Bingbing Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bingbing Song has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Tian Liu
State Key Laboratory of Millimeter Waves, School of Information Science and Engineering, Southeast University, Nanjing, China
5 shared publications - Wei-Bing Lu
State Key Laboratory of Millimeter Waves, School of Information Science and Engineering, Southeast University, Nanjing, China
5 shared publications - Wu Yang
State Key Laboratory of Millimeter Waves, School of Information Science and Engineering, Southeast University, Nanjing, China
5 shared publications - Fei Guo
State Key Laboratory of Millimeter Waves, School of Information Science and Engineering, Southeast University, Nanjing, China
3 shared publications - Jian Wei You
State Key Laboratory of Millimeter Wave Southeast University Nanjing China
3 shared publications Fanxu Meng
College of Artificial Intelligence, Nanjing Tech University, Nanjing, China
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (10) , 9886-9899
Intelligent Subentire-Domain Basis Function Method Based on Adaptive Physics-Informed Transformer Framework
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (10) , 9886-9899
Intelligent Subentire-Domain Basis Function Method Based on Adaptive Physics-Informed Transformer Framework
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 25 (1) , 319-323
Efficient Analysis of Electromagnetic Scattering From Composite Finite Periodic Structures by Prior Physics-Driven Graph Neural Network
In this letter, a novel prior physics-driven graph neural network (PPDGNN) is proposed firstly to rapidly compute the far-field scattering in the composite large-scale finite periodic structures (LFPSs). Each composite cell is considered as a graph node and all nodes are prior physically connected according to the mutual coupling relationship. The current coefficients of the metal cell are taken as a priori physical information, which together with the structural parameters forms the feature matrix. The PPDGNN can effectively capture the scattering field of the composite structure driven by the prior information, instead of filling and solving impedance matrix equations. Additionally, transfer learning is applied to reduce the time cost by nearly 80%, while enabling the model to analyze structures with larger scales and complex metal cells. Numerical experiments demonstrate that the PPDGNN exhibits accuracy, generalization, and efficiency.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 25 (1) , 319-323
Efficient Analysis of Electromagnetic Scattering From Composite Finite Periodic Structures by Prior Physics-Driven Graph Neural Network
In this letter, a novel prior physics-driven graph neural network (PPDGNN) is proposed firstly to rapidly compute the far-field scattering in the composite large-scale finite periodic structures (LFPSs). Each composite cell is considered as a graph node and all nodes are prior physically connected according to the mutual coupling relationship. The current coefficients of the metal cell are taken as a priori physical information, which together with the structural parameters forms the feature matrix. The PPDGNN can effectively capture the scattering field of the composite structure driven by the prior information, instead of filling and solving impedance matrix equations. Additionally, transfer learning is applied to reduce the time cost by nearly 80%, while enabling the model to analyze structures with larger scales and complex metal cells. Numerical experiments demonstrate that the PPDGNN exhibits accuracy, generalization, and efficiency.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (12) , 4970-4974
Efficient Analysis of Electromagnetic Scattering in Large-Scale Finite Periodic Structures Using Characteristic Modes
Periodic characteristic mode (CM) analysis (PCMA) has proven to be an efficient method for analyzing large-scale finite periodic structures (LFPSs). However, its CMs are obtained solely from the reference cell, the solution process neglects the coupling effects among cells. To address this issue, this letter proposes an accurate method for analyzing the scattering properties of LFPSs. On one hand, by introducing dummy cells, the computation of CMs incorporates the coupling effects of surrounding cells, thereby improving accuracy. On the other hand, the compressive sensing (CS) technique is utilized to partially fill the impedance matrix to rapidly construct an overdetermined equation instead of a reduced matrix equation. Numerical examples are given to verify the accuracy and efficiency of the proposed method.
- 6 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 24 (12) , 4970-4974
Efficient Analysis of Electromagnetic Scattering in Large-Scale Finite Periodic Structures Using Characteristic Modes
Periodic characteristic mode (CM) analysis (PCMA) has proven to be an efficient method for analyzing large-scale finite periodic structures (LFPSs). However, its CMs are obtained solely from the reference cell, the solution process neglects the coupling effects among cells. To address this issue, this letter proposes an accurate method for analyzing the scattering properties of LFPSs. On one hand, by introducing dummy cells, the computation of CMs incorporates the coupling effects of surrounding cells, thereby improving accuracy. On the other hand, the compressive sensing (CS) technique is utilized to partially fill the impedance matrix to rapidly construct an overdetermined equation instead of a reduced matrix equation. Numerical examples are given to verify the accuracy and efficiency of the proposed method.
