First written in 2003 for a book that was never published. Last updated on January 29, 2011. You can find the most recent version at www.designers-guide.org. Contact the author via email at monte.mar@comcast.net. Permission to make copies, either paper or electronic, of this work for personal or classroom use is granted without fee provided that the copies are not made or distributed for profit or commercial advantage and that the copies are complete and unmodified. To distribute otherwise, to publish, to post on servers, or to distribute to lists, requires prior written permission.

ΣΔ Data Converters

In the last few years, intensive research has been done to enhance artificial intelligence (AI) using optimization techniques. In this paper, we present an extensive review of artificial neural networks (ANNs) based optimization algorithm techniques with some of the famous optimization techniques, e.g., genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), and backtracking search algorithm (BSA) and some modern developed techniques, e.g., the lightning search algorithm (LSA) and whale optimization algorithm (WOA), and many more. The entire set of such techniques is classified as algorithms based on a population where the initial population is randomly created. Input parameters are initialized within the specified range, and they can provide optimal solutions. This paper emphasizes enhancing the neural network via optimization algorithms by manipulating its tuned parameters or training parameters to obtain the best structure network pattern to dissolve the problems in the best way. This paper includes some results for improving the ANN performance by PSO, GA, ABC, and BSA optimization techniques, respectively, to search for optimal parameters, e.g., the number of neurons in the hidden layers and learning rate. The obtained neural net is used for solving energy management problems in the virtual power plant system.

Artificial Neural Networks Based Optimization Techniques: A Review

This study presents an automated optimization-oriented strategy for designing high power amplifiers (HPAs) using deep neural networks (DNNs). The proposed strategy consists of two optimization phases that are applied sequentially. In the first phase, the circuit topology is optimized by determining the number of passive components in the input and output matching networks using deep learning classification network. In the second optimization phase, component values are estimated using a deep learning regression network with electromagnetic-based Thompson Sampling Efficient Multiobjective Optimization (TSEMO). The proposed approach is compact, in the sense that the optimum solution is automatically generated by the process, opposite to the conventional approaches where manual post-processing is required to prune the process outcomes. It addresses the problem of heavy reliance of the system performance on the designer’s experience and automatically generates valid layouts. In the demanding HPA design problem, uses of DNNs have been shown to provide much more accuracy than conventional shallow neural networks. The effectiveness of the proposed method is verified by implementing two designed HPAs, including GaN HEMTs. The efficiency-oriented optimized amplifier reveals higher than 60% drain efficiency, and the gain-oriented optimized amplifier has 17.6–18 dB linear gain in the frequency band of 1.8–2.2 GHz.

Automated Deep Neural Learning-Based Optimization for High Performance High Power Amplifier Designs

Fast replacement models (or surrogates) have been widely applied in the recent years to accelerate simulation-driven design procedures in microwave engineering. The fundamental reason is a considerable—and often prohibitive—CPU cost of massive full-wave electromagnetic (EM) analyses related to solving common tasks such as parametric optimization or uncertainty quantification. The most popular class of surrogates are data-driven models, which are fast to evaluate, versatile, and easy to handle. Notwithstanding, the curse of dimensionality as well as the utility demands (e.g., so that the model covers sufficiently broad ranges of the system operating conditions), limit the applicability of conventional methods. A performance-driven modeling paradigm allows for mitigating these issue by focusing the surrogate setup process in a constrained domain encapsulating designs being of high quality w.r.t. the assumed figures of interest. The nested kriging framework capitalizing on this idea, renders the constrained surrogate using kriging interpolation, and has been shown to surpass traditional approaches. In pursuit of further accuracy improvements, this work incorporates the performance-driven concept into the fully-connected regression model (FRCM). The latter has been recently introduced in the context of frequency selective surfaces, and combined deep neural networks with Bayesian optimization, the latter employed to determine the network architecture and hyper-parameters. Using two examples of miniaturized microstrip couplers, our methodology is demonstrated to outperform both conventional modeling techniques and nested kriging, with reliable models constructed over multi-dimensional parameters spaces using just a few hundreds of samples.

