dual-Channel Sensor Measurements: Development of Baseline System”, Proceedings of ASME Turbo-Expo 2008, June 09–13, 2008, 13 p.
Borguet S. and Leonard O. (2007). “A sensor-fault-tolerant diagnosis tool based on a quadratic programming approach”, Proceedings of ASME Turbo Expo 2007, 10 p.
Kobayashi T. and Simon D.L. (2007). “Integration of on-line and off-line diagnostic algorithms for aircraft engine health management”, Proceedings of ASME Turbo Expo 2007, 11 p.
Alessandri A., Cuneo M. and Pagnan S. (2001). “On the convergence of EKF-based parameters optimization for Neural Networks”, Proceedings of the 42nd IEEE Conference on Decision and Control, vol. 6, pp. 6181–6186.
Feldkamp L.A. and Puskorius G.V. (1994). “Training controllers for robustness: multi–stream DEKF”, Proceedings of International Conference on Neural Networks, 27 June 27 – July 02, 1994, vol. 4, pp. 2377–2382
Haykin S. (2006). Neural networks: full course, Moscow, Williams, 1104 p.
Haykin S. (2009). Neural Networks and Learning Machines (Third Edition), New York, Prentice Hall, 936 р.
