An Efficient Method for Antenna Design Optimization Based on Evolutionary Computation and Machine Learning Techniques

In recent years, various methods from the evolutionary computation (EC) field have been applied to electromagnetic (EM) design problems and have shown promising results. However, due to the high computational cost of the EM simulations, the efficiency of directly using evolutionary algorithms is oft...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on antennas and propagation Jg. 62; H. 1; S. 7 - 18
Hauptverfasser: Bo Liu, Aliakbarian, Hadi, Zhongkun Ma, Vandenbosch, Guy A. E., Gielen, Georges, Excell, Peter
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York, NY IEEE 01.01.2014
Institute of Electrical and Electronics Engineers
Schlagworte:
Antenna design optimization
antenna synthesis
Antennas
Applied classical electromagnetism
Applied sciences
Computational modeling
differential evolution
efficient global optimization
Electromagnetic wave propagation, radiowave propagation
Electromagnetism; electron and ion optics
Exact sciences and technology
expensive black-box optimization
Fundamental areas of phenomenology (including applications)
Gaussian process
Mathematical model
Optimization
Physics
Predictive models
Radiocommunications
surrogate model assisted evolutionary algorithm
Telecommunications
Telecommunications and information theory
Training data
Performance evaluation
Electromagnetism
Evolutionary algorithm
Industrial application
Evolutionary computation
Global optimum
Antenna design optimization
Computational complexity
Particle swarm optimization
efficient global optimization
differential evolution
Gaussian process
Biomimetics
Simulation
surrogate model assisted evolutionary algorithm
On line processing
Artificial intelligence
expensive black-box optimization
Antenna
Antenna synthesis
ISSN:0018-926X, 1558-2221
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In recent years, various methods from the evolutionary computation (EC) field have been applied to electromagnetic (EM) design problems and have shown promising results. However, due to the high computational cost of the EM simulations, the efficiency of directly using evolutionary algorithms is often very low (e.g., several weeks' optimization time), which limits the application of these methods for many industrial applications. To address this problem, a new method, called surrogate model assisted differential evolution for antenna synthesis (SADEA), is presented in this paper. The key ideas are: (1) A Gaussian Process (GP) surrogate model is constructed on-line to predict the performances of the candidate designs, saving a lot of computationally expensive EM simulations. (2) A novel surrogate model-aware evolutionary search mechanism is proposed, directing effective global search even when a traditional high-quality surrogate model is not available. Three complex antennas and two mathematical benchmark problems are selected as examples. Compared with the widely used differential evolution and particle swarm optimization, SADEA can obtain comparable results, but achieves a 3 to 7 times speed enhancement for antenna design optimization.
ISSN:0018-926X
1558-2221
DOI:10.1109/TAP.2013.2283605