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 time
import sys
import frequency_filter as ff
from datetime import datetime

warnings.filterwarnings("ignore", category=FutureWarning)  # 忽略特定警告
plt.rcParams['font.sans-serif'] = ['SimHei']  # 使用黑体
plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题


def result_main():

    """
    创建data目录，返回历史分析数据存放的文件路径
    """

    # 获取当前程序的绝对路径
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')
    # 检查data文件夹是否存在，如果不存在则创建
    if not os.path.exists(data_folder):
        os.makedirs(data_folder)

    # CSV文件路径
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    # 检查CSV文件是否存在，如果不存在则创建一个空的CSV文件
    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(names):

    """
    删除历史分析数据
    :param names: 删除条件
    :return: csv文件路径
    """

    # 获取当前程序的绝对路径
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')

    # CSV文件路径
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    df = pd.read_csv(csv_file_path)

    for name in names:
        # 检查条件
        condition = ((df['时间'].str.contains(name[0])) &
                     (df['场站'].str.contains(name[1])) &
                     (df['风机编号'].str.contains(name[2])))

        # 删除满足条件的行
        df = df[~condition]
    # 如果需要，可以将修改后的 DataFrame 保存回 CSV 文件
    df.to_csv(csv_file_path, index=False)

    return csv_file_path


def history_data(name):
    """
    读取历史分析数据
    :param name: 接口返回列表
    :return:
    """

    wind_name, turbine_code, time_code = name[1], name[2], name[0]
    # 获取当前程序的绝对路径
    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]):

    """
    创建data目录，把分析数据保存到历史记录中，同时返回全量分析数据
    """

    locate_file = path[0]
    measure_file = path[1]
    noise_reduction = 0.000001  # 如果一个距离值的所有样本量小于总样本量的noise_reduction，则被去掉
    min_difference = 1.5  # 如果相邻2个点的距离差大于min_difference，则被注意是否是周期节点
    angle_cone = float(path[2])  # 锥角
    axial_inclination = float(path[3])  # 轴向倾角
    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, sampling_fq_1, angle_tip, 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_tip, data_root = process_data(measure_file)

    start_tip, end_tip, filtered_data_tip = cycle_calculate(data_tip, noise_reduction, min_difference)
    start_root, end_root, filtered_data_root = cycle_calculate(data_root, noise_reduction, min_difference)
    filtered_data_cen = tower_filter(data_cen, noise_reduction)
    dist_cen = np.mean(filtered_data_cen.iloc[:, 1].tolist())

    if end_tip.iloc[0, 0] < start_root.iloc[0, 0]:
        start_tip = start_tip.drop(start_tip.index[0])
        end_tip = end_tip.drop(end_tip.index[0])
    if start_root.iloc[0, 0] < start_tip.iloc[0, 0] < end_tip.iloc[0, 0] < end_root.iloc[0, 0]:
        pass
    else:
        raise ValueError("The elements are not in the expected