2026-09-29 11:57:39 +08:00
<!DOCTYPE html>
< html lang = "zh-CN" >
< head >
< meta charset = "UTF-8" >
< meta name = "viewport" content = "width=device-width, initial-scale=1.0" >
2026-10-05 21:51:54 +08:00
< title > Physics AI Fluent Analysis - GPU 流场仿真 - 人工智能工程技术研究-江北的渔夫</ title >
2026-09-29 11:57:39 +08:00
< meta name = "description" content = "Physics AI Fluent Analysis —— 用 GPU 加速的 3D D3Q19 格子玻尔兹曼方法求解水平卧式流化床空床气相流场：恒功率风机曲线 + 多孔布风板自洽求解，为 AI for Science 神经算子提供真值引擎与数据工厂。" >
< meta name = "keywords" content = "Physics AI Fluent, GPU LBM, 格子玻尔兹曼, 流化床, 流场仿真, AI for Science, 神经算子, FNO, GNN" >
< link rel = "stylesheet" href = "/static/css/style.css" >
< link rel = "icon" href = "/static/img/logo.svg" type = "image/svg+xml" >
< script src = "/static/js/nav.js" ></ script >
</ head >
< body >
< header class = "site-header" >
< div class = "container header-inner" >
< a class = "brand" href = "/" >
2026-10-10 11:45:30 +08:00
< img src = "/static/img/logo.svg" alt = "Easy Design Collection" >
< span class = "brand-name" > EDC|江北的渔夫</ span >
2026-09-29 11:57:39 +08:00
</ a >
< nav class = "main-nav" id = "mainNav" >
< div class = "nav-item has-dropdown" >
< a class = "nav-link" href = "/research/" > 前沿技术研究</ a >
< button class = "nav-caret" type = "button" aria-label = "展开前沿技术研究" > ▾</ button >
< div class = "dropdown" >
< a href = "http://124.220.63.9:25000" > Research Digest</ a >
< a href = "/research/neural/" > Neural Research</ a >
< a href = "/research/reslib/" > ResLib</ a >
</ div >
</ div >
< div class = "nav-item has-dropdown" >
< a class = "nav-link active" href = "/tools/" > 工具开发</ a >
< button class = "nav-caret" type = "button" aria-label = "展开工具开发" > ▾</ button >
< div class = "dropdown" >
< a href = "/tools/sequence-diagram/" > Sequence-Diagram</ a >
< a href = "/tools/uni-viewer/" > Uni-Viewer</ a >
2026-10-10 11:45:30 +08:00
< a href = "/tools/serial-terminal/" > Serial Terminal</ a >
< a href = "/tools/enthalpy-diagram/" > Enthalpy Diagram</ a >
2026-09-29 11:57:39 +08:00
< a href = "/tools/edc-lite-erp/" > EDC Lite ERP</ a >
< a class = "active" href = "/tools/physics-ai-fluent/" > Physics AI Fluent</ a >
</ div >
</ div >
< div class = "nav-item has-dropdown" >
< a class = "nav-link" href = "/license/" > License</ a >
< button class = "nav-caret" type = "button" aria-label = "展开 License" > ▾</ button >
< div class = "dropdown" >
< a href = "/license/apply" > 申请 License</ a >
< a href = "/license/status" > 查询 / 下载</ a >
< a href = "/license/package" > 资源包获取</ a >
</ div >
</ div >
< a class = "nav-link" href = "/blog/" > 博客</ a >
</ nav >
< button class = "nav-toggle" id = "navToggle" aria-label = "菜单" > ☰</ button >
</ div >
</ header >
< main >
< section class = "page-hero" >
< div class = "container" >
< p class = "hero-eyebrow" > 工具开发 · AI FOR SCIENCE</ p >
< h1 > Physics AI Fluent Analysis< br > 水平卧式流化床 · 空床流场仿真</ h1 >
< p class = "page-hero-sub" > 用 GPU 加速的 3D D3Q19 格子玻尔兹曼方法（LBM）求解流化床空床气相流场：以恒功率离心风机曲线为压力进口、布风板为多孔板，流量与压差由物理自洽涌现；为 AI for Science / 神经算子提供真值引擎与数据工厂。</ p >
< div class = "hero-actions" >
< a href = "http://124.220.63.9:30000/admin/Physics-Ai-Fluent-Analysis" class = "btn btn-light" > 项目主页（Gitea） </ a >
< a href = "/tools/" class = "btn btn-outline-light" > 返回工具开发</ a >
</ div >
< div class = "hero-stats" >
< div class = "hero-stat" >< b > ~120 MLUPS</ b >< span > GPU 格点更新/秒</ span ></ div >
< div class = "hero-stat" >< b > 827 万</ b >< span > 网格单元（100 格/m） </ span ></ div >
< div class = "hero-stat" >< b > 184 s</ b >< span > 3900 步求解</ span ></ div >
