新增solverType参数，区分不同相态

ML/nmWTAI-ML/scripts/compare_single_case.py

@@ -42,7 +42,11 @@ from src.common.experiment_paths import (
     processed_path_for_tag,
 )
 from src.data.curve_processing import clean_curve_for_dataset, is_valid_curve, resample_curve_to_model_features
-from src.data.param_features import param_feature_transform_from_meta, transform_param_features
+from src.data.param_features import (
+    build_raw_param_vector,
+    param_feature_transform_from_meta,
+    transform_param_features,
+)
 from src.data.params import Params, Schedule
 from src.data.runner_client import CppRunner, read_result_bin
 from src.data.schedule_features import build_schedule_model_vector
@@ -103,6 +107,13 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--h", type=float, default=DEFAULT_SINGLE_CASE["params"]["h"])
     parser.add_argument("--Ct", type=float, default=DEFAULT_SINGLE_CASE["params"]["Ct"])
     parser.add_argument("--Cf", type=float, default=DEFAULT_SINGLE_CASE["params"]["Cf"])
+    parser.add_argument("--solver-type", type=int, choices=[1, 2, 3, 4], default=None)
+    parser.add_argument(
+        "--dataset-case",
+        type=str,
+        default=None,
+        help="Dataset case name used to select the matching scene/PVT files",
+    )
     parser.add_argument(
         "--well-index",
         type=int,
@@ -277,12 +288,26 @@ def resolve_paths(args: argparse.Namespace) -> tuple[Config, Path, Path, Path]:
     if config_path is None:
         config_path = str(config_for_stage(args.stage) or Path("configs/data_gen_family_random.yaml"))
 
-    processed_path = Path(args.processed) if args.processed is not None else processed_path_for_tag(tag)
-    model_path = (
-        Path(args.model)
-        if args.model is not None
-        else model_checkpoint_for_tag(tag, use_schedule=not args.no_schedule)
-    )
+    cfg = Config(config_path, dataset_case=args.dataset_case)
+    if args.processed is not None:
+        processed_path = Path(args.processed)
+    else:
+        processed_candidates = [
+            processed_path_for_tag(tag),
+            cfg.paths.processed_dir / f"dataset_{tag}.pkl",
+            cfg.paths.processed_dir / f"processed_{tag}.pkl",
+        ]
+        processed_path = next((path for path in processed_candidates if path.exists()), processed_candidates[0])
+
+    if args.model is not None:
+        model_path = Path(args.model)
+    else:
+        model_candidates = [
+            model_checkpoint_for_tag(tag, use_schedule=not args.no_schedule),
+            cfg.paths.models_dir / str(tag) / "forward_surrogate_best.pt",
+            cfg.paths.models_dir / f"forward_surrogate_{tag}" / "forward_surrogate_best.pt",
+        ]
+        model_path = next((path for path in model_candidates if path.exists()), model_candidates[0])
 
     if args.output_dir is not None:
         output_dir = Path(args.output_dir)
@@ -290,7 +315,19 @@ def resolve_paths(args: argparse.Namespace) -> tuple[Config, Path, Path, Path]:
         suffix = "" if not args.no_schedule else "_no_schedule"
         output_dir = Path("results") / (f"single_compare_{tag}{suffix}" if tag else f"single_compare{suffix}")
 
-    return Config(config_path), processed_path, model_path, output_dir
+    return cfg, processed_path, model_path, output_dir
+
+
+def resolve_solver_type(args: argparse.Namespace, cfg: Config) -> int | None:
+    """Resolve solverType from an explicit CLI value or the selected dataset case."""
+    configured = cfg.get("solver_type", default=None)
+    if args.solver_type is not None and configured is not None:
+        if int(args.solver_type) != int(configured):
+            raise ValueError(
+                f"--solver-type={args.solver_type} conflicts with dataset case solver_type={configured}"
+            )
+    value = args.solver_type if args.solver_type is not None else configured
+    return None if value is None else int(value)
 
 
 def build_params_from_args(args: argparse.Namespace, cfg: Config, schedule: Schedule) -> Params:
@@ -405,6 +442,7 @@ def predict_surrogate_curve(
     params: Params,
     schedule: Schedule,
     cfg: Config,
+    solver_type: int | None = None,
 ) -> np.ndarray:
     """使用正演代理模型预测单个参数和流量制度对应的完整曲线。"""
     scaler_params = processed["scaler_params"]
@@ -414,10 +452,7 @@ def predict_surrogate_curve(
 
