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

"""
run_dqn_decide.py

UF 超滤 DQN 决策主入口（Inference / Online Assist）

职责：
1. 构造物理世界（physics）
2. 实例化决策器（UFDQNDecider）
3. 构造当前工厂状态（observation）
4. 调用模型给出策略建议
5. 生成 PLC 下发指令（限幅 / 限速）
6. 评估该指令在物理模型下的效果（只评估，不下发）
"""

from pathlib import Path

# ============================================================
# 1. 导入模块
# ============================================================
CURRENT_DIR = Path(__file__).resolve().parent

UF_RL_ROOT = CURRENT_DIR.parents[2]     # uf_train  # uf-rl

# ========== 参数 / 物理 ==========
from env.uf_resistance_models_load import load_resistance_models
from env.uf_physics import UFPhysicsModel
from env.env_params import UFState, UFActionSpec
from env.env_config_loader import EnvConfigLoader, create_env_params_from_yaml

# ========== 决策器 ==========
from rl_model.DQN.uf_decide.dqn_decider import UFDQNDecider


def build_physics(IS_TIMES, phys_params):
    """
    构造与训练一致的物理模型（只做一次）
    """
    res_fp, res_bw = load_resistance_models(phys_params)

    physics = UFPhysicsModel(
        phys_params=phys_params,
        resistance_model_fp=res_fp,
        resistance_model_bw=res_bw,
        IS_TIMES = IS_TIMES
    )
    return physics

def 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):
    """
    根据工厂当前值、模型上一轮决策值和模型当前轮决策值，生成PLC指令。

    新增功能：
    1. 处理None值情况：如果模型上一轮值为None，则使用工厂当前值；
       如果工厂当前值也为None，则返回None并提示错误。
    """

    action_spec = action_spec
    adjustment_threshold = 1.0

    # 处理None值情况
    if model_prev_L_s is None:
        if current_L_s is None:
            print("错误: 过滤时长的工厂当前值和模型上一轮值均为None")
            return None, None
        else:
            # 使用工厂当前值作为基准
            effective_current_L = current_L_s
            source_L = "工厂当前值(模型上一轮值为None)"
    else:
        # 模型上一轮值不为None，继续检查工厂当前值
        if current_L_s is None:
            effective_current_L = model_prev_L_s
            source_L = "模型上一轮值(工厂当前值为None)"
        else:
            effective_current_L = model_prev_L_s
            source_L = "模型上一轮值"

    # 对反洗时长进行同样的处理
    if model_prev_t_bw_s is None:
        if current_t_bw_s is None:
            print("错误: 反洗时长的工厂当前值和模型上一轮值均为None")
            return None, None
        else:
            effective_current_t_bw = current_t_bw_s
            source_t_bw = "工厂当前值(模型上一轮值为None)"
    else:
        if current_t_bw_s is None:
            effective_current_t_bw = model_prev_t_bw_s
            source_t_bw = "模型上一轮值(工厂当前值为None)"
        else:
            effective_current_t_bw = model_prev_t_bw_s
            source_t_bw = "模型上一轮值"

    # 检测所有输入值是否在规定范围内（只对非None值进行检查）
    # 工厂当前值检查（警告）
    if current_L_s is not None and not (action_spec.L_min_s <= current_L_s <= action_spec.L_max_s):
        print(f"警告: 当前过滤时长 {current_L_s} 秒不在允许范围内 [{action_spec.L_min_s}, {action_spec.L_max_s}]")
    if current_t_bw_s is not None and not (action_spec.t_bw_min_s <= current_t_bw_s <= action_spec.t_bw_max_s):
        print(f"警告: 当前反洗时长 {current_t_bw_s} 秒不在允许范围内 [{action_spec.t_bw_min_s}, {action_spec.t_bw_max_s}]")

    # 模型上一轮决策值检查（警告）
    if model_prev_L_s is not None and not (action_spec.L_min_s <= model_prev_L_s <= action_spec.L_max_s):
        print(f"警告: 模型上一轮过滤时长 {model_prev_L_s} 秒不在允许范围内 [{action_spec.L_min_s}, {action_spec.L_max_s}]")
    if model_prev_t_bw_s is not None and not (action_spec.t_bw_min_s <= model_prev_t_bw_s <= action_spec.t_bw_max_s):
        print(f"警告: 模型上一轮反洗时长 {model_prev_t_bw_s} 秒不在允许范围内 [{action_spec.t_bw_min_s}, {action_spec.t_bw_max_s}]")

    # 模型当前轮决策值检查
    if model_L_s is None:
        raise ValueError("错误: 决策模型建议的过滤时长不能为None")
    model_L_s = max(action_spec.L_min_s, min(model_L_s, action_spec.L_max_s))

    if model_t_bw_s is None:
        raise ValueError("错误: 决策模型建议的反洗时长不能为None")
    model_t_bw_s = max(action_spec.t_bw_min_s, min(model_t_bw_s, action_spec.t_bw_max_s))


    print(f"过滤时长基准: {source_L}, 值: {effective_current_L}")
    print(f"反洗时长基准: {source_t_bw}, 值: {effective_current_t_bw}")

