Journal ArticleDOI
Artificial Neural Network Models for the Bend Discontinuities in Stripline Circuits
Jing-Song Hong,Bing-Zhong Wang +1 more
TLDR
Bend as one type of the stripline discontinuities will be modeled in this paper as a multilayer perceptron neural network (MLPNN) is used to model the bend discontinUities in striplines.Abstract:
Stripline discontinuities are basic elements of many stripline circuits, such as the multilayer microwave monolithic ICs and the interconnect systems in high-speed digital circuits. Bend as one type of the stripline discontinuities will be modeled in this paper. A multilayer perceptron neural network(MLPNN) is used to model the bend discontinuities in stripline circuits. The MLPNN is electromagnetically developed with a set of training data that are produced by the full-wave finite-difference time-domain (FDTD) method. The full-factor design of experiments is used to determine the size of the training data.read more
Citations
More filters
Journal ArticleDOI
Modeling stripline discontinuities by neural network with knowledge-based neurons
TL;DR: A three-layer neural network with knowledge-based neurons in the hidden layer (NNKBN) is presented for modeling stripline discontinuities and can map the input-output relationships with fewer hidden neurons and has higher reliability for extrapolation beyond training data range.
Journal ArticleDOI
Microwave imaging of dielectric cylinders from experimental scattering data based on the genetic algorithms, neural networks and a hybrid micro genetic algorithm with conjugate gradient
TL;DR: The application of three techniques for the reconstruction of the permittivity profile of cylindrical objects from scattered field measurements is studied and three algorithms: conjugate gradient with Polak–Ribiere updates, Levenberg–Marquardt and gradient descent are used to train the ANN.
Proceedings ArticleDOI
NNKBN model for the microstrip T-junction structure
Jingsong Hong,Bing-zhong Wang +1 more
TL;DR: A novel three-layer neural network with knowledge-based neurons in the hidden layer (NNKBN) has been applied to model the microstrip T-junction structure to show that the NNKBN model has many advantages over the conventional multi-layer perceptron model.
Journal ArticleDOI
Robust Knowledge-Based Neural-Network Model for Microstrip T-Junction Structure
Jing-Song Hong,Bing-Zhong Wang +1 more
TL;DR: A robust knowledge-based neural‐network model (RKBNN), whose neurons in the hidden layer are all knowledge‐based neurons instead of conventional neurons, is proposed for the microstrip T‐junction structure.
Journal ArticleDOI
Neural network with knowledge-based neurons for the modeling of crossover discontinuities in stripline circuits
TL;DR: A novel three‐layer neural network with knowledge‐based neurons in hidden layer (NNKBN) has been applied to model the crossover discontinuities in stripline circuits to show advantages over the conventional multilayer perceptron model.
References
More filters
Journal ArticleDOI
Time-domain finite difference approach to the calculation of the frequency-dependent characteristics of microstrip discontinuities
Zhang Xiaolei,K.K. Mei +1 more
TL;DR: In this paper, the frequency-dependent characteristics of the microstrip discontinuities have been analyzed using full-wave approaches and the time-domain finite-difference (TD-FD) method is presented.
Journal ArticleDOI
EM-ANN models for microstrip vias and interconnects in dataset circuits
P.M. Watson,K.C. Gupta +1 more
TL;DR: A novel approach for accurate and efficient modeling of monolithic microwave/millimeter wave integrated circuit (MMIC) components by using electromagnetically trained artificial neural network (EM-ANN) software modules is presented.
Journal ArticleDOI
Artificial neural networks for fast and accurate EM-CAD of microwave circuits
TL;DR: The results presented indicate that the MLPNN can predict the s-parameters of these passive elements to nearly the same degree of accuracy as that afforded by EM simulation.
Journal ArticleDOI
The application of neural networks to EM-based simulation and optimization of interconnects in high-speed VLSI circuits
TL;DR: A neural network based approach to the electromagnetic (EM) simulation and optimization of high-speed interconnects is discussed, which is ideally suited for use in iterative CAD and optimization routines.
Related Papers (5)
Equivalent circuit modeling of interconnects from time domain measurements
J.M. Jong,B. Janko,V.K. Tripathi +2 more
A finite-difference transmission line matrix method incorporating a nonlinear device model
R.H. Voelker,R.J. Lomax +1 more