Modeling of microstrip lines using neural networks: Applications to the design and analysis of distributed microstrip circuits

Soliman, Ezzeldin A.; Bakr, Mohamed H.; Nikolova, Natalia K.

doi:10.1002/mmce.10127

Cited by 8 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in microwave application conventional computer aided design(CAD) has been coupled with ANN to obtain an efficient and accurate results that can be seen as a candidate with massive computations such as: broadband nonlinear RF/microwave circuits [15], calculation of Green's Functions [16], analysis and synthesis of RF/microwave planar transmission lines [17], computational electromagnetics [18], and modeling of microstrip lines [19].…”

Section: Introductionmentioning

confidence: 99%

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

Hayati

Lotfi

2011

Micro & Optical Tech Letters

View full text Add to dashboard Cite

In this article, S‐parameters of compact microstrip resonator cell are predicted using artificial neural network (ANN) to design class of elliptic function compact low‐pass filter with sharp cut‐off frequency. The ANN structure used in this work is multilayer perceptron (MLP) neural network. The data used for training the network is obtained using electromagnetic (EM) simulator. We compared measurement results and simulation results of filter by EM‐simulator and ANN. The results show accurate attenuation at cut off frequency. In comparison with EM‐simulator, simulation results by ANN have merits such as: mitigated consumption time, efficient performance and good accuracy. © 2011 Wiley Periodicals, Inc. Microwave Opt Technol Lett 53:1323–1328, 2011; View this article online at wileyonlinelibrary.com. DOI 10.1002/mop.26008

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

Hayati

Lotfi

2011

Micro & Optical Tech Letters

View full text Add to dashboard Cite

show abstract

“…Ability and adaptability to learn, generalisability, fast real-time operation, and ease of implementation have made NNs popular for a number of microwave design problems in recent years [2]. Citing just a number of examples: NNs have been used in the design of passive microwave circuits [3], analysis and synthesis of microstrip lines [4], calculation of the characteristic impedance of air-suspended trapezoidal and rectangular-shaped microshield lines [5], design of nonlinear microwave circuits based on active devices [6], design of microstrip patch antennas [7,8], direction of arrival estimation with antenna arrays [9,10], radar target recognition [11], aperture antenna shape prediction [12], inverse scattering of dielectric cylinders [13], near field to far filed transformation [14], and synthesis of antenna array [15,16]. In addition to modeling the response, NNs can also be employed within the core of the full-wave solvers based on the method of moments [17,18].…”

Section: Introductionmentioning

confidence: 99%

Neural Frequency Sweeper for Accelerating S-Parameters Calculation of Planar Microwave Structures

Soliman¹,

Ibrahim²

2008

PIER M

View full text Add to dashboard Cite

Abstract-This paper presents a new frequency-sweep approach for the efficient calculation of S-parameters of planar microwave structures. The approach is based on approximating the frequency dependence of the real and imaginary parts of the S-parameters using neural networks. Due to its superior performance, radial basis functions neural network (RBF-NN) is adopted. A limited number of frequency samples are used to train the RBF-NN. Then, the trained RBF-NN is capable of providing a smooth frequency response with very high accuracy in a fraction of a second. The proposed method is applied to a number of planar microwave structures such as: Patch antenna with an inset feed, band-rejection filter, and branch-line coupler. According to the presented results, a speed factor of at least 10 is measured, and a maximum percentage error of 3.29% is recorded.

show abstract

“…Chapter 2 provides a literature review of existing microwave modeling and op- ANN techniques have been reported in various microwave applications such as filters [13]- [16], power amplifiers [17]- [20], antennas [106], microstrip components and circuits [107], [108], very-large-scale-integration (VLSI) interconnects [109], [110],…”

Section: Thesis Organizationmentioning

confidence: 99%

Advanced Neural Network Modeling and Electromagnetic Optimization Approaches for Microwave Passive Components

Jin¹

View full text Add to dashboard Cite

Microwave modeling and optimization techniques play important roles in electromagnetic (EM)-based microwave component design. The purpose of this thesis is to propose advanced neural network modeling and EM optimization approaches for microwave passive components. This thesis first proposes a new deep neural network technique to solve high-dimensional microwave modeling problems which are more challenging than those solved by previous shallow neural networks. A smooth rectified linear unit (ReLU) is proposed for the new deep neural network. The proposed deep neural network employs both the sigmoid function and the smooth ReLU as activation functions. An advanced three-stage deep learning algorithm is proposed to train the new deep neural network model. This algorithm can determine the number of hidden layers with sigmoid functions and those with smooth ReLUs in the training process. It can also overcome the vanishing gradient problem for training the deep neural network. The proposed deep neural network technique can solve microwave modeling problems in higher dimension than the previous neural network method, i.e., shallow neural network method. Compared to the standard deep neural network using only ReLUs, the proposed deep neural network can achieve higher accuracy with fewer number of hidden neurons. The proposed deep neural network technique is a useful surrogate modeling technique for microwave components. Based on the investigation of the surrogate modeling technique, this thesis further studies the efficient surrogate-based EM optimization method and proposes an advanced cognition-driven EM optimization incorporating transfer function-based feature surrogate for EM geometry optimization of microwave filters. The proposed i optimization technique addresses the situations where the response at the starting point for the design optimization is substantially misaligned with the design specifications. We propose to extract transfer function-based feature parameters for optimization to address the challenge that the features cannot be clearly and explicitly identified from the filter response. Multiple transfer function-based feature parameters are extracted and used to develop the feature surrogate model for the proposed cognition-driven optimization. Furthermore, we derive new objective functions for the cognition-driven optimization directly in the feature space. The proposed cognition-driven optimization incorporating transfer function-based feature surrogate can achieve faster convergence than the existing feature-assisted EM optimization methods.Moreover, to address the EM topology optimization that our proposed cognitiondriven optimization method is not applicable, this thesis further proposes an efficient EM topology optimization technique for microwave component design. In the proposed technique, the finite element method (FEM) is used for EM simulation. We propose a new method to integrate Matrix Padé via Lanczos (MPVL) and Householder formula. The proposed method combines the advantages of MPVL and H...

show abstract

Modeling of microstrip lines using neural networks: Applications to the design and analysis of distributed microstrip circuits

Cited by 8 publications

References 15 publications

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

Modeling of compact microstrip resonator using neural network: Application to design of compact low‐pass filter with sharp cut‐off frequency

Neural Frequency Sweeper for Accelerating S-Parameters Calculation of Planar Microwave Structures

Advanced Neural Network Modeling and Electromagnetic Optimization Approaches for Microwave Passive Components

Contact Info

Product

Resources

About