用机器学习反推吸波材料结构，加速高性能设计。
A Machine Learning Approach for Design of Frequency Selective Surface based Radar Absorbing Material via Image Prediction
- 以吸波系数为输入，反向生成FSS单元图像。
- 六种模型训练准确率超90%，频段覆盖1-30GHz。
- 适合电磁材料设计、快速优化的工程师和研究者。
本文提出一种基于机器学习的新方法，用于设计频率选择表面（FSS）基吸波材料。传统方法以FSS单元尺寸为输入预测吸波系数，而本文将吸波系数作为输入，由机器学习模型生成FSS单元图像，再据此提取参数。在1GHz至30GHz宽频带范围内，研究了11种不同机器学习模型，其中6种表现优异：(a) 随机森林分类、(b) K近邻分类、(c) 网格搜索回归、(d) 随机森林回归、(e) 决策树分类、(f) 决策树回归，训练准确率均超过90%。对生成图像的吸波性能通过商用电磁仿真器评估，结果表明模型性能良好，未来可加速高性能FSS基吸波材料的设计与优化。
原文摘要 · Abstract (English)
The paper presents an innovative methodology for designing frequency selective surface (FSS) based radar absorbing materials using machine learning (ML) technique. In conventional electromagnetic design, unit cell dimensions of FSS are used as input and absorption coefficient is then predicted for a given design. In this paper, absorption coefficient is considered as input to ML model and image of FSS unit cell is predicted. Later, this image is used for generating the FSS unit cell parameters. Eleven different ML models are studied over a wide frequency band of 1GHz to 30GHz. Out of which six ML models (i.e. (a) Random Forest classification, (b) K- Neighbors Classification, (c) Grid search regression, (d) Random Forest regression, (e) Decision tree classification, and (f) Decision tree regression) show training accuracy more than 90%. The absorption coefficients with varying frequencies of these predicted images are subsequently evaluated using commercial electromagnetic solver. The performance of these ML models is encouraging, and it can be used for accelerating design and optimization of high performance FSS based radar absorbing material for advanced electromagnetic applications in future.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。