This paper gives an overview of some stochastic optimization strategies, namely, evolution strategies, genetic algorithms, and simulated annealing, and how these methods can be applied to problems in electrical engineering. Since these methods usually require a careful tuning of the parameters which control the behavior of the strategies (strategy parameters), significant features of the algorithms implemented by the authors are presented. An analytical comparison among them is performed. Finally, results are discussed on three optimization problems.

Stochastic algorithms in electromagnetic optimization

The use of artificial neural networks in the solution of inverse electromagnetic field problems is investigated. It is shown that artificial neural networks, while being no panacea, have a role to play in a limited domain of applications-that is, while it is ineffective to train networks to cover a broad class of devices, it is indeed possible to develop well-trained networks that function effectively over a narrow range of performance of a particular class of device. Particularly if one knows the desired geometry approximately and uses training sets around this geometry, simple neural networks with a few training sets can be used to do an effective job. However, neural networks cannot be used efficiently without such prior knowledge. >

Artificial neural networks in the solution of inverse electromagnetic field problems

A new technique for the design optimization of electromagnetic devices that adopts the genetic algorithms (GAs) as the search method is presented. The method is applied to the optimization of the shape of a pole face in an electric motor. The electromagnetic analysis of the devices implemented is performed using 2D finite elements. The results show an excellent promise and potential of using GAs as an efficient technique for the optimal design problem. >

Utilizing genetic algorithms for the optimal design of electromagnetic devices

We propose an optimization methodology suitable for the design of various antenna structures. This methodology includes a rapidly-converging iterative scheme. In each iteration stage, the algorithm generates a parameterized Cauchy model using the available results from previous iterations. Optimization is then applied to this Cauchy model to obtain better design parameters that are also used in enhancing the accuracy of the model. This cycle continues until the speciflcations are met. In addition, this on-the-∞y technique produces an analytical model of the behavior of the antenna structure. Sensitivity and tolerance analysis can thus be e-ciently carried out without the need for further costly electromagnetic simulations.

/pdf/accelerated-antenna-design-methodology-exploiting-4jifju2w0k.pdf

Accelerated Antenna Design Methodology Exploiting Parameterized Cauchy Models

Optimizing complex engineering problems may demand large computational efforts because of the use of numerical models. Global optimization can be established through the use of evolutionary algorithms, but may demand a prohibitive amount of computational time. In order to reduce the computational time, we incorporate in the global optimization procedures a physics-based fast coarse model. This paper presents a two-level genetic algorithm (2LGA) for electromagnetic optimization. This algorithm employs the global convergence properties of the genetic algorithm, where acceleration of the optimization results from the fast computations of the coarse model (low level) and where accuracy is guaranteed by using a limited number of fine model (high level) evaluations. Using the coarse model, we iteratively build surrogate models (intermediate levels) where metamodels produce surrogate models which approximate the fine model. The proposed algorithm comprises internal parameters which are self-tunable. We applied the 2LGA to the optimization of an algebraic test function, to the optimization of a die press model (TEAM Workshop Problem 25) and to the optimization of an octangular double-layered electromagnetic shield. The results show that the 2LGA is converging to the optimal solutions as the traditional genetic algorithm and that the acceleration is dependent on the accuracy of the low level. An acceleration factor of more than two can be achieved.

/pdf/a-two-level-genetic-algorithm-for-electromagnetic-45ab7wrzxz.pdf

A Two-Level Genetic Algorithm for Electromagnetic Optimization

A novel method for the optimal design of the electromagnetic devices is presented The method utilizes artificial neural networks (ANNs) in a design environment which encompasses numerical computations and expert's input for generating a variety of ANN training data Results of two implementation examples are provided The optimal design is obtained quickly (in a matter of milliseconds) once the ANNs are trained with a variety of geometrical topologies The procedure explained can be used to provide good initial designs for use with iterative search techniques (currently used) to reduce searching time This aspect is highly desirable in connection with increasing the effectiveness of the optimal design procedure >

Chen Ziqiang

Papers

Design optimization of electromagnetic devices using artificial neural networks