A library of adaptive neural networks for control purposes
Tóm tắt
In this paper, a library of adaptive neural networks to be used within the Simulink/spl reg/ environment is presented. The library has been developed by the authors with the intent of giving to the Simulink user an easy access to a variety of adaptive approximators. The neural networks contained in the library are ready to be used and interchanged within the user's application. Different from existing neural network collections and toolboxes, in this library, a neural network is strictly treated as a dynamic system with its inputs, outputs and states, and the "dynamics" of the approximation process are therefore considered as an essential part of this "system". The library is introduced and the featured network architectures are analyzed in detail. Finally, as an example, a comparison is performed between two of the presented networks.
Từ khóa
#Libraries #Adaptive systems #Programmable control #Adaptive control #Neural networks #Mathematical model #Artificial neural networks #Airplanes #Computer networks #Aerospace electronicsTài liệu tham khảo
10.1016/S1874-5946(98)80085-0
1999, SIMULINK - Writing S-Functions
ahrns, 1995, On-line learning with dynamic cell structures, Proc Int Conf Artificial Neural Networks, 2, 141
10.1162/neco.1991.3.2.213
jorgensen, 1997, Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks, NASA TM 112198
10.1016/S1369-8869(00)00009-4
10.2514/6.1991-2631
lu, 2000, Analysis of Minimal Radial Basis Function Network Algorithm for Real-time identification of nonlinear dynamic systems, IEE Proceedings Control Theory and Applications, 4, 476
10.1023/A:1026571426761
10.1109/ACC.2002.1024840
friske, 1995, Growing cell structures: a self-organizing network for unsupervised and supervised learning, Neural Networks, 7, 1441
1998, Neural Network Toolbox Users Guide