/pdf/improved-modeling-of-microwave-structures-using-performance-3ssu91ntgi.pdf

Improved Modeling of Microwave Structures Using Performance-Driven Fully-Connected Regression Surrogate

A low profile, light weight, and low cost antenna for dual-band operation in Ku-band is presented for satellite applications. Antenna has broadside radiation pattern and it is a single-layer and single-patch antenna which has the added advantage of less complexity in realising the antenna. This dual-band antenna meets the requirement of International Telecommunication Union for region 3. Lower and upper band of antenna include the frequency band for fixed satellite services (FSS) and direct broadcasting satellite for receive mode and FSS for transmit mode, respectively. The proposed design provide 10% and 8% bandwidth in lower and upper band, respectively, with a low frequency ratio of 1.2.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-map.2016.0393

Single-layer single-patch dual band antenna for satellite applications

Design and optimization of wideband nonlinear RF circuits are time-consuming and challenging design issue. Both electronic design automation (EDA) and numerical analysis tools can be used to design microwave circuits. However, they have different capabilities regarding calculation and optimization processes. In this study, EDA and numerical analysis tools are operated collaboratively and sequentially to create an automated co-simulation based iterative design and optimization methodology for wideband power amplifier design. Co-simulation based optimization provides uninterrupted and un-intervened design and optimization process. Consequently, the required effort and time to achieve a high-performance circuit are reduced dramatically. Keysight ADS is used nonlinear analysis of the circuits and MATLAB used to control process and for optimization. Initial circuit parameters were generated by simplified real frequency technique (SRFT). A Class-AB X-Band high power amplifier including a GaN HEMT was designed and optimized with the proposed methodology.

Power Amplifier Design Optimization with Simultaneous Cooperation of EDA Tool and Numeric Analyzer

In the recent years, microstrip antennas have quickly developed from a research novelty to a practical reality, with applications in a wide range of communication systems that must thank to their numerous appreciated features. The present work proposes a low nature slotted microstrip antenna with ground plane structure for Ku-band satellite communications. Firstly, a single Ku-band slotted patch antenna designed and then 2×2 array structure modelled and simulated by using Ansoft HFSS 3D electromagnetic simulation tool. High directivity of antenna has been realized by using full ground plane and via has fed array elements. Array feed circuit placed behind of antenna in the third layer. The gain of array antenna is about 12dBi and it is usable between 12.2 GHz and 13.1 GHz band frequency. The configuration of the proposed antenna shows the way to fabricate and make it appropriate for Ku-band applications in satellite communications.

Ku - Band slotted rectangular patch array antenna design

Automated optimization for broadband flat-gain antenna designs with artificial neural network

This study presents an automated RF power amplifier design procedure and methods which aim to convert systematically built-in lumped elements to distributed elements by simultaneously optimizing power gain, output power and efficiency. This approach which is performed by using Bayesian optimization results in ready-to-fabricate optimized designs with layout. The optimization process is performed automatically by using a commercial electronic design automation and a mathematical computing environment. To validate the proposed strategy, a power amplifier consisting of a 10 W GaN HEMT is designed for 1.7 - 2.3 GHz band frequency. The power amplifier provides an efficiency of between 53 % - 63 % at the 3 dB gain compression and linear power gain higher than 14 dB in the operation band.

Lida Kouhalvandi

Papers

Automated Deep Neural Learning-Based Optimization for High Performance High Power Amplifier Designs

Power Amplifier Design Optimization with Simultaneous Cooperation of EDA Tool and Numeric Analyzer

Ku - Band slotted rectangular patch array antenna design

Automated optimization for broadband flat-gain antenna designs with artificial neural network

Automated RF Power Amplifier Optimization and Design: From Lumped Elements to Distributed Elements