    # 使用选定的基准值进行计算调整
    L_diff = model_L_s - effective_current_L
    L_adjustment = 0
    if abs(L_diff) >= adjustment_threshold * action_spec.L_step_s:
        if L_diff >= 0:
            L_adjustment = action_spec.L_step_s
        else:
            L_adjustment = -action_spec.L_step_s
    next_L_s = effective_current_L + L_adjustment

    t_bw_diff = model_t_bw_s - effective_current_t_bw
    t_bw_adjustment = 0
    if abs(t_bw_diff) >= adjustment_threshold * action_spec.t_bw_step_s:
        if t_bw_diff >= 0:
            t_bw_adjustment = action_spec.t_bw_step_s
        else:
            t_bw_adjustment = -action_spec.t_bw_step_s
    next_t_bw_s = effective_current_t_bw + t_bw_adjustment

    return next_L_s, next_t_bw_s



def calc_uf_cycle_metrics(current_state, max_tmp_during_filtration, min_tmp_during_filtration, L_s: float, t_bw_s: float):
    """
    计算 UF 超滤系统的核心性能指标

    参数:

        L_s (float): 单次过滤时间（秒）
        t_bw_s (float): 单次反洗时间（秒）

    返回:
        dict: {
            "k_bw_per_ceb": 小周期次数,
            "ton_water_energy_kWh_per_m3": 吨水电耗,
            "recovery": 回收率,
            "net_delivery_rate_m3ph": 净供水率 (m³/h),
            "daily_prod_time_h": 日均产水时间 (小时/天)
            "max_permeability": 全周期最高渗透率(lmh/bar)
        }
    """

    # 模拟该参数下的超级周期
    info, next_state = physics.simulate_one_supercycle(current_state, L_s=L_s, t_bw_s=t_bw_s)

    # 获得模型模拟周期信息
    k_bw_per_ceb = info["k_bw_per_ceb"]
    ton_water_energy_kWh_per_m3 = info["ton_water_energy_kWh_per_m3"]
    recovery = info["recovery"]
    daily_prod_time_h = info["daily_prod_time_h"]

    # 获得模型模拟周期内最高跨膜压差/最低跨膜压差
    if max_tmp_during_filtration is None:
        max_tmp_during_filtration = info["max_TMP_during_filtration"]
    if min_tmp_during_filtration is None:
        min_tmp_during_filtration = info["min_TMP_during_filtration"]

    # 计算最高渗透率
    max_permeability = 100 * current_state.q_UF / (128*40) / min_tmp_during_filtration


    return {
        "k_bw_per_ceb": k_bw_per_ceb,
        "ton_water_energy_kWh_per_m3": ton_water_energy_kWh_per_m3,
        "recovery": recovery,
        "daily_prod_time_h": daily_prod_time_h,
        "max_permeability": max_permeability
    }

def run_dqn_decide(
    model_path: Path,
    physics,
    action_spec,
    reward_params,
    state_bounds,
# -------- 工厂当前值 --------
    current_state: UFState
):
    """
    单轮 DQN 决策流程
    """

    # 构造决策器
    decider = UFDQNDecider(
        physics=physics,
        action_spec=action_spec,
        reward_params=reward_params,
        state_bounds=state_bounds,
        model_path=model_path,
        seed=0,
    )
    # 模型决策（不推进真实环境）

    decision = decider.decide(current_state)
    action_id = decision["action_id"]
    model_L_s = decision["L_s"]
    model_t_bw_s = decision["t_bw_s"]

    return action_id, model_L_s, model_t_bw_s


# ==============================
# 示例调用
# ==============================
if __name__ == "__main__":

    MODEL_PATH = UF_RL_ROOT / "longting" / "48h_dqn_model.zip"
    ENV_CONFIG_PATH = UF_RL_ROOT / "longting" / "env_config.yaml"
    TMP0 = 0.019  # 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)

    config_loader = EnvConfigLoader(ENV_CONFIG_PATH)
    config_loader.validate_config()
    config_loader.print_config_summary()
    (
        uf_state_default,  # UFState默认值
        phys_params,  # UFPhysicsParams
        action_spec,  # UFActionSpec
        reward_params,  # UFRewardParams
        state_bounds  # UFStateBounds
    ) = create_env_params_from_yaml(ENV_CONFIG_PATH)

    physics = build_physics(IS_TIMES, phys_params)

    action_id, model_L_s, model_t_bw_s = run_dqn_decide(
        model_path=MODEL_PATH,
        physics=physics,
        action_spec=action_spec,
        reward_params=reward_params,
        state_bounds=state_bounds,
        current_state=current_state,
    ) # 环境实例化，模型加载等功能放在UFDQNDecider类中

    current_L_s = 3800
    current_t_bw_s = 40
    model_prev_L_s = 4040
    model_prev_t_bw_s = 60
    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

    L_s = 4100
    t_bw_s = 96
    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)
    print("\n===== 单步决策结果 =====")
    print(f"模型选择的动作: {action_id}")
    print(f"模型选择的L_s: {model_L_s} 秒, 模型选择的t_bw_s: {model_t_bw_s} 秒")
    print(f"指令下发的L_s: {L_s} 秒, 指令下发的t_bw_s: {t_bw_s} 秒")
    print(f"指令对应的反洗次数: {execution_result['k_bw_per_ceb']}")
    print(f"指令对应的吨水电耗: {execution_result['ton_water_energy_kWh_per_m3']}")
    print(f"指令对应的回收率: {execution_result['recovery']}")
    print(f"指令对应的日均产水时间: {execution_result['daily_prod_time_h']}")
    print(f"指令对应的最高渗透率: {execution_result['max_permeability']}")