Modeling of frequency agile devices: development of PKI neuromodeling library based on hierarchical network structure

P. Sanchez; J. Hinojosa; R. Ruiz

doi:10.1117/12.607975

30 June 2005 Modeling of frequency agile devices: development of PKI neuromodeling library based on hierarchical network structure

P. Sanchez, J. Hinojosa, R. Ruiz

Author Affiliations +

Proceedings Volume 5837, VLSI Circuits and Systems II; (2005) https://doi.org/10.1117/12.607975
Event: Microtechnologies for the New Millennium 2005, 2005, Sevilla, Spain

Abstract

Recently, neuromodeling methods of microwave devices have been developed. These methods are suitable for the model generation of novel devices. They allow fast and accurate simulations and optimizations. However, the development of libraries makes these methods to be a formidable task, since they require massive input-output data provided by an electromagnetic simulator or measurements and repeated artificial neural network (ANN) training. This paper presents a strategy reducing the cost of library development with the advantages of the neuromodeling methods: high accuracy, large range of geometrical and material parameters and reduced CPU time. The library models are developed from a set of base prior knowledge input (PKI) models, which take into account the characteristics common to all the models in the library, and high-level ANNs which give the library model outputs from base PKI models. This technique is illustrated for a microwave multiconductor tunable phase shifter using anisotropic substrates. Closed-form relationships have been developed and are presented in this paper. The results show good agreement with the expected ones.

Citation Download Citation

P. Sanchez, J. Hinojosa, and R. Ruiz "Modeling of frequency agile devices: development of PKI neuromodeling library based on hierarchical network structure", Proc. SPIE 5837, VLSI Circuits and Systems II, (30 June 2005); https://doi.org/10.1117/12.607975

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available