Kentaro Yaji 研究室

主宰者：Kentaro Yaji

大阪大学

AI 要約（直近 5 年の研究成果）

本研究室では、複雑な物理現象を伴う工学設計問題を解くために、トポロジー最適化（構造物や機械部品の形状を自動で決定する手法）と人工知能を組み合わせた研究を展開しています。特に、流体の流れや熱移動が関わる熱交換器やマイクロチャネル冷却装置など、多くの局所最適解が存在して従来の最適化手法では解きにくい問題を対象としています。低精度で高速な計算モデルと高精度だが計算量が多いモデルを組み合わせる多忠実度最適化や、深層学習を用いた生成モデルによる勾配計算不要な最適化フレームワークなど、複数のアプローチを開発しています。具体的には、格子ボルツマン法などの流体シミュレーション手法と随伴変数法を組み合わせて設計感度を効率的に計算したり、深い神経ネットワークで設計領域を圧縮表現し新しい設計案を生成したりしています。さらに、これらの手法を乱流熱伝達やナノ流体を用いた冷却装置、粒子流体混合など、産業上重要な多様な熱流体システムの設計に適用しており、数値シミュレーションと実験を統合した検証も進めています。研究成果は航空宇宙エンジンや電子機器の熱管理など、実際の工学応用を目指しています。

※ AI（Claude）が、公開されている論文要旨から研究の問い・手法・主要な発見を事実情報として抽出・再構成して自動生成しています。誤りを含む可能性があるため、正確性は研究室公式情報でご確認ください。

外部リンク

研究成果（34 件）

[2025] Multifidelity Topology Design for Turbulent Heat Transfer Problems Using a Darcy Flow Model Incorporating Pseudo-Boundary Layer
DOI: https://doi.org/10.1115/1.4070209
[2025] Lessons Learned during 50 kg Manufacturing of Suzuki–Miyaura Coupling Reaction
DOI: https://doi.org/10.1021/acs.oprd.5c00207
[2025] Homogenization-Based Design for Non-Uniform Lattice Structures in Air-Cooled Heat Sinks: A Comparative Study of Unit Cell Patterns
DOI: https://doi.org/10.1115/detc2025-168776
[2025] Image fragmented learning for data-driven topology design
DOI: https://doi.org/10.1007/s00158-025-04054-3
[2025] Performance enhancement of variously shaped ribbed wall microchannel through topology optimization
DOI: https://doi.org/10.1016/j.csite.2025.106700
[2025] Data-driven topology design with persistent homology for enhancing population diversity
DOI: https://doi.org/10.1016/j.ijmecsci.2025.110493
[2025] Data-Driven Morphological Exploration and Shape Optimization for Turbulent Pipe Systems
DOI: https://doi.org/10.1115/1.4068984
[2025] Improved adjoint lattice Boltzmann method for topology optimization of laminar convective heat transfer
DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2025.127315
[2025] Deep concept identification for generative design
DOI: https://doi.org/10.1016/j.aei.2025.103354
[2025] Adjoint lattice kinetic scheme for topology optimization in fluid problems
DOI: https://doi.org/10.1016/j.jcp.2025.114001

続きを表示（残り 24 件）

[2025] Topology optimization for microchannel heat sinks with nanofluids using an Eulerian-Eulerian approach
DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2025.126870
[2025] Topology optimization for particle flow problems using Eulerian-Eulerian model with a finite difference method
DOI: https://doi.org/10.1016/j.compfluid.2025.106573
[2025] Data-driven multifidelity topology design for enhancing turbulent natural convection cooling
DOI: https://doi.org/10.1016/j.ijheatmasstransfer.2024.126659
[2025] Topology optimization for thermal-fluid systems considering maximum temperature constraints
DOI: https://doi.org/10.1299/transjsme.25-00089
[2024] Topology optimization for hybrid additive-subtractive manufacturing incorporating dynamic process planning
DOI: https://doi.org/10.1016/j.cma.2024.117270
[2024] Data-driven multi-fidelity topology design of fin structures for latent heat thermal energy storage
DOI: https://doi.org/10.1016/j.apenergy.2024.124596
[2024] Multifidelity Topology Design for Turbulent Heat Transfer Problems Using a Darcy Flow Model Incorporating Pseudo-Boundary Layer
DOI: https://doi.org/10.1115/detc2024-143380
[2024] Latent Crossover for Data-Driven Multifidelity Topology Design
DOI: https://doi.org/10.1115/1.4064979
[2024] Nanofluid micro heat sink design via topology optimization with the Eulerian-Eulerian Model
DOI: https://doi.org/10.1299/jsmecmd.2024.37.os-0319
[2024] Topologically Optimized Rocket Engine Heat Exchanger Based on Pseudo Boundary Layered Darcy Model
DOI: https://doi.org/10.1299/jsmedsd.2024.34.2107
[2024] Multi-Stage Optimal Design for Turbulent Pipe Systems by Data-Driven Morphological Exploration and Evolutionary Shape Optimization
DOI: https://doi.org/10.1115/detc2024-143383
[2023] Data-Driven Multifidelity Topology Design With a Latent Crossover Operation
DOI: https://doi.org/10.1115/detc2023-111079
[2023] Topology optimization using the lattice Boltzmann method for unsteady natural convection problems
DOI: https://doi.org/10.1007/s00158-023-03522-y
[2023] Tackling an Exact Maximum Stress Minimization Problem With Gradient-Free Topology Optimization Incorporating a Deep Generative Model
DOI: https://doi.org/10.1115/detc2023-111265
[2022] Practical Isolation of tert-Butyl [(1S,2R)-2-Aminocyclohexyl]carbamate (R)-Mandelate through Diastereomeric Salt Formation under Thermodynamic Control
DOI: https://doi.org/10.1021/acs.oprd.2c00215
[2022] Classification-Directed Conceptual Structure Design Based on Topology Optimization, Deep Clustering, and Logistic Regression
DOI: https://doi.org/10.1115/detc2022-88548
[2022] Topology optimization for the elastic field using the lattice Boltzmann method
DOI: https://doi.org/10.1016/j.camwa.2022.01.032
[2021] Optimum design of micromixer for a non-Newtonian fluid by topology optimization
DOI: https://doi.org/10.1016/j.cej.2021.131367
[2021] Level set-based topology optimization for two dimensional turbulent flow using an immersed boundary method
DOI: https://doi.org/10.1016/j.jcp.2021.110630
[2021] Design Concept Generation With Variational Deep Embedding Over Comprehensive Optimization
DOI: https://doi.org/10.1115/detc2021-69544
[2021] Data-driven multifidelity topology design using a deep generative model: Application to forced convection heat transfer problems
DOI: https://doi.org/10.1016/j.cma.2021.114284
[2021] Data-driven topology design using a deep generative model
DOI: https://doi.org/10.1007/s00158-021-02926-y
[2021] Topology optimization for incompressible viscous fluid flow using the lattice kinetic scheme
DOI: https://doi.org/10.1016/j.camwa.2021.05.032
[2021] Three-dimensional topology optimization model to simulate the external shapes of bone
DOI: https://doi.org/10.1371/journal.pcbi.1009043

科研費（0 件）

まだデータがありません（KAKEN 取り込み後に表示）。

所属学会・役職（0 件）

まだデータがありません（学会データ連携後に表示）。

AI 要約（直近 5 年の研究成果）

外部リンク

関連研究室(8 件)

研究成果（34 件）

科研費（0 件）

所属学会・役職（0 件）