Spaces:
Running
Running
| title: CNT AI Pipeline Platform | |
| emoji: ⚗️ | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: docker | |
| pinned: false | |
| short_description: AI-driven Fe(Cp)2 → CNT manufacturing digital twin | |
| # ⚗️ Fe(Cp)₂ → CNT · AI Platform | |
| **AI-Driven Carbon Nanotube Manufacturing Simulator** | |
| An interactive digital twin platform for CNT synthesis optimization, combining ReaxFF molecular dynamics simulation data with a 5-stage ML pipeline for predicting and optimizing CNT manufacturing conditions. | |
| ## Features | |
| ### ⚡ Digital Twin Reactor | |
| - 3D interactive Plotly visualization of ferrocene molecular dynamics | |
| - Temperature-dependent bond evolution (200–2000 K) | |
| - Live reactor metrics: pressure, potential/kinetic energy, bond statistics | |
| - Real-time cluster analysis and CNT potential scoring | |
| - **NEW:** Multi-catalyst support (Fe, Fe-C, Fe-S, Fe-Mo-C, Fe-Co-C, Fe-Ni-C) | |
| ### 🎬 Decomposition Analysis | |
| - 6-frame molecular decomposition movie (Intact → Catalyst Nanoparticle) | |
| - Bond order vs temperature animated chart (Fe–Cp, C–C, C–H) | |
| - Bond survival landscape heatmap | |
| - Decomposition pathway with thermal thresholds | |
| ### 🔵 Catalyst & CNT Predictor | |
| - Fe nanoparticle cluster growth trajectory simulation | |
| - CNT growth predictor with interactive input sliders | |
| - Semi-circle gauge chart for nucleation probability | |
| - T vs Cluster Size nucleation probability heatmap | |
| ### 🌳 Pathways & Summary | |
| - Sankey diagram of reaction pathway tree | |
| - Pathway branching probabilities | |
| - Pipeline completion status | |
| - Executive summary dashboard (91 simulation runs, 13.6M timesteps) | |
| ### 🤖 AI Pipeline | |
| - **NEW:** 8,000-row synthetic DI-FCCVD dataset with **6 catalyst types** (Fe, Fe-C, Fe-S, Fe-Mo-C, Fe-Co-C, Fe-Ni-C) | |
| - **NEW:** Multi-product support (SWCNT, DWCNT, MWCNT) | |
| - **NEW:** Catalyst composition tracking (Mo, Co, Ni promoters in ppm) | |
| - 5-stage ML cascade (Random Forest, R² 0.88–0.96) | |
| - Feature correlation heatmap | |
| - Bayesian optimization — Top 5 synthesis recipes | |
| - **NEW:** CNT type and catalyst type distribution pie charts | |
| - Downloadable master dataset | |
| ### ⚙️ ReaxFF Optimization (**NEW TAB**) | |
| - **CMA-ES optimization simulation** with loss function evolution | |
| - Parameter subset optimization (Bond → vdW → Angle → Off-diagonal) | |
| - Energy/Force R² metrics and RMSE tracking | |
| - **CNT nucleation probability calculator** with multi-catalyst comparison | |
| - **Arrhenius plot** comparing all 6 catalyst types | |
| - Activation energy barriers by catalyst (1.6–2.1 eV) | |
| - DFT database statistics (300+ calculations, 3,000+ entries) | |
| - Configuration types: Supercells, vacancies, strain, substitutions, interstitials, slabs | |
| ## Pipeline Architecture | |
| ``` | |
| Public Data + Synthetic DI-FCCVD Data | |
| → Data Cleaning & Feature Engineering | |
| → Model 1: Atomistic Catalyst (decomposition_rate) | |
| → Model 2: Fe NP Formation (NP_size_nm) | |
| → Model 3: CNT Growth (cnt_growth_prob) | |
| → Model 4: Reactor Surrogate (residence_time_s) | |
| → Model 5: CNT Quality (purity, yield, diameter) | |
| → Bayesian Optimization → Best Recipe | |
| ``` | |
| ## Key Results | |
| - **Decomposition onset**: T ≈ 900–1100 K (Fe–Cp bond order < 0.3) | |
| - **Optimal catalyst**: Fe₅ nanoparticle, ~0.75 nm radius | |
| - **SWCNT range**: 1–5 nm catalyst clusters (3–15 Fe atoms) | |
| - **GPU acceleration**: 38× speedup vs CPU baseline | |
| - **Dataset**: 91 temperature points, 13.6M ReaxFF timesteps | |
| - **NEW:** Best catalyst for nucleation: **Fe-Mo-C** (E_a = 1.6 eV) | |
| - **NEW:** Multi-catalyst comparison across 6 compositions | |
| - **NEW:** DFT-trained ReaxFF optimization: Energy R² = 0.293, Force R² = 0.377 | |
| ## Recent Improvements (v2.0) | |
| ### Multi-Catalyst Support | |
| - Added 6 catalyst types: Fe, Fe-C, Fe-S, Fe-Mo-C, Fe-Co-C, Fe-Ni-C | |
| - Tracked promoter metals (Mo, Co, Ni) in ppm | |
| - Catalyst-specific activation energy barriers (1.6–2.1 eV) | |
| ### Multi-Product CNT Types | |
| - SWCNT (Single-Wall) | |
| - DWCNT (Double-Wall) | |
| - MWCNT (Multi-Wall with 3–15 layers) | |
| - Ultra-Long CNT, CNT Fiber, Conductive Network, High-Purity targets | |
| ### ReaxFF Optimization Module (Tab 6) | |
| - CMA-ES genetic algorithm visualization | |
| - Parameter subset optimization workflow | |
| - CNT nucleation probability calculator | |
| - Multi-catalyst Arrhenius comparison | |
| - DFT training database statistics | |
| ### Enhanced AI Pipeline (Tab 5) | |
| - CNT type distribution pie chart | |
| - Catalyst composition distribution chart | |
| - Expanded dataset from 14 to 21 feature columns | |
| - Nucleation barrier tracking by catalyst | |