Design of a Broadband Solar Thermal Absorber Using a Deep Neural Network and Experimental Demonstration of Its Performance

Seo, Jae M.; Jung, Pil Hoon; Kim, Mingeon; Yang, Sounghyeok; Lee, Ikjin; Lee, Jungchul; Lee, Heon; Lee, Bong Jae

doi:10.1038/s41598-019-51407-2

Cited by 22 publications

(14 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the computational cost, we decided to build a surrogate model to estimate the absorption efficiency of each nanoparticle, i.e., [Input: geometry of i-th particle and λ → Output: Q a,i (λ )]. To ensure the accuracy of the surrogate model, an artificial neural network model 34 was employed as part of a modelling technique. To train the neural network models, samples were composed with 2 nm intervals of the design variables and a 10 nm interval of the wavelength.…”

Section: Absorption Coefficient Of a Blended Plasmonic Nanofluidmentioning

confidence: 99%

Tailoring the Spectral Absorption Coefficient of a Blended Plasmonic Nanofluid Using a Customized Genetic Algorithm

Seo,

Qin,

Lee

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Recently, plasmonic nanofluids (i.e., a suspension of plasmonic nanoparticles in a base fluid) have been widely employed in direct-absorption solar collectors because the localized surface plasmon supported by plasmonic nanoparticles can greatly improve the direct solar thermal conversion performance. Considering that the surface plasmon resonance frequency of metallic nanoparticles, such as gold, silver, and aluminum, is usually located in the ultraviolet to visible range, the absorption coefficient of a plasmonic nanofluid must be spectrally tuned for full utilization of the solar radiation in a broad spectrum. In the present study, a modern design process in the form of a genetic algorithm (GA) is applied to the tailoring of the spectral absorption coefficient of a plasmonic nanofluid. To do this, the major components of a conventional GA, such as the gene description, fitness function for the evaluation, crossover, and mutation function, are modified to be suitable for the inverse problem of tailoring the spectral absorption coefficient of a plasmonic nanofluid. By applying the customized GA, we obtained an optimal combination for a blended nanofluid with the desired spectral distribution of the absorption coefficient, specifically a uniform distribution, solar-spectrum-like distribution, and a step-function-like distribution. The resulting absorption coefficient of the designed plasmonic nanofluid is in good agreement with the prescribed spectral distribution within about 10% to 20% of error when six types of nanoparticles are blended. Finally, we also investigate how the inhomogeneous broadening effect caused by the fabrication uncertainty of the nanoparticles changes their optimal combination.

show abstract

Section: Absorption Coefficient Of a Blended Plasmonic Nanofluidmentioning

confidence: 99%

Tailoring the Spectral Absorption Coefficient of a Blended Plasmonic Nanofluid Using a Customized Genetic Algorithm

Seo,

Qin,

Lee

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A branch of machine learning (ML), DL methods have shown to have a high degree of non-linear abstraction from datasets 36 and to address complex issues such as self-driving cars 37 , speech recognition 38 , and natural language processing 39 . Deep Learning has been used in the field of photonics and nanophotonics to predict and model problems such as plasmonic interactions 36 , 40 , grating structures 41 – 43 , particles 44 , 45 , and nanostructures 46 . DL has also been extensively applied within the field of thermal engineering to study topics such as thermal conductivity 47 , boiling heat transfer 48 , and radiative thermal transport 49 – 51 .…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based inverse design of microstructured materials for optical optimization and thermal radiation control

Sullivan

Mirhashemi

Lee

2023

Sci Rep

View full text Add to dashboard Cite

Microstructures with engineered properties are critical to thermal management in aerospace and space applications. Due to the overwhelming number of microstructure design variables, traditional approaches to material optimization can have time-consuming processes and limited use cases. Here, we combine a surrogate optical neural network with an inverse neural network and dynamic post-processing to form an aggregated neural network inverse design process. Our surrogate network emulates finite-difference time-domain simulations (FDTD) by developing a relationship between the microstructure’s geometry, wavelength, discrete material properties, and the output optical properties. The surrogate optical solver works in tandem with an inverse neural network to predict a microstructure’s design properties that will match an input optical spectrum. As opposed to conventional approaches that are constrained by material selection, our network can identify new material properties that best optimize the input spectrum and match the output to an existing material. The output is evaluated using critical design constraints, simulated in FDTD, and used to retrain the surrogate—forming a self-learning loop. The presented framework is applicable to the inverse design of various optical microstructures, and the deep learning-derived approach will allow complex and user-constrained optimization for thermal radiation control in future aerospace and space systems.