- 13 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 73 (9) , 6707-6717
Hybrid Variational Quantum Algorithm Enhanced Subentire-Domain Basis Functions Method With High Learning Efficiency and Better Robustness
The subentire-domain (SED) basis functions method is the most effective method for analyzing the electromagnetic properties of large-scale finite periodic structures (LFPSs). Recently, artificial neural networks have been employed to accelerate this method by rapidly predicting the expansion coefficients of SED basis functions without filling mutual coupling matrices. However, the training processes of prediction models can be further improved due to its classical computational paradigm. In this paper, a novel variational quantum algorithm enhanced SED basis functions method is proposed and the quantum computing paradigm is utilized to analyze LFPSs for the first time. In our algorithm, the array features are expanded and encoded onto few qubits, and the resulting quantum state is unitarily transformed into expansion coefficients by the parameterized quantum circuit. In addition, the algorithm is deployed on the quantum simulator for numerical experiments. The experimental results demonstrate that our method can accurately and quickly analyze LFPSs. Furthermore, the quantum-inspired models achieve 27%-62% improvements in learning efficiency for corner and edge cells, and 22%-59% improvements in robustness for all types of cells.
- 13 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 73 (9) , 6707-6717
Hybrid Variational Quantum Algorithm Enhanced Subentire-Domain Basis Functions Method With High Learning Efficiency and Better Robustness
The subentire-domain (SED) basis functions method is the most effective method for analyzing the electromagnetic properties of large-scale finite periodic structures (LFPSs). Recently, artificial neural networks have been employed to accelerate this method by rapidly predicting the expansion coefficients of SED basis functions without filling mutual coupling matrices. However, the training processes of prediction models can be further improved due to its classical computational paradigm. In this paper, a novel variational quantum algorithm enhanced SED basis functions method is proposed and the quantum computing paradigm is utilized to analyze LFPSs for the first time. In our algorithm, the array features are expanded and encoded onto few qubits, and the resulting quantum state is unitarily transformed into expansion coefficients by the parameterized quantum circuit. In addition, the algorithm is deployed on the quantum simulator for numerical experiments. The experimental results demonstrate that our method can accurately and quickly analyze LFPSs. Furthermore, the quantum-inspired models achieve 27%-62% improvements in learning efficiency for corner and edge cells, and 22%-59% improvements in robustness for all types of cells.
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (12) , 4089-4093
Rapid Estimation Method for Coupling Degree of Airborne Antenna Based on Quantum Neural Network
Estimation of coupling degree between antennas installed on an aircraft is essential for antenna layout design, which is closely related to electromagnetic compatibility (EMC). Traditional electromagnetic (EM) methods require multiple modeling and simulation when parameters of the antenna change, which is very time-consuming and inefficient. To tackle these difficulties, a quantum neural network (QNN) is applied for the first time to estimate the coupling degree of airborne antennas and it enables the rapid prediction of dual antenna coupling under different conditions on an aircraft. The unique quantum properties and coding approaches enable a more effective capture of the characteristics of data during training, leading to the discovery of more complex patterns and correlations. Four validation sets are created for experimentation, and the proposed method demonstrates well generalization ability and fast computational speed. It showcases developmental potential comparable to that of the artificial neural network (ANN).
- 22 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (12) , 4089-4093
Rapid Estimation Method for Coupling Degree of Airborne Antenna Based on Quantum Neural Network
Estimation of coupling degree between antennas installed on an aircraft is essential for antenna layout design, which is closely related to electromagnetic compatibility (EMC). Traditional electromagnetic (EM) methods require multiple modeling and simulation when parameters of the antenna change, which is very time-consuming and inefficient. To tackle these difficulties, a quantum neural network (QNN) is applied for the first time to estimate the coupling degree of airborne antennas and it enables the rapid prediction of dual antenna coupling under different conditions on an aircraft. The unique quantum properties and coding approaches enable a more effective capture of the characteristics of data during training, leading to the discovery of more complex patterns and correlations. Four validation sets are created for experimentation, and the proposed method demonstrates well generalization ability and fast computational speed. It showcases developmental potential comparable to that of the artificial neural network (ANN).