laser_cal/data_clean.py

import os
import json
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from typing import Tuple, List
import warnings
import sys
import frequency_filter as ff
from datetime import datetime
from scipy.optimize import least_squares, differential_evolution
from scipy.signal import savgol_filter


warnings.filterwarnings("ignore", category=FutureWarning)  
plt.rcParams['font.sans-serif'] = ['SimHei']  
plt.rcParams['axes.unicode_minus'] = False  


def result_main():
    
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')
    
    if not os.path.exists(data_folder):
        os.makedirs(data_folder)

    
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    
    if not os.path.exists(csv_file_path):
        pd.DataFrame(columns=['时间', '场站', '风机编号', '采样频率',
                              '叶片1角度偏差', '叶片2角度偏差', '叶片3角度偏差', '相对角度偏差',
                              '叶片1净空值', '叶片2净空值', '叶片3净空值',
                              '叶片1扭转', '叶片2扭转', '叶片3扭转', '平均扭转',
                              '振动幅值', '振动主频']).to_csv(csv_file_path, index=False)

    return csv_file_path


def delete_data(name):

    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')

    
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    df = pd.read_csv(csv_file_path)

    condition = ((df['时间'].astype(str).str.contains(name[0])) &
                 (df['场站'].astype(str).str.contains(name[1])) &
                 (df['风机编号'].astype(str).str.contains(name[2])))

    df = df[~condition]
    
    df.to_csv(csv_file_path, index=False)

    return csv_file_path


def history_data(name):


    time_code = name[0]
    wind_name = name[1]
    turbine_code = name[2]
    
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')

    time_code_cleaned = time_code.replace("-", "").replace(":", "").replace(" ", "")
    json_filename = f"{wind_name}_{turbine_code}_{time_code_cleaned}.json"
    json_file_path = os.path.join(data_folder, json_filename)

    if not os.path.exists(json_file_path):
        raise ValueError("文件不存在")
    with open(json_file_path, 'r') as f:
        data = json.load(f)

    return data


def data_analyse(path: List[str]):


    locate_file = path[0]
    measure_file = path[1]
    noise_reduction = 0.000001  
    min_difference = 1.5  
    angle_cone = float(path[2])
    axial_inclination = float(path[3])
    lift_up_limit = float(path[4])
    group_length = [10000, 20000, 5000]
    return_list = []

    wind_name, turbine_code, time_code, sampling_fq, angle_nan, angle_cen = find_param(locate_file)
    wind_name_1, turbine_code_1, time_code_1, sampling_fq_1, angle_flange, angle_root = find_param(measure_file)

    sampling_fq_1 = sampling_fq_1 * 1000
    sampling_fq = sampling_fq * 1000

    data_nan, data_cen = process_data(locate_file)
    data_flange, data_root = process_data(measure_file)

    if lift_up_limit >= 0.1:
        discrete_values = np.arange(0, 0.101, 0.001)
        condition = data_flange['distance'] > lift_up_limit
        n = condition.sum()
        random_discrete = np.random.choice(discrete_values, size=n)
        data_flange.loc[condition, 'distance'] = lift_up_limit + 3 + random_discrete
    elif np.abs(lift_up_limit) < 0.1:
        pass
    else:
        raise ValueError("lift_up_limit error.")

    start_flange, end_flange, filtered_data_flange = cycle_calculate(data_flange, noise_reduction, min_difference)
    start_root, end_root, filtered_data_root = cycle_calculate(data_root, noise_reduction, min_difference)
    start_nan, end_nan, filtered_data_nan = cycle_calculate(data_nan, noise_reduction, min_difference)
    filtered_data_cen = tower_filter(data_cen, noise_reduction)
    dist_cen = np.mean(filtered_data_cen.iloc[:, 1].tolist())
    filtered_data_cen.iloc[:, 1] = filtered_data_cen.iloc[:, 1] * np.cos(np.deg2rad(angle_cen + axial_inclination))

    tower_dist_flange = ff.tower_cal(filtered_data_flange, start_flange, end_flange, sampling_fq_1)
    tower_dist_root = ff.tower_cal(filtered_data_root, start_root, end_root, sampling_fq_1)
    tower_dist_nan = ff.tower_cal(filtered_data_nan, start_nan, end_nan, sampling_fq)
    lowpass_data, fft_x, fft_y, tower_freq, tower_max = ff.process_fft(filtered_data_cen, sampling_fq)

    result_line_flange, result_scatter_flange, border_rows_flange, cycle_len_flange, min_flange \
        = data_normalize(filtered_data_flange, start_flange, end_flange, group_length[0])
    result_line_root, result_scatter_root, border_rows_root, cycle_len_root, min_root \
        = data_normalize(filtered_data_root, start_root, end_root, group_length[1])
    result_line_nan, result_scatter_nan, border_rows_nan, cycle_len_nan, min_nan \
        = data_normalize(filtered_data_nan, start_nan, end_nan, group_length[2])

    result_avg_flange, result_diff_flange = blade_shape(result_line_flange)
    result_avg_root, result_diff_root = blade_shape(result_line_root)

    border_rows_flange_new, angle_flange_new = coordinate_normalize(border_rows_flange, angle_flange)
    border_rows_nan_new, angle_nan_new = coordinate_normalize(border_rows_nan, angle_nan)

