Title :
Neural network models for the coupling micro-strip line design
Author :
Li, Jiusheng ; Bao, Zhenm
Author_Institution :
Coll. of Electron. Inf. Eng., Tianjin Univ., China
Abstract :
Artificial neural network model is built for coupling micro-strip line, which is in turn analyzed, designed and optimized through the model. In this paper, with the structure size of coupling micro-strip line defined as input samples, the odd and even mode characteristic impedance and the normalized wavelength defined as output samples, a kind of coupling micro-strip line is designed by the method. With its good precision and effectiveness, the application of neural network has the advantages of reliability, accuracy, time saving, and knowledge aid design. The results of neural network simulation design are in good agreement with the numerical value calculation of electromagnetism field.
Keywords :
artificial intelligence; coupled transmission lines; microstrip lines; radial basis function networks; accuracy; artificial neural network model; coupling micro-strip line design; electromagnetism field; knowledge aid design; mode characteristic impedance; normalized wavelength; numerical value calculation; reliability; Costs; Coupling circuits; Design engineering; Design methodology; Design optimization; Electronic mail; Impedance; Integrated circuit modeling; Microwave devices; Neural networks;
Conference_Titel :
Systems, Man and Cybernetics, 2003. IEEE International Conference on
Print_ISBN :
0-7803-7952-7
DOI :
10.1109/ICSMC.2003.1245761