Research on hybrid optimization and deep learning modeling method in the performance seeking control

A novel performance seeking control method based on hybrid optimization algorithm and deep learning modeling method is proposed to get a better engine performance. The deep learning modeling method, deep neural network, which has strong representation capability and can deal with big training data, is adopted to establish an on-board engine model. A hybrid optimization algorithm—genetic algorithm particle swarm optimization–feasible sequential quadratic programming—is proposed and applied to performance seeking control. The genetic algorithm particle swarm optimization–feasible sequential quadratic programming not only has the global search ability of genetic algorithm particle swarm optimization, but also has the high local search accuracy of feasible sequential quadratic programming. The final simulation experiments show that, compared with feasible sequential quadratic programming, genetic algorithm particle swarm optimization, and genetic algorithm, the proposed optimization algorithm can get more installed thrust, decrease fuel consumption between 2% to 3%, and decrease turbine blade temperature larger than 15k, while meeting all of the constraints. Moreover, it also shows that the proposed modeling method has high accuracy and real-time performance.

[1]  James W. Denham.  STOVL Integrated Flight and Propulsion Control: Current Successes and Remaining Challenges , 2002 .

[2]  H. H. Lambert,et al.  Preliminary Flight Evaluation of an Engine Performance Optimization Algorithm , 1991 .

[3]  Trindel A. Maine,et al.  A preliminary evaluation of an F100 engine parameter estimation process using flight data , 1990 .

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[6]  Prerna Gaur,et al.  Comparative Analysis of Hybrid GAPSO Optimization Technique With GA and PSO Methods for Cost Optimization of an Off-Grid Hybrid Energy System , 2014 .

[7]  Sheryll Goecke Powers.  An Electronic Workshop on the Performance Seeking Control and Propulsion Controlled Aircraft Results of the F-15 Highly Integrated Digital Electronic Control Flight Research Program , 1995 .

[8]  Haibo Zhang,et al.  On-board real-time optimization control for turbofan engine thrust under flight emergency condition , 2017, J. Syst. Control. Eng..

[9]  Kamran Behdinan,et al.  Particle swarm approach for structural design optimization , 2007 .

[10]  Lizhen Miao,et al.  On-Board Real-Time Optimization Control for Turbo-Fan Engine Life Extending , 2016 .

[11]  Timothy R. Conners,et al.  Supersonic Flight Test Results of a Performance Seeking Control Algorithm on a NASA F-15 Aircraft , 1997 .

[12]  Donald L. Simon,et al.  Adaptive Optimization of Aircraft Engine Performance Using Neural Networks , 1995 .

[13]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[14]  Lizhen Miao,et al.  A Study on the Installed Performance Seeking Control for Aero-Propulsion under Supersonic State , 2015 .

[15]  Steven G. Nobbs.  PSC algorithm description , 1995 .

[16]  Hong Chun Qu,et al.  Civil Aeroengine Fault Diagnosis Based on Fuzzy Least Square Support Vector Machine , 2011 .

[17]  Peter J. Fleming,et al.  Performance optimization of gas turbine engine , 2005, Eng. Appl. Artif. Intell..

[18]  Sun Jian-guo.  Aero-Engine Performance Seeking Control Based on Sequential Quadratic Programming Algorithm , 2005 .

[19]  Kushal Mukherjee,et al.  Fault detection and isolation in aircraft gas turbine engines. Part 2: Validation on a simulation test bed , 2008 .

[20]  Zhang Xiu-hua,et al.  A Hybrid Optimization Based on Linear Programming and Model-Assisted Pattern Search Method in PSC , 2006 .

[21]  Ahmed A. Kishk,et al.  Particle Swarm Optimization: A Physics-Based Approach , 2008, Particle Swarm Optimization.

[22]  Zhang Haibo,et al.  Application of Feasible Descent Sequential Linear Programming to Aeroengine Online Optimization , 2010 .

[23]  Haibo Zhang,et al.  Aero-Engine On-Board Dynamic Adaptive MGD Neural Network Model Within a Large Flight Envelope , 2018, IEEE Access.

[24]  Daren Yu,et al.  An approximate non-linear model for aeroengine control , 2011 .

[25]  Michael N. Vrahatis,et al.  Interval Analysis Based Neural Network Inversion: A Means for Evaluating Generalization , 2017, EANN.

[26]  Sandy H. Huang,et al.  Adversarial Attacks on Neural Network Policies , 2017, ICLR.

[27]  Liang Jia-hong,et al.  Parameters Nonlinear Estimation of the Propulsion System Performance Seeking Control Using Improved PSO , 2010 .

[28]  Haibo Zhang,et al.  A turboshaft engine NMPC scheme for helicopter autorotation recovery maneuver , 2018 .