    flange_ava = pd.concat([df['distance'] for df in border_rows_flange_new]).mean(numeric_only=True).mean()
    root_ava = pd.concat([df['distance'] for df in border_rows_root]).mean(numeric_only=True).mean()

    d_radius = np.abs((flange_ava * np.cos(np.deg2rad(angle_flange_new))
               - root_ava * np.cos(np.deg2rad(angle_root))) * np.sin(np.deg2rad(axial_inclination))
               + (flange_ava * np.sin(np.deg2rad(angle_flange_new))
               - root_ava * np.sin(np.deg2rad(angle_root))) * np.cos(np.deg2rad(axial_inclination)))

    flange_root_dist = np.sqrt(flange_ava ** 2 + root_ava ** 2 - 2 * flange_ava * root_ava * np.cos(np.deg2rad(angle_flange_new - angle_root)))

    blade_axis = blade_axis_cal(filtered_data_flange, start_flange, end_flange,
                                   angle_flange + angle_cone + axial_inclination)
    blade_axis_new, angle_flange_new = flange_coordinate_normalize(blade_axis, angle_flange)

    flange_r = radius_cal(border_rows_flange_new, angle_flange_new, dist_cen, angle_cen, axial_inclination, angle_cone)
    root_r = radius_cal(border_rows_root, angle_root, dist_cen, angle_cen, axial_inclination, angle_cone)
    nan_r = radius_cal(border_rows_nan_new, angle_nan_new, dist_cen, angle_cen, axial_inclination, angle_cone)

    if np.abs((root_r - flange_r) - d_radius) > 0.5:
        raise ValueError("Radius err1.")

    if np.abs(flange_root_dist - d_radius) > 0.5:
        raise ValueError("Radius err2.")

    blade_axis_new["中心y"] = blade_axis_new["中心y"] - (flange_ava - root_ava)

    aero_dist_flange, v_speed_flange, cen_blade_flange = (
        blade_angle_aero_dist(border_rows_flange, flange_r, cycle_len_flange, tower_dist_flange, angle_flange_new))
    aero_dist_root, v_speed_root, cen_blade_root = (
        blade_angle_aero_dist(border_rows_root, root_r, cycle_len_root, tower_dist_root, angle_root))
    aero_dist_nan, v_speed_nan, cen_blade_nan = (
        blade_angle_aero_dist(border_rows_nan_new, nan_r, cycle_len_nan, tower_dist_nan, angle_nan_new))
    pitch_angle_root, v_speed_root = (
        blade_angle(border_rows_root, blade_axis_new, root_r, cycle_len_root, angle_root + axial_inclination))

    blade_axis_new["中心y"] = blade_axis_new["中心y"]*np.cos(np.deg2rad(angle_root + angle_cone + axial_inclination))
    
    cen_blade_flange_array = np.array(cen_blade_flange)
    cen_blade_nan_array = np.array(cen_blade_nan)
    min_flange_array = np.array(min_flange)
    min_nan_array = np.array(min_nan)
    abs_diff = np.abs(cen_blade_flange_array - min_flange_array)
    abs_diff_nan = np.abs(cen_blade_nan_array - min_nan_array)
    blade_dist_flange = abs_diff * np.cos(np.deg2rad(angle_flange_new))
    blade_dist_nan = abs_diff_nan * np.cos(np.deg2rad(angle_nan_new))
    blade_dist_flange.tolist()
    blade_dist_nan.tolist()


    dist_distribute_nan = blade_dist_distribute_cal(filtered_data_nan, start_nan, end_nan,
                                                tower_dist_nan, angle_nan_new, blade_dist_nan)
    dist_distribute = [df.round(5) for df in dist_distribute_nan]

    
    min_values = []
    min_keys = []
    max_values = []
    max_keys = []
    mean_values = []
    for df in dist_distribute:
        second_col_min = df[df.columns[1]].min()
        second_col_max = df[df.columns[1]].max()
        min_row = df[df[df.columns[1]] == second_col_min]
        max_row = df[df[df.columns[1]] == second_col_max]
        min_values.append(round(second_col_min, 2))
        min_keys.append(round(min_row.iloc[0][df.columns[0]], 2))
        max_values.append(round(second_col_max, 2))
        max_keys.append(round(max_row.iloc[0][df.columns[0]], 2))

    for i in range(3):
        mean_values.append(round((max_values[i] + min_values[i]) / 2, 2))

    for df in result_line_flange:
        first_column = df.iloc[:, 0]
        sec_column = df.iloc[:, 1]
        df.iloc[:, 0] = first_column * v_speed_flange
        min_time = df.iloc[:, 0].min()
        df.iloc[:, 0] -= min_time
        df.iloc[:, 1] = sec_column * np.cos(np.deg2rad(angle_flange_new + angle_cone + axial_inclination))

    for df in result_line_root:
        first_column = df.iloc[:, 0]
        sec_column = df.iloc[:, 1]
        df.iloc[:, 0] = first_column * v_speed_root
        min_time = df.iloc[:, 0].min()
        df.iloc[:, 0] -= min_time
        df.iloc[:, 1] = sec_column * np.cos(np.deg2rad(angle_root + angle_cone + axial_inclination))

    avg_flange = result_avg_flange.iloc[:, 0]
    result_avg_flange.iloc[:, 0] = avg_flange * v_speed_flange
    avg_root = result_avg_root.iloc[:, 0]
    result_avg_root.iloc[:, 0] = avg_root * v_speed_root

