Machine Learning Driven Window Blinds Inspired Porous Carbon-Based Flake for Ultra-Broadband Electromagnetic Wave...

Area of Science:

• Materials Science
• Electromagnetics
• Artificial Intelligence

Background:

• Developing lightweight, high-efficiency electromagnetic wave absorbers is challenging due to the need for decoupled impedance matching and loss performance.
• Existing materials often struggle to balance absorption bandwidth, thickness, and weight.

Purpose of the Study:

• To design and fabricate a novel Discrete Slat Tunable Electromagnetic Wave Absorption Material (DSTEAM).
• To leverage magneto-electric coupling and AI-driven optimization for enhanced absorption properties.
• To achieve ultra-broadband absorption in a thin and lightweight material.

Main Methods:

• Inspired by window blind structures, a DSTEAM was designed.
• Magneto-electric coupling principles were incorporated.
• An artificial intelligence-assisted, data-driven optimization strategy was employed for material design and fabrication.

Main Results:

• The fabricated DSTEAM demonstrated reflection loss below -10 dB over an ultra-broadband frequency range (2.6-40 GHz).
• The material maintained a thin thickness of 9.85 mm and a low areal density of 0.566 kg/m².
• Performance was attributed to gradient-induced multiple scattering, synergistic field enhancement, and magneto-electric coupling.

Conclusions:

• The DSTEAM exhibits superior lightweight and ultra-broadband electromagnetic wave absorption capabilities.
• The AI-driven collaborative design strategy provides a novel approach for next-generation absorber development.
• This work offers an effective pathway for creating advanced electromagnetic wave absorbing materials.