< div class = "hero-stat" >< b > Q ≈ 1463 m³/h</ b >< span > 自洽涌现工况点</ span ></ div >
</ div >
</ div >
</ section >
< section class = "section" >
< div class = "container" >
< h2 class = "section-title" > 物理场景</ h2 >
< p class = "section-desc" > 水平卧式流化床空床（无颗粒）气相流场，完整还原布风板、分区风箱、渐扩段与排风结构。</ p >
< div class = "grid" >
< div class = "card" >< div class = "icon" > ▤</ div >< h3 > 布风板</ h3 >< p > 2400 mm × </ p ></ div >
< div class = "card" >< div class = "icon" > ◫</ div >< h3 > 分区进风</ h3 >< p > 沿长度均分 4 段（每段 600 mm），每段独立风箱（高 450 mm），DN300 侧进风、风向平行床板。</ p ></ div >
< div class = "card" >< div class = "icon" > ⇱</ div >< h3 > 沸腾 / 渐扩段</ h3 >< p > 1000 mm 高度内由 2400 × × </ p ></ div >
< div class = "card" >< div class = "icon" > ◎</ div >< h3 > 排风</ h3 >< p > 顶部居中 DN800 圆管排出，形成完整的进风—布风—沸腾—排风路径。</ p ></ div >
< div class = "card" >< div class = "icon" > ⚙</ div >< h3 > 恒功率风机</ h3 >< p > 单段额定 2500 m³/h（合计 10000 m³/h）、额定压差 2900 Pa；恒功率 Δp · Q = P ≈ 8056 W，关死压力 4350 Pa。</ p ></ div >
< div class = "card" >< div class = "icon" > ◈</ div >< h3 > 物理自洽的工况点</ h3 >< p > 2500 m³/h 与 2900 Pa 是风机额定点，不是独立约束。仿真只施加风机曲线压力，流量由「风机曲线 ∩ 系统阻力」唯一交点自然涌现。</ p ></ div >
</ div >
</ div >
</ section >
< section class = "section section-alt" >
< div class = "container" >
< h2 class = "section-title" > 数值方法</ h2 >
< div class = "grid" >
< div class = "card" >< div class = "icon" > ◍</ div >< h3 > GPU 格子玻尔兹曼</ h3 >< p > D3Q19 + BGK 碰撞 + 推流 + 半步反弹固体边界；NVIDIA GPU（ </ p ></ div >
< div class = "card" >< div class = "icon" > ▦</ div >< h3 > 网格</ h3 >< p > 100 格/m， × × </ p ></ div >
< div class = "card" >< div class = "icon" > ⇄</ div >< h3 > 边界条件</ h3 >< p > 压力进口（固定密度 = 风机曲线压力，速度零梯度自由）；压力出口（密度 = 1）；固体壁无滑移。</ p ></ div >
< div class = "card" >< div class = "icon" > ⏱</ div >< h3 > 求解成本</ h3 >< p > 3900 步 / 184 s 完成；对比传统 CFD 小时～天级，把空床流场分析压到分钟级。</ p ></ div >
</ div >
</ div >
</ section >
< section class = "section" >
< div class = "container" >
< h2 class = "section-title" > 仿真结果</ h2 >
< p class = "section-desc" > 压力符号、结构、量级均正确：风箱高压 → 布风板节流降压 → 沸腾段低压 → 向排风递减。</ p >
< div class = "grid" >
< div class = "card" >< h3 > 工况点风量</ h3 >< p >< b > Q ≈ 1463 m³/h</ b > （风机曲线与系统阻力交点）</ p ></ div >
< div class = "card" >< h3 > 风箱静压</ h3 >< p >< b > 4061 Pa</ b > （ </ p ></ div >
< div class = "card" >< h3 > 沸腾段静压</ h3 >< p >< b > 181 Pa</ b > （经布风板节流后）</ p ></ div >
< div class = "card" >< h3 > 布风板压差</ h3 >< p >< b > +3880 Pa</ b > （风箱 > 沸腾段）</ p ></ div >
< div class = "card" >< h3 > 最大流速</ h3 >< p >< b > 4.89 m/s</ b > （射流区）</ p ></ div >
< div class = "card" >< h3 > 求解</ h3 >< p >< b > 3900 步 / 184 s</ b > （ ， </ p ></ div >
</ div >
</ div >
</ section >
< section class = "section section-alt" >
< div class = "container" >
< h2 class = "section-title" > 流场图集</ h2 >
< p class = "section-desc" > 全部由 GPU 求解器输出（4× 分辨率原始图，网页为压缩版）。</ p >
< div class = "gallery" >
< figure class = "shot wide" >
< img src = "/static/img/physics-ai-fluent/fbed-overview.jpg" alt = "流化床空床流场四联总览" >
< figcaption > 四联总览 —— 垂直切面（风箱 / 布风板 / 沸腾段 / 排风）、侧向渐扩、布风板近区射流与沸腾段水平切面。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-streamlines.jpg" alt = "双大图流线" >
< figcaption > 流线图 —— 布风板射流合并与渐扩段速度衰减。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-pressure.jpg" alt = "静压场四联" >
< figcaption > 静压场四联 —— 风箱高压到排风的完整压力梯度。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-cutaway.jpg" alt = "三正交切面三维剖切" >
< figcaption > 三正交切面三维剖切 —— 立体观察内部流场结构。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-uniformity.jpg" alt = "各区段流量均匀性" >
< figcaption > 各区段流量均匀性 —— 验证 4 段配气一致性。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-decay.jpg" alt = "沿高度气速衰减" >