    pitch_angle_flange = [0, 0, 0]
    twist_1 = round(np.abs(pitch_angle_root[0] - pitch_angle_flange[0]), 2)
    twist_2 = round(np.abs(pitch_angle_root[1] - pitch_angle_flange[1]), 2)
    twist_3 = round(np.abs(pitch_angle_root[2] - pitch_angle_flange[2]), 2)
    twist_avg = round((twist_1 + twist_2 + twist_3) / 3, 2)

    sampling_num = int(0.015 * sampling_fq_1)
    data_flange.iloc[:, 0] = data_flange.iloc[:, 0] / 5000000
    data_root.iloc[:, 0] = data_root.iloc[:, 0] / 5000000
    lowpass_data.iloc[:, 0] = lowpass_data.iloc[:, 0] / 5000000


    return_list.append(str(time_code))
    return_list.append(str(wind_name))
    return_list.append(str(turbine_code))
    return_list.append(sampling_fq_1)
    return_list.append(pitch_angle_root[0])
    return_list.append(pitch_angle_root[1])
    return_list.append(pitch_angle_root[2])
    return_list.append(pitch_angle_root[3])
    return_list.append(mean_values[0])
    return_list.append(mean_values[1])
    return_list.append(mean_values[2])
    return_list.append(twist_1)
    return_list.append(twist_2)
    return_list.append(twist_3)
    return_list.append(twist_avg)
    return_list.append(tower_max)
    return_list.append(tower_freq)


    
    df_new_row = pd.DataFrame([return_list],
                              columns=['时间', '场站', '风机编号', '采样频率',
                                       '叶片1角度偏差', '叶片2角度偏差', '叶片3角度偏差', '相对角度偏差',
                                       '叶片1净空值', '叶片2净空值', '叶片3净空值',
                                       '叶片1扭转', '叶片2扭转', '叶片3扭转', '平均扭转',
                                       '振动幅值', '振动主频'])

    json_output = {
        'original_plot': {
            'blade_tip': {
                'xdata': data_flange.iloc[:, 0].tolist()[::sampling_num],
                'ydata': data_flange.iloc[:, 1].tolist()[::sampling_num]
            },
            'blade_root': {
                'xdata': data_root.iloc[:, 0].tolist()[::sampling_num],
                'ydata': data_root.iloc[:, 1].tolist()[::sampling_num]
            }
        },
        'fft_plot': {
            'lowpass': {
                'xdata': lowpass_data['time'].tolist()[::sampling_num],
                'ydata': lowpass_data['distance_filtered'].tolist()[::sampling_num],
                'xmax': max(lowpass_data['time'].tolist()),
                'xmin': min(lowpass_data['time'].tolist()),
                'ymax': max(lowpass_data['distance_filtered'].tolist()) + 0.02,
                'ymin': min(lowpass_data['distance_filtered'].tolist()) - 0.02
            },
            'fft': {
                'xdata': fft_x,
                'ydata': fft_y,
                'xmax': max(fft_x),
                'xmin': min(fft_x),
                'ymax': max(fft_y) + 0.02,
                'ymin': 0
            }
        },
        'blade_tip': {
            'first_blade': {
                'xdata': result_line_flange[0].iloc[:, 0].tolist(),
                'ydata': result_line_flange[0].iloc[:, 1].tolist()
            },
            'second_blade': {
                'xdata': result_line_flange[1].iloc[:, 0].tolist(),
                'ydata': result_line_flange[1].iloc[:, 1].tolist()
            },
            'third_blade': {
                'xdata': result_line_flange[2].iloc[:, 0].tolist(),
                'ydata': result_line_flange[2].iloc[:, 1].tolist()
            },
            'avg_blade': {
                'xdata': result_avg_flange.iloc[:, 0].tolist(),
                'ydata': result_avg_flange.iloc[:, 1].tolist()
            }
        },
        'blade_root': {
            'first_blade': {
                'xdata': result_line_root[0].iloc[:, 0].tolist(),
                'ydata': result_line_root[0].iloc[:, 1].tolist()
            },
            'second_blade': {
                'xdata': result_line_root[1].iloc[:, 0].tolist(),
                'ydata': result_line_root[1].iloc[:, 1].tolist()
            },
            'third_blade': {
                'xdata': result_line_root[2].iloc[:, 0].tolist(),
                'ydata': result_line_root[2].iloc[:, 1].tolist()
            },
            'avg_blade': {
                'xdata': result_avg_root.iloc[:, 0].tolist(),
                'ydata': result_avg_root.iloc[:, 1].tolist()
            }
        },
        'dist_distribution': {
            'first_blade': {
                'xdata': dist_distribute[0].iloc[:, 0].tolist(),
                'ydata': dist_distribute[0].iloc[:, 1].tolist()
            },
            'second_blade': {
                'xdata': dist_distribute[1].iloc[:, 0].tolist(),
                'ydata': dist_distribute[1].iloc[:, 1].tolist()
            },
            'third_blade': {
                'xdata': dist_distribute[2].iloc[:, 0].tolist(),
                'ydata': dist_distribute[2].iloc[:, 1].tolist()
            }
        },
        'analyse_table': {
            'pitch_angle_diff': {
                'blade_1': pitch_angle_root[0],
                'blade_2': pitch_angle_root[1],
                'blade_3': pitch_angle_root[2],
                'blade_relate': pitch_angle_root[3]
            },
            'aero_dist': {
                'first_blade': {
                    'x_min': min_keys[0],
                    'y_min': min_values[0],
                    'x_max': max_keys[0],
                    'y_max': max_values[0],
                    'y_diff': np.abs(max_values[0] - min_values[0]),
                    'y_ava': mean_values[0]
                },
                'second_blade': {
                    'x_min': min_keys[1],
                    'y_min': min_values[1],
                    'x_max': max_keys[1],
                    'y_max': max_values[1],
                    'y_diff': np.abs(max_values[1] - min_values[1]),
                    'y_ava': mean_values[1]
                },
                'third_blade': {
                    'x_min': min_keys[2],
                    'y_min': min_values[2],
                    'x_max': max_keys[2],
                    'y_max': max_values[2],
                    'y_diff': np.abs(max_values[2] - min_values[2]),
                    'y_ava': mean_values[2]
                }
            },
            'blade_twist': {
                'blade_1': twist_1,
                'blade_2': twist_2,
                'blade_3': twist_3,
                'blade_avg': twist_avg
            },
            'tower_vibration': {
                'max_vibration': tower_max,
                'main_vibration_freq': tower_freq
            }
        }
    }