show abstract

“…DL and Machine Learning (ML) have been used, in a broad setting, to solve complex problems ranging from machine vision for self-driving vehicles 32 to automatic speech recognition 33 and spacecraft system optimization 34 – 37 . In the field of optics, DL has been used recently to predict and model plasmonic behavior 31 , 38 – 42 , grating structures 43 , 44 , ceramic metasurfaces 45 , 46 , chiral materials 47 , 48 , particles and nanosturctures 49 – 51 , and to do inverse design 31 , 41 , 50 – 54 . Deep-Learning has also been used extensively in the field of heat transfer for applications such as predicting thermal conductivity 55 , 56 and thermal boundary resistance 57 , studying transport phenomena 58 , optimizing integrated circuits 59 , modelling boiling heat transfer 60 , predicting thermal-optical properties 44 , 61 , 62 , and addressing thermal radiation problems 63 – 66 .…”

Section: Introductionmentioning

confidence: 99%

“…In this paper we propose a methodology based on a DNN to predict the optical properties of micropyramids across a wide design space of geometries, wavelengths, and, most importantly, materials. As opposed to many other studies that provide a deep learning approach to a structure with a single material 38 , 52 , a geometry with fixed materials 44 , 47 , 51 , or a material input defined by one-hot encoding with a random forest 50 , our DNN is designed to predict the optical properties of a vast array of materials and is not constrained by material input. While there are many available machine learning methods 42 , 50 , 61 , 70 – 74 , we choose to utilize the deep neural network approach due to the method’s input flexibility, scalability, and the ability to extrapolate outputs from unseen inputs.…”

Section: Introductionmentioning

confidence: 99%

Deep learning based analysis of microstructured materials for thermal radiation control

Sullivan

Mirhashemi

Lee

2022

Sci Rep

View full text Add to dashboard Cite

Microstructured materials that can selectively control the optical properties are crucial for the development of thermal management systems in aerospace and space applications. However, due to the vast design space available for microstructures with varying material, wavelength, and temperature conditions relevant to thermal radiation, the microstructure design optimization becomes a very time-intensive process and with results for specific and limited conditions. Here, we develop a deep neural network to emulate the outputs of finite-difference time-domain simulations (FDTD). The network we show is the foundation of a machine learning based approach to microstructure design optimization for thermal radiation control. Our neural network differentiates materials using discrete inputs derived from the materials’ complex refractive index, enabling the model to build relationships between the microtexture’s geometry, wavelength, and material. Thus, material selection does not constrain our network and it is capable of accurately extrapolating optical properties for microstructures of materials not included in the training process. Our surrogate deep neural network can synthetically simulate over 1,000,000 distinct combinations of geometry, wavelength, temperature, and material in less than a minute, representing a speed increase of over 8 orders of magnitude compared to typical FDTD simulations. This speed enables us to perform sweeping thermal-optical optimizations rapidly to design advanced passive cooling or heating systems. The deep learning-based approach enables complex thermal and optical studies that would be impossible with conventional simulations and our network design can be used to effectively replace optical simulations for other microstructures.

show abstract

Design of a Broadband Solar Thermal Absorber Using a Deep Neural Network and Experimental Demonstration of Its Performance

Cited by 22 publications

References 27 publications

Tailoring the Spectral Absorption Coefficient of a Blended Plasmonic Nanofluid Using a Customized Genetic Algorithm

Tailoring the Spectral Absorption Coefficient of a Blended Plasmonic Nanofluid Using a Customized Genetic Algorithm

Deep learning-based inverse design of microstructured materials for optical optimization and thermal radiation control

Deep learning based analysis of microstructured materials for thermal radiation control

Contact Info

Product

Resources

About