Deep‐Learning‐Enabled Intelligent Design of Thermal Metamaterials

Abstract

Thermal metamaterials are mixture‐based materials that are engineered to manipulate, control, and process the flow of heat, enabling numerous advanced thermal metadevices. Conventional thermal metamaterials are predominantly designed with tractable regular geometries owing to the delicate analytical solution and easy‐to‐implement effective structures. Nevertheless, it is challenging to achieve the design of thermal metamaterials with arbitrary geometry, letting alone intelligent (automatic, real‐time, and customizable) design of thermal metamaterials. Here, an intelligent design framework of thermal metamaterials is presented via a pre‐trained deep learning model, which gracefully achieves the desired functional structures of thermal metamaterials with exceptional speed and efficiency, regardless of arbitrary geometry. It possesses incomparable versatility and is of great flexibility to achieve the corresponding design of thermal metamaterials with different background materials, anisotropic geometries, and thermal functionalities. The transformation thermotics‐induced, freeform, background‐independent, and omnidirectional thermal cloaks, whose structural configurations are automatically designed in real‐time according to shape and background, are numerically and experimentally demonstrated. This study sets up a novel paradigm for an automatic and real‐time design of thermal metamaterials in a new design scenario. More generally, it may open a door to the realization of an intelligent design of metamaterials in also other physical domains.

Analytical realization of complex thermal meta-devices

“…2D . For both cases, the isotherms outside the cloak remain straight and uniform, and the Relative Temperature Differences (RTD, see Supplementary Note 7 for definition, RTD-Y and RTD-X, respectively, correspond to Y- and X-direction applied heat) that evaluate the relative 2-norm temperature error compared to a homogeneous background medium are 1.37% and 1.27%, demonstrating very effective thermal cloaking and out-competing the state-of-the-art in 47 . The heat flux distributions are shown in Fig.…”

“…Although producing 3D-printable structures, the reliance on numerical design demands high computational cost and heavy post-processing to ensure inter-cell connection while producing overly complex and potentially sub-optimal structures. Replacement of numerical design with data-driven approaches can effectively reduce the cost 47 , but the resulting structures remain sub-optimal and geometrically complex.…”

Intelligent Materials and Nanomaterials Improving Physical Properties and Control Oriented on Electronic Implementations

“…AI is an advanced technology supporting material design [99][100][101][102][103][104][105][106][107][108][109][110][111][112][113][114], material production sustainability [115][116][117][118][119][120][121], and material data processing, usable to generate new polymeric materials [122][123][124][125][126][127][128][129][130][131][132][133][134][135][136]. In Table 3 are listed some selected works about AI application in the material fabrication process.…”

Synergy between AI and Optical Metasurfaces: A Critical Overview of Recent Advances

“…Thus, a path to acoustic metamaterials has been paved [44]. Other useful newly introduced classes were thermal metamaterials [45,46] that control heat flow and mechanical metamaterials [47][48][49] enabling the design of structures with mechanical properties exceeding the natural ones. A currently valid general definition of a metamaterial is that it represents an artificial structure with subwavelength functional building blocks (meta-atoms) tailored to have one or more effective properties that are seldom or never observed in nature.…”