GA基本正常

AGENTS.md

@@ -0,0 +1,34 @@
+# Repository Guidelines
+
+## Project Structure & Module Organization
+- Core simulation: `simulation_model.py` (Mesa `Model`), `production_line.py`, `demand_agent.py`.
+- UI & orchestration: `app.py` (Solara dashboard, matplotlib plotting, loads `data/<year>` based on `year.json`).
+- Optimization helpers: `genetic_calibration.py`, `ga_two_factor_calibration.py`, `build_distance_matrix.py`.
+- Data: `data/<year>/` CSV/JSON inputs and outputs; temporary artifacts can live in `output/`.
+
+## Setup, Build, and Run
+- Create env: `conda env create -f environment.yml` then `conda activate gw`.
+- Launch dashboard locally: `solara run app.py --host 0.0.0.0 --port 8765` (loads year set in `year.json`).
+- Recompute distance matrix when locations change: `python build_distance_matrix.py`.
+- Run calibration scripts headless: `python genetic_calibration.py` or `python ga_two_factor_calibration.py` (writes tuned params under `data/<year>`).
+
+## Coding Style & Naming Conventions
+- Follow Python 3.13 + PEP 8; 4-space indents; prefer type hints and docstrings for public functions/classes.
+- Use `snake_case` for variables/functions/modules, `CapWords` for classes, and descriptive names for data columns.
+- Keep plotting/fonts consistent with existing matplotlib config (Chinese labels enabled); reuse helpers instead of duplicating logic.
+- Guard data-file access with clear error messages and UTF-8/GBK fallbacks as seen in `app.py`.
+
+## Testing Guidelines
+- No formal suite exists yet; add `pytest`-style tests under `tests/` when feasible, mocking file I/O and using small sample CSVs.
+- For quick checks, run calibration scripts on a narrowed product set and validate outputs in `output/` or `data/<year>` before committing.
+- Validate UI flows by running `solara` and confirming charts render and download links work for the target year.
+
+## Commit & Pull Request Guidelines
+- Commit messages: short, imperative summaries (e.g., `Add capacity cap to Shenzhen lines`); keep body focused on rationale and data assumptions.
+- PRs should include: scope summary, affected year(s) in `data/`, before/after metrics or screenshots for UI changes, and steps to reproduce or rerun (`solara run ...`, script commands).
+- Link related issues/requests and note any regenerated files (e.g., `distance_matrix.csv`, calibration outputs) so reviewers can verify.
+
+## Data & Configuration Tips
+- Set `year.json` to the active dataset before running any scripts; keep year directories consistent (`data/2025`, `data/2026`, etc.).
+- Preserve CSV headers and encodings; when adding factories/products, update `factory_mapping.json` and rerun distance matrix generation.
+- Avoid committing large intermediate artifacts under `output/` unless they are required inputs; prefer deterministic script outputs for reviewability.

build_factory_data.py

@@ -0,0 +1,73 @@
+import json
+import os
+import pandas as pd
+from pathlib import Path
+
+
+def load_factory_mapping(year: int) -> dict:
+    path = os.path.join("data", str(year), "factory_mapping.json")
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def load_model_params(year: int) -> dict:
+    path = os.path.join("data", str(year), "model_params.json")
+    with open(path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+def load_benchmark_factories(year: int) -> list[str]:
+    path = Path("data") / str(year) / "benchmark.csv"
+    encodings = ("utf-8", "utf-8-sig", "gbk")
+    last_error = None
+    df = None
+    for enc in encodings:
+        try:
+            df = pd.read_csv(path, encoding=enc)
+            break
+        except UnicodeDecodeError as exc:
+            last_error = exc
+            continue
+    if df is None:
+        raise last_error if last_error else FileNotFoundError(f"Missing {path}")
+    # Assume first column holds factory name (aligns with factory_mapping keys)
+    factory_col = df.columns[0]
+    return df[factory_col].astype(str).str.strip().unique().tolist()
+
+
+def build_factory_dataframe(year: int) -> pd.DataFrame:
+    mapping = load_factory_mapping(year)
+    params = load_model_params(year)
+    default_factor = params.get("factor_default", 1)
+    benchmark_factories = load_benchmark_factories(year)
+    rows = []
+    for cn_name in benchmark_factories:
+        code = mapping.get(cn_name)
+        if code is None:
+            raise KeyError(f"benchmark.csv中的工厂“{cn_name}”未在 factory_mapping.json 中找到映射。")
+        factor = params.get(f"factor_{code}", default_factor if default_factor is not None else 1)
+        rows.append(
+            {
+                "工厂中文名": cn_name,
+                "工厂英文名": code,
+                "工厂平均磨合系数": float(factor),
+                "最小误差": 1_000_000,
+            }
+        )
+    return pd.DataFrame(rows)
+
+
+def write_factory_csv(df: pd.DataFrame, year: int) -> str:
+    out_path = os.path.join("data", str(year), "factory_data.csv")
+    df.to_csv(out_path, index=False, encoding="utf-8-sig")
+    return out_path
+
+
+def main():
+    year = 2025
+    df = build_factory_dataframe(year)
+    out_path = write_factory_csv(df, year)
+    print(f"factory_data.csv generated at: {out_path}")
+
+
+if __name__ == "__main__":
+    main()

data/2025/ProductionLine.csv

@@ -1,113 +1,113 @@
-区域名,工厂名,是否新工厂,产线ID,生产型号,开始月份,结束月份
-西北东部,艾郎玉门,是,艾郎玉门1,GWBD-A2,1,12
-西北东部,艾郎玉门,是,艾郎玉门2,GWBD-A2,1,12
-华北,艾郎张北,是,艾郎张北1,GWBD-A2,1,12
-华北,艾郎张北,是,艾郎张北2,GWBD-A2,1,12
-西北西部,时代巴里坤,是,时代巴里坤1,GWBD-A2,5,12
-西北西部,时代巴里坤,是,时代巴里坤2,GWBD-A2,5,12
-西北西部,时代巴里坤,是,时代巴里坤3,GW99A,3,4
-西北西部,时代巴里坤,是,时代巴里坤4,GW99A,6,9
-华南,时代百色,是,时代百色1,GWBD-A3,5,12
-华南,时代百色,是,时代百色2,GWBD-A3,5,12
-华东南北部,时代射阳,是,时代射阳1,GW130,9,12
-华东南北部,时代射阳,是,时代射阳2,GW130,9,12
-东北,时代松原,是,时代松原1,GWBD-A3,6,12
-东北,时代松原,是,时代松原2,GWBD-A3,6,12
-华东南南部,时代株洲,是,时代株洲1,GW99A,4,12
-华东南南部,时代株洲,是,时代株洲2,GW99A,4,12
-华东南北部,双瑞大丰,是,双瑞大丰1,GW110.5,2,11
-华东南北部,双瑞大丰,是,双瑞大丰2,GW110.5,2,11
-华东南北部,双瑞大丰,是,双瑞大丰3,GW93,1,1
-华东南北部,双瑞东营,否,双瑞东营1,GWBD-A2,10,12
-华东南北部,双瑞东营,否,双瑞东营2,GWBD-A2,10,12
-华东南北部,双瑞东营,否,双瑞东营3,GWBD-A2,10,12
-华东南北部,双瑞东营,否,双瑞东营4,GWBD-A2,10,12
-华东南北部,天顺濮阳,否,天顺濮阳1,GW99A,8,12
-华东南北部,天顺濮阳,否,天顺濮阳2,GW99A,8,12
-华东南北部,天顺沙洋,否,天顺沙洋1,GW93,2,2
-华东南北部,天顺沙洋,是,天顺沙洋2,GW93,5,5
-华东南北部,天顺沙洋,否,天顺沙洋3,GW93,11,11
-华东南北部,天顺沙洋,否,天顺沙洋4,GW99,10,11
-华东南北部,天顺沙洋,否,天顺沙洋5,GW99A,5,12
-华东南北部,天顺沙洋,否,天顺沙洋6,GW99A,5,12
-东北,中材白城,否,中材白城1,GWBD-A3,8,8
-华东南北部,中材阜宁,是,中材阜宁1,GW110.5,4,11
-华东南北部,中材阜宁,是,中材阜宁2,GW110.5,4,11
-华东南北部,中材阜宁,是,中材阜宁3,GW110.5,4,11
-华东南北部,中材阜宁,是,中材阜宁4,GW83.4,1,11
-华东南北部,中材阜宁,否,中材阜宁5,GW93,6,8
-华东南北部,中材阜宁,否,中材阜宁6,GW99A,1,7
-华东南北部,中材阜宁,否,中材阜宁7,GW99A,1,7
-华东南北部,中材阜宁,否,中材阜宁8,SI90.2,1,12
-华东南北部,中材阜宁,否,中材阜宁9,SI90.2,1,12
-华东南北部,中材阜宁,是,中材阜宁10,SI90.2,3,12
-华东南北部,中材阜宁,是,中材阜宁11,SI90.2,3,12
-华东南北部,中材阜宁,是,中材阜宁12,SI90.2,3,12
-华东南北部,中材阜宁,是,中材阜宁13,SI90.2,3,12
-西北西部,中材哈密,否,中材哈密1,GWBD-A3,7,11
-西北西部,中材哈密,否,中材哈密2,GWBD-A3,7,11
-华北,中材邯郸,否,中材邯郸1,GW99A,1,12
-华北,中材邯郸,否,中材邯郸2,GW99A,1,12
-华北,中材邯郸,是,中材邯郸3,GWBD-A2,4,12
-华北,中材邯郸,是,中材邯郸4,GWBD-A2,4,12
-西北东部,中材酒泉,否,中材酒泉1,GW99,1,12
-西北东部,中材酒泉,否,中材酒泉2,GW99,1,12
-西北东部,中材酒泉,否,中材酒泉3,GWBD-A2,2,12
-西北东部,中材酒泉,否,中材酒泉4,GWBD-A2,2,12
-西北东部,中材酒泉,否,中材酒泉5,GWBD-A2,2,12
-西北东部,中材酒泉,是,中材酒泉6,GWBD-A2,2,12
-西北东部,中材酒泉,否,中材酒泉7,SI90.2,1,1
-西北东部,中材酒泉,否,中材酒泉8,SI90.2,3,4
-西北东部,中材酒泉,否,中材酒泉9,SI90.2,3,4
-西北东部,中材酒泉,否,中材酒泉10,SI90.2,9,9
-西北东部,中材酒泉,是,中材酒泉11,SI90.2,4,12
-西北东部,中材酒泉,是,中材酒泉12,SI90.2,4,12
-华东南北部,中材连云港,是,中材连云港1,GW93,4,4
-华东南北部,中材连云港,否,中材连云港2,GW93,1,12
-华东南北部,中材连云港,否,中材连云港3,GW93,1,12
-华东南南部,中材萍乡,否,中材萍乡1,GW83.4,2,3
-华东南南部,中材萍乡,是,中材萍乡2,GW93,1,10
-华东南南部,中材萍乡,是,中材萍乡3,GW93,1,10
-华东南南部,中材萍乡,是,中材萍乡4,GWBD-A3,2,12
-华东南南部,中材萍乡,是,中材萍乡5,GWBD-A3,2,12
-东北,中材锡林,否,中材锡林1,GW99,1,12
-东北,中材锡林,否,中材锡林2,GW99,1,12
-东北,中材锡林,是,中材锡林3,GWBD-A2,2,12
-东北,中材锡林,是,中材锡林4,GWBD-A2,2,12
-东北,中材锡林,是,中材锡林5,GWBD-A2,2,12
-东北,中材锡林,否,中材锡林6,SI90.2,1,1
-东北,中材锡林,否,中材锡林7,SI90.2,1,1
-东北,中材兴安盟,是,中材兴安盟1,GW93,1,9
-东北,中材兴安盟,是,中材兴安盟2,GW93,1,9
-华南,中材阳江,是,中材阳江1,GW130,11,12
-华南,中材阳江,是,中材阳江2,GW130,11,12
-华南,中材阳江,否,中材阳江3,SI122,1,12
-华南,中材阳江,否,中材阳江4,SI122,1,12
-西北西部,中材伊吾,否,中材伊吾1,GWBD-A2,3,12
-西北西部,中材伊吾,否,中材伊吾2,GWBD-A2,3,12
-西北西部,中材伊吾,是,中材伊吾3,GWBD-A3,7,9
-华南,中材玉溪,否,中材玉溪1,GW93,3,3
-西北西部,重通昌吉,否,重通昌吉1,GW99,11,11
-西北西部,重通昌吉,是,重通昌吉2,GW99A,2,10
-西北西部,重通昌吉,否,重通昌吉3,GWBD-A2,1,12
-西北西部,重通昌吉,否,重通昌吉4,GWBD-A2,1,12
-西北西部,重通昌吉,否,重通昌吉5,GWBD-A2,1,12
-东北,重通大安,是,重通大安1,GWBD-A2,3,12
-东北,重通大安,是,重通大安2,GWBD-A2,4,12
-华东南北部,重通如东,是,重通如东1,GW110.5,6,10
-华东南北部,重通如东,是,重通如东2,GW110.5,6,10
-华东南北部,重通如东,否,重通如东3,GW76,1,6
-华东南北部,重通如东,否,重通如东4,GW76,1,6
-华东南北部,重通如东,否,重通如东5,GW76,11,12
-华东南北部,重通如东,否,重通如东6,GW76,11,12
-华东南北部,重通如东,否,重通如东7,GW81,1,12
-华东南北部,重通如东,否,重通如东8,GW81,1,12
-华东南北部,重通如东,否,重通如东9,GW86,10,12
-华东南北部,重通如东,否,重通如东10,GWBD-D,10,10
-华东南北部,重通如东,是,重通如东11,GW83.3,7,9
-西北东部,重通武威,否,重通武威1,GW83.4,1,1
-西北东部,重通武威,否,重通武威2,GW99A,1,1
-西北东部,重通武威,否,重通武威3,GWBD-A2,1,12
-西北东部,重通武威,否,重通武威4,GWBD-A2,1,12
-西北东部,重通武威,否,重通武威5,GWBD-A3,4,12
-西北东部,重通武威,否,重通武威6,GWBD-A3,4,12
+区域名,工厂名,是否新工厂,产线ID,生产型号,开始月份,结束月份,磨合系数,系数最小值,系数最大值
+西北东部,艾郎玉门,是,艾郎玉门1,GWBD-A2,1,12,1.07380061238005,0.5,3
+西北东部,艾郎玉门,是,艾郎玉门2,GWBD-A2,1,12,1.3086756673917384,0.5,3
+华北,艾郎张北,是,艾郎张北1,GWBD-A2,1,12,1.0005776141701213,0.5,3
+华北,艾郎张北,是,艾郎张北2,GWBD-A2,1,12,1.2558624416001731,0.5,3
+西北西部,时代巴里坤,是,时代巴里坤1,GWBD-A2,2,12,2.877701634836078,0.5,3
+西北西部,时代巴里坤,是,时代巴里坤2,GWBD-A2,2,12,2.148476381702223,0.5,3
+西北西部,时代巴里坤,是,时代巴里坤3,GW99A,1,4,2.8216375801071467,0.5,3
+西北西部,时代巴里坤,是,时代巴里坤4,GW99A,1,9,3.0,0.5,3
+华南,时代百色,是,时代百色1,GWBD-A3,2,12,1.2209565088767191,0.5,3
+华南,时代百色,是,时代百色2,GWBD-A3,2,12,2.13505523373714,0.5,3
+华东南北部,时代射阳,是,时代射阳1,GW130,6,12,2.977100640862942,0.5,3
+华东南北部,时代射阳,是,时代射阳2,GW130,8,12,1.4108697454394656,0.5,3
+东北,时代松原,是,时代松原1,GWBD-A3,4,12,1.085052120762868,0.5,3
+东北,时代松原,是,时代松原2,GWBD-A3,4,12,1.4804124608992453,0.5,3
+华东南南部,时代株洲,是,时代株洲1,GW99A,2,12,0.8320501509514534,0.5,3
+华东南南部,时代株洲,是,时代株洲2,GW99A,2,12,1.4984461065581405,0.5,3
+华东南北部,双瑞大丰,是,双瑞大丰1,GW110.5,2,11,0.6454103640653669,0.5,3
+华东南北部,双瑞大丰,是,双瑞大丰2,GW110.5,2,11,0.6530684517974175,0.5,3
+华东南北部,双瑞大丰,否,双瑞大丰3,GW93,1,1,2.085029344273428,0.5,3
+华东南北部,双瑞东营,是,双瑞东营1,GWBD-A2,6,12,2.925213291566798,0.5,3
+华东南北部,双瑞东营,是,双瑞东营2,GWBD-A2,6,12,2.975043017037072,0.5,3
+华东南北部,双瑞东营,是,双瑞东营3,GWBD-A2,7,12,2.9397351966791594,0.5,3
+华东南北部,双瑞东营,是,双瑞东营4,GWBD-A2,7,12,2.616967714504933,0.5,3
+华东南北部,天顺濮阳,否,天顺濮阳1,GW99A,8,12,2.790744177175357,0.5,3
+华东南北部,天顺濮阳,否,天顺濮阳2,GW99A,8,12,0.6411549575195108,0.5,3
+华东南北部,天顺沙洋,否,天顺沙洋1,GW93,2,2,0.8340035880432236,0.5,3
+华东南北部,天顺沙洋,是,天顺沙洋2,GW93,5,5,1.1301574312833809,0.5,3
+华东南北部,天顺沙洋,否,天顺沙洋3,GW93,11,11,2.025384406078239,0.5,3
+华东南北部,天顺沙洋,否,天顺沙洋4,GW99,10,11,1.0429815540113208,0.5,3
+华东南北部,天顺沙洋,否,天顺沙洋5,GW99A,5,12,1.123628778712014,0.5,3
+华东南北部,天顺沙洋,否,天顺沙洋6,GW99A,5,12,0.979164298651741,0.5,3
+东北,中材白城,否,中材白城1,GWBD-A3,8,8,1.763581199916676,0.5,3
+华东南北部,中材阜宁,否,中材阜宁1,GW110.5,1,11,2.959144662478874,0.5,3
+华东南北部,中材阜宁,否,中材阜宁2,GW110.5,1,11,2.92540109166913,0.5,3
+华东南北部,中材阜宁,否,中材阜宁3,GW110.5,1,11,1.1010708194893164,0.5,3
+华东南北部,中材阜宁,否,中材阜宁4,GW83.4,1,11,2.694547075119285,0.5,3
+华东南北部,中材阜宁,否,中材阜宁5,GW93,6,8,2.3745893939183,0.5,3
+华东南北部,中材阜宁,否,中材阜宁6,GW99A,1,7,1.8223796976955784,0.5,3
+华东南北部,中材阜宁,否,中材阜宁7,GW99A,1,7,2.468575784243612,0.5,3
+华东南北部,中材阜宁,否,中材阜宁8,SI90.2,1,12,0.7272902159645727,0.5,3
+华东南北部,中材阜宁,否,中材阜宁9,SI90.2,1,12,2.181467973934617,0.5,3
+华东南北部,中材阜宁,是,中材阜宁10,SI90.2,1,12,1.5244257562540415,0.5,3
+华东南北部,中材阜宁,是,中材阜宁11,SI90.2,1,12,1.4259873327753854,0.5,3
+华东南北部,中材阜宁,是,中材阜宁12,SI90.2,2,12,1.253548054276315,0.5,3
+华东南北部,中材阜宁,是,中材阜宁13,SI90.2,2,12,0.6644941460935946,0.5,3
+西北西部,中材哈密,否,中材哈密1,GWBD-A3,7,11,2.3686587068604954,0.5,3
+西北西部,中材哈密,否,中材哈密2,GWBD-A3,7,11,1.1015355190681149,0.5,3
+华北,中材邯郸,否,中材邯郸1,GW99A,1,12,1.925686336774216,0.5,3
+华北,中材邯郸,否,中材邯郸2,GW99A,1,12,1.166441845882635,0.5,3
+华北,中材邯郸,是,中材邯郸3,GWBD-A2,2,12,2.1539372175131355,0.5,3
+华北,中材邯郸,是,中材邯郸4,GWBD-A2,3,12,0.6366978576009893,0.5,3
+西北东部,中材酒泉,否,中材酒泉1,GW99,1,12,1.1568681400683591,0.5,3
+西北东部,中材酒泉,否,中材酒泉2,GW99,1,12,1.1064271136987875,0.5,3
+西北东部,中材酒泉,否,中材酒泉3,GWBD-A2,1,12,0.9954163068389692,0.5,3
+西北东部,中材酒泉,是,中材酒泉4,GWBD-A2,1,12,1.2193407437521984,0.5,3
+西北东部,中材酒泉,是,中材酒泉5,GWBD-A2,2,12,0.959238907870878,0.5,3
+西北东部,中材酒泉,是,中材酒泉6,GWBD-A2,3,12,1.218588133158403,0.5,3
+西北东部,中材酒泉,否,中材酒泉7,SI90.2,1,1,1.2323208798346863,0.5,3
+西北东部,中材酒泉,否,中材酒泉8,SI90.2,1,4,1.1083005779929354,0.5,3
+西北东部,中材酒泉,否,中材酒泉9,SI90.2,3,4,1.0979168774354644,0.5,3
+西北东部,中材酒泉,否,中材酒泉10,SI90.2,9,9,0.6134714785903335,0.5,3
+西北东部,中材酒泉,否,中材酒泉11,SI90.2,4,12,0.9060377208252096,0.5,3
+西北东部,中材酒泉,否,中材酒泉12,SI90.2,4,12,0.8588420476065148,0.5,3
+华东南北部,中材连云港,否,中材连云港1,GW93,1,4,0.6959224018718012,0.5,3
+华东南北部,中材连云港,否,中材连云港2,GW93,1,12,2.388840113565708,0.5,3
+华东南北部,中材连云港,否,中材连云港3,GW93,1,12,2.023924901276327,0.5,3
+华东南南部,中材萍乡,否,中材萍乡1,GW83.4,1,3,2.7904582895129884,0.5,3
+华东南南部,中材萍乡,否,中材萍乡2,GW93,1,10,1.6925578180285972,0.5,3
+华东南南部,中材萍乡,否,中材萍乡3,GW93,1,10,0.8982597799795793,0.5,3
+华东南南部,中材萍乡,否,中材萍乡4,GWBD-A3,1,12,1.3711168227538089,0.5,3
+华东南南部,中材萍乡,否,中材萍乡5,GWBD-A3,1,12,1.219691503974376,0.5,3
+东北,中材锡林,否,中材锡林1,GW99,1,12,2.9557253831441828,0.5,3
+东北,中材锡林,否,中材锡林2,GW99,1,12,2.462362813243516,0.5,3
+东北,中材锡林,是,中材锡林3,GWBD-A2,1,12,0.5982166642652442,0.5,3
+东北,中材锡林,是,中材锡林4,GWBD-A2,1,12,2.644080826558284,0.5,3
+东北,中材锡林,是,中材锡林5,GWBD-A2,2,12,0.5145312169222124,0.5,3
+东北,中材锡林,否,中材锡林6,SI90.2,1,1,0.9769481674143102,0.5,3
+东北,中材锡林,否,中材锡林7,SI90.2,1,1,1.238170985113167,0.5,3
+东北,中材兴安盟,否,中材兴安盟1,GW93,1,9,1.0683346058426026,0.5,3
+东北,中材兴安盟,否,中材兴安盟2,GW93,1,9,0.942117080768859,0.5,3
+华南,中材阳江,是,中材阳江1,GW130,1,12,1.633431132348781,0.5,3
+华南,中材阳江,是,中材阳江2,GW130,11,12,1.081038974714554,0.5,3
+华南,中材阳江,否,中材阳江3,SI122,1,12,2.975783026146584,0.5,3
+华南,中材阳江,否,中材阳江4,SI122,1,12,1.6018405358345469,0.5,3
+西北西部,中材伊吾,否,中材伊吾1,GWBD-A2,1,12,2.1810444878994515,0.5,3
+西北西部,中材伊吾,否,中材伊吾2,GWBD-A2,1,12,1.613919507763036,0.5,3
+西北西部,中材伊吾,是,中材伊吾3,GWBD-A3,7,9,0.5,0.5,3
+华南,中材玉溪,否,中材玉溪1,GW93,3,3,1.890269922258364,0.5,3
+西北西部,重通昌吉,否,重通昌吉1,GW99,11,11,0.5574628792523443,0.5,3
+西北西部,重通昌吉,是,重通昌吉2,GW99A,1,10,2.1349045617509983,0.5,3
+西北西部,重通昌吉,否,重通昌吉3,GWBD-A2,1,12,2.3607990485978285,0.5,3
+西北西部,重通昌吉,否,重通昌吉4,GWBD-A2,1,12,0.5733216621135748,0.5,3
+西北西部,重通昌吉,是,重通昌吉5,GWBD-A2,1,12,1.6300547095229956,0.5,3
+东北,重通大安,是,重通大安1,GWBD-A2,1,12,2.9190166685770587,0.5,3
+东北,重通大安,是,重通大安2,GWBD-A2,2,12,0.8731389130785212,0.5,3
+华东南北部,重通如东,否,重通如东1,GW110.5,6,10,1.6258348677031254,0.5,3
+华东南北部,重通如东,否,重通如东2,GW110.5,6,10,1.376510869994889,0.5,3
+华东南北部,重通如东,否,重通如东3,GW76,1,6,1.221180288569112,0.5,3
+华东南北部,重通如东,否,重通如东4,GW76,11,12,0.9304707434434764,0.5,3
+华东南北部,重通如东,否,重通如东5,GW76,11,12,1.0654063065239228,0.5,3
+华东南北部,重通如东,否,重通如东6,GW81,1,12,1.1315290493015806,0.5,3
+华东南北部,重通如东,否,重通如东7,GW81,1,12,1.1404930117692385,0.5,3
+华东南北部,重通如东,否,重通如东8,GW81,1,12,1.3014091708393016,0.5,3
+华东南北部,重通如东,是,重通如东9,GW86,10,12,0.5738779043252348,0.5,3
+华东南北部,重通如东,是,重通如东10,GWBD-D,4,10,0.9593048041664796,0.5,3
+华东南北部,重通如东,是,重通如东11,GW83.3,7,9,2.1135988495299616,0.5,3
+西北东部,重通武威,否,重通武威1,GW83.4,1,1,1.0090685780114246,0.5,3
+西北东部,重通武威,否,重通武威2,GW99A,1,1,0.9928464185174258,0.5,3
+西北东部,重通武威,否,重通武威3,GWBD-A2,1,12,0.7701006517043388,0.5,3
+西北东部,重通武威,否,重通武威4,GWBD-A2,1,12,2.1830368275462857,0.5,3
+西北东部,重通武威,是,重通武威5,GWBD-A3,2,12,0.6427854133739357,0.5,3
+西北东部,重通武威,是,重通武威6,GWBD-A3,2,12,0.7212222730295578,0.5,3

data/2025/ProductionLine未修改.csv

@@ -1,106 +0,0 @@
-区域名,工厂名,是否新工厂,产线ID,生产型号,开始月份,结束月份
-西北东部,艾郎玉门,否,艾郎玉门1,GWBD-A2,1,12
-西北东部,艾郎玉门,否,艾郎玉门2,GWBD-A2,1,12
-华北,艾郎张北,否,艾郎张北1,GWBD-A2,1,12
-华北,艾郎张北,否,艾郎张北2,GWBD-A2,1,12
-西北西部,时代巴里坤,是,时代巴里坤1,GWBD-A2,5,12
-西北西部,时代巴里坤,是,时代巴里坤2,GWBD-A2,5,12
-西北西部,时代巴里坤,是,时代巴里坤3,GW99A,3,9
-华南,时代百色,是,时代百色1,GWBD-A3,5,12
-华南,时代百色,是,时代百色2,GWBD-A3,5,12
-华东南北部,时代射阳,是,时代射阳1,GW130,9,12
-华东南北部,时代射阳,是,时代射阳2,GW130,9,12
-东北,时代松原,是,时代松原1,GWBD-A3,5,12
-东北,时代松原,是,时代松原2,GWBD-A3,5,12
-华东南南部,时代株洲,否,时代株洲1,GW99A,4,12
-华东南南部,时代株洲,否,时代株洲2,GW99A,4,12
-华东南北部,双瑞大丰,否,双瑞大丰1,GW110.5,2,11
-华东南北部,双瑞大丰,否,双瑞大丰2,GW110.5,2,11
-华东南北部,双瑞大丰,否,双瑞大丰3,GW93,1,1
-华东南北部,双瑞东营,是,双瑞东营1,GWBD-A2,9,12
-华东南北部,双瑞东营,是,双瑞东营2,GWBD-A2,9,12
-华东南北部,双瑞东营,是,双瑞东营3,GWBD-A2,9,12
-华东南北部,双瑞东营,是,双瑞东营4,GWBD-A2,9,12
-华东南北部,天顺濮阳,是,天顺濮阳1,GW99A,8,12
-华东南北部,天顺濮阳,是,天顺濮阳2,GW99A,8,12
-华东南北部,天顺沙洋,否,天顺沙洋1,GW93,2,11
-华东南北部,天顺沙洋,否,天顺沙洋2,GW99,10,11
-华东南北部,天顺沙洋,是,天顺沙洋3,GW99A,5,12
-华东南北部,天顺沙洋,是,天顺沙洋4,GW99A,5,12
-东北,中材白城,是,中材白城1,GWBD-A3,8,8
-华东南北部,中材阜宁,否,中材阜宁1,GW110.5,4,12
-华东南北部,中材阜宁,是,中材阜宁2,GW110.5,4,12
-华东南北部,中材阜宁,是,中材阜宁3,GW110.5,4,12
-华东南北部,中材阜宁,否,中材阜宁4,GW83.4,1,11
-华东南北部,中材阜宁,否,中材阜宁5,GW93,1,8
-华东南北部,中材阜宁,否,中材阜宁6,GW99A,1,7
-华东南北部,中材阜宁,否,中材阜宁7,GW99A,1,7
-华东南北部,中材阜宁,否,中材阜宁8,SI90.2,1,12
-华东南北部,中材阜宁,否,中材阜宁9,SI90.2,1,12
-华东南北部,中材阜宁,否,中材阜宁10,SI90.2,1,12
-华东南北部,中材阜宁,否,中材阜宁11,SI90.2,1,12
-华东南北部,中材阜宁,是,中材阜宁12,SI90.2,3,12
-华东南北部,中材阜宁,是,中材阜宁13,SI90.2,3,12
-西北西部,中材哈密,是,中材哈密1,GWBD-A3,7,12
-西北西部,中材哈密,是,中材哈密2,GWBD-A3,7,12
-华北,中材邯郸,否,中材邯郸1,GW99A,1,12
-华北,中材邯郸,否,中材邯郸2,GW99A,1,12
-华北,中材邯郸,是,中材邯郸3,GWBD-A2,4,12
-华北,中材邯郸,是,中材邯郸4,GWBD-A2,4,12
-西北东部,中材酒泉,否,中材酒泉1,GW99,1,12
-西北东部,中材酒泉,否,中材酒泉2,GW99,1,12
-西北东部,中材酒泉,否,中材酒泉3,GWBD-A2,1,12
-西北东部,中材酒泉,否,中材酒泉4,GWBD-A2,1,12
-西北东部,中材酒泉,否,中材酒泉5,GWBD-A2,1,12
-西北东部,中材酒泉,是,中材酒泉6,GWBD-A2,2,12
-西北东部,中材酒泉,否,中材酒泉7,SI90.2,1,12
-西北东部,中材酒泉,否,中材酒泉8,SI90.2,1,12
-西北东部,中材酒泉,否,中材酒泉9,SI90.2,4,12
-西北东部,中材酒泉,否,中材酒泉10,SI90.2,4,12
-华东南北部,中材连云港,否,中材连云港1,GW93,4,4
-华东南北部,中材连云港,否,中材连云港2,GW93,1,12
-华东南北部,中材连云港,否,中材连云港3,GW93,1,12
-华东南南部,中材萍乡,否,中材萍乡1,GW83.4,2,6
-华东南南部,中材萍乡,否,中材萍乡2,GW93,1,10
-华东南南部,中材萍乡,否,中材萍乡3,GW93,1,10
-华东南南部,中材萍乡,否,中材萍乡4,GWBD-A3,2,12
-华东南南部,中材萍乡,否,中材萍乡5,GWBD-A3,2,12
-东北,中材锡林,否,中材锡林1,GW99,1,12
-东北,中材锡林,否,中材锡林2,GW99,1,12
-东北,中材锡林,否,中材锡林3,GWBD-A2,1,12
-东北,中材锡林,否,中材锡林4,GWBD-A2,1,12
-东北,中材锡林,是,中材锡林5,GWBD-A2,4,12
-东北,中材锡林,否,中材锡林6,SI90.2,1,1
-东北,中材锡林,否,中材锡林7,SI90.2,1,1
-东北,中材兴安盟,否,中材兴安盟1,GW93,1,9
-东北,中材兴安盟,否,中材兴安盟2,GW93,1,9
-华南,中材阳江,是,中材阳江1,GW130,11,12
-华南,中材阳江,是,中材阳江2,GW130,11,12
-华南,中材阳江,否,中材阳江3,SI122,1,12
-华南,中材阳江,否,中材阳江4,SI122,1,12
-西北西部,中材伊吾,否,中材伊吾1,GWBD-A2,3,12
-西北西部,中材伊吾,否,中材伊吾2,GWBD-A2,3,12
-西北西部,中材伊吾,是,中材伊吾3,GWBD-A3,7,9
-华南,中材玉溪,否,中复玉溪1,GW93,3,3
-西北西部,重通昌吉,否,重通昌吉1,GW99,11,11
-西北西部,重通昌吉,否,重通昌吉2,GW99A,2,10
-西北西部,重通昌吉,否,重通昌吉3,GWBD-A2,1,12
-西北西部,重通昌吉,否,重通昌吉4,GWBD-A2,1,12
-西北西部,重通昌吉,是,重通昌吉5,GWBD-A2,11,12
-东北,重通大安,是,重通大安1,GWBD-A2,3,12
-东北,重通大安,是,重通大安2,GWBD-A2,4,12
-华东南北部,重通如东,是,重通如东1,GW110.5,6,10
-华东南北部,重通如东,是,重通如东2,GW110.5,6,10
-华东南北部,重通如东,否,重通如东3,GW76,1,12
-华东南北部,重通如东,否,重通如东4,GW76,1,12
-华东南北部,重通如东,否,重通如东5,GW81,1,12
-华东南北部,重通如东,否,重通如东6,GW81,1,12
-华东南北部,重通如东,否,重通如东7,GW86,3,12
-华东南北部,重通如东,是,重通如东8,GWBD-D,6,11
-华东南北部,重通如东,否,重通如东9,GW83.3,7,9
-西北东部,重通武威,否,重通武威1,GW83.4,1,1
-西北东部,重通武威,否,重通武威2,GW99A,1,1
-西北东部,重通武威,否,重通武威3,GWBD-A2,1,12
-西北东部,重通武威,否,重通武威4,GWBD-A2,1,12
-西北东部,重通武威,否,重通武威5,GWBD-A3,4,12
-西北东部,重通武威,否,重通武威6,GWBD-A3,4,12

data/2025/benchmark未修改.csv

@@ -1,28 +0,0 @@
-工厂,1月,2月,3月,4月,5月,6月,7月,8月,9月,10月,11月,12月,全年
-艾郎玉门,2,6,12,13,12,12,9,14,12,12,12,12,128
-艾郎张北,3,6,12,14,12,12,12,12,12,12,12,12,131
-时代巴里坤,0,0,7,2,2,9,6,16,14,13,12,12,93
-时代百色,0,0,0,0,5,9,12,8,15,13,12,12,86
-时代射阳,0,0,0,0,0,0,0,0,1,0,6,6,13
-时代松原,0,0,0,0,0,6,5,10,15,16,12,12,76
-时代株洲,0,0,0,7,9,14,14,14,14,14,14,14,114
-双瑞大丰,1,2,11,6,7,10,8,10,10,10,6,0,81
-双瑞东营,0,0,0,0,0,0,0,0,3,15,14,14,46
-天顺濮阳,2,0,0,0,0,0,0,12,11,9,10,11,55
-天顺沙洋,1,4,0,0,9,13,13,13,13,17,19,11,113
-中材白城,0,0,0,0,0,0,0,3,0,0,0,0,3
-中材阜宁,34,18,31,50,42,45,52,48,46,43,49,31,489
-中材哈密,0,0,0,0,0,0,8,9,9,6,7,0,39
-中材邯郸,12,6,3,17,18,27,18,21,23,19,20,14,198
-中材酒泉,11,20,52,56,43,45,50,53,59,52,52,40,533
-中材连云港,6,9,13,16,13,12,5,5,5,0,0,7,91
-中材萍乡,2,17,21,19,24,27,29,28,17,13,14,5,216
-中材锡林,28,6,17,25,36,32,27,36,27,30,32,21,317
-中材兴安盟,2,8,10,18,14,18,12,11,14,0,0,0,107
-中材阳江,4,1,5,5,5,5,5,5,5,5,7,7,59
-中材伊吾,0,0,10,14,5,4,8,16,16,8,15,10,106
-中材玉溪,0,0,3,0,0,0,0,0,0,0,0,0,3
-重通昌吉,13,9,19,21,22,23,23,28,27,18,23,19,245
-重通大安,0,0,2,9,6,12,11,10,11,11,13,12,97
-重通如东,24,7,24,19,23,26,27,24,30,33,34,35,306
-重通武威,22,7,14,27,31,29,29,28,30,28,29,29,303

data/2025/factory_data.csv

@@ -0,0 +1,28 @@
+工厂中文名,工厂英文名,工厂平均磨合系数,最小误差
+艾郎玉门,AilangYumen,1.1912381398858942,0.0383592943400758
+艾郎张北,AilangZhangbei,1.1282200278851473,0.0383834069943968
+时代巴里坤,ShidaiBalikun,2.711953899161362,0.0372831200518159
+时代百色,ShidaiBaise,1.6780058713069297,0.0383834069943968
+时代射阳,ShidaiSheyang,2.193985193151204,0.0381459900903132
+时代松原,ShidaiSongyuan,1.2827322908310568,0.0352284680862539
+时代株洲,ShidaiZhuzhou,1.1652481287547969,0.0351743203712874
+双瑞大丰,ShuangruiDafeng,1.1278360533787375,0.0345299766068848
+双瑞东营,ShuangruiDongying,2.8642398049469904,0.0345680805544538
+天顺濮阳,TianshunPuyang,1.715949567347434,0.0345299766068848
+天顺沙洋,TianshunShayang,1.1892200094633198,0.0350377531255757
+中材白城,ZhongcaiBaicheng,1.763581199916676,0.0352284680862539
+中材阜宁,ZhongcaiFuning,1.855609384916356,0.0344731713353556
+中材哈密,ZhongcaiHami,1.7350971129643051,0.0344731713353556
+中材邯郸,ZhongcaiHandan,1.4706908144427435,0.03437964346405
+中材酒泉,ZhongcaiJiuquan,1.0393974106393948,0.0335524068644557
+中材连云港,ZhongcaiLianyungang,1.7028958055712788,0.034108309859383
+中材萍乡,ZhongcaiPingxiang,1.59441684284987,0.0334380950217488
+中材锡林,ZhongcaiXilin,1.6271480080944165,0.0313354095754113
+中材兴安盟,ZhongcaiXinganmeng,1.0052258433057308,0.0334092499773274
+中材阳江,ZhongcaiYangjiang,1.8230234172611164,0.0302713991840371
+中材伊吾,ZhongcaiYiwu,1.4316546652208293,0.0332345469724357
+中材玉溪,ZhongcaiYuxi,1.890269922258364,0.0302713991840371
+重通昌吉,ChongtongChangji,1.4513085722475485,0.0303973755004896
+重通大安,ChongtongDaan,1.89607779082779,0.0301428254177608
+重通如东,ChongtongRudong,1.2217832605605747,0.0383834069943968
+重通武威,ChongtongWuwei,1.0531766936971614,0.028380612159397973

data/2025/factory_data_bak.csv

@@ -0,0 +1,28 @@
+工厂中文名,工厂英文名,工厂磨合系数,最小误差
+艾郎玉门,AilangYumen,1.120967033,0.0596663792039552
+艾郎张北,AilangZhangbei,1.08697518,0.0833197284386998
+时代巴里坤,ShidaiBalikun,1.0187437400861858,0.0842943873080955
+时代百色,ShidaiBaise,0.9004477644319165,0.0596663792039552
+时代射阳,ShidaiSheyang,0.8752331051886796,0.060527705646677
+时代松原,ShidaiSongyuan,0.8553030538583956,0.0833197284386998
+时代株洲,ShidaiZhuzhou,0.8,0.0464062054499543
+双瑞大丰,ShuangruiDafeng,0.8017981082680407,0.0464062054499543
+双瑞东营,ShuangruiDongying,1.4195340001397942,0.0454229212808294
+天顺濮阳,TianshunPuyang,1.11666927,0.0454229212808294
+天顺沙洋,TianshunShayang,1.038912690288306,0.0454229212808294
+中材白城,ZhongcaiBaicheng,1.6168654948182766,0.0454229212808294
+中材阜宁,ZhongcaiFuning,1.1496044423912932,0.0409542399205325
+中材哈密,ZhongcaiHami,1.5404408015710631,0.0406113043924118
+中材邯郸,ZhongcaiHandan,1.1753569549522398,0.0386749691227432
+中材酒泉,ZhongcaiJiuquan,0.979817498,10000.0
+中材连云港,ZhongcaiLianyungang,1.5319296291566933,0.039797303578411
+中材萍乡,ZhongcaiPingxiang,1.11513483685553,0.0406113043924118
+中材锡林,ZhongcaiXilin,1.029797177,0.0386749691227432
+中材兴安盟,ZhongcaiXinganmeng,0.9871605854669068,0.0379826880566304
+中材阳江,ZhongcaiYangjiang,1.2807141141229423,0.0198011028048272
+中材伊吾,ZhongcaiYiwu,1.241739515,0.0198011028048272
+中材玉溪,ZhongcaiYuxi,1.705602538488603,0.0198011028048272
+重通昌吉,ChongtongChangji,1.07645347634814,0.0373780017376583
+重通大安,ChongtongDaan,0.9935803675177745,0.0186556274325477
+重通如东,ChongtongRudong,0.9317437521783424,0.0149035093013446
+重通武威,ChongtongWuwei,0.8658294473858272,0.014659040410011074

data/2025/model_params.json

@@ -1,6 +1,6 @@
 {
-  "holiday_days_1": 5,
-  "holiday_days_2": 12,
+  "holiday_days_1": 10,
+  "holiday_days_2": 6,
   "holiday_days_3": 2,
   "holiday_days_4": 2,
   "holiday_days_5": 2,
@@ -11,37 +11,6 @@
   "holiday_days_10": 7,
   "holiday_days_11": 2,
   "holiday_days_12": 2,
-  "month1": 235.2024236560018,
-  "month2": 80.13430957369465,
-  "month3": 40.81815120444523,
-  "month4": 35.573307322844045,
-  "factor_AilangYumen": 1.1209670325377996,
-  "factor_AilangZhangbei": 1.0869751796074336,
-  "factor_ShidaiBalikun": 1.064344356385733,
-  "factor_ShidaiBaise": 0.925644739081089,
-  "factor_ShidaiSheyang": 2.2354053357800834,
-  "factor_ShidaiSongyuan": 0.8850280359740502,
-  "factor_ShidaiZhuzhou": 0.8,
-  "factor_ShuangruiDafeng": 1.3485391587995974,
-  "factor_ShuangruiDongying": 1.4720254802974653,
-  "factor_TianshunPuyang": 1.1166692701637255,
-  "factor_TianshunShayang": 1.060367420503057,
-  "factor_ZhongcaiBaicheng": 1.8461095046937892,
-  "factor_ZhongcaiFuning": 1.3124938381864457,
-  "factor_ZhongcaiHami": 1.4843503931169255,
-  "factor_ZhongcaiHandan": 1.210604184057787,
-  "factor_ZhongcaiJiuquan": 0.9798174978126551,
-  "factor_ZhongcaiLianyungang": 1.6036280376162886,
-  "factor_ZhongcaiPingxiang": 1.132040522281658,
-  "factor_ZhongcaiXilin": 1.0297971770720127,
-  "factor_ZhongcaiXinganmeng": 0.9769716839603864,
-  "factor_ZhongcaiYangjiang": 2.386768108574698,
-  "factor_ZhongcaiYiwu": 1.2417395146436796,
-  "factor_ZhongcaiYuxi": 1.7093165019081604,
-  "factor_ChongtongChangji": 1.0895870479908367,
-  "factor_ChongtongDaan": 1.0187316107483142,
-  "factor_ChongtongRudong": 1.0270541553649646,
-  "factor_ChongtongWuwei": 0.8811374580269447,
   "product_set": [
     "GWBD-A2",
     "GWBD-A3",

ga_calibration_all_factories.py

@@ -0,0 +1,75 @@
+import argparse
+import json
+import subprocess
+import sys
+from concurrent.futures import ProcessPoolExecutor, as_completed
+from pathlib import Path
+
+import pandas as pd
+
+
+def load_factory_codes(year: int) -> list[str]:
+    csv_path = Path("data") / str(year) / "factory_data.csv"
+    encodings = ("utf-8", "utf-8-sig", "gbk")
+    last_error = None
+    df = None
+    for enc in encodings:
+        try:
+            df = pd.read_csv(csv_path, encoding=enc)
+            break
+        except UnicodeDecodeError as exc:
+            last_error = exc
+            continue
+    if df is None:
+        raise last_error if last_error else FileNotFoundError(f"Missing {csv_path}")
+    col_map = {c.strip(): c for c in df.columns}
+    if "工厂英文名" not in col_map:
+        raise ValueError(f"{csv_path} 缺少字段: 工厂英文名")
+    return df[col_map["工厂英文名"]].astype(str).str.strip().tolist()
+
+
+def run_single(factory_code: str, python_exe: str, script_path: Path) -> tuple[str, int, str]:
+    cmd = [python_exe, str(script_path), "--factory", factory_code]
+    result = subprocess.run(cmd, capture_output=True, text=True)
+    output = (result.stdout or "") + (result.stderr or "")
+    return factory_code, result.returncode, output
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Parallel GA calibration for all factories.")
+    parser.add_argument("--max-workers", type=int, default=6, help="并行进程数上限（默认 6）")
+    args = parser.parse_args()
+
+    year = json.load(open("year.json", "r", encoding="utf-8"))["year"]
+    codes = load_factory_codes(year)
+    script_path = Path("ga_calibration_by_one_factory.py")
+    if not script_path.exists():
+        raise FileNotFoundError(f"找不到 {script_path}")
+
+    python_exe = sys.executable
+    results = []
+    with ProcessPoolExecutor(max_workers=args.max_workers) as executor:
+        future_map = {
+            executor.submit(run_single, code, python_exe, script_path): code for code in codes
+        }
+        for future in as_completed(future_map):
+            code = future_map[future]
+            try:
+                factory, rc, out = future.result()
+            except Exception as exc:
+                results.append((code, 1, f"Exception: {exc}"))
+                continue
+            results.append((factory, rc, out))
+            status = "OK" if rc == 0 else f"FAIL({rc})"
+            print(f"[{status}] {factory}")
+
+    print("\n详细输出：")
+    for factory, rc, out in results:
+        status = "OK" if rc == 0 else f"FAIL({rc})"
+        print(f"--- {factory} [{status}] ---")
+        print(out.strip())
+        print("---------------")
+
+
+if __name__ == "__main__":
+    main()

ga_calibration_by_one_factory.py

@@ -0,0 +1,280 @@
+import argparse
+import json
+import random
+from pathlib import Path
+from typing import List, Tuple
+
+import pandas as pd
+import time
+import os
+
+from simulation_model import SimulationModel
+
+POP_SIZE = 20
+GENERATIONS = 50
+MUTATION_RATE = 0.2
+MUTATION_STD = 0.05  # for factors
+LOCK_TIMEOUT = 120  # seconds
+STAGNATION_WINDOW = 5  # generations without improvement before injecting LHS samples
+
+
+def clip(val: float, bounds: Tuple[float, float]) -> float:
+    lo, hi = bounds
+    return max(lo, min(hi, val))
+
+
+def load_factory_row(csv_path: Path, factory_code: str) -> tuple[pd.Series, pd.DataFrame, dict]:
+    df, cols, _ = read_csv_with_encoding(csv_path, required={"工厂中文名", "工厂英文名", "工厂平均磨合系数", "最小误差"})
+    row = df.loc[df[cols["工厂英文名"]].astype(str).str.strip() == factory_code]
+    if row.empty:
+        raise ValueError(f"在 {csv_path} 中找不到工厂英文名: {factory_code}")
+    return row.iloc[0], df, cols
+
+
+def _csv_lock_path(csv_path: Path) -> Path:
+    return csv_path.with_suffix(csv_path.suffix + ".lock")
+
+
+def _acquire_lock(lock_path: Path, timeout: float = LOCK_TIMEOUT, interval: float = 0.5):
+    start = time.time()
+    while True:
+        try:
+            fd = os.open(lock_path, os.O_CREAT | os.O_EXCL | os.O_RDWR)
+            os.write(fd, str(os.getpid()).encode())
+            return fd
+        except FileExistsError:
+            if time.time() - start > timeout:
+                raise TimeoutError(f"获取锁超时: {lock_path}")
+            time.sleep(interval)
+
+
+def _release_lock(lock_path: Path, fd: int):
+    try:
+        os.close(fd)
+    finally:
+        if lock_path.exists():
+            try:
+                lock_path.unlink()
+            except Exception:
+                pass
+
+
+def update_factory_csv(csv_path: Path, factory_code: str, new_factor: float, new_error: float) -> None:
+    lock_path = _csv_lock_path(csv_path)
+    fd = _acquire_lock(lock_path)
+    try:
+        df, cols, enc = read_csv_with_encoding(csv_path, required={"工厂中文名", "工厂英文名", "工厂平均磨合系数", "最小误差"})
+        mask = df[cols["工厂英文名"]].astype(str).str.strip() == factory_code
+        if not mask.any():
+            raise ValueError(f"在 {csv_path} 中找不到工厂英文名: {factory_code}")
+        df.loc[mask, cols["工厂平均磨合系数"]] = float(new_factor)
+        df.loc[mask, cols["最小误差"]] = float(new_error)
+        df.to_csv(csv_path, index=False, encoding=enc)
+    finally:
+        _release_lock(lock_path, fd)
+
+
+def update_production_line_csv(csv_path: Path, factory_name_cn: str, line_ids: List[str], best_genes: List[float]) -> None:
+    lock_path = _csv_lock_path(csv_path)
+    fd = _acquire_lock(lock_path)
+    try:
+        df, cols, enc = read_csv_with_encoding(csv_path, required={"工厂名", "产线ID", "磨合系数"})
+        mask = df[cols["工厂名"]].astype(str).str.strip() == factory_name_cn
+        if not mask.any():
+            raise ValueError(f"在 {csv_path} 中找不到工厂名: {factory_name_cn}")
+        line_to_factor = dict(zip(line_ids, best_genes))
+        df.loc[mask, cols["产线ID"]] = df[cols["产线ID"]].astype(str)
+        for idx, row in df[mask].iterrows():
+            lid = str(row[cols["产线ID"]]).strip()
+            if lid in line_to_factor:
+                df.at[idx, cols["磨合系数"]] = float(line_to_factor[lid])
+        df.to_csv(csv_path, index=False, encoding=enc)
+    finally:
+        _release_lock(lock_path, fd)
+
+
+def evaluate(factory_code: str, line_ids: List[str], genes: List[float]) -> float:
+    factory_factors = {}
+    model = SimulationModel(
+        factory_factors=factory_factors,
+        output_enabled=False,
+        is_calibration_mode=True,
+    )
+    # Override per-line factors
+    for lid, val in zip(line_ids, genes):
+        model.line_factor[lid] = float(val)
+    while model.running:
+        model.step()
+    return model.mean_abs_error
+
+
+def mutate(genes: List[float]) -> List[float]:
+    new = genes.copy()
+    for i in range(len(new)):
+        if random.random() < MUTATION_RATE:
+            jitter = random.gauss(0, MUTATION_STD)
+            new[i] = new[i] + jitter
+    return new
+
+
+def crossover(p1: List[float], p2: List[float]) -> Tuple[List[float], List[float]]:
+    if len(p1) == 1:
+        return [p1[0]], [p2[0]]
+    point = random.randint(1, len(p1) - 1)
+    c1 = p1[:point] + p2[point:]
+    c2 = p2[:point] + p1[point:]
+    return c1, c2
+
+
+def init_population(seed_vals: List[float]) -> List[List[float]]:
+    pop = []
+    for idx in range(POP_SIZE):
+        if idx == 0:
+            pop.append([float(v) for v in seed_vals])
+            continue
+        indiv = [float(v) for v in seed_vals]
+        for j in range(len(indiv)):
+            jitter = random.uniform(-0.1, 0.1)
+            indiv[j] = indiv[j] + jitter
+        pop.append(indiv)
+    return pop
+
+
+def read_csv_with_encoding(path: Path, required: set[str]):
+    encodings = ("utf-8", "utf-8-sig", "gbk")
+    last_error = None
+    df = None
+    for enc in encodings:
+        try:
+            df = pd.read_csv(path, encoding=enc)
+            break
+        except UnicodeDecodeError as exc:
+            last_error = exc
+            continue
+    if df is None:
+        raise last_error if last_error else FileNotFoundError(f"Missing {path}")
+    cols = {c.strip(): c for c in df.columns}
+    missing = required - set(cols)
+    if missing:
+        raise ValueError(f"{path} 缺少字段: {', '.join(sorted(missing))}")
+    return df, cols, enc
+
+
+def load_factory_lines(year: int, factory_name_cn: str):
+    path = Path("data") / str(year) / "ProductionLine.csv"
+    df, cols, enc = read_csv_with_encoding(path, required={"工厂名", "产线ID", "磨合系数", "系数最小值", "系数最大值"})
+    mask = df[cols["工厂名"]].astype(str).str.strip() == factory_name_cn
+    if not mask.any():
+        raise ValueError(f"ProductionLine.csv 中未找到工厂 {factory_name_cn}")
+    lines = []
+    for _, row in df[mask].iterrows():
+        line_id = str(row[cols["产线ID"]]).strip()
+        seed = float(row[cols["磨合系数"]])
+        min_b = float(row[cols["系数最小值"]])
+        max_b = float(row[cols["系数最大值"]])
+        lines.append((line_id, seed, min_b, max_b))
+    return lines
+
+
+def apply_bounds(genes: List[float], bounds: List[Tuple[float, float]]) -> List[float]:
+    return [clip(val, b) for val, b in zip(genes, bounds)]
+
+
+def latin_hypercube_samples(n_samples: int, bounds: List[Tuple[float, float]]) -> List[List[float]]:
+    if n_samples <= 0:
+        return []
+    dims = len(bounds)
+    samples = []
+    # Latin hypercube with per-dimension random permutations and jitter inside each stratum
+    strata = [list(range(n_samples)) for _ in range(dims)]
+    for s in strata:
+        random.shuffle(s)
+    for i in range(n_samples):
+        point = []
+        for d in range(dims):
+            lo, hi = bounds[d]
+            # random point inside the i-th stratum of dimension d
+            u = random.random()
+            stratum_idx = strata[d][i]
+            frac = (stratum_idx + u) / n_samples
+            val = lo + frac * (hi - lo)
+            point.append(val)
+        samples.append(point)
+    random.shuffle(samples)
+    return samples
+
+
+def main():
+    parser = argparse.ArgumentParser(description="GA calibration for a single factory factor.")
+    parser.add_argument(
+        "--factory",
+        required=True,
+        help="Factory English code (matches '工厂英文名' in factory_data.csv).",
+    )
+    args = parser.parse_args()
+
+    # set year
+    year = json.load(open("year.json", "r", encoding="utf-8"))["year"]
+    filename = f"{year}"
+    csv_path = Path("data") / filename / "factory_data.csv"
+    line_csv_path = Path("data") / filename / "ProductionLine.csv"
+
+    factory_row, factory_df, factory_cols = load_factory_row(csv_path, args.factory)
+    factory_name_cn = str(factory_row[factory_cols["工厂中文名"]]).strip()
+    seed_lines = load_factory_lines(year, factory_name_cn)
+    line_ids = [lid for lid, _, _, _ in seed_lines]
+    seed_vals = [seed for _, seed, _, _ in seed_lines]
+    bounds = [(mn, mx) for _, _, mn, mx in seed_lines]
+    prev_best_error = float(factory_row["最小误差"]) if pd.notna(factory_row["最小误差"]) else float("inf")
+
+    print(f"[START] 校准工厂 {args.factory} / {factory_name_cn} (产线数={len(line_ids)}, baseline_error={prev_best_error:.6f})")
+
+    best_genes = None
+    best_score = float("inf")
+    last_improve_gen = -1
+    population = init_population(seed_vals)
+
+    for gen in range(GENERATIONS):
+        scored = []
+        for indiv in population:
+            indiv = apply_bounds(indiv, bounds)
+            score = evaluate(args.factory, line_ids, indiv)
+            # print(f"[{args.factory}] Gen {gen+1} try factors={indiv} -> error={score:.6f}")
+            scored.append((score, indiv))
+            if score < best_score:
+                best_score = score
+                best_genes = indiv
+                last_improve_gen = gen
+        scored.sort(key=lambda x: x[0])
+        next_pop = [scored[0][1]]
+        while len(next_pop) < POP_SIZE:
+            parents = random.sample(scored[:max(3, len(scored))], 2)
+            c1, c2 = crossover(parents[0][1], parents[1][1])
+            next_pop.append(apply_bounds(mutate(c1), bounds))
+            if len(next_pop) < POP_SIZE:
+                next_pop.append(apply_bounds(mutate(c2), bounds))
+        # Stagnation: inject Latin Hypercube samples to escape local optima
+        if last_improve_gen >= 0 and (gen - last_improve_gen) >= STAGNATION_WINDOW:
+            lhs_samples = latin_hypercube_samples(max(POP_SIZE // 2, 2), bounds)
+            lhs_samples = [apply_bounds(s, bounds) for s in lhs_samples]
+            next_pop = next_pop[: POP_SIZE // 4] + lhs_samples
+            next_pop = next_pop[:POP_SIZE]
+            last_improve_gen = gen
+            print(f"[{args.factory}] Stagnation detected ({STAGNATION_WINDOW} gens). Injected {len(lhs_samples)} LHS samples.")
+        population = next_pop
+        print(f"[{args.factory}] Generation {gen+1}/{GENERATIONS}: best_error={best_score:.6f}")
+
+    best_genes = apply_bounds(best_genes, bounds)
+    best_avg_factor = sum(best_genes) / len(best_genes)
+    print(f"[DONE] {args.factory}: best_error={best_score:.6f} (prev best {prev_best_error:.6f})")
+
+    if best_score < prev_best_error:
+        update_factory_csv(csv_path, args.factory, best_avg_factor, best_score)
+        update_production_line_csv(line_csv_path, factory_name_cn, line_ids, best_genes)
+        print(f"[UPDATE] {args.factory} / {factory_name_cn}: avg_factor={best_avg_factor:.6f}, error={best_score:.6f} 已写入 {csv_path} 与 ProductionLine.csv")
+    else:
+        print(f"[SKIP] {args.factory}: 未优于历史最小误差，CSV 未更新。")
+
+
+if __name__ == "__main__":
+    main()

ga_two_factor_calibration.py

@@ -1,121 +0,0 @@
-import json
-import random
-from pathlib import Path
-from typing import List, Tuple
-
-from simulation_model import SimulationModel
-
-# Decision variables: two factory factors only
-TARGET_FACTORIES = ["ZhongcaiBaicheng", "ZhongcaiHami"]
-
-# set year
-year = json.load(open('year.json', 'r', encoding='utf-8'))['year']
-filename = f"{year}"
-
-# Bounds
-FACTOR_BOUNDS = (0.8, 3.0)
-
-POP_SIZE = 20
-GENERATIONS = 50
-MUTATION_RATE = 0.2
-MUTATION_STD = 0.05  # for factors
-
-
-def clip(val: float, bounds: Tuple[float, float]) -> float:
-    lo, hi = bounds
-    return max(lo, min(hi, val))
-
-
-def evaluate(genes: List[float]) -> float:
-    factory_factors = {fid: val for fid, val in zip(TARGET_FACTORIES, genes)}
-    model = SimulationModel(factory_factors=factory_factors, output_enabled=False)
-    while model.running:
-        model.step()
-    return model.mean_abs_error
-
-
-def mutate(genes: List[float]) -> List[float]:
-    new = genes.copy()
-    for i in range(len(new)):
-        if random.random() < MUTATION_RATE:
-            jitter = random.gauss(0, MUTATION_STD)
-            new[i] = clip(new[i] + jitter, FACTOR_BOUNDS)
-    return new
-
-
-def crossover(p1: List[float], p2: List[float]) -> Tuple[List[float], List[float]]:
-    point = random.randint(1, len(p1) - 1)
-    c1 = p1[:point] + p2[point:]
-    c2 = p2[:point] + p1[point:]
-    return c1, c2
-
-
-def init_population() -> List[List[float]]:
-    pop = []
-    best_path = Path("data") / filename / "ga_two_best_params.json"
-    seed_indiv = None
-    if best_path.exists():
-        try:
-            best = json.loads(best_path.read_text(encoding="utf-8"))
-            seed_indiv = [float(best.get(f"factor_{fid}", random.uniform(*FACTOR_BOUNDS))) for fid in TARGET_FACTORIES]
-        except Exception:
-            seed_indiv = None
-
-    for idx in range(POP_SIZE):
-        if seed_indiv is not None and idx == 0:
-            pop.append(seed_indiv)
-            continue
-        indiv = [random.uniform(*FACTOR_BOUNDS) for _ in TARGET_FACTORIES]
-        pop.append(indiv)
-    return pop
-
-
-def main():
-    best_genes = None
-    best_score = float("inf")
-    population = init_population()
-
-    for gen in range(GENERATIONS):
-        scored = []
-        for indiv in population:
-            score = evaluate(indiv)
-            scored.append((score, indiv))
-            if score < best_score:
-                best_score = score
-                best_genes = indiv
-        scored.sort(key=lambda x: x[0])
-        next_pop = [scored[0][1], scored[1][1]]
-        while len(next_pop) < POP_SIZE:
-            parents = random.sample(scored[:max(3, len(scored))], 2)
-            c1, c2 = crossover(parents[0][1], parents[1][1])
-            next_pop.append(mutate(c1))
-            if len(next_pop) < POP_SIZE:
-                next_pop.append(mutate(c2))
-        population = next_pop
-        print(f"Generation {gen+1}: best={best_score:.4f}")
-
-    result = {}
-    for fid, val in zip(TARGET_FACTORIES, best_genes):
-        result[f"factor_{fid}"] = val
-
-    data_path = Path("data") / filename / "ga_two_best_params.json"
-    prev_score = float("inf")
-    if data_path.exists():
-        try:
-            prev = json.loads(data_path.read_text(encoding="utf-8"))
-            prev_score = float(prev.get("best_score", float("inf")))
-        except Exception:
-            prev_score = float("inf")
-
-    if best_score < prev_score:
-        data_path.write_text(
-            json.dumps({"best_score": best_score, **result}, ensure_ascii=False, indent=2),
-            encoding="utf-8",
-        )
-        print(f"New best mean abs error: {best_score:.4f}, saved to {data_path}")
-    else:
-        print(f"Best mean abs error: {best_score:.4f} (not better than {prev_score:.4f}, not saved)")
-
-
-if __name__ == "__main__":
-    main()

production_line.py

@@ -4,23 +4,30 @@ from mesa.agent import Agent
 class ProductionLineAgent(Agent):
     """A production line agent with basic production scheduling."""
 
-    def __init__(self, model, line_id, region, factory, is_new_factory, schedule, ramp_ranges):
+    def __init__(self, model, line_id, region, factory, is_new_factory, schedule, ramp_ranges, line_factor: float):
         super().__init__(model)
         self.line_id = line_id
         self.region = region
         self.factory = factory
         self.is_new_factory = is_new_factory
+        self.line_factor = float(line_factor)
         # List of dicts: {"product": str, "start_month": int, "end_month": int}
         self.schedule = schedule
-        # ramp_ranges: {1: value, 2: value, 3: value, 4: value}
+        # ramp_ranges: {product: {1: value, 2: value, 3: value, 4: value}}
         self.ramp_ranges = ramp_ranges
         self.blade_stock = {}  # 临时叶片库存 {product: blades not yet assembled}
         self.unit_stock = {}  # 叶片机组库存 {product: assembled units}
 
     def _sample_cycle_hours(self, product, month_index):
         idx = min(max(month_index, 1), 4)
-        base = self.ramp_ranges[idx]
-        factor = self.model.get_factory_factor(self.factory)
+        prod_key = str(product).strip()
+        base_by_month = self.ramp_ranges.get(prod_key)
+        if base_by_month is None:
+            raise KeyError(f"未找到产品 {prod_key} 的生产效率。")
+        base = base_by_month.get(idx, base_by_month.get(4))
+        if base is None:
+            raise KeyError(f"产品 {prod_key} 在 month{idx} 缺少生产效率。")
+        factor = self.model.get_factory_factor(self.factory, self.line_id, self.line_factor)
         return base * factor
 
     def step(self):
@@ -45,6 +52,14 @@ class ProductionLineAgent(Agent):
             cycle_hours = self._sample_cycle_hours(product, month_index)
 
         produced_blades = available_hours / cycle_hours
+        self.model.record_blade_production(
+            line_id=self.line_id,
+            factory=self.factory,
+            region=self.region,
+            month=month,
+            product=product,
+            blades=produced_blades,
+        )
 
         # Update blade and unit inventories
         current_blades = self.blade_stock.get(product, 0) + produced_blades
@@ -53,6 +68,14 @@ class ProductionLineAgent(Agent):
         if units_to_add > 0:
             self.unit_stock[product] = self.unit_stock.get(product, 0) + units_to_add
         self.blade_stock[product] = remaining_blades
+        self.model.record_blade_stock(
+            line_id=self.line_id,
+            factory=self.factory,
+            region=self.region,
+            month=month,
+            product=product,
+            blades_stock=remaining_blades,
+        )
 
         self.model.record_production(
             line_id=self.line_id,

schedule_pulp.py

@@ -1,173 +0,0 @@
-# -*- coding: utf-8 -*-
-import pandas as pd
-import pulp
-from math import radians, sin, cos, sqrt, atan2
-
-#  1. 读取数据
-inventory_df = pd.read_excel('可调拨库存表.xlsx')
-factory_loc_df = pd.read_excel('工厂位置.xlsx')
-demand_df = pd.read_excel('需求表.xlsx')        # 型号、市、需求
-city_loc_df = pd.read_excel('地名经纬度.xlsx')    # 市、经度、纬度
-
-#  2. 数据合并
-inventory_df['可调拨库存'] = pd.to_numeric(inventory_df['可调拨库存'], errors='coerce').fillna(0)
-demand_df['需求'] = pd.to_numeric(demand_df['需求'], errors='coerce').fillna(0)
-
-# 工厂库存合并
-factory_capacity = {}
-for _, row in inventory_df.groupby(['工厂', '型号'])['可调拨库存'].sum().reset_index().iterrows():
-    f, p, cap = row['工厂'], row['型号'], int(row['可调拨库存'])
-    if cap > 0:
-        factory_capacity.setdefault(f, {})[p] = cap
-
-# 城市需求合并
-city_demand = {}
-for _, row in demand_df.iterrows():
-    city, p, dem = row['市'], row['型号'], int(row['需求'])
-    if dem > 0:
-        city_demand.setdefault(city, {})
-        city_demand[city][p] = city_demand[city].get(p, 0) + dem
-
-factory_lonlat = dict(zip(factory_loc_df['工厂'], zip(factory_loc_df['经度'], factory_loc_df['纬度'])))
-city_lonlat    = dict(zip(city_loc_df['市'], zip(city_loc_df['经度'], city_loc_df['纬度'])))
-
-# missing = set(city_demand) - set(city_lonlat)
-# if missing:
-#     raise ValueError(f"缺少经纬度：{missing}")
-
-#  3. 距离
-dist = {}
-for f in factory_capacity:
-    for c in city_demand:
-        lon1, lat1 = factory_lonlat[f]
-        lon2, lat2 = city_lonlat[c]
-        dlon = radians(lon2-lon1)
-        dlat = radians(lat2-lat1)
-        a = sin(dlat/2)**2 + cos(radians(lat1))*cos(radians(lat2))*sin(dlon/2)**2
-        dist[(f,c)] = 6371 * 2 * atan2(sqrt(a), sqrt(1-a))
-
-#  4. 单位运费函数
-def get_real_unit_cost(distance_km, product):
-    d = distance_km
-    p = str(product).strip()
-    if p in ['GWBD-A2', 'GWBD-A3', 'GWBD-B']:
-        if distance_km <= 100:
-            return 15802.31
-        elif distance_km <= 200:
-            return 18445.12
-        elif distance_km <= 300:
-            return 22391.35
-        elif distance_km <= 600:
-            return 62.29 * d
-        elif distance_km <= 900:
-            return 44.75 * d
-        elif distance_km <= 1200:
-            return 38.23 * d
-        elif distance_km <= 1500:
-            return 36.08 * d
-        elif distance_km <= 2000:
-            return 33.44 * d
-        elif distance_km <= 2500:
-            return 32.76 * d
-        elif distance_km <= 3500:
-            return 26.68 * d
-        else:
-            return 24.27
-    # 其他型号用第二套
-    else:
-        if distance_km <= 100:
-            return 12859.46
-        elif distance_km <= 200:
-            return 14946.73
-        elif distance_km <= 300:
-            return 18662.46
-        elif distance_km <= 600:
-            return 52.83 * d
-        elif distance_km <= 900:
-            return 38.36 * d
-        elif distance_km <= 1200:
-            return 32.89 * d
-        elif distance_km <= 1500:
-            return 30.69 * d
-        elif distance_km <= 2000:
-            return 28.49 * d
-        elif distance_km <= 2500:
-            return 27.76 * d
-        elif distance_km <= 3500:
-            return 22.87 * d
-        else:
-            return 21.02 * d
-
-#  5. 规划模型
-prob = pulp.LpProblem("最小化运费", pulp.LpMinimize)
-
-x = {}
-for f in factory_capacity:
-    for p in factory_capacity[f]:
-        for city in city_demand:
-            if city_demand[city].get(p, 0) > 0:
-                x[(f,city,p)] = pulp.LpVariable(f"ship_{f}_{city}_{p}", lowBound=0, cat="Integer")
-
-# 缺货惩罚
-shortage = {(city,p): pulp.LpVariable(f"short_{city}_{p}", lowBound=0, cat="Continuous")
-            for city in city_demand for p in city_demand[city]}
-
-BIG_M = 1e10
-prob += pulp.lpSum(
-    x[k] * get_real_unit_cost(dist[(k[0],k[1])], k[2])   # 真实单位运费
-    for k in x
-) + pulp.lpSum(BIG_M * s for s in shortage.values())
-
-# 库存硬约束
-for f in factory_capacity:
-    for p in factory_capacity[f]:
-        prob += pulp.lpSum(x.get((f,c,p), 0) for c in city_demand) <= factory_capacity[f][p]
-
-# 需求软约束
-for city in city_demand:
-    for p, dem in city_demand[city].items():
-        prob += pulp.lpSum(x.get((f,city,p), 0) for f in factory_capacity) + shortage[(city,p)] >= dem
-
-# 6. 求解
-status = prob.solve(pulp.PULP_CBC_CMD(msg=True, timeLimit=600))
-
-print(f"\n求解状态: {pulp.LpStatus[status]}")
-if status != 1:
-    print("无解（请检查总库存）")
-else:
-    print("有解")
-    # real_cost = pulp.value(prob.objective)
-    # print(f"实际运输总费用: {real_cost:,.2f} 元")
-
-# ====================== 7. 输出 ======================
-result = []
-for (f,city,p), var in x.items():
-    q = int(pulp.value(var) or 0)
-    if q >= 1:
-        d = dist[(f,city)]
-        # unit = get_real_unit_cost(d, p)
-        result.append({
-            "工厂": f,
-            "型号": p,
-            "需求方": city,
-            "调拨数量": q,
-            # "距离_km": round(d, 1),
-            # "真实单位运费": round(unit, 3),
-            # "总运费": round(q * unit, 2)
-        })
-
-df = pd.DataFrame(result)
-if not df.empty:
-    df = df.sort_values(["工厂", "型号"])  # 按单位运费排序
-    df[["工厂","型号","需求方","调拨数量"]].to_excel("调拨方案.xlsx", index=False)
-    # print("\n调拨方案已保存（真实单位运费最优，优先满足单价更低的城市）")
-    # print(df[["工厂","型号","需求方","调拨数量"]].to_string(index=False))
-else:
-    print("\n无调拨记录")
-
-# 校验报告
-# print("\n各城市需求满足情况：")
-# for city in city_demand:
-#     for p, dem in city_demand[city].items():
-#         sup = sum(r["调拨数量"] for r in result if r["需求方"]==city and r["型号"]==p)
-#         print(f"  {city} | {p}: 需求 {dem} → 调拨 {sup} → {'完美' if sup==dem else '异常'}")

simulation_model.py

@@ -8,6 +8,9 @@ import matplotlib.pyplot as plt
 from mesa.datacollection import DataCollector
 from mesa.model import Model
 import pulp
+import warnings
+import sys
+import traceback
 
 from production_line import ProductionLineAgent
 from demand_agent import DemandAgent
@@ -19,6 +22,36 @@ matplotlib.rcParams["axes.unicode_minus"] = False
 # set year
 year = json.load(open('year.json', 'r', encoding='utf-8'))['year']
 filename = f"{year}"
+# Silence noisy deprecation warnings from dependencies; prefer explicit conversions.
+warnings.filterwarnings("ignore", category=FutureWarning)
+
+
+class _FilterMessageTracer:
+    """Silence and trace unexpected 'filter element' messages."""
+
+    def __init__(self, stream, log_path):
+        self._stream = stream
+        self._log_path = log_path
+
+    def write(self, msg):
+        lower_msg = msg.lower()
+        if "filter element" in lower_msg:
+            # Record stack once per message and swallow it from console.
+            with open(self._log_path, "a", encoding="utf-8") as f:
+                f.write(msg)
+                traceback.print_stack(file=f)
+            return len(msg)
+        return self._stream.write(msg)
+
+    def flush(self):
+        return self._stream.flush()
+
+
+# Capture mysterious "filter element" prints while keeping stdout/stderr usable.
+_filter_log = os.path.join("output", filename, "debug_filter.log")
+os.makedirs(os.path.dirname(_filter_log), exist_ok=True)
+sys.stdout = _FilterMessageTracer(sys.stdout, _filter_log)
+sys.stderr = _FilterMessageTracer(sys.stderr, _filter_log)
 
 class SimulationModel(Model):
     """
@@ -28,35 +61,26 @@ class SimulationModel(Model):
 
     def __init__(
         self,
-        month1: float | None = None,
-        month2: float | None = None,
-        month3: float | None = None,
-        month4: float | None = None,
         factory_factors: dict | None = None,
         output_enabled: bool = False,
         is_within_region_allocation_only: bool | None = None,
         product_set: tuple | list | set | str | None = None,
+        is_calibration_mode: bool = False,
         **kwargs,
     ):
         super().__init__()
         cfg = self._load_model_params()
         # Apply overrides if provided
         self.month_holiday_days = self._load_month_holiday_days(cfg)
-        self.ramp_ranges = {
-            1: float(month1 if month1 is not None else cfg["month1"]),
-            2: float(month2 if month2 is not None else cfg["month2"]),
-            3: float(month3 if month3 is not None else cfg["month3"]),
-            4: float(month4 if month4 is not None else cfg["month4"]),
-        }
+        self.ramp_ranges = self._load_product_month_efficiency()
         self.factory_mapping = self._load_factory_mapping()
-        self.factory_factors = self._load_factory_factors(cfg)
+        self.factory_factors = {}
         merged_factors = {}
         merged_factors.update({k: v for k, v in kwargs.items() if k.startswith("factor_")})
         if factory_factors:
             merged_factors.update(factory_factors)
         if merged_factors:
             self._merge_factory_factors(merged_factors)
-        self.default_new_factory_factor = cfg.get("factor_default", 1.3)
         self.within_region_only = self._to_bool(
             is_within_region_allocation_only if is_within_region_allocation_only is not None else cfg.get("is_within_region_allocation_only", False)
         )
@@ -91,6 +115,10 @@ class SimulationModel(Model):
         self.product_names = set()
         self.product_list = []
         self.monthly_allocation_summary = []
+        self.blade_production_log = []
+        self.blade_stock_log = []
+        self.calibration_mode = bool(is_calibration_mode)
+        self.line_factor = {}
 
         self._load_month_hours()
         self._load_agents_from_csv()
@@ -194,6 +222,32 @@ class SimulationModel(Model):
         with open(f"data/{filename}/model_params.json", "r", encoding="utf-8") as f:
             return json.load(f)
 
+    def _load_product_month_efficiency(self) -> dict:
+        path = f"data/{filename}/month_efficiency.xlsx"
+        if not os.path.exists(path):
+            raise FileNotFoundError(f"Missing month efficiency file: {path}")
+        df = pd.read_excel(path)
+        df.columns = [str(c).strip().lower() for c in df.columns]
+        required = {"product_id", "month1", "month2", "month3", "month4"}
+        missing = required - set(df.columns)
+        if missing:
+            raise ValueError(f"month_efficiency.xlsx is missing columns: {', '.join(sorted(missing))}")
+        ramp = {}
+        for _, row in df.iterrows():
+            product = str(row["product_id"]).strip()
+            if not product:
+                continue
+            values = {}
+            for idx in range(1, 5):
+                val = row[f"month{idx}"]
+                if pd.isna(val):
+                    raise ValueError(f"产品 {product} 的 month{idx} 为空，请在 month_efficiency.xlsx 中补充。")
+                values[idx] = float(val)
+            ramp[product] = values
+        if not ramp:
+            raise ValueError("month_efficiency.xlsx contains no product rows.")
+        return ramp
+
     def _load_month_holiday_days(self, cfg: dict) -> dict:
         # Default 2 days off per month unless overridden
         holidays = {m: 2 for m in range(1, 13)}
@@ -211,7 +265,8 @@ class SimulationModel(Model):
 
     def _load_factory_mapping(self) -> dict:
         with open(f"data/{filename}/factory_mapping.json", "r", encoding="utf-8") as f:
-            return json.load(f)
+            mapping = json.load(f)
+        return mapping
 
     def _parse_product_set(self, val) -> tuple:
         if val is None:
@@ -231,13 +286,9 @@ class SimulationModel(Model):
             return val.strip().lower() in {"true", "1", "yes", "y", "是", "对"}
         return bool(val)
 
-    def _load_factory_factors(self, cfg: dict) -> dict:
-        factors = {}
-        for key, val in cfg.items():
-            if key.startswith("factor_"):
-                suffix = key[len("factor_") :]
-                factors[suffix] = float(val)
-        return factors
+    def _load_factory_factors(self) -> dict:
+        # Deprecated: factors now provided per production line; keep for compatibility with overrides.
+        return {}
 
     def _merge_factory_factors(self, overrides: dict):
         for key, val in overrides.items():
@@ -249,9 +300,20 @@ class SimulationModel(Model):
     def get_factory_code(self, factory_name: str) -> str:
         return self.factory_mapping.get(factory_name, self._sanitize_product(factory_name))
 
-    def get_factory_factor(self, factory_name: str) -> float:
+    def get_factory_factor(self, factory_name: str, line_id: str | None = None, line_factor: float | None = None) -> float:
         code = self.get_factory_code(factory_name)
-        return self.factory_factors.get(code, self.default_new_factory_factor)
+        if line_id and line_id in self.line_factor:
+            base = self.line_factor.get(line_id)
+        else:
+            base = None
+        override = self.factory_factors.get(code)
+        if override is not None:
+            return float(override)
+        if base is not None:
+            return float(base)
+        if line_factor is not None:
+            return float(line_factor)
+        raise KeyError(f"未找到工厂 {factory_name} (line_id={line_id}) 的磨合系数。")
 
     def _load_agents_from_csv(self):
         encodings = ("utf-8", "utf-8-sig", "gbk")
@@ -275,8 +337,11 @@ class SimulationModel(Model):
         for line_id, group in df.groupby("产线ID"):
             first = group.iloc[0]
             schedule = []
+            line_factor_val = None
             for _, row in group.iterrows():
-                product = row["生产型号"]
+                product = str(row["生产型号"]).strip()
+                if product not in self.ramp_ranges:
+                    raise KeyError(f"缺少产品 {product} 的生产效率，请在 month_efficiency.xlsx 中补充。")
                 schedule.append(
                     {
                         "product": product,
@@ -284,10 +349,17 @@ class SimulationModel(Model):
                         "end_month": int(row["结束月份"]),
                     }
                 )
-                self.product_names.add(str(product).strip())
+                self.product_names.add(product)
             is_new_factory = str(first["是否新工厂"]).strip() in {"是", "Yes", "True", "true", "1"}
             self.line_factory[line_id] = first["工厂名"]
             self.line_region[line_id] = first["区域名"]
+            if "磨合系数" not in first:
+                raise KeyError("ProductionLine.csv 缺少磨合系数字段。")
+            try:
+                line_factor_val = float(first.get("磨合系数"))
+            except Exception:
+                raise ValueError(f"无法解析产线 {line_id} 的磨合系数。")
+            self.line_factor[line_id] = line_factor_val
             ProductionLineAgent(
                 model=self,
                 line_id=line_id,
@@ -296,6 +368,7 @@ class SimulationModel(Model):
                 is_new_factory=is_new_factory,
                 schedule=schedule,
                 ramp_ranges=self.ramp_ranges,
+                line_factor=line_factor_val,
             )
 
     def _load_demand_agents_from_csv(self):
@@ -462,9 +535,43 @@ class SimulationModel(Model):
         self.cumulative_production += units
         self.region_totals[region] = self.region_totals.get(region, 0) + units
 
+    def record_blade_production(self, line_id, factory, region, month, product, blades):
+        self.blade_production_log.append(
+            {
+                "line_id": line_id,
+                "factory": factory,
+                "region": region,
+                "month": month,
+                "product": product,
+                "blades": float(blades),
+            }
+        )
+
+    def record_blade_stock(self, line_id, factory, region, month, product, blades_stock):
+        self.blade_stock_log.append(
+            {
+                "line_id": line_id,
+                "factory": factory,
+                "region": region,
+                "month": month,
+                "product": product,
+                "blades_stock": float(blades_stock),
+            }
+        )
+
     def step(self):
         for agent in list(self.agents):
             agent.step()
+        if self.calibration_mode:
+            if self.current_month >= 12:
+                self.running = False
+                self._finalize_factory_errors(write_files=self.output_enabled)
+                if self.output_enabled:
+                    self._write_report()
+            self.datacollector.collect(self)
+            self.current_month += 1
+            return
+
         # Allocation after production for current month
         self._run_allocation()
         self._update_region_inventory()
@@ -513,6 +620,40 @@ class SimulationModel(Model):
         os.makedirs(output_dir, exist_ok=True)
         out_path = os.path.join(output_dir, f"production_report_{timestamp}.csv")
         pivot.to_csv(out_path, index=False, encoding="utf-8-sig")
+        self._write_blade_reports(timestamp, output_dir)
+
+    def _write_blade_reports(self, timestamp: str, output_dir: str):
+        def build_and_write(log, value_col, filename_prefix, value_name):
+            if not log:
+                return
+            df = pd.DataFrame(log)
+            pivot = (
+                df.groupby(["product", "line_id", "factory", "month"])[value_col]
+                .sum()
+                .reset_index()
+                .pivot_table(
+                    index=["product", "line_id", "factory"],
+                    columns="month",
+                    values=value_col,
+                    fill_value=0.0,
+                )
+            )
+            for m in range(1, 13):
+                if m not in pivot.columns:
+                    pivot[m] = 0.0
+            pivot = pivot[sorted([c for c in pivot.columns if isinstance(c, int)])]
+            pivot["total"] = pivot.sum(axis=1)
+            pivot.reset_index(inplace=True)
+            pivot.columns = (
+                ["生产型号", "产线名称", "工厂名"]
+                + [f"{m}月" for m in range(1, 13)]
+                + ["总计"]
+            )
+            out_path = os.path.join(output_dir, f"{filename_prefix}_{timestamp}.csv")
+            pivot.to_csv(out_path, index=False, encoding="utf-8-sig")
+
+        build_and_write(self.blade_production_log, "blades", "production_blade_current_report", "blades")
+        build_and_write(self.blade_stock_log, "blades_stock", "production_blade_stock_report", "blades_stock")
 
     def _write_allocation_workbook(self):
         if not self.monthly_allocation_summary:
@@ -694,23 +835,33 @@ class SimulationModel(Model):
         except UnicodeDecodeError:
             benchmark = pd.read_csv(f"data/{filename}/benchmark.csv", encoding="gbk")
         benchmark_sorted = benchmark.sort_values(by=benchmark.columns[0])
+
         total_col = "总计"
         month_cols = [f"{m}月" for m in range(1, 13)]
         if total_col not in benchmark_sorted.columns:
             benchmark_sorted[total_col] = benchmark_sorted[month_cols].sum(axis=1)
-        bench_total = benchmark_sorted[total_col].astype(float).reset_index(drop=True)
-        prod_total = factory_pivot["总计"].astype(float).reset_index(drop=True)
-        min_len = min(len(bench_total), len(prod_total))
-        if min_len == 0:
+        errors = []
+        bench_name_col = benchmark_sorted.columns[0]
+        for _, prow in factory_pivot.iterrows():
+            fname = prow["工厂名称"]
+            brow = benchmark_sorted[benchmark_sorted[bench_name_col] == fname]
+            if brow.empty:
+                continue
+            prod_months = pd.Series([float(prow[f"{m}月"]) for m in range(1, 13)])
+            bench_months = pd.Series([float(brow.iloc[0][f"{m}月"]) for m in range(1, 13)])
+            prod_cum = prod_months.cumsum()
+            bench_cum = bench_months.cumsum()
+            actual_total = float(brow.iloc[0][total_col]) if total_col in brow.columns else float(bench_cum.iloc[-1])
+            if actual_total <= 0:
+                continue
+            diff = prod_cum - bench_cum
+            pct = diff.abs() / actual_total
+            err = pct.mean()
+            errors.append(float(err))
+        if not errors:
             self.mean_abs_error = float("inf")
             return
-        bench_total = bench_total.iloc[:min_len]
-        prod_total = prod_total.iloc[:min_len]
-        bench_total_safe = bench_total.replace(0, pd.NA)
-        rel_errors = (prod_total - bench_total_safe) / bench_total_safe
-        rel_errors = rel_errors.fillna(0).astype(float)
-        abs_rel_errors = rel_errors.abs()
-        self.mean_abs_error = abs_rel_errors.mean()
+        self.mean_abs_error = sum(errors) / len(errors)
 
         if not write_files:
             return
@@ -739,7 +890,7 @@ class SimulationModel(Model):
         bench_months = benchmark_sorted[[f"{m}月" for m in range(1, 13)]].iloc[:min_len].astype(float)
         bench_months_safe = bench_months.replace(0, pd.NA)
         month_pct_errors = (prod_months - bench_months_safe) / bench_months_safe * 100
-        month_pct_errors = month_pct_errors.fillna(0).convert_dtypes().astype(float)
+        month_pct_errors = month_pct_errors.fillna(0).infer_objects(copy=False).astype(float)
         month_error_means = pd.Series(month_pct_errors.mean(axis=0), index=[f"{m}月" for m in range(1, 13)])
 
         plt.figure(figsize=(10, 5))
@@ -753,7 +904,7 @@ class SimulationModel(Model):
 
         bench_totals_safe = bench_total.replace(0, pd.NA)
         factory_pct_errors = (prod_total - bench_totals_safe) / bench_totals_safe * 100
-        factory_pct_errors = factory_pct_errors.fillna(0).convert_dtypes().astype(float)
+        factory_pct_errors = factory_pct_errors.fillna(0).infer_objects(copy=False).astype(float)
         factory_names = factory_pivot["工厂名称"].iloc[:min_len].reset_index(drop=True)
         factory_df = pd.DataFrame({"name": factory_names, "error_pct": factory_pct_errors}).sort_values(
             by="error_pct"