scispace - formally typeset
Search or ask a question
Journal ArticleDOI

A neural network modeling approach to circuit optimization and statistical design

01 Jun 1995-IEEE Transactions on Microwave Theory and Techniques (IEEE)-Vol. 43, Iss: 6, pp 1349-1358
TL;DR: This paper presents a new approach to microwave circuit optimization and statistical design featuring neural network models at either device or circuit levels, which has the capability to handle high-dimensional and highly nonlinear problems.
Abstract: The trend of using accurate models such as physics-based FET models, coupled with the demand for yield optimization results in a computationally challenging task. This paper presents a new approach to microwave circuit optimization and statistical design featuring neural network models at either device or circuit levels. At the device level, the neural network represents a physics-oriented FET model yet without the need to solve device physics equations repeatedly during optimization. At the circuit level, the neural network speeds up optimization by replacing repeated circuit simulations. This method is faster than direct optimization of original device and circuit models. Compared to existing polynomial or table look-up models used in analysis and optimization, the proposed approach has the capability to handle high-dimensional and highly nonlinear problems. >
Citations
More filters
Journal ArticleDOI
TL;DR: Fundamental concepts in this emerging area of neural-network computational modules are described at teaching RF/microwave engineers what neural networks are, why they are useful, when they can be used, and how to use them.
Abstract: Neural-network computational modules have recently gained recognition as an unconventional and useful tool for RF and microwave modeling and design. Neural networks can be trained to learn the behavior of passive/active components/circuits. A trained neural network can be used for high-level design, providing fast and accurate answers to the task it has learned. Neural networks are attractive alternatives to conventional methods such as numerical modeling methods, which could be computationally expensive, or analytical methods which could be difficult to obtain for new devices, or empirical modeling solutions whose range and accuracy may be limited. This tutorial describes fundamental concepts in this emerging area aimed at teaching RF/microwave engineers what neural networks are, why they are useful, when they can be used, and how to use them. Neural-network structures and their training methods are described from the RF/microwave designer's perspective. Electromagnetics-based training for passive component models and physics-based training for active device models are illustrated. Circuit design and yield optimization using passive/active neural models are also presented. A multimedia slide presentation along with narrative audio clips is included in the electronic version of this paper. A hyperlink to the NeuroModeler demonstration software is provided to allow readers practice neural-network-based design concepts.

608 citations

Journal ArticleDOI
TL;DR: Recent progress in deep-learning-based photonic design is reviewed by providing the historical background, algorithm fundamentals and key applications, with the emphasis on various model architectures for specific photonic tasks.
Abstract: Innovative approaches and tools play an important role in shaping design, characterization and optimization for the field of photonics. As a subset of machine learning that learns multilevel abstraction of data using hierarchically structured layers, deep learning offers an efficient means to design photonic structures, spawning data-driven approaches complementary to conventional physics- and rule-based methods. Here, we review recent progress in deep-learning-based photonic design by providing the historical background, algorithm fundamentals and key applications, with the emphasis on various model architectures for specific photonic tasks. We also comment on the challenges and perspectives of this emerging research direction. The application of deep learning to the design of photonic structures and devices is reviewed, including algorithm fundamentals.

446 citations

Journal Article
TL;DR: A generic space-mapping optimization algorithm is formulated, explained step-by-step using a simple microstrip filter example, and its robustness is demonstrated through the fast design of an interdigital filter.
Abstract: In this article we review state-of-the-art concepts of space mapping and place them con- textually into the history of design optimization and modeling of microwave circuits. We formulate a generic space-mapping optimization algorithm, explain it step-by-step using a simple microstrip filter example, and then demonstrate its robustness through the fast design of an interdigital filter. Selected topics of space mapping are discussed, including implicit space mapping, gradient-based space mapping, the optimal choice of surrogate model, and tuning space mapping. We consider the application of space mapping to the modeling of microwave structures. We also discuss a software package for automated space-mapping optimization that involves both electromagnetic (EM) and circuit simulators.

327 citations


Cites methods from "A neural network modeling approach ..."

  • ...In the 1990s, EM modeling and optimization were explored through novel technologies such as response surface modeling [13], model-reduction techniques [22], and artificial neural networks [23]....

    [...]

Journal ArticleDOI
Abstract: This paper reviews the current state-of-the-art in electromagnetic (EM)-based design and optimization of microwave circuits using artificial neural networks (ANNs). Measurement-based design of microwave circuits using ANNs is also reviewed. The conventional microwave neural optimization approach is surveyed, along with typical enhancing techniques, such as segmentation, decomposition, hierarchy, design of experiments, and clusterization. Innovative strategies for ANN-based design exploiting microwave knowledge are reviewed, including neural space-mapping methods. The problem of developing synthesis neural networks is treated. EM-based statistical analysis and yield optimization using neural networks is reviewed. The key issues in transient EM-based design using neural networks are summarized. The use of ANNs to speed up "global modeling" for EM-based design of monolithic microwave integrated circuits is briefly described. Future directions in ANN techniques to microwave design are suggested.

