JLJin-Pin Liu

Jin-Pin Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jin-Pin Liu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Computationally Efficient Inverse Design Method for Conformal Apertures Based on EAM-PINN

    by Yu-Hang Liu, Shi-Yu Meng, Jing-Cheng Liang, Yinchen Wang, Jinsong Fan, Bing-Zhong Wang, Ren Wang, Jin-Pin Liu, Chuan-Sheng Chen

    Conformal antenna design is an important and challenging topic in antenna engineering, especially when deploying large-aperture antenna arrays on complex curved surfaces such as aircraft fuselages. Traditional design methodologies, which are primarily based on array synthesis, often suffer from limited optimization efficiency due to the highly constrained solution space. In contrast, inverse design demonstrates superior performance over array synthesis in multiple aspects. This paper is the first to incorporate the physics-informed neural network with embedded analytical models (EAM-PINN) method into the inverse design process, achieving efficient solutions for complex and highly nonlinear conformal aperture fields without requiring any prior training data. The inverse design method based on EAM-PINN significantly outperforms existing inverse design approaches in both computational speed and accuracy. The results demonstrate that EAM-PINN delivers excellent performance across various challenging scenarios, exhibiting strong generalization capability. This method is expected to become a mainstream approach for the design of large-aperture conformal antennas.

  • Electromagnetic Inverse Design Method for 2-D Parametric-Curve-Defined Metallic Structures Based on PINNs

    by Jinsong Fan, Junjie Shao, Jin-Pin Liu, Hongyuan Chang, Yuhang Liu, Ren Wang, Bing-Zhong Wang

    Physics-informed neural networks (PINNs) are not dependent on data-driven methods but are solely constrained by physical laws. This makes them more aligned with the ideal inverse design process, which aims to minimize human intervention. More importantly, thanks to automatic differentiation, PINNs do not require iterative optimization algorithms like topology optimization, where each iteration involves solving forward matrix equations twice to determine gradient updates. Instead, PINNs only need a single forward pass to establish quantitative gradient relationships between variables, giving them significant potential for inverse design in electromagnetic devices. This paper presents a PINN-based framework for the inverse design of metallic structures defined by parametric curves in 2-D free space. Without predefined special boundary conditions like periodic boundary conditions, the framework simultaneously incorporates user-defined target field constraints and physical law constraints, optimizing the metallic structure to meet the desired field while predicting the electric field distribution across the entire domain.


  • An Efficient and Versatile Conformal Aperture Inverse Design Framework Based on IDMBSA

    by Chuan-Sheng Chen, Jing-Cheng Liang, Jin-Pin Liu, Junjie Shao, Ren Wang, Bing-Zhong Wang

    Conformal aperture inverse design faces significant challenges in computational efficiency and applicability due to its inherent curved geometry complexity. This paper proposes an efficient and versatile conformal aperture inverse design framework that transforms the complex conformal inverse design problem into a more tractable planar aperture synthesis through the equivalence principle, significantly reduces problem dimensionality and computational complexity. The framework’s innovation lies in its ability to inverse design tangential field distributions on curved surfaces to achieve desired radiation patterns, providing unprecedented design flexibility for conformal apertures with broad implementation possibilities. Any antenna element that maintains acceptable performance under conformal conditions can be integrated into this framework, and it can potentially be extended to other implementations such as metasurfaces and transmitarrays, providing designers with extensive flexibility in practical applications. The feasibility of the proposed framework is thoroughly validated through theoretical analysis, full-wave simulations, and experimental measurements of a prototype conformal sparse array. The results demonstrate its potential for practical applications in aerospace and other fields requiring conformal antenna designs.


  • Open Access

    A PINN framework for inverse physical design of metal-loaded electromagnetic devices

    by Yu-Hang Liu, Jin-Pin Liu, Bing-Zhong Wang, Ren Wang

    To solve the difficulty of inverse design of metal-loaded electromagnetic devices, we propose a physics-informed neural network (PINN) framework. With the emergence of PINNs, some scholars within the field of electromagnetism have utilized them to design dielectric-loaded electromagnetic devices. However, using PINN to design metal-loaded electromagnetic devices is still uncommon due to the difficulty of binarization of metal shapes. In light of this, we propose a PINN framework to address the inverse physical design of metal-loaded electromagnetic devices. In PINN, we embed mathematical-physics models into the network, which endows the training parameters of PINN with practical physical significance. The main innovation of this paper is to solve the binarization problem in the inverse design of metal-loaded devices within the PINN. To verify the feasibility of our method, we provide an example of designing a dual-layer metal diaphragm-loaded parallel plate waveguide device. The PINN presented with metal binarization in this paper offers a novel approach to the inverse physical design of metal-loaded electromagnetic devices.


