chore: SR pipeline restructuring + DRL training infrastructure

SR_analysis restructured: - Stage 1/2/3/4 unified pipeline with per-stage docs - Old scripts/sindy/validate moved to old/archive - Results reorganized: formulas/validations/figures with scene_registry.json - Added diagnostic plots and PIPELINE.md drl_pinball/train: - New illusion training pipeline: env_illusion.py, train_illusion.py - Cross-Re transfer: crossre_transfer.sh, extend_transfer.sh - Calibration data: 0.75L/1L/1.5L/2L + re60/re100/re200/re400 - Launch scripts for multi-GPU training Cleaned 100+ intermediate/dead files from SR_analysis. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-05 17:36:29 +08:00
parent 5f061bec06
commit 1835f517e9
215 changed files with 2230 additions and 2376 deletions
@@ -1,84 +1,81 @@
-# SR_analysis: Symbolic Regression Analysis Pipeline
+# SR_analysis: Symbolic Regression for DRL Flow Control

-Extracts interpretable control laws (`obs -> act`) from DRL-trained policies for the
-fluidic pinball. Uses **PySR symbolic regression** on dimensionless physical features with
-G-equivariant structural constraints (v23: front no-bias, rear shared-head).
+Extracts interpretable control laws (obs -> act) from DRL-trained PPO policies
+for the fluidic pinball using PySR symbolic regression. Validates all formulas
+in CFD closed-loop and produces publication-quality figures.
+
+## Pipeline
+
+```
+stage_1_infer.py -> stage_2_fit.py -> stage_3_validate.py -> stage_4_analyze.py
+   (PPO data)       (PySR formula)     (CFD closed-loop)      (paper figures)
+```

 ## Quick Start

 ```bash
-# 1. Generate PPO data
+# Generate PPO inference data
 conda run -n pycuda_3_10 python stage_1_infer.py --scene karman_re100 --device 2

-# 2. Fit formula
-conda run -n sr_env python stage_2_fit.py --scene karman_re100 --mode per-scene
+# Fit symbolic formula
+conda run -n sr_env python stage_2_fit.py --scenes illusion_0.75L,illusion_1L --mode joint --deep

-# 3. Validate in CFD
-conda run -n pycuda_3_10 python stage_3_validate.py \\
-    --scene karman_re100 --device 2 --mode pysr \\
-    --formula-front results/formulas/karman_joint_front.json \\
-    --formula-top results/formulas/karman_joint_top.json
+# Validate in CFD
+conda run -n pycuda_3_10 python stage_3_validate.py \
+    --scene illusion_1L --device 2 --mode pysr \
+    --formula-front results/formulas/illusion_joint_front.json \
+    --formula-top results/formulas/illusion_joint_top.json

-# 4. Analyze
-conda run -n pycuda_3_10 python stage_4_analyze.py --scene karman_re100 --mode ppo-viz
-```
-
-## Pipeline Architecture
-
-```
-stage_1_infer.py  →  stage_2_fit.py  →  stage_3_validate.py  →  stage_4_analyze.py
-    (PPO数据)          (PySR拟合)         (CFD闭环验证)           (分析/画图)
+# Generate figures
+conda run -n pycuda_3_10 python stage_4_analyze.py
 ```

 ## Directory Structure

 ```
 SR_analysis/
-  PIPELINE.md                 # 总览文档 (入口)
-  README.md                   # 本文件
-  sindy_sr_knowledge.md       # 知识库 (bugs, 事实, 结果)
-  sindy_sr_notes.md           # 任务清单
-  scene_registry.json         # 所有场景的规范结果索引
-  configs.py                  # 场景注册表
-  core/                       # 共享工具库
-    features.py               # 特征构建 (无量纲化+phase-state)
-    fitting.py                # STLSQ拟合+特征矩阵
-    cfd.py                    # LegacyCelerisLab接口
-    g_operator.py             # G-mirror变换
-  data/                       # 运行时生成的.npz数据
+  stage_1_infer.py          # PPO inference (all scenes)
+  stage_2_fit.py            # PySR symbolic regression fitting
+  stage_3_validate.py       # CFD closed-loop validation
+  stage_4_analyze.py        # Publication figure generation
+  configs.py                # All scene definitions (19 scenes)
+  scene_registry.json       # Canonical results registry
+  utils/                    # Shared library (features, CFD, fitting)
+  data/                     # Runtime .npz data per scene
  results/
-    formulas/                 # 规范公式JSON
-    validations/              # CFD闭环验证结果
-    archive/                  # 归档的中间文件
-  stage_1_infer.py            # Stage 1: 统一PPO推理入口
-  STAGE_1_INFER.md
-  stage_2_fit.py              # Stage 2: 统一PySR拟合入口
-  STAGE_2_FIT.md
-  stage_3_validate.py         # Stage 3: 统一CFD闭环验证入口
-  STAGE_3_VALIDATE.md
-  stage_4_analyze.py          # Stage 4: 统一分析/画图入口
-  STAGE_4_ANALYZE.md
+    formulas/               # Canonical formula JSONs
+    validations/            # CFD validation outputs
+    figures/                # Publication-quality PNG/PDF
+    FIGURE_INDEX.md         # Figure catalog with captions
+    README.md               # Formula + validation index
+  docs/
+    SR_analysis_report.md   # Full analysis report
+    illusion_joint_formula_analysis.md
+  PIPELINE.md               # Detailed reproduction guide
+  literature_note.md        # Paper writing + literature positioning
+  old/                      # Archived historical files
 ```

---
+## Key Results

-## Key Design Decisions
+| Scene | Formula | CFD Similarity |
+|-------|---------|:---:|
+| Karman cross-Re (joint) | alpha_F = daF_dt - 14.95*mu*Cl_tot | avg 0.847 |
+| Illusion joint (0.75L+1L) | alpha_F = Cd_tot - Cd_err - 5.43 + 0.01*(du_a_dt+u_a) | 0.978/0.970 |
+| Vortex lamb (Karman formula) | Karman joint, zero retraining | 0.949 (exceeds PPO) |

-1. **Feature levels**: Static (8-dim) -> Phase-state (6-dim) -> Illusion-phase (10-dim)
-2. **Output target**: Non-dimensional alpha, not physical omega
-3. **v23 structure**: Front no-bias, rear shared-head (Bottom = -Top(Gx))
-4. **Final judge**: CFD closed-loop similarity, not one-step R2
+## Environments

-## Key Documentation
+- `pycuda_3_10`: CFD + DRL model loading + visualization (stages 1, 3, 4)
+- `sr_env`: PySR symbolic regression (stage 2)
+- GPU: device 2 recommended
+
+## Documentation

 | File | Content |
 |------|---------|
-| `PIPELINE.md` | **Primary entry** — pipeline overview, environment, conventions |
-| `sindy_sr_knowledge.md` | Bug history, confirmed facts, known limitations |
-| `sindy_sr_notes.md` | Task list, current status |
-| `docs/SR_analysis_report.md` | Full report (465+ lines) |
-| `docs/illusion_joint_formula_analysis.md` | Illusion joint formula deep dive |
-
-## Core Files (≤20)
-
-`stage_1_infer.py`, `stage_2_fit.py`, `stage_3_validate.py`, `stage_4_analyze.py`, `configs.py`, `scene_registry.json`, `core/features.py`, `core/fitting.py`, `core/cfd.py`, `core/g_operator.py` + 8 docs.
+| `PIPELINE.md` | Full reproduction guide with all commands |
+| `docs/SR_analysis_report.md` | Complete methodology + results + discussion |
+| `results/figures/FIGURE_INDEX.md` | All figures with paper-ready captions |
+| `literature_note.md` | Literature positioning + writing guidance |
+| `results/README.md` | Formula + validation file index |