On the Use of Normalized Gaussian Network for Topology Optimization of Planar Components

In this paper, a novel topology optimization scheme based on normalized Gaussian network (NGnet) is proposed for design of planar microwave components. Since NGnet can treat the fine mesh structure with a lower dimension of design matrix, NGnet can be expected to improve the optimization efficiency of component design. Performances of the proposed NGnet-based optimization scheme is demonstrated by challenging the dynamic range of generalized inductance and generalized capacitance of a small planar structure on PCB. Results show that the widest dynamic range are acquired by NGnet-based scheme with interval of 4 and radius of 3, and the average optimization time is reduced by almost 70% than the traditional optimization scheme.

[1]  G. Wang,et al.  Design of High-Data-Density Chipless RFID Tag Embedded in QR Code , 2022, IEEE Transactions on Antennas and Propagation.

[2]  Qi-jun Zhang,et al.  Efficient EM Topology Optimization Incorporating Advanced Matrix Padé Via Lanczos and Genetic Algorithm for Microwave Design , 2021, IEEE transactions on microwave theory and techniques.

[3]  Hajime Igarashi,et al.  Topology Optimization Accelerated by Deep Learning , 2019, IEEE Transactions on Magnetics.

[4]  Jian Wang,et al.  Topology Optimization of Conical-Beam Antennas Exploiting Rotational Symmetry , 2018, IEEE Transactions on Antennas and Propagation.

[5]  Erfu Yang,et al.  Design of High-Isolation Wideband Dual-Polarized Compact MIMO Antennas With Multiobjective Optimization , 2018, IEEE Transactions on Antennas and Propagation.

[6]  Hajime Igarashi,et al.  Topology Optimization Using Basis Functions for Improvement of Rotating Machine Performances , 2018, IEEE Transactions on Magnetics.

[7]  Lu Wang,et al.  Design of High-Directivity Wideband Microstrip Directional Coupler With Fragment-Type Structure , 2015, IEEE Transactions on Microwave Theory and Techniques.

[8]  Qingfu Zhang,et al.  MOEA/D: A Multiobjective Evolutionary Algorithm Based on Decomposition , 2007, IEEE Transactions on Evolutionary Computation.