    
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')
    
    if not os.path.exists(data_folder):
        os.makedirs(data_folder)

    
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    
    if not os.path.exists(csv_file_path):
        pd.DataFrame(columns=['时间', '场站', '风机编号', '采样频率',
                              '叶片1角度偏差', '叶片2角度偏差', '叶片3角度偏差', '相对角度偏差',
                              '叶片1净空值', '叶片2净空值', '叶片3净空值',
                              '叶片1扭转', '叶片2扭转', '叶片3扭转', '平均扭转',
                              '振动幅值', '振动主频']).to_csv(csv_file_path, index=False)

    df_new_row.to_csv(csv_file_path, mode='a', header=False, index=False)

    time_code_cleaned = time_code.replace("-", "").replace(":", "").replace(" ", "")
    json_filename = f"{wind_name}_{turbine_code}_{time_code_cleaned}.json"
    json_file_path = os.path.join(data_folder, json_filename)
    with open(json_file_path, 'w') as json_file:
        json.dump(json_output, json_file, indent=4)

    return json_output


def process_data(file_path):

    
    data = pd.read_csv(file_path, usecols=[1, 3, 4, 8, 9], header=None, engine='c')
    data = data.head(int(len(data) * 0.95))

    
    max_value = data.iloc[:, 0].max()
    max_index = data.iloc[:, 0].idxmax()
    min_index = data.iloc[:, 0].idxmin()

    
    if min_index == max_index + 1:
        
        data.iloc[min_index:, 0] += max_value

    
    last_time = data.iloc[-1, 0]
    first_time = data.iloc[0, 0]
    data = data[data.iloc[:, 0] >= first_time]
    data = data[data.iloc[:, 0] <= last_time]
    data.reset_index(drop=True, inplace=True)
    
    min_time = data.iloc[:, 0].min()
    data.iloc[:, 0] -= min_time

    
    data_1 = data.iloc[:, [0, 1, 2]]
    data_2 = data.iloc[:, [0, 3, 4]]


    data_1.columns = ['time', 'distance', 'grey']
    data_2.columns = ['time', 'distance', 'grey']

    return data_1, data_2


def tower_filter(data_group: pd.DataFrame, noise_threshold: float):


    distance_counts = data_group['distance'].value_counts(normalize=True)
    noise_distance_threshold = distance_counts[distance_counts < noise_threshold].index
    noise_indices = data_group[data_group['distance'].isin(noise_distance_threshold)].index
    data_group.loc[noise_indices, 'distance'] = np.nan

    
    top_5_distances = distance_counts.head(5).index
    mean_values = data_group[data_group['distance'].isin(top_5_distances)]['distance'].mean()
    data_group.loc[(data_group['distance'] < mean_values - 20) | (
            data_group['distance'] > mean_values * 1.1), 'distance'] = np.nan

    
    data_group['distance'] = data_group['distance'].fillna(method='ffill')
    filtered_data = data_group

    return filtered_data


def cycle_calculate(data_group: pd.DataFrame, noise_threshold: float, min_distance: float):

    
    distance_counts = data_group['distance'].value_counts(normalize=True)
    noise_distance_threshold = distance_counts[distance_counts < noise_threshold].index
    noise_indices = data_group[data_group['distance'].isin(noise_distance_threshold)].index
    data_group.loc[noise_indices, 'distance'] = np.nan

    if 0 in distance_counts.nlargest(3).index:
        pass
    else:
        # 选择频率最大的5个值
        top_5_distances = distance_counts.head(5).index
        mean_values = data_group[data_group['distance'].isin(top_5_distances)]['distance'].mean()
        data_group.loc[(data_group['distance'] < mean_values - 30) | (
                data_group['distance'] > mean_values * 1.1), 'distance'] = np.nan
    
    data_group['distance'] = data_group['distance'].fillna(method='ffill')
    filtered_data = data_group
    
    filtered_data['distance_diff'] = filtered_data['distance'].diff()
    large_diff_indices = filtered_data[filtered_data['distance_diff'] > min_distance].index
    small_diff_indices = filtered_data[filtered_data['distance_diff'] < -min_distance].index
    filtered_data = filtered_data.drop(columns=['distance_diff'])

    start_points = pd.DataFrame()
    end_points = pd.DataFrame()

    
    for idx in large_diff_indices:
        
        current_distance = filtered_data.loc[idx, 'distance']

        next_rows_large = filtered_data.loc[idx - 500: idx - 1]

        
        if next_rows_large['distance'].le(current_distance - min_distance).all():
            
            end_points = pd.concat([end_points, filtered_data.loc[[idx - 1]]])

    for idx in small_diff_indices:
        
        current_distance = filtered_data.loc[idx - 1, 'distance']

        next_rows_small = filtered_data.iloc[idx: idx + 500]

        
        if next_rows_small['distance'].le(current_distance - min_distance).all():
            
            start_points = pd.concat([start_points, filtered_data.loc[[idx]]])
            
    if 0 in distance_counts.nlargest(3).index:
        end_points, start_points = start_points, end_points

    if end_points.iloc[0, 0] < start_points.iloc[0, 0]:
        end_points = end_points.drop(end_points.index[0])
    if end_points.iloc[-1, 0] < start_points.iloc[-1, 0]:
        start_points = start_points.drop(start_points.index[-1])
    else:
        pass

    return start_points, end_points, filtered_data


def data_normalize(data_group: pd.DataFrame, start_points: pd.DataFrame, end_points: pd.DataFrame, group_len: int) \
        -> Tuple[List[pd.DataFrame], List[pd.DataFrame], List[pd.DataFrame], int, list]:


    combined_df_sorted = pd.concat([start_points, end_points]).sort_values(by='time')
    
    if combined_df_sorted.iloc[0].equals(end_points.iloc[0]):
        combined_df_sorted = combined_df_sorted.iloc[1:]
    if combined_df_sorted.iloc[-1].equals(start_points.iloc[-1]):
        combined_df_sorted = combined_df_sorted.iloc[:-1]
    combined_df_sorted.reset_index(drop=True, inplace=True)

    
    start_times = combined_df_sorted['time'].tolist()

    normalize_cycle = start_times[1] - start_times[0]
    full_cycle = int((start_times[2] - start_times[0]) * 3)
    turbines = [pd.DataFrame() for _ in range(3)]

    
    for i in range(0, len(start_times), 2):

        
        start_time = start_times[i]
        end_time = start_times[i + 1]

        
        segment = data_group[(data_group['time'] > start_time) & (data_group['time'] <= end_time)]

        if segment is None:
            pass
        else:
            
            ratio = (end_time - start_time) / normalize_cycle
            segment.loc[:, 'time'] = (segment['time'] - start_time) / ratio

            
            turbines[i % 3] = pd.concat([turbines[i % 3], segment])

    
    turbines_processed = []
    turbines_scattered = []
    min_list = []
    sd_time = [-1, -1]
    time_list = list(range(0, normalize_cycle, group_len))

    for turbine in turbines:
        
        turbine_sorted = turbine.sort_values(by='time').reset_index(drop=True)

        grey_start_index = int(len(turbine_sorted) * 0.1)
        grey_end_index = int(len(turbine_sorted) * 0.9)
        subset_grey = turbine_sorted[grey_start_index:grey_end_index]
        mean_grey = subset_grey['grey'].mean() * 0.8
        turbine_sorted = turbine_sorted[turbine_sorted['grey'] > mean_grey]
        
        first_time = turbine_sorted['time'].iloc[0]

        
        bins = list(range(int(first_time), int(turbine_sorted['time'].max()), group_len))
        
        
        grouped = turbine_sorted.groupby(pd.cut(turbine_sorted['time'], bins=bins, right=False))

        
        processed_df = pd.DataFrame()
        scattered_df = pd.DataFrame()
        mean_points = []
        diff_points = []

        
        for _, group in grouped:
            
            quantile_5 = group['distance'].quantile(0.05)
            quantile_95 = group['distance'].quantile(0.95)
            filtered_group = group[(group['distance'] > quantile_5) & (group['distance'] < quantile_95)]

            
            mean_point = filtered_group['distance'].mean()
            mean_points.append(mean_point)

        
        for i in range(len(mean_points) - 1):
            diff = abs(mean_points[i + 1] - mean_points[i])
            diff_points.append(diff)

        start_index = int(len(diff_points) * 0.05)
        end_index = int(len(diff_points) * 0.95)
        subset1 = diff_points[start_index:end_index]
        sdr_diff = np.max(subset1) * 1.1
        min_list.append(min(mean_points))

        
        first_index = np.where(diff_points < sdr_diff)[0][0]
        last_index = np.where(diff_points < sdr_diff)[0][-1]

        for index, (bin, group) in enumerate(grouped):

            
            quantile_5 = group['distance'].quantile(0.05)
            quantile_95 = group['distance'].quantile(0.95)
            filtered_group = group[(group['distance'] > quantile_5) & (group['distance'] < quantile_95)]

            if first_index <= index < last_index:  

