A size-transferring radial basis function network for aero-engine thrust estimation

Abstract Thrust regulation plays an important role in the aero-engine control. However, the thrust is unmeasurable in flight which poses a great challenge to the thrust control. Traditional thrust control methods are implemented by controlling the parameters tightly related to thrust and reserve enough safety margins to protect the engine. To realize the direct thrust control, the methods to estimate thrust is urgently required. In this paper, a new algorithm based on particle swarm optimization (PSO) and radial basis function neural network (RBFNN) is proposed to estimate the thrust. A strategy named “size-transferring” is developed to select and adjust the network size of the RBFNN. Besides, to solve the high-dimensional optimization problem during the estimation, a new approach based on the PSO algorithm is also illustrated. The successful application of the proposed algorithm to the aero-engine thrust estimation problem demonstrates its effectiveness.

[1]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[2]  Manfredi Maggiore,et al.  Estimator design in jet engine applications , 2003 .

[3]  P. Toint,et al.  Partitioned variable metric updates for large structured optimization problems , 1982 .

[4]  Wei Lu,et al.  An Adaptive-PSO-Based Self-Organizing RBF Neural Network , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Henry Cohen,et al.  Gas turbine theory , 1973 .

[7]  Sun Jian-guo Direct Control of Aeroengine Thrust Based on Correlation Analysis and Neural Networks , 2005 .

[8]  Jonathan S. Litt,et al.  An Optimal Orthogonal Decomposition Method for Kalman Filter-Based Turbofan Engine Thrust Estimation , 2013 .

[9]  S. N. Sivanandam,et al.  Introduction to genetic algorithms , 2007 .

[10]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[11]  Sun Jian-guo Application of adaptive genetic neural network algorithm in design of thrust estimator , 2007 .

[12]  Zhang Sheng-xiu Aero Engine Thrust Estimator Design Based on Kernel Method , 2013 .

[13]  Sun Jian-guo Aeroengine thrust estimation using least squares support vector regression machine , 2009 .

[14]  Harold Brown,et al.  Control of jet engines , 1999 .

[15]  Noureddine Zerhouni,et al.  SW-ELM: A summation wavelet extreme learning machine algorithm with a priori parameter initialization , 2014, Neurocomputing.

[16]  Claes Breitholtz,et al.  Model-based on-board turbofan thrust estimation , 2011 .

[17]  George B. Dantzig,et al.  Decomposition Principle for Linear Programs , 1960 .

[18]  Zhi-Qiang Li,et al.  A proposed self-organizing radial basis function network for aero-engine thrust estimation , 2019, Aerospace Science and Technology.

[19]  Zhang Tianhong,et al.  Aero-engine Thrust Estimation Based on Ensemble of Improved Wavelet Extreme Learning Machine , 2018 .

[20]  Donald L. Simon,et al.  Aircraft Engine Gas Path Diagnostic Methods: Public Benchmarking Results , 2014 .

[21]  Zbigniew Michalewicz,et al.  Impacts of Coefficients on Movement Patterns in the Particle Swarm Optimization Algorithm , 2017, IEEE Transactions on Evolutionary Computation.

[22]  P. N. Suganthan,et al.  Multi-population differential evolution with balanced ensemble of mutation strategies for large-scale global optimization , 2015, Appl. Soft Comput..

[23]  Chen Ting-hao Thrust estimator design based on K-means clustering and reduced least squares support vector regression , 2010 .

[24]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .