fix：修改了轻量级决策脚本中的错误识别逻辑

refactor：优化了轻量级决策脚本中的决策状态生成逻辑

models/uf-rl/rl_model/DQN/uf_decide/run_dqn_decide.py

@@ -13,9 +13,11 @@ UF 超滤 DQN 决策主入口（Inference / Online Assist）
 """
 
 from pathlib import Path
+from dataclasses import replace
+
 
 # ============================================================
-# 1. 导入模块
+# 导入模块
 # ============================================================
 CURRENT_DIR = Path(__file__).resolve().parent
 
@@ -73,22 +75,6 @@ def check_state_bounds(current_state, state_bounds, unit_name):
             "error_feature": f"{unit_name}Per"
         }
 
-    q_UF_min = state_bounds.q_UF_min
-    q_UF_max = state_bounds.q_UF_max
-    if not (q_UF_min <= current_state.q_UF <= q_UF_max):
-        return {
-            "error_time": error_time,
-            "error_feature": f"{unit_name}Per"
-        }
-
-    temp_min = state_bounds.temp_min
-    temp_max = state_bounds.temp_max
-    if not (temp_min <= current_state.temp <= temp_max):
-        return {
-            "error_time": error_time,
-            "error_feature": f"{unit_name}Per"
-        }
-
     return None
 
 
@@ -258,8 +244,8 @@ def run_dqn_decide(
         model_path=model_path,
         seed=0,
     )
-    # 模型决策（不推进真实环境）
 
+    # 模型决策
     decision = decider.decide(current_state)
     action_id = decision["action_id"]
     model_L_s = decision["L_s"]
@@ -273,16 +259,19 @@ def run_dqn_decide(
 # ==============================
 if __name__ == "__main__":
 
-    MODEL_PATH = UF_RL_ROOT / "config_and_model" / "anzhen" / "48h_dqn_model.zip"
-    ENV_CONFIG_PATH = UF_RL_ROOT / "config_and_model" / "anzhen" / "env_config.yaml"
+    # ========== 模型及配置路径指定 ==========
+    IS_TIMES = False # 外部指定变量，表示CEB间隔为时间控制/次数控制，T表示48次bw一次CEB，F表示48h一次CEB
+    MODEL_PATH = UF_RL_ROOT / "config_and_model" / "anzhen" / "48h_dqn_model.zip" # 需根据IS_TIMES变量值指定模型为48h_dqn_model.zip/48times_dqn_model.zip
+    ENV_CONFIG_PATH = UF_RL_ROOT / "config_and_model" / "anzhen" / "env_config.yaml" # 环境配置路径
+
+    # ========== 外部调用输入 ==========
+    # 轻量版，仅输入当前周期起始状态变量
     units_to_run = ["UF1"] # 新增输入：本次调用的机组对象名
     TMP0 = 0.07  # 原始 TMP0
     q_UF = 300 # 进水流量
     temp = 20.0 #进水温度
-    IS_TIMES = False # 新增指定变量，表示CEB间隔为时间控制/次数控制，T表示48次bw一次CEB，F表示48h一次CEB
-
-    current_state = UFState(TMP=TMP0, q_UF=q_UF, temp=temp)
 
+    # ========== 模型及配置加载 ==========
     config_loader = EnvConfigLoader(ENV_CONFIG_PATH)
     config_loader.validate_config()
     config_loader.print_config_summary()
@@ -293,15 +282,24 @@ if __name__ == "__main__":
         reward_params,  # UFRewardParams
         state_bounds  # UFStateBounds
     ) = create_env_params_from_yaml(ENV_CONFIG_PATH)
-
     physics = build_physics(IS_TIMES, phys_params,state_bounds)
 
-    # ========== 异常检查（仅检查，不中断，后续归一化时将异常状态强制归一化至上下限） ==========
+    # ========== 调用模型生成模型指令 ==========
+    # 基于外部输入构建当前状态
+    current_state = replace(
+        uf_state_default,
+        TMP=TMP0,
+        q_UF=q_UF,
+        temp=temp
+    )
+
+    # 状态异常检查（仅检查，不中断，出现异常时后续归一化中将异常状态强制归一化至上下限）
     for unit_name in units_to_run:
         error_result = check_state_bounds(current_state, state_bounds, unit_name)
         if error_result:
             print(f"错误发生时间: {error_result['error_time']}；错误特征量：{error_result['error_feature']}")
 
+    # 模型输出指令
     action_id, model_L_s, model_t_bw_s = run_dqn_decide(
         model_path=MODEL_PATH,
         physics=physics,
@@ -311,6 +309,7 @@ if __name__ == "__main__":
         current_state=current_state,
     ) # 环境实例化，模型加载等功能放在UFDQNDecider类中
 
+    # ========== 生成工厂下发指令 ==========
     current_L_s = 3800
     current_t_bw_s = 40
     model_prev_L_s = 4040
@@ -318,6 +317,7 @@ if __name__ == "__main__":
     L_s, t_bw_s = generate_plc_instructions(action_spec, current_L_s, current_t_bw_s, model_prev_L_s, model_prev_t_bw_s, model_L_s,
                                             model_t_bw_s)  # 获取模型下发指令
 
+    # ========== 生成指令模拟执行结果 ==========
     max_tmp_during_filtration = 0.050176 # 新增工厂数据接口：周期最高/最低跨膜压差，无工厂数据接入时传入None，calc_uf_cycle_metrics()自动获取模拟周期中的跨膜压差最值
     min_tmp_during_filtration = 0.012496
     execution_result = calc_uf_cycle_metrics(current_state, max_tmp_during_filtration, min_tmp_during_filtration, L_s, t_bw_s)