AI for Applied Physics/Mechanics

Overview

Artificial Intelligence (AI) has become a transformative force across various scientific domains, offering novel methodologies for simulation, design, and optimization. Its integration into scientific research promises accelerated discoveries, enhanced precision in simulations, and optimized design processes that can tackle complex multi-variable systems. This project leverages AI’s robust capabilities in three critical areas: multiferroic composites, complex fluid flows, and near-field radiative heat transfer, each presenting unique challenges and opportunities for technological advancements.

Enhancing Solid-State Cooling with AI-Driven Phase-Field Simulations

The first paper introduces an innovative non-isothermal Phase-Field Model (PFM) integrated with machine learning to study the magneto-elastocaloric effect in multiferroic composites. This approach simulates the interactions of martensitic transformation, mechanics, heat transfer, and magnetostrictive behaviors under low magnetic fields. By employing a machine learning algorithm on PFM simulation data, the research optimizes the geometrical dimensions of Magnetostrictive-Shape Memory Alloys (MEA-SMA) composites to achieve significant improvements in the adiabatic temperature change and operational temperature range. This combined methodology not only augments the design of more efficient solid-state cooling devices but also extends its applicability to other multicaloric effects like the electro-elastocaloric effect. (Tang et al., 2024)

Workflow proposed in this paper.

Deciphering Complex Fluid Dynamics through Convolutional Neural Networks

The second paper explores the application of a convolutional neural network (CNN) for feature identification in subsonic buffet flows over high-incidence airfoils. By training the CNN with a limited dataset, the study achieves near-perfect accuracy in distinguishing between periodic, quasi-periodic, and chaotic flow regimes. The neural network identifies large-scale coherent structures without requiring temporal information, enhancing our understanding of fluid dynamics across various Reynolds numbers. This research highlights the potential of AI to not only predict fluid behavior but also to provide deeper insights into the underlying dynamics of complex fluid systems. (Wen et al., 2023)

Fluid's pattern identification.

Optimizing Near-Field Radiative Heat Transfer Designs with Machine Learning

The third paper presents a machine learning strategy combining artificial neural networks (ANN) and genetic algorithms (GA) to model and optimize near-field radiative heat transfer (NFRHT) scenarios. This approach significantly simplifies the design process of thermal devices like thermal photovoltaics and thermal diodes, traditionally reliant on designer intuition and expertise. The ANN models NFRHT between various materials, including metamaterials and nanoparticles, accurately predicting heat flow and rectification ratios. The genetic algorithm then optimizes physical parameters to achieve the best thermal performance, showcasing how AI can lead to precise, effective design solutions in thermal management applications. (Wen et al., 2022)

Proposed workflow.

Conclusion

This project illustrates the substantial benefits of integrating AI into scientific research, where complex systems and phenomena can be modeled, analyzed, and optimized more efficiently than ever before. It paves the way for future innovations that could revolutionize industries dependent on cooling technology, fluid dynamics, and thermal management.

References

2024

IJMS

Phase-field simulation and machine learning of low-field magneto-elastocaloric effect in a multiferroic composite

Wei Tang, Shizheng Wen, Huilong Hou, Qihua Gong, Min Yi, and Wanlin Guo

International Journal of Mechanical Sciences, 2024

Abs HTML PDF

Achieving appreciable elastocaloric effect under low external field is critical for solid-state cooling technology. Here, a non-isothermal Phase-Field Model (PFM) coupling martensitic transformation with mechanics, heat transfer and magnetostrictive behavior is proposed to simulate Magneto-elastoCaloric Effect (M-eCE) that is induced by magnetic field in a multiferroic composite (e.g., Magnetostrictive-Shape Memory Alloys (MEA-SMA) composite). In the PFM, a nonlinear constitutive hyperbolic tangent model is utilized to model the macroscopic magnetostrictive behavior of MEA, and the heat transfer coupled with phase transformation is employed to calculate the adiabatic temperature change (∆T_ad) during M-eC cooling cycles. The influences of magnetic field, geometrical dimension, and ambient temperature on ∆T_ad are comprehensively investigated. Machine Learning (ML) is further conducted on the database from PFM simulations to accelerate the prediction and design of MEA-SMA composite with an improved ∆T_ad. It is found that a large ∆T_ad of 10–14 K and a wide working temperature window of 30 K can be achieved under ultra-low magnetic field of 0.15–0.38 T by optimizing the composite’s geometrical dimension. The present work combining PFM and ML for evaluating M-eCE provides a theoretical framework for the optimization of M-eC cooling devices, and is also potentially extended to other multicaloric effects (e.g., electro-elastocaloric effect).

2023

TAML

Feature Identification in Complex Fluid Flows by Convolutional Neural Networks

Shizheng Wen, Michael W Lee, Kai M Kruger Bastos, Ian Eldridge-Allegra, and Earl H Dowell

Theoretical and Applied Mechanics Letters, 2023

Abs HTML PDF

Recent advancements have established machine learning’s utility in predicting nonlinear fluid dynamics, with predictive accuracy being a central motivation for employing neural networks. However, the pattern recognition central to the network’s function is equally valuable for enhancing our dynamical insight into the complex fluid dynamics. In this paper, a single-layer convolutional neural network (CNN) was trained to recognize three qualitatively different subsonic buffet flows (periodic, quasi-periodic and chaotic) over a high-incidence airfoil, and a near-perfect accuracy was obtained with only a small training dataset. The convolutional kernels and corresponding feature maps, developed by the model with no temporal information provided, identified large-scale coherent structures in agreement with those known to be associated with buffet flows. Sensitivity to hyperparameters including network architecture and convolutional kernel size was also explored. The coherent structures identified by these models enhance our dynamical understanding of subsonic buffet over high-incidence airfoils over a wide range of Reynolds numbers.

2022

APL

A machine learning strategy for modeling and optimal design of near-field radiative heat transfer

Shizheng Wen, Chunzhuo Dang, and Xianglei Liu

Applied Physics Letters, 2022

Abs HTML PDF

The past decade has witnessed the advent of near-field radiative heat transfer (NFRHT) in a wide range of applications, including thermal photovoltaics and thermal diodes. However, the design process for these thermal devices has remained complex, often relying on the intuition and expertise of the designer. To address these challenges, a machine learning (ML) strategy based on the combination of artificial neural network (ANN) and genetic algorithm (GA) is presented. The ANN is trained to model representative scenarios, viz. NFRHT between metamaterials, NFRHT and thermal rectification between nanoparticles. The influence of different problem complexities, i.e. the number of input variables of function to be fitted, on effectiveness of the trained ANN is investigated. Test results show that ANNs can obtain the radiative heat flow and rectification ratio accurately and rapidly. Subsequently, physical parameters for the largest radiative heat flow and rectification ratio are determined by the utilization of GA on the trained ANN, and underlying mechanisms of deterministic optimum are discussed. Our work shows that data-driven ML methods are a powerful tool which offers unprecedented opportunities for future NFRHT research.