Fast Multi-Objective Optimization of Multi-Parameter Antenna Structures Based on Improved BPNN Surrogate Model

In this paper, a surrogate model based on a sparsely connected back propagation neural networks (SC-BPNN) is proposed to reduce the large computational cost of conventional multi-objective antenna optimization problems. In this model, the connection parameters and network structure can be adaptively tuned by a hybrid real-binary particle swarm optimization (HPSO) algorithm for better network global optimization capability. Also, a time-varying transfer function is introduced to improve the problem of easily trapping into local optimum and to accelerate network convergence. Further, a fast multi-objective optimization framework based on the proposed SC-BPNN is established for multi-parameter antenna structures. Finally, a Pareto-optimal planar miniaturized multiband antenna design is presented, indicating that the proposed model predicts antenna performance more accurately and saves considerable computational cost compared to those previously published approaches.

[1]  Paolo Rocca,et al.  Learning-by-examples techniques as applied to electromagnetics , 2018 .

[2]  Cheng Liao,et al.  HYBRID-SURROGATE-MODEL-BASED EFFICIENT GLOBAL OPTIMIZATION FOR HIGH-DIMENSIONAL ANTENNA DESIGN , 2012 .

[3]  Michael R. Lyu,et al.  A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training , 2007, Appl. Math. Comput..

[4]  M. John,et al.  Antenna Optimization With a Computationally Efficient Multiobjective Evolutionary Algorithm , 2009, IEEE Transactions on Antennas and Propagation.

[5]  Jian Dong,et al.  Fast multi-objective optimization of multi-parameter antenna structures based on improved MOEA/D with surrogate-assisted model , 2017 .

[6]  Lianwen Deng,et al.  Design of Fragment-Type Antenna Structure Using an Improved BPSO , 2018, IEEE Transactions on Antennas and Propagation.

[7]  Abdolali Abdipour,et al.  ANN-based design of a versatile millimetre-wave slotted patch multi-antenna configuration for 5G scenarios , 2017 .

[8]  Slawomir Koziel,et al.  Expedited EM-Driven Multiobjective Antenna Design in Highly Dimensional Parameter Spaces , 2014, IEEE Antennas and Wireless Propagation Letters.

[9]  Xiao Dong Chen,et al.  Neural network modeller for design optimisation of multilayer patch antennas , 2004 .

[10]  A. Patnaik,et al.  Design of Custom-Made Fractal Multi-Band Antennas Using ANN-PSO [Antenna Designer's Notebook] , 2011, IEEE Antennas and Propagation Magazine.

[11]  Nanbo Jin,et al.  Hybrid Real-Binary Particle Swarm Optimization (HPSO) in Engineering Electromagnetics , 2010, IEEE Transactions on Antennas and Propagation.

[12]  Wei Shao,et al.  An Improved NSGA-II and its Application for Reconfigurable Pixel Antenna Design , 2014 .

[13]  M. Stein.  Large sample properties of simulations using latin hypercube sampling , 1987 .

[14]  Donald R. Jones,et al.  A Taxonomy of Global Optimization Methods Based on Response Surfaces , 2001, J. Glob. Optim..

[15]  J. P. Jacobs,et al.  Efficient Resonant Frequency Modeling for Dual-Band Microstrip Antennas by Gaussian Process Regression , 2015, IEEE Antennas and Wireless Propagation Letters.

[16]  Slawomir Koziel,et al.  Fast multi-objective surrogate-assisted design of multi-parameter antenna structures through rotational design space reduction , 2016 .

[17]  Guy A. E. Vandenbosch,et al.  An Efficient Method for Antenna Design Optimization Based on Evolutionary Computation and Machine Learning Techniques , 2014, IEEE Transactions on Antennas and Propagation.

[18]  Asok De,et al.  Prediction of Slot-Size and Inserted Air-Gap for Improving the Performance of Rectangular Microstrip Antennas Using Artificial Neural Networks , 2013, IEEE Antennas and Wireless Propagation Letters.

[19]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[20]  Slawomir Koziel,et al.  Multi-Objective Design of Antennas Using Variable-Fidelity Simulations and Surrogate Models , 2013, IEEE Transactions on Antennas and Propagation.

[21]  R. K. Ursem.  Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[22]  Zhi-qiang Lin,et al.  Sidelobe reduction of the low profile multi-subarray antenna by genetic algorithm , 2012 .

[23]  Hyeong-Seok Kim,et al.  Hybrid Algorithm Combing Genetic Algorithm With Evolution Strategy for Antenna Design , 2016, IEEE Transactions on Magnetics.

[24]  A. Owen.  A Central Limit Theorem for Latin Hypercube Sampling , 1992 .

[25]  Andrew Lewis,et al.  How important is a transfer function in discrete heuristic algorithms , 2015, Neural Computing and Applications.

[26]  Bing-Zhong Wang,et al.  An Improved PSO Algorithm and Its Application to UWB Antenna Design , 2013, IEEE Antennas and Wireless Propagation Letters.

[27]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[28]  Slawomir Koziel,et al.  Multi‐objective design optimization of antennas for reflection, size, and gain variability using kriging surrogates and generalized domain segmentation , 2018 .