To solve the difficulty of establishing models for starting process of a certain type of turbo-shaft engine by analytical methods, a data-driven method for model identification of the starting process of a turbo-shaft engine based on the Extreme Learning Machine optimized by the Quantum-behaved Particle Swarm Optimization (QPSO-ELM) algorithm is proposed. Firstly, a subsection model for the starting process of the turbo-shaft engine is constructed in light of the description of the state space method. Then, the QPSO-ELM algorithm is adopted to identify the constructed model in combination with data of the engine starting test. The identification results of the speed of the gas generator rotor, the speed of the engine output shaft and the temperature of the gas turbine outlet are all close to measured data, the mean maximum relative errors are 1.358%, 1.628% and 2.195%, respectively, which can meet the precision requirement of practical application. In addition, the identification accuracy of the QPSO-ELM is better than the Extreme Learming Machine (ELM), the Support Vector Machine (SVM) and the Back Propagation (BP) neural network.
[1] ASGARI H, VENTURINI M, CHEN X Q, et al. Modeling and simulation of the transient behavior of an industrial power plant gas turbine[J]. Journal of Engineering for Gas Turbines and Power, 2014, 7(2): 13-24.
[2] POGORELOV G I, KULIKOV G G, ABDULNAGIMOV A I, et al. Application of neural network technology and high-performance computing for identification and real-time hardware-in-the-loop simulation of gas turbine engines[J]. Procedia Engineering, 2017, 176: 402-408.
[3] 陈超, 王剑影. 基于RBF神经网络的航空发动机起动模型辨识与仿真[J]. 燃气涡轮试验与研究, 2005, 18(1): 17-26. CHEN C, WANG J Y. Identification and simulation of an engine start model based on RBF neural networks[J]. Gas Turbine Experiment and Research, 2005, 18(1): 17-26 (in Chinese).
[4] 李应红, 刘建勋. 基于支持向量机的涡扇发动机起动性能估算研究[J]. 航空学报, 2005, 26(1): 32-35. LI Y H, LIU J X. Turbofan engine starting characteristics estimation based on support vector machines[J]. Acta Aeronautica et Astronautica Sinica, 2005, 26(1): 32-35 (in Chinese).
[5] 王冠超, 杨春, 徐波, 等. 基于改进PSO-SVM参数优化的发动机起动过程辨识[J]. 燃气涡轮试验与研究, 2011, 24(1): 35-41. WANG G C, YANG C, XU B, et al. Engine start identification based on parameter optimization of improved PSO-SVM[J]. Gas Turbine Experiment and Research, 2011, 24(1): 35-41 (in Chinese).
[6] 焦洋, 李秋红, 朱正琛, 等. 基于ADE-ELM的涡轴发动机建模方法[J]. 航空动力学报, 2016, 31(4): 965-973. JIAO Y, LI Q H, ZHU Z C, et al. Turbo-shaft engine modeling method based on ADE-ELM[J]. Journal of Aerospace Power, 2016, 31(4): 965-973 (in Chinese).
[7] HUANG G B, DING X, ZHOU H. Optimization method based extreme learning machine for classification[J]. Neurocomputing, 2010, 74(1-3): 155-163.
[8] LIU N, WANG H. Ensemble based extreme learning machine[J]. IEEE Signal Processing Letters, 2010, 17(8): 754-757.
[9] DENG C W, HUANG G B, JIA X U, et al. Extreme learning machines: New trends and applications[J]. Science China Information Sciences, 2015, 58(2): 1-16.
[10] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[11] HUANG G B. What are extreme learning machines? Fill ing the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle[J]. Cognitive Computation, 2015, 7(3): 263-278.
[12] 范庚, 马登武. 基于组合优化相关向量机的航空发动机性能参数概率预测方法[J]. 航空学报, 2013, 34(9): 2110-2121. FAN G, MA D W. Probalistic prediction method for aeroengine performance parameters based on combined optimum relevance vector machine[J]. Acta Aeronautica et Astronautica Sinica, 2013, 34(9): 2110-2121 (in Chinese).
[13] ZHANG J, XIA P Q. An improved PSO algorithm for parameter identification of nonlinear dynamic hysteretic models[J]. Journal of Sound and Vibration, 2017, 389: 153-167.
[14] SATO M, FUKUYAMA Y. Total optimization of smart community by differential evolutionary particle swarm optimization[J]. International Federation of Automatic Control, 2017, 50(1): 201-206.
[15] 逄珊, 杨欣毅, 林学森. 一种基于量子粒子群优化的极限学习机[J]. 系统仿真学报, 2017, 29(10): 2447-2458. PANG S, YANG X Y, LIN X S. Evolutionary extreme learning machine optimized by quantum-behaved particle swarm optimization[J]. Journal of System Simulation, 2017, 29(10): 2447-2458 (in Chinese).
[16] YANG X Y, PANG S, SHEN W, et al. Aero-engine fault diagnosis using an optimized extreme learning machine[J]. International Journal of Aerospace Engineering, 2016, 2016: 7892875.
[17] YANG X Y, SHEN W, PANG S, et al. A novel gas turbine engine health status estimation method using quantum-behaved particle swarm optimization[J]. Mathematical Problems in Engineering, 2014, 2014: 302514.
[18] JIANG T Y, LI J, HUANG K W. Longitudinal parameter identification of a small unmanned aerial vehicle based on modified particle swarm optimization[J]. Chinese Journal of Aeronautics, 2015, 28(3): 865-873.
[19] 宋汉强, 李本威, 张赟, 等. 基于聚类与粒子群极限学习机的航空发动机推力估计器设计[J]. 推进技术, 2017, 38(6): 1379-1385. SONG H Q, LI B W, ZHANG Y, et al. Aero-engine thrust estimator design based on clustering and particle swarm optimization extreme learning machine[J]. Journal of Propulsion Technology, 2017, 38(6): 1379-1385 (in Chinese).
[20] 邵干, 张曙光, 唐鹏. 小型无人机气动参数辨识的新型HGAPSO算法[J]. 航空学报, 2017, 38(4): 120365. SHAO G, ZHANG S G, TANG P. HGAPSO: A new aerodynamic parameters identification algorithm for small unmanned aerial vehicles[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(4): 120365 (in Chinese).
[21] SUN J, FENG B, XU W B. Particle swarm optimization with particles having quantum behavior[C]//Proceeding of the IEEE Congress on Evolutionary Computation. Piscataway, NJ: IEEE Press, 2004: 325-331.
[22] 樊思齐, 刘清波, 荣向军, 等. 利用飞行试验信号对发动机模型辨识的研究[J]. 航空学报, 1993, 14(8): 399-423. FAN S Q, LIU Q B, RONG X J. Identification investigation of engine model using flight test signals[J]. Acta Aeronautica et Astronautica Sinica, 1993, 14(8): 399-423 (in Chinese).
CJA