Next-Generation Solvers for Complex Microwave Engineering Problems

复杂微波工程问题的下一代求解器

• 批准号: DP240102682
• 负责人: Prof Amin Abbosh
• 金额: $ 37.42万
• 依托单位: The University of Queensland
• 依托单位国家: 澳大利亚
• 项目类别: Discovery Projects
• 财政年份: 2024
• 资助国家: 澳大利亚
• 起止时间: 2024-01-01 至 2026-12-31
• 项目状态: 未结题
• 来源: https://dataportal.arc.gov.au/RGS/Web/Grants/DP240102682
• 关键词: Next; Generation; Solvers; Complex; Microwave

This project aims to design a complementary physics-guided, data-driven method that can accurately solve complex microwave engineering problems in a timely manner. The primary bottleneck so far preventing that approach, which is the disparity between the trained theoretical model and reality, will be overcome using a multi-frequency complex-valued domain adaptation technique. The method will use deep neural networks to reliably learn the physical concepts of microwave engineering problems. This project will have significant economic and societal benefits, such as supporting the efficient design, installation and operation of communication systems, mining, infrastructure inspection, security, remote sensing, and microwave imaging.

该项目旨在设计一种互补的物理引导，数据驱动的方法，该方法可以及时准确地解决复杂的微波工程问题。迄今为止，将使用多频率复合物值的域适应技术克服这种方法的主要瓶颈，即训练有素的理论模型与现实之间的差异。该方法将使用深层神经网络可靠地了解微波工程问题的物理概念。该项目将具有重大的经济和社会利益，例如支持通信系统，采矿，基础设施检查，安全性，遥感和微波成像的有效设计，安装和运行。