                
                mid_point = filtered_group.mean()
                
                mid_point_df = pd.DataFrame([mid_point])
                mid_point_df.iloc[0, 0] = time_list[index]
                processed_df = pd.concat([processed_df, mid_point_df], ignore_index=True)
                scattered_df = pd.concat([scattered_df, filtered_group], ignore_index=True)
            else:
                pass

        
        min_time = processed_df['time'].min()
        max_time = processed_df['time'].max()

        if sd_time == [-1, -1]:
            sd_time = [min_time, max_time]
        elif sd_time[0] < min_time:
            sd_time[0] = min_time
        elif sd_time[1] > max_time:
            sd_time[1] = max_time

        
        turbines_processed.append(processed_df)
        turbines_scattered.append(scattered_df)

    border_rows = []
    for i, turbine in enumerate(turbines_processed):
        
        closest_index_0 = (turbine['time'] - sd_time[0]).abs().idxmin()
        turbine.at[closest_index_0, 'time'] = sd_time[0]
        sd_time_row_0 = turbine.loc[closest_index_0]

        
        closest_index_1 = (turbine['time'] - sd_time[1]).abs().idxmin()
        turbine.at[closest_index_1, 'time'] = sd_time[1]
        sd_time_row_1 = turbine.loc[closest_index_1]

        
        turbines_processed[i] = turbine.iloc[closest_index_0:closest_index_1 + 1].reset_index(drop=True)

        sd_time_rows_turbine = pd.concat([pd.DataFrame([sd_time_row_0]), pd.DataFrame([sd_time_row_1])]
                                         , ignore_index=True)
        border_rows.append(sd_time_rows_turbine)


    return turbines_processed, turbines_scattered, border_rows, full_cycle, min_list


def blade_shape(turbines_processed: List[pd.DataFrame]):


    row_counts = [df.shape[0] for df in turbines_processed]
    num_rows = min(row_counts)

    
    turbine_avg = pd.DataFrame(index=range(num_rows), columns=['time', 'distance'])
    turbine_diff = [pd.DataFrame(index=range(num_rows), columns=['time', 'distance']) for _ in turbines_processed]

    
    for i in range(num_rows):
        distances = [df.loc[i, 'distance'] for df in turbines_processed]  
        avg_distance = sum(distances) / len(distances)  
        time_value = turbines_processed[0].loc[i, 'time']  
        turbine_avg.loc[i, 'time'] = time_value
        turbine_avg.loc[i, 'distance'] = avg_distance

        for j in range(len(distances)):
            distances[j] = distances[j] - avg_distance
            turbine_diff[j].loc[i, 'time'] = time_value
            turbine_diff[j].loc[i, 'distance'] = distances[j]

    return turbine_avg, turbine_diff


def coordinate_normalize(tip_border_rows: List[pd.DataFrame], tip_angle):

    tip_angle1 = np.deg2rad(tip_angle)
    tip_angle_list = []
    for turbine in tip_border_rows:
        tip_angle_cal0 = ((np.sin(tip_angle1) * turbine['distance'] - 0.07608) /
                             (np.cos(tip_angle1) * turbine['distance']))
        tip_angle_cal = np.arctan(tip_angle_cal0)
        turbine['distance'] = (turbine['distance'] ** 2 + 0.0057881664 -
                               0.15216 * turbine['distance'] * np.sin(tip_angle1)) ** 0.5

        tip_angle_list.append(tip_angle_cal)

    tip_angle_new = float(np.mean(tip_angle_list))
    tip_angle_new1 = np.rad2deg(tip_angle_new)

    return tip_border_rows, tip_angle_new1


def flange_coordinate_normalize(flange_cen_row: pd.DataFrame, flange_angle):

    flange_angle1 = np.deg2rad(flange_angle)

    flange_angle_cal0 = ((np.sin(flange_angle1) * flange_cen_row['中心y'] - 0.07608) /
                         (np.cos(flange_angle1) * flange_cen_row['中心y']))
    flange_angle_cal = np.arctan(flange_angle_cal0)

    flange_cen_row['中心y'] = (flange_cen_row['中心y'] ** 2 + 0.0057881664 -
                                     0.15216 * flange_cen_row['中心y'] * np.sin(flange_angle1)) ** 0.5

    flange_angle_new = float(flange_angle_cal)
    flange_angle_new1 = np.rad2deg(flange_angle_new)

    return flange_cen_row, flange_angle_new1


def blade_axis_cal(data_group: pd.DataFrame, start_points: pd.DataFrame, end_points: pd.DataFrame, horizon_angle: float) \
        -> pd.DataFrame:

    def fit_circle(df, v_bounds=(2, 10), top_k=5, prefilter=True):

        def smooth_savgol(y, window_length=101, polyorder=3):
            wl = min(window_length, len(y) if len(y) % 2 == 1 else len(y) - 1)
            if wl < 3:
                return y
            if wl % 2 == 0:
                wl -= 1
            return savgol_filter(y, wl, polyorder)

        t = np.asarray(df['time'])
        d_raw = np.asarray(df['distance'])

        # ---------- 平滑 ----------
        d_smooth = smooth_savgol(d_raw, window_length=101, polyorder=3) if prefilter else d_raw

        bounds = [v_bounds, (0, 5), (200, 201), (1, 3)]

        def residuals_sq(params):
            v, xc, yc, R = params
            if v <= 0 or R <= 0:
                return 1e6 * np.ones_like(t)
            x = v * t
            return (x - xc) ** 2 + (d_smooth - yc) ** 2 - R ** 2

        def objective_mean_sq(params):
            res = residuals_sq(params)
            return np.mean(res ** 2)