     # 构建参数特征向量
     # 顺序必须与训练阶段保持一致
-    params_vec = np.asarray(
-        [params.k, params.skin, params.wellboreC, params.phi, params.h, params.Cf],
-        dtype=np.float32,
-    ).reshape(1, -1)
+    params_vec = build_raw_param_vector(params, param_transform, solver_type=solver_type)
     # 将流量制度 schedule 编码成模型输入向量
     schedule_vec = build_schedule_vector(cfg, schedule).reshape(1, -1)
 
@@ -534,6 +569,7 @@ def main() -> None:
     # 先用同一组参数和制度跑真实求解器，再用代理模型预测同一输入，保证对比公平。
     schedule = resolve_case_schedule(cfg, args)
     params = build_params_from_args(args, cfg, schedule)
+    solver_type = resolve_solver_type(args, cfg)
 
     print("Running solver...")
     # 运行真实数值求解器
@@ -553,6 +589,7 @@ def main() -> None:
         params=params,
         schedule=schedule,
         cfg=cfg,
+        solver_type=solver_type,
     )
 
     plot_path = output_dir / "single_case_comparison.png"
@@ -583,6 +620,7 @@ def main() -> None:
             "h": params.h,
             "Ct": params.Ct,
             "Cf": params.Cf,
+            "solverType": solver_type,
         },
         "schedule": {
             "sectionIndex": schedule.sectionIndex,

ML/nmWTAI-ML/scripts/score_pso_candidates.py

@@ -34,7 +34,7 @@ from src.data.params import Params, Schedule
 from src.evaluation.autofit_objective import dual_log_objective
 
 
-PARAM_COLUMNS = ["k", "skin", "wellboreC", "phi", "h", "Cf"]
+PARAM_COLUMNS = ["k", "skin", "wellboreC", "phi", "h", "Cf", "solverType"]
 
 
 def parse_args() -> argparse.Namespace:
@@ -44,7 +44,7 @@ def parse_args() -> argparse.Namespace:
         "--candidates",
         required=True,
         type=str,
-        help="候选粒子 CSV，包含 particle_id,k,skin,wellboreC,phi,h,Cf",
+        help="候选粒子 CSV，包含 particle_id,k,skin,wellboreC,phi,h,Cf,solverType",
     )
     parser.add_argument(
         "--trace-meta",
@@ -67,8 +67,27 @@ def resolve_paths(args: argparse.Namespace) -> tuple[Path, Path, Path]:
     config_path = Path(args.config) if args.config else config_for_stage(args.stage)
     if config_path is None:
         raise ValueError(f"Cannot resolve config for stage={args.stage!r}; pass --config explicitly")
-    processed_path = Path(args.processed) if args.processed else processed_path_for_tag(tag)
-    model_path = Path(args.model) if args.model else model_checkpoint_for_tag(tag, use_schedule=True)
+    cfg = Config(config_path)
+
+    if args.processed:
+        processed_path = Path(args.processed)
+    else:
+        processed_candidates = [
+            processed_path_for_tag(tag),
+            cfg.paths.processed_dir / f"dataset_{tag}.pkl",
+            cfg.paths.processed_dir / f"processed_{tag}.pkl",
+        ]
+        processed_path = next((path for path in processed_candidates if path.exists()), processed_candidates[0])
+
+    if args.model:
+        model_path = Path(args.model)
+    else:
+        model_candidates = [
+            model_checkpoint_for_tag(tag, use_schedule=True),
+            cfg.paths.models_dir / str(tag) / "forward_surrogate_best.pt",
+            cfg.paths.models_dir / f"forward_surrogate_{tag}" / "forward_surrogate_best.pt",
+        ]
+        model_path = next((path for path in model_candidates if path.exists()), model_candidates[0])
     return config_path.resolve(), processed_path.resolve(), model_path.resolve()
 