  • Inverse Design Method of Metal Structures in Multiport Waveguide Based on Numerical Green’s Function

    by Jin-Pin Liu, Junjie Shao, Jinsong Fan, Chuan-Sheng Chen, Ren Wang, Bing-Zhong Wang

    This article proposes an inverse design method based on numerical Green’s function (NGF-IDM) to achieve the intelligent and efficient design of waveguide devices. Inspired by the metal inverse scattering theory, we use the induced current source model to inverse-design metal structures in a waveguide. We divide the design domain by meshing grid points and parameterize the design metal structure and the induced current distribution. Through the numerical method, we extract the numerical Green’s function of the multiport waveguide at one time. Different structures will be transformed into different current sources placed in the background waveguide through the least-squares method. Then, under the constraints of physical equations, we achieve the inverse solution from the design target to the metal structure. Case 1 presents an inverse-designed 1-to-3 phase-shifting power divider, proving the method’s capability for designing multifunctional electromagnetic devices. Keeping the background waveguide structure unchanged, Case 2 realizes a 1-to-3 frequency divider, illustrating the flexibility of the NGF-IDM. The experimental results show that the theoretical, simulation, and measurement results are highly consistent, proving the feasibility and effectiveness of our method. NGF-IDM enables efficient design in complex environments without iterative full-wave simulations, significantly improving design efficiency. This article provides a new idea for the integrated and highly flexible design of electromagnetic waveguide devices.


  • Inverse Design Method for Horn Antennas Based on Knowledge-Embedded Physics-Informed Neural Networks

    by Jin-Pin Liu, Bing-Zhong Wang, Chuan-Sheng Chen, Ren Wang

    This letter aims to overcome the challenges faced by physics-informed neural networks (PINNs) in metal structure design. Taking the design of horn antennas as an example, we propose knowledge-embedded PINNs inverse design framework. Normalized Maxwell's equations are employed to address convergence issues caused by differences in magnitudes. Unlike traditional PINNs, we built field component neural networks, inherently satisfying the boundary conditions of the metal structure. At the same time, the boundary conditions of the port and aperture fields are embedded within the neural network using a hard constraint boundary approach. The embedded knowledge further simplifies the loss function. The numerical experiments showcase the inverse design results of the H-plane horn antenna profile under different target aperture field requirements. The results demonstrate that the inverse-designed antennas effectively achieve the super-gain and beam deflection, respectively, validating the feasibility and practical value of the proposed method.


  • Determining Aperture Field for Arbitrary Phaseless Far-Field Utilizing Inverse Design Method Based on Spectral Analysis

    by Chuan-Sheng Chen, Ren Wang, Jin-Pin Liu, Bing-Zhong Wang

    In this communication, we propose an inverse design method based on spectral analysis (IDMBSA) for achieving desired far-field radiation pattern through aperture field design. The aperture field obtained through IDMBSA can be utilized for array synthesis and sparse array design, and it can also serve as a design objective for existing aperture field implementation methods. IDMBSA combined with the coordinate transformation enables the fulfillment of design requirements for arbitrary phaseless radiation pattern and polarization needs. Non-linearity introduced by phaseless is addressed with a multi-objective optimization (MOO) algorithm. Compared to traditional array synthesis methods, IDMBSA significantly reduces the number of optimization variables by using modal expansion and further reduces the computational burden by utilizing analytical solutions. The inherent smoothness of the aperture field obtained through IDMBSA allows for direct application in existing aperture field implementation methods, facilitating the direct design of radiating devices with arbitrary far-field radiation pattern. Simulations were conducted to explore IDMBSA’s application in array synthesis, sparse arrays, and dual-polarization independent design, the results show the practicability of IDMBSA and its wide application prospect.


  • Flatness Scanning and Superdirectivity in Planar Antenna Arrays: An Analysis and Design Approach Using IDMBSA

    by Chuan-Sheng Chen, Ren Wang, Jin-Pin Liu, Bing-Zhong Wang

    This letter focuses on the important challenge of realizing superdirectivity at large scanning angles (achieving flatness scanning) from the perspective of the array factor. Upon analysing the derivation of the array factor theory, this letter determines that the directivity of planar arrays drops as cosine of the angle ( the cosine law ) is the result of an approximate derivation. This indicates that an aperture field can exhibit superdirectivity at large angles. Subsequently, we employed the inverse design method based on spectral analysis (IDMBSA) starting from arbitrary phaseless radiation pattern formerly proposed by us to design a series of aperture fields, which realizing superdirectivity, achieving flatness scanning, breaking the cosine law . The numerical simulation results aligned with expectations, verifying the correctness of the analysis. Further, we can use this property to compensate for the element factor and thus achieve flatness scanning. This study provides a useful reference for designing antenna arrays with superdirectivity and flatness scanning.