        # ---------- 差分进化 ----------
        result = differential_evolution(
            objective_mean_sq,
            bounds,
            strategy='rand2bin',
            mutation=(0.8, 1.2),
            recombination=0.8,
            popsize=30,
            maxiter=1000,
            polish=False,
            seed=42,
            workers=1
        )

        # 多候选点精修
        pop = result.population
        energies = result.population_energies
        idx = np.argsort(energies)[:top_k]
        candidates = pop[idx]

        best_rmse = np.inf
        best_result = None

        for cand in candidates:
            res = least_squares(
                residuals_sq,
                x0=cand,
                bounds=([v_bounds[0], -np.inf, -np.inf, 1e-6],
                        [v_bounds[1], np.inf, np.inf, np.inf]),
                method='trf',
                loss='linear',
                max_nfev=50000,
                xtol=1e-12,
                ftol=1e-12,
                gtol=1e-12
            )
            v_opt, xc_opt, yc_opt, R_opt = res.x
            x_all = v_opt * t
            Ri_all = np.sqrt((x_all - xc_opt) ** 2 + (d_smooth - yc_opt) ** 2)
            geo_rmse = np.sqrt(np.mean((Ri_all - R_opt) ** 2))

            if geo_rmse < best_rmse:
                best_rmse = geo_rmse
                best_result = [v_opt, xc_opt, yc_opt, R_opt, geo_rmse]

        result_df = pd.DataFrame([best_result],
                                 columns=['旋转半径', '中心x', '中心y', '圆半径', '几何RMSE'])  # 旋转半径本身为测量点线速度
        return result_df

    group_len = 10000
    combined_df_sorted = pd.concat([start_points, end_points]).sort_values(by='time')
    # 检查排序后的数据从start开始，end结束
    if combined_df_sorted.iloc[0].equals(end_points.iloc[0]):
        combined_df_sorted = combined_df_sorted.iloc[1:]
    if combined_df_sorted.iloc[-1].equals(start_points.iloc[-1]):
        combined_df_sorted = combined_df_sorted.iloc[:-1]
    combined_df_sorted.reset_index(drop=True, inplace=True)

    # 将 start_points 中的时间点转换为列表
    start_times = combined_df_sorted['time'].tolist()

    data_group['distance'] = data_group['distance'] * np.cos(np.deg2rad(horizon_angle))
    normalize_cycle = start_times[1] - start_times[0]
    full_cycle = int((start_times[2] - start_times[0]) * 3)
    angle_speed = (np.pi / full_cycle) * 5000000
    turbines = [pd.DataFrame() for _ in range(3)]

    for i in range(0, len(start_times), 2):


        start_time = start_times[i]
        end_time = start_times[i + 1]
        segment = data_group[(data_group['time'] > start_time) & (data_group['time'] <= end_time)]
        if segment is None or segment.empty:
            raise ValueError("Segment is empty")

        segment = segment.copy()
        ratio = (end_time - start_time) / normalize_cycle
        segment.loc[:, 'time'] = (segment['time'] - start_time) / ratio

        turbines[i % 3] = pd.concat([turbines[i % 3], segment])

    turbines_processed = []
    turbines_scattered = []
    turbines_result = []
    result_df = pd.DataFrame()
    time_list = list(range(0, normalize_cycle, group_len))
    for turbine in turbines:
        # 按时间排序
        turbine_sorted = turbine.sort_values(by='time').reset_index(drop=True)

        # 找到time列的第一个值
        first_time = turbine_sorted['time'].iloc[0]

        # 分组，时间列每1000为一组（每40个时间点一组）
        bins = list(range(int(first_time), int(turbine_sorted['time'].max()), group_len))
        grouped = turbine_sorted.groupby(pd.cut(turbine_sorted['time'], bins=bins, right=False))

        process_df = pd.DataFrame()
        for index, (bin, group) in enumerate(grouped):

            mid_point = group.mean()
            # 将中点转换为 DataFrame 并添加到处理后的 DataFrame 中
            mid_point_df = pd.DataFrame([mid_point])
            mid_point_df.iloc[0, 0] = time_list[index]
            process_df = pd.concat([process_df, mid_point_df], ignore_index=True)

        process_df['time'] = process_df['time'] / 5000000
        lower_bound = process_df['time'].quantile(0.2)
        upper_bound = process_df['time'].quantile(0.7)
        processed_df = process_df[(process_df['time'] >= lower_bound) & (process_df['time'] <= upper_bound)]
        blade_cen_est = fit_circle(processed_df)

        turbines_processed.append(processed_df)
        turbines_scattered.append(turbine)
        result_df = pd.concat([result_df, blade_cen_est], ignore_index=True)
        if blade_cen_est['几何RMSE'].iloc[0] >= 0.1:
            raise ValueError("叶片几何误差过大")

    result_df = result_df.mean(numeric_only=True).to_frame().T
    result_df["中心y"] = result_df["中心y"] / np.cos(np.deg2rad(horizon_angle))

    return result_df



def radius_cal(border_rows, meas_angle, cen_dist, cen_angle, angle_main, angle_rotate):

    aero_dist = (pd.concat([df['distance'] for df in border_rows]).mean())
    radius = np.abs(aero_dist * np.sin(np.deg2rad(meas_angle - angle_main))
                    - cen_dist * np.sin(np.deg2rad(cen_angle - angle_main)))
    return radius


def blade_angle_aero_dist(border_rows: List[pd.DataFrame], radius: float, full_cycle: int,
                                   tower_dist: float, v_angle: float):