 
@@ -132,6 +151,17 @@ def params_from_row(row: dict) -> Params:
     )
 
 
+def solver_type_from_row(row: dict) -> int | None:
+    """Read solverType while keeping legacy candidate CSV files usable with legacy models."""
+    raw = row.get("solverType")
+    if raw is None or str(raw).strip() == "":
+        return None
+    value = float(raw)
+    if not value.is_integer():
+        raise ValueError(f"solverType must be an integer, got {raw!r}")
+    return int(value)
+
+
 def main() -> None:
     """用训练好的正演代理模型快速评价一批 PSO 候选粒子的目标函数。"""
     args = parse_args()
@@ -177,6 +207,7 @@ def main() -> None:
             }
             try:
                 params = params_from_row(row)
+                solver_type = solver_type_from_row(row)
                 params.schedule = schedule
                 # 代理预测的曲线与 trace 中的目标曲线使用同一套双对数目标函数比较。
                 pred_curve = predict_surrogate_curve(
@@ -187,6 +218,7 @@ def main() -> None:
                     params=params,
                     schedule=schedule,
                     cfg=cfg,
+                    solver_type=solver_type,
                 )
                 obj = dual_log_objective(target_curve, pred_curve, curve_layout)
                 out["surrogate_objective"] = f"{obj['dual_log_objective']:.17g}"

ML/nmWTAI-ML/scripts/score_pso_candidates_server.py

@@ -27,6 +27,7 @@ from scripts.score_pso_candidates import (
     params_from_row,
     read_candidates,
     resolve_paths,
+    solver_type_from_row,
 )
 from scripts.validate_autofit_local_ranking import infer_curve_layout, predict_surrogate_curve
 from src.common.config import Config
@@ -108,6 +109,7 @@ class PsoScoringServer:
                 }
                 try:
                     params = params_from_row(row)
+                    solver_type = solver_type_from_row(row)
                     params.schedule = self.schedule
                     # 预测曲线后直接与固定目标曲线比较；这里不再启动数值求解器。
                     pred_curve = predict_surrogate_curve(
@@ -118,6 +120,7 @@ class PsoScoringServer:
                         params=params,
                         schedule=self.schedule,
                         cfg=self.cfg,
+                        solver_type=solver_type,
                     )
                     obj = dual_log_objective(self.target_curve, pred_curve, self.curve_layout)
                     out["surrogate_objective"] = f"{obj['dual_log_objective']:.17g}"

ML/nmWTAI-ML/scripts/validate_autofit_local_ranking.py

@@ -27,7 +27,11 @@ import torch
 from src.common.config import Config
 from src.common.experiment_paths import config_for_stage, model_checkpoint_for_tag, normalize_tag, processed_path_for_tag
 from src.data.curve_processing import clean_curve_for_dataset, is_valid_curve, resample_curve_to_model_features
-from src.data.param_features import param_feature_transform_from_meta, transform_param_features
+from src.data.param_features import (
+    build_raw_param_vector,
+    param_feature_transform_from_meta,
+    transform_param_features,
+)
 from src.data.params import Params, Schedule
 from src.data.runner_client import CppRunner, read_result_bin
 from src.data.schedule_features import build_schedule_model_vector
@@ -85,6 +89,8 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument("--h", type=float, default=DEFAULT_CASE["params"]["h"])
     parser.add_argument("--Ct", type=float, default=DEFAULT_CASE["params"]["Ct"])
     parser.add_argument("--Cf", type=float, default=DEFAULT_CASE["params"]["Cf"])
+    parser.add_argument("--solver-type", type=int, choices=[1, 2, 3, 4], default=None)
+    parser.add_argument("--dataset-case", type=str, default=None)
     return parser.parse_args()
 
