In this paper an intelligent control methodology is developed and used for the design and implementation of reconfigurable controllers capable of switching between different operating conditions of a longitudinal aircraft model. The methodology is based on the adaptive-neuro fuzzy inference system (ANFIS) and is used to design reconfigurable controllers for commercial aircrafts operating under uncertain flight conditions. This methodology is an attempt to solve the problems of using indicator function presented in [1]. Some of these problems include; discontinuity when switching between operating conditions, requirement of an indicator function and, impracticality for real-time implementation. Several linearized longitudinal aircraft models are extracted from a Generic Transport Model (GTM) and are used to test by simulation the performance of the developed control system. In the work, two adaptive controllers are designed and used to test the performance of the reconfigurable control system. Two additional optimal controllers are developed using the LQR method and are used to establish two reference models of the aircraft operating at two different flight conditions. Then an ANFIS based reconfigurable controllers are trained to work in coordination with the established reference models. Finally, the ANFIS based reconfigurable control system is tested under several operating conditions near the operating conditions of the reference models. The different tests of the ANFIS based reconfigurable control system produced desirable results under different operating condition with minimum performance error. The design of the adaptive controllers as well as the development and test results of the reconfigurable control system are all presented in this paper.
[1]
菅野 道夫,et al.
Industrial applications of fuzzy control
,
1985
.
[2]
Ii Robert J. Marks.
Fuzzy Logic Technology and Applications I
,
1994
.
[3]
Robert LIN,et al.
NOTE ON FUZZY SETS
,
2014
.
[4]
Rahmat A. Shoureshi.
Intelligent Control Systems: Are They for Real?
,
1993
.
[5]
Michio Sugeno,et al.
Industrial Applications of Fuzzy Control
,
1985
.
[6]
Elif Derya Übeyli,et al.
Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients
,
2005,
Journal of Neuroscience Methods.
[7]
W. Pedrycz,et al.
An introduction to fuzzy sets : analysis and design
,
1998
.
[8]
R. M. Hueschen,et al.
Development of the Transport Class Model (TCM) Aircraft Simulation From a Sub-Scale Generic Transport Model (GTM) Simulation
,
2011
.
[9]
Bart Kosko,et al.
Fuzzy Engineering
,
1996
.
[10]
M Steinberg,et al.
Historical Overview of Research in Reconfigurable Flight Control
,
2005
.
[11]
R. Mehra,et al.
Multiple-Model Adaptive Flight Control Scheme for Accommodation of Actuator Failures
,
2002
.