    v_speed = 2 * np.pi * radius / full_cycle  # 叶片线速度m/(1计时器单位）
    aero_dist_list = []
    cen_blade = []
    for turbine in border_rows:

        mean_col2 = (turbine.iloc[1, 1] + turbine.iloc[0, 1]) / 2
        aero_dist = abs(mean_col2 - tower_dist) * np.cos(np.deg2rad(v_angle))

        aero_dist_list.append(aero_dist)
        cen_blade.append(mean_col2)

    aero_dist_list.append(np.mean(aero_dist_list))
    aero_dist_list = [round(num, 2) for num in aero_dist_list]

    return aero_dist_list, v_speed, cen_blade

def blade_angle(border_rows: List[pd.DataFrame], cen_data: pd.DataFrame, radius: float, full_cycle: int,
                                   v_angle: float):

    v_speed = 2 * np.pi * radius / full_cycle

    values = []
    for df in border_rows:
        if df.shape[0] >= 2 and df.shape[1] >= 2:
            values.append(df.iloc[0, 1])
            values.append(df.iloc[1, 1])

    mean_value = sum(values) / len(values) if values else float('nan')

    if np.abs(cen_data['中心y'].iloc[0] - mean_value) > 0.3:
        cen_data['中心y'].iloc[0] = mean_value
    if cen_data['中心x'].iloc[0] > 1.5:
        cen_data['中心x'].iloc[0] = 1.5
    if cen_data['中心x'].iloc[0] < 0.75:
        cen_data['中心x'].iloc[0] = 0.75

    pitch_angle_list = []
    for idx, turbine in enumerate(border_rows, start=1):

        diff_time = np.abs((turbine.iloc[0, 0] - turbine.iloc[1, 0]) * 0.66 * v_speed)
        diff_len = np.abs((cen_data['中心y'].iloc[0] - turbine.iloc[1, 1]) * np.cos(np.deg2rad(v_angle)))
        pitch_angle = np.degrees(np.arctan(diff_len / diff_time))
        pitch_angle_list.append(pitch_angle)

    pitch_mean = np.mean(pitch_angle_list)
    pitch_angle_list = [angle - pitch_mean for angle in pitch_angle_list]
    pitch_angle_list.append(max(pitch_angle_list) - min(pitch_angle_list))
    pitch_angle_list = [round(num, 2) for num in pitch_angle_list]

    return pitch_angle_list, v_speed


def find_param(path: str):


    path = path.replace('\\', '/')
    last_slash_index = path.rfind('/')
    result = path[last_slash_index + 1:]

    underscore_indices = []
    start = 0
    while True:
        index = result.find('_', start)
        if index == -1:
            break
        underscore_indices.append(index)
        start = index + 1

    wind_name = result[: underscore_indices[0]]
    turbine_code = result[underscore_indices[0] + 1: underscore_indices[1]]
    time_code = result[underscore_indices[1] + 1: underscore_indices[2]]
    sampling_fq = int(result[underscore_indices[2] + 1: underscore_indices[3]])
    tunnel_1 = float(result[underscore_indices[3] + 1: underscore_indices[4]])
    tunnel_2 = float(result[underscore_indices[4] + 1: -4])

    dt = datetime.strptime(time_code, "%Y%m%d%H%M%S")
    standard_time_str = dt.strftime("%Y-%m-%d %H:%M:%S")

    return wind_name, turbine_code, standard_time_str, sampling_fq, tunnel_1, tunnel_2


def blade_dist_distribute_cal(data_group: pd.DataFrame, start_points: pd.DataFrame, end_points: pd.DataFrame,
                              tower_dist: float, v_angle: float, blade_cen_dist: list):


    combined_df_sorted = pd.concat([start_points, end_points]).sort_values(by='time')
    
    if combined_df_sorted.iloc[0].equals(end_points.iloc[0]):
        combined_df_sorted = combined_df_sorted.iloc[1:]
    if combined_df_sorted.iloc[-1].equals(start_points.iloc[-1]):
        combined_df_sorted = combined_df_sorted.iloc[:-1]
    combined_df_sorted.reset_index(drop=True, inplace=True)

    
    start_times = combined_df_sorted['time'].tolist()

    normalize_cycle = start_times[1] - start_times[0]
    tower_clearance = [pd.DataFrame() for _ in range(3)]

    
    for i in range(0, len(start_times) - 2, 2):
        
        start_time = start_times[i]
        end_time = start_times[i + 1]

        
        segment = data_group[(data_group['time'] > start_time) & (data_group['time'] <= end_time)]
        min_distance = segment['distance'].min()
        clearance = np.abs(tower_dist - min_distance - blade_cen_dist[i % 3]) * np.cos(np.deg2rad(v_angle))
        r_speed = round(60 / ((start_times[i + 2] - start_times[i]) * 3 / 5000000), 2)

        
        ratio = (end_time - start_time) / normalize_cycle
        segment.loc[:, 'time'] = (segment['time'] - start_time) / ratio

        new_df = pd.DataFrame({
            'r_speed': [r_speed],
            'clearance': [clearance]
        })

        
        tower_clearance[i % 3] = pd.concat([tower_clearance[i % 3], new_df])

    tower_clearance = [df.sort_values(by='r_speed') for df in tower_clearance]

    return tower_clearance