 
@@ -135,14 +141,47 @@ def resolve_paths(args: argparse.Namespace) -> tuple[Config, Path, Path, Path]:
     if config_path is None:
         config_path = str(config_for_stage(args.stage) or Path(DEFAULT_CASE["config"]))
 
-    processed_path = (Path(args.processed) if args.processed is not None else processed_path_for_tag(tag)).resolve()
-    model_path = (Path(args.model) if args.model is not None else model_checkpoint_for_tag(tag, use_schedule=True)).resolve()
+    cfg = Config(config_path, dataset_case=args.dataset_case)
+    if args.processed is not None:
+        processed_path = Path(args.processed)
+    else:
+        processed_candidates = [
+            processed_path_for_tag(tag),
+            cfg.paths.processed_dir / f"dataset_{tag}.pkl",
+            cfg.paths.processed_dir / f"processed_{tag}.pkl",
+        ]
+        processed_path = next((path for path in processed_candidates if path.exists()), processed_candidates[0])
+
+    if args.model is not None:
+        model_path = Path(args.model)
+    else:
+        model_candidates = [
+            model_checkpoint_for_tag(tag, use_schedule=True),
+            cfg.paths.models_dir / str(tag) / "forward_surrogate_best.pt",
+            cfg.paths.models_dir / f"forward_surrogate_{tag}" / "forward_surrogate_best.pt",
+        ]
+        model_path = next((path for path in model_candidates if path.exists()), model_candidates[0])
+
+    processed_path = processed_path.resolve()
+    model_path = model_path.resolve()
 
     if args.output_dir is not None:
         output_dir = Path(args.output_dir).resolve()
     else:
         output_dir = (Path("results") / f"autofit_local_validation_{tag}").resolve()
-    return Config(config_path), processed_path, model_path, output_dir
+    return cfg, processed_path, model_path, output_dir
+
+
+def resolve_solver_type(args: argparse.Namespace, cfg: Config) -> int | None:
+    """Resolve solverType from an explicit CLI value or the selected dataset case."""
+    configured = cfg.get("solver_type", default=None)
+    if args.solver_type is not None and configured is not None:
+        if int(args.solver_type) != int(configured):
+            raise ValueError(
+                f"--solver-type={args.solver_type} conflicts with dataset case solver_type={configured}"
+            )
+    value = args.solver_type if args.solver_type is not None else configured
+    return None if value is None else int(value)
 
 
 def build_params_from_args(args: argparse.Namespace, schedule: Schedule) -> Params:
@@ -192,6 +231,7 @@ def predict_surrogate_curve(
     params: Params,
     schedule: Schedule,
     cfg: Config,
+    solver_type: int | None = None,
 ) -> np.ndarray:
     """使用正演代理模型预测单个参数和流量制度对应的完整曲线。"""
     scaler_params = processed["scaler_params"]
@@ -199,10 +239,7 @@ def predict_surrogate_curve(
     scaler_curve = processed["scaler_curve"]
     param_transform = param_feature_transform_from_meta(processed.get("meta", {}))
 
-    params_vec = np.asarray(
-        [params.k, params.skin, params.wellboreC, params.phi, params.h, params.Cf],
-        dtype=np.float32,
-    ).reshape(1, -1)
+    params_vec = build_raw_param_vector(params, param_transform, solver_type=solver_type)
     schedule_vec = build_schedule_vector(cfg, schedule).reshape(1, -1)
 
     params_x = scaler_params.transform(transform_param_features(params_vec, param_transform)).astype(np.float32)
@@ -412,6 +449,7 @@ def main() -> None:
     curve_layout = infer_curve_layout(processed["meta"], int(processed["meta"]["curve_dim"]))
     schedule = resolve_case_schedule(cfg)
     target_params = build_params_from_args(args, schedule)
+    solver_type = resolve_solver_type(args, cfg)
     search_names = _search_param_names(cfg)
 
     model, use_schedule, device = load_model(model_path)
@@ -479,6 +517,7 @@ def main() -> None:
                     params=cand,
                     schedule=schedule,
                     cfg=cfg,
+                    solver_type=solver_type,
                 )
 
                 solver_obj = dual_log_objective(target_curve, solver_curve, curve_layout)