321 citations

Journal ArticleDOI
TL;DR: In this article, a neural network inverse model is proposed for microwave modeling and design using the concept of inverse modeling where the inputs to the inverse model are electrical parameters and outputs are geometrical parameters.
Abstract: In this paper, systematic neural network modeling techniques are presented for microwave modeling and design using the concept of inverse modeling where the inputs to the inverse model are electrical parameters and outputs are geometrical parameters. Training the neural network inverse model directly may become difficult due to the nonuniqueness of the input-output relationship in the inverse model. We propose a new method to solve such a problem by detecting multivalued solutions in training data. The data containing multivalued solutions are divided into groups according to derivative information using a neural network forward model such that individual groups do not have the problem of multivalued solutions. Multiple inverse models are built based on divided data groups, and are then combined to form a complete model. A comprehensive modeling methodology is proposed, which includes direct inverse modeling, segmentation, derivative division, and model combining techniques. The methodology is applied to waveguide filter modeling and more accurate results are achieved compared to the direct neural network inverse modeling method. Full electromagnetic simulation and measurement results of Ku-band circular waveguide dual-mode pseudoelliptic bandpass filters are presented to demonstrate the efficiency of the proposed neural network inverse modeling methodology.

282 citations


Cites methods from "A neural network modeling approach ..."

  • ...It has been applied to various microwave design applications [1], [2] such as vias and interconnects [3], embedded passives [4], coplanar waveguide components [5], transistor modeling [6]–[8], noise modeling [9], power-amplifier modeling [10], analysis of multilayer shielded microwave circuits [11], nonlinear microwave circuit optimization [12], etc....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification and exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components.
Abstract: Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.

7,798 citations

Journal ArticleDOI
TL;DR: In this paper, a new method for the solution of nonlinear periodic networks has been developed, where the network is decomposed into a minimum number of linear and nonlinear subnetworks.
Abstract: A new method for the solution of nonlinear periodic networks has been developed. It avoids the time domain solution of the dynamic equations. In the proposed method, the network is decomposed into a minimum number of linear and nonlinear subnetworks. Only frequency domain solutions of the linear subnetworks are required. It is shown that considerable reduction in the size of the computational problem can be achieved by taking advantage of the linearities present in the network.

357 citations

Journal ArticleDOI
TL;DR: A survey of modern nonlinear CAD techniques as applied to the specific field of microwave circuits shows that the various subjects are not just separate items, but rather can be chained in a strictly logical sequence.
Abstract: The authors present a survey of modern nonlinear CAD (computer-aided design) techniques as applied to the specific field of microwave circuits. A number of fundamental aspects of the nonlinear CAD problem, including simulation, optimization, intermodulation, frequency conversion, stability, and noise, are addressed and developed. For each one it is shown that either well-established CAD solutions are available, or at least a solution approach suitable for implementation in a general-purpose CAD environment can be outlined. Also, the discussion shows that the various subjects are not just separate items, but rather can be chained in a strictly logical sequence. Finally, an elementary treatment of vector processing is given, to show that supercomputers can handle the involved large-size numerical problems efficiently. >

314 citations

Journal ArticleDOI
TL;DR: A unified hierarchical treatment of circuit models forms the basis of the presentation, and the concepts of design centering, tolerance assignment, and postproduction tuning in relation to yield enhancement and cost reduction suitable for integrated circuits are discussed.
Abstract: The authors review the current state of the art in circuit optimization, emphasizing techniques suitable for modern microwave CAD (computer-aided design). The main thrust in the field is currently the solution of realistic design and modeling problems, addressing such concepts as physical tolerances and model uncertainties. A unified hierarchical treatment of circuit models forms the basis of the presentation. It exposes tolerance phenomena at different parameter/response levels. The concepts of design centering, tolerance assignment, and postproduction tuning in relation to yield enhancement and cost reduction suitable for integrated circuits are discussed. Suitable techniques for optimization oriented worst-case and statistical design are reviewed. A generalized l/sub p/ centering algorithm is proposed and discussed. Multicircuit optimization directed at both CAD and robust device modeling is formalized. Tuning is addressed in some detail, both at the design stage and for production alignment. State-of-the-art gradient-based nonlinear optimization methods are reviewed with emphasis given to recent, but well tested, advances in minimax, l/sub 1/, and l/sub 2/ optimization. >

238 citations

Journal ArticleDOI
TL;DR: The harmonic balance method is a technique for the numerical solution of nonlinear analog circuits operating in a periodic, or quasi-periodic, steady-state regime as mentioned in this paper, which can be used to efficiently derive the continuous-wave response of numerous nonlinear microwave components including amplifiers, mixers, and oscillators.
Abstract: The harmonic balance method is a technique for the numerical solution of nonlinear analog circuits operating in a periodic, or quasi-periodic, steady-state regime. The method can be used to efficiently derive the continuous-wave response of numerous nonlinear microwave components including amplifiers, mixers, and oscillators. Its efficiency derives from imposing a predetermined steady-state form for the circuit response onto the nonlinear equations representing the network, and solving for the set of unknown coefficients in the response equation. Its attractiveness for nonlinear microwave applications results from its speed and ability to simply represent the dispersive, distributed elements that are common at high frequencies. The last decade has seen the development and application of harmonic balance techniques to model analog circuits, particularly microwave circuits. The first part of this paper reviews the fundamental achievements made during this time. The second part covers the extension of the method to quasi-periodic regimes, optimization analysis, and practical application. A critical assessment of the various types of harmonic balance techniques is given. The different sampling and Fourier transform methods are compared, and numerical speed and precision results are given enabling a quantitative analysis of the merits of the major variants of the harmonic balance technique. Examples of designs which have been modeled using the harmonic balance technique and built both in hybrid and MMIC form are presented.

197 citations