近日，浙江大学张春利团队研究了压电半导体非线性多场耦合分析。2025年10月21日出版的《中国科学：物理学 力学 天文学》杂志发表了这项成果。

研究组提出了一种通过任务分解（DD PINN-TD）的数据驱动的物理知情神经网络（PINN），用于模拟压电半导体（PS）的非线性热变形极化载体（TDPC）耦合力学行为。通过将PS结构的三维（3D）、板和梁方程分别嵌入DD PINNs TD框架的约束中，开发了三种具有代表性的PINNs，与传统PINNs相比，它们在计算效率和精度方面具有显著优势。 

利用提出的DD PINN-TD模型，研究组分析了PS结构在不同载荷下的TDPC耦合响应。数值结果表明，所提出的模型在预测PS的非线性多场耦合力学行为方面表现出了这些模型的准确性和稳定性。值得注意的是，与基于3D方程的模型相比，基于板和梁理论的DD PINN-TD模型实现了更高的计算效率。该研究为分析PS结构中的非线性多场耦合响应奠定了理论基础，在工程应用中具有重要实用价值。

附：英文原文

Title: Nonlinear multi-field coupling analysis of piezoelectric semiconductors via PINNs

Author: Xiao, Zhengguang, Weng, Yilin, Yao, Wen, Chen, Weiqiu, Zhang, Chunli

Issue&Volume: 2025-10-21

Abstract: We propose a data-driven physics-informed neural networks (PINNs) via task-decomposition (DD-PINNs-TD) for modeling nonlinear thermal-deformation-polarization-carrier (TDPC) coupling mechanical behaviors of piezoelectric semiconductors (PSs). By embedding three-dimensional (3D), plate, and beam equations of PS structures into the constraints of the DD-PINNs-TD framework, respectively, we develop three representative PINNs that exhibit significant advantages in computational efficiency and accuracy compared to traditional PINNs. Using the proposed DD-PINNs-TD models, we investigate the TDPC coupling responses of PS structures under different loadings. Numerical results demonstrate that the proposed models exhibit accuracy and stability of these models in predicting the nonlinear multi-field coupling mechanical behaviors of PSs. Notably, the plate and beam-theory-based DD-PINNs-TD models achieve superior computational efficiency relative to their 3D-equation-based counterparts. This study establishes a theoretical foundation for analyzing nonlinear multi-field coupling responses in PS structures and has significant practical value in engineering applications.

DOI: 10.1007/s11433-025-2742-6

Source: https://link.springer.com/article/10.1007/s11433-025-2742-6