< figcaption > 沿高度气速衰减 —— 沸腾段与自由空域的速度剖面。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-flowrate.jpg" alt = "风量平衡" >
< figcaption > 风量平衡 —— 进风 / 布风板 / 排风三段流量守恒校核。</ figcaption >
</ figure >
< figure class = "shot" >
< img src = "/static/img/physics-ai-fluent/fbed-tilt.jpg" alt = "布风板 5° 倾斜影响" >
< figcaption > 布风板 5° 倾斜对近板风向的影响分析。</ figcaption >
</ figure >
</ div >
</ div >
</ section >
< section class = "section" >
< div class = "container" >
< h2 class = "section-title" > AI for Science 闭环</ h2 >
< p class = "section-desc" > 本项目天然是 AI for Science / 神经算子的数据工厂与落地场景。</ p >
< div class = "gallery" >
< figure class = "shot wide" >
< img src = "/static/img/physics-ai-fluent/pipeline.jpg" alt = "数据与训练流水线" >
< figcaption > 数据与训练流水线 —— 参数空间采样 → 批量仿真 → 数据工程 → 神经算子训练（FNO / DeepONet / GNN）→ 推理引擎部署（ONNX → TensorRT）→ 实时仿真服务（gRPC + WebSocket），并设置精度 / 稳定性 / 成本 / 可复现四道门禁。</ figcaption >
</ figure >
</ div >
< div class = "grid" >
< div class = "card" >< div class = "icon" > ◈</ div >< h3 > 神经算子</ h3 >< p > FNO / DeepONet 把「解算子」参数化为网络权重：输入几何 + 边界，输出全场。</ p ></ div >
< div class = "card" >< div class = "icon" > ▦</ div >< h3 > 图神经网络</ h3 >< p > MeshGraphNet 类模型适配非结构 / 复杂几何，天然处理不规则边界。</ p ></ div >
< div class = "card" >< div class = "icon" > ⚡</ div >< h3 > 代理模型加速</ h3 >< p > 用约 1% 的算力逼近求解器精度，支撑大规模参数扫描与在线优化。</ p ></ div >
< div class = "card" >< div class = "icon" > ◉</ div >< h3 > 数字孪生</ h3 >< p > 毫秒级推理 → 参数拖拽即时刷新 → 在线优化与预测性维护。</ p ></ div >
</ div >
</ div >
</ section >
< section class = "section section-alt" >
< div class = "container" >
< h2 class = "section-title" > 复现与技术栈</ h2 >
< p class = "section-desc" > Python 3.11+ · numpy · numba · numba-cuda（ （ </ p >
< div class = "grid" >
< div class = "card" >< h3 > 主仿真</ h3 >< p >< span class = "mono" > python tools/fbed_simulation.py</ span > （ </ p ></ div >
< div class = "card" >< h3 > 批量出图</ h3 >< p >< span class = "mono" > python tools/fbed_figures.py</ span > · < span class = "mono" > python tools/fbed_analysis.py</ span > （秒级）</ p ></ div >
< div class = "card" >< h3 > 可调参数</ h3 >< p >< span class = "mono" > FBED_PPM</ span > 网格分辨率 · < span class = "mono" > FBED_ULB</ span > 参考格速 · < span class = "mono" > FBED_DP</ span > 额定压差等环境变量</ p ></ div >
< div class = "card" >< h3 > 脚本体系</ h3 >< p > 求解器 / 出图 / 分析 / 通量诊断 / 切面探针 / RANS 尝试版（留档）</ p ></ div >
</ div >
< div class = "pill-row mt-24" >
< span class = "pill" > Python</ span >
< span class = "pill" > D3Q19 LBM</ span >
< span class = "pill" > numba.cuda</ span >
< span class = "pill" > CUDA</ span >
< span class = "pill" > GPU 120 MLUPS</ span >
< span class = "pill" > FNO / GNN</ span >
</ div >
</ div >
</ section >
</ main >
< footer class = "site-footer" >
< div class = "container footer-inner" >
< div class = "footer-brand" >
< img src = "/static/img/logo.svg" alt = "" >
2026-10-10 11:45:30 +08:00
< span > Easy Design Collection</ span >
2026-09-29 11:57:39 +08:00
</ div >
2026-10-10 11:45:30 +08:00
< span > Copyright © 2026 Easy Design Collection. All rights reserved.</ span >
2026-09-29 11:57:39 +08:00
< span class = "footer-links" >
2026-10-10 11:45:30 +08:00
< a href = "/resources/" > 内部研究</ a >< span class = "sep" > ·</ span >
2026-09-29 11:57:39 +08:00
< a href = "/license/" > License</ a >< span class = "sep" > ·</ span >
< a href = "/admin" > 管理页面</ a >< span class = "sep" > ·</ span >
< a href = "https://beian.miit.gov.cn/" target = "_blank" rel = "noopener" > 苏ICP备2026056863号</ a >
</ span >
</ div >
</ footer >
</ body >
</ html >
