IEEE Transactions on Microwave Theory and Techniques · 2017 · 122 citations · 24 references
ComputingComputational EngineeringElectrical EngineeringComputational ElectromagneticsMicrowave EngineeringOptimizationEvolutionary ComputationMicrowave FiltersMicrowave System DesignSurrogate ModelingSurrogate-assisted OptimizationSurrogate-based OptimizationDifferential EvolutionEvolutionary AlgorithmsFiltersFull-wave Electromagnetic SimulationGlobal OptimaLocal OptimaLocal OptimizationSurrogate-assisted Evolutionary Algorithms
Local optimization is a routine approach for full-wave optimization of microwave filters. For filter optimization problems with numerous local optima or where the initial design is not near to the optimal region, the success rate of the routine method may not be high. Traditional global optimization techniques have a high success rate for such problems, but are often prohibitively computationally expensive considering the cost of full-wave electromagnetic simulations. To address the above challenge, a new method, called surrogate model-assisted evolutionary algorithm for filter optimization (SMEAFO), is proposed. In SMEAFO, considering the characteristics of filter design landscapes, Gaussian process surrogate modeling, differential evolution operators, and Gaussian local search are organized in a particular way to balance the exploration ability and the surrogate model quality, so as to obtain high-quality results in an efficient manner. The performance of SMEAFO is demonstrated by two real-world design cases (a waveguide filter and a microstrip filter), which do not appear to be solvable by popular local optimization techniques. Experiments show that SMEAFO obtains high-quality designs comparable with global optimization techniques but within a reasonable amount of time. Moreover, SMEAFO is not restricted by certain types of filters or responses. The SMEAFO-based filter design optimization tool can be downloaded from http://fde.cadescenter.com.
24
Design and Analysis of Computer Experiments
Jerome Sacks, William J. Welch, Toby J. Mitchell et al. · Statistical Science · 1989 · 7K citations · Full text
Evolutionary programming made faster
Xin Yao, Yong Liu, Guangming Lin · IEEE Transactions on Evolutionary Computation · 1999 · 3.9K citations
Sequential Quadratic Programming
Paul T. Boggs, Jon W. Tolle · Acta Numerica · 1995 · 1.8K citations