Src/nmNum/nmCalculation/nmCalculationAutoFitPSO.cpp

@@ -75,6 +75,8 @@ static const double kSurrogateHMin = 2.0;                  // 代理模型训练
 static const double kSurrogateHMax = 50.0;                 // 代理模型训练域：储层厚度上界。
 static const double kSurrogateCfFixed = 4.315e-4;          // 当前代理模型按近似固定 Cf 训练。
 static const double kSurrogateCfRelTol = 0.25;             // Cf 允许相对偏差，超过则不使用代理筛选。
+static const double kSurrogateCfMin = 1.0e-6;              // 变化 PVT 模型的 Cf 训练域下界。
+static const double kSurrogateCfMax = 5.0e-3;              // 变化 PVT 模型的 Cf 训练域上界。
 static const int kSurrogateMinProdSections = 3;            // 代理训练流量制度：生产段数量下界。
 static const int kSurrogateMaxProdSections = 5;            // 代理训练流量制度：生产段数量上界。
 static const double kSurrogateProdTimeMin = 24.0;          // 代理训练流量制度：生产总时长下界。
@@ -1224,7 +1226,7 @@ QString nmCalculationAutoFitPSO::getSurrogateTag() const
 {
     // 当前 C++ 绑定的代理模型实验标识，对应 ML 侧训练输出目录/checkpoint 命名。
     // 如果以后换模型，需要同步更新这里和 ML 脚本可识别的 tag。
-    return "family_random_v2_q_50k_noslope";
+    return "T1_T4_merged_40000";
 }
 
 QString nmCalculationAutoFitPSO::getSurrogateStage() const
@@ -1277,7 +1279,7 @@ bool nmCalculationAutoFitPSO::writeSurrogateCandidateCsv(const QString& candidat
     //
     // 文件位置通常是 ML/nmWTAI-ML/data/temp/pso_screen_candidates_<run_id>_gen<N>.csv。
     // 字段顺序必须与 ML 脚本 score_pso_candidates*.py 保持一致：
-    // particle_id,k,skin,wellboreC,phi,h,Cf
+    // particle_id,k,skin,wellboreC,phi,h,Cf,solverType
     //
     // 这里写的是“完整参数体系”中的关键字段，不是粒子内部紧凑向量。
     // 例如用户没有勾选 Cf 时，Cf 会从当前 DataManager 取值写入 CSV。
@@ -1289,8 +1291,16 @@ bool nmCalculationAutoFitPSO::writeSurrogateCandidateCsv(const QString& candidat
     }
 
     QTextStream out(&file);
+    nmDataAnalyzeManager* dataManager = nmDataAnalyzeManager::getCurrentInstance();
+
+    if(!dataManager) {
+        DEBUG_OUT("Failed to write surrogate candidates: data manager is unavailable");
+        return false;
+    }
+
+    int solverType = static_cast<int>(dataManager->getSolverModelType());
     // 代理模型只需要这些输入字段；其它参数当前不在训练输入集中。
-    out << "particle_id,k,skin,wellboreC,phi,h,Cf\n";
+    out << "particle_id,k,skin,wellboreC,phi,h,Cf,solverType\n";
 
     for(int i = 0; i < m_swarm.size(); ++i) {
         QVector<double> params = buildTraceParameterVector(m_swarm[i].position);
@@ -1301,7 +1311,8 @@ bool nmCalculationAutoFitPSO::writeSurrogateCandidateCsv(const QString& candidat
              << traceParamAt(params, 2)
              << traceParamAt(params, 3)
              << traceParamAt(params, 5)
-             << traceParamAt(params, 7);
+             << traceParamAt(params, 7)
+             << QString::number(solverType);
         out << cols.join(",") << "\n";
     }
 
@@ -1851,6 +1862,22 @@ bool nmCalculationAutoFitPSO::isSurrogateRunContextSupported(QString* reason) co
         return false;
     }
 
+    NM_SOLVER_MODEL_TYPE solverModelType = dataManager->getSolverModelType();
+    bool isVariablePvt = solverModelType == SMT_Oil_VariablePvt ||
+                         solverModelType == SMT_Water_VariablePvt;
+    bool isSupportedSolverType = solverModelType == SMT_Oil_ConstPvt ||
+                                 solverModelType == SMT_Oil_VariablePvt ||
+                                 solverModelType == SMT_Water_ConstPvt ||
+                                 solverModelType == SMT_Water_VariablePvt;
+
+    if(!isSupportedSolverType) {
+        if(reason) {
+            *reason = QString("solverType=%1 is outside the T1-T4 surrogate model")
+                      .arg(static_cast<int>(solverModelType));
+        }
+        return false;
+    }
+
     // 网格类型 gate：当前代理模型只按 PEBI 网格样本训练。
     if(dataManager->getGridType() != NM_Grid_PEBI) {
         if(reason) *reason = "surrogate model is trained only for PEBI grid cases";
@@ -1898,11 +1925,15 @@ bool nmCalculationAutoFitPSO::isSurrogateRunContextSupported(QString* reason) co
         return false;
     }
 
-    // 参数 gate：代理输入目前只覆盖 k/skin/wellboreC/phi/h，Cf 作为固定背景参数传入。
+    // 参数 gate：变化 PVT 的 T2/T4 允许 Cf 参与拟合；常数 PVT 的 T1/T3 仍固定 Cf。
     // 用户勾选其它参数时，代理无法可靠反映这些参数变化，直接禁用代理筛选。
     QVector<int> allowedParamIndices;
     allowedParamIndices << 0 << 1 << 2 << 3 << 5;
 
+    if(isVariablePvt) {
+        allowedParamIndices << 7;
+    }
+
     for(int i = 0; i < m_enabledParamIndices.size(); ++i) {
         if(!allowedParamIndices.contains(m_enabledParamIndices[i])) {
             if(reason) {
@@ -1919,10 +1950,12 @@ bool nmCalculationAutoFitPSO::isSurrogateRunContextSupported(QString* reason) co
     nmDataReservoir reservoirData = dataManager->getReservoirDataCopy();
     double cf = reservoirData.getCf().getValue().toDouble();
 
-    // Cf gate：当前模型按近似固定 Cf 训练，允许小范围相对偏差。
-    if(!isNearRelative(cf, kSurrogateCfFixed, kSurrogateCfRelTol)) {
+    bool cfSupported = isVariablePvt
+                       ? isInClosedRange(cf, kSurrogateCfMin, kSurrogateCfMax)
+                       : isNearRelative(cf, kSurrogateCfFixed, kSurrogateCfRelTol);
+    if(!cfSupported) {
         if(reason) {
-            *reason = QString("Cf=%1 is outside surrogate fixed-Cf domain").arg(cf, 0, 'g', 10);
+            *reason = QString("Cf=%1 is outside surrogate domain").arg(cf, 0, 'g', 10);
         }
 
         return false;
@@ -2075,7 +2108,16 @@ bool nmCalculationAutoFitPSO::isSurrogateCandidateInDomain(const QVector<double>
         return false;
     }
 
-    if(!isNearRelative(cf, kSurrogateCfFixed, kSurrogateCfRelTol)) {
+    nmDataAnalyzeManager* dataManager = nmDataAnalyzeManager::getCurrentInstance();
+    NM_SOLVER_MODEL_TYPE solverModelType = dataManager
+                                          ? dataManager->getSolverModelType()
+                                          : SMT_Oil_ConstPvt;
+    bool isVariablePvt = solverModelType == SMT_Oil_VariablePvt ||
+                         solverModelType == SMT_Water_VariablePvt;
+    bool cfSupported = isVariablePvt
+                       ? isInClosedRange(cf, kSurrogateCfMin, kSurrogateCfMax)
+                       : isNearRelative(cf, kSurrogateCfFixed, kSurrogateCfRelTol);
+    if(!cfSupported) {
         if(reason) *reason = QString("Cf=%1").arg(cf, 0, 'g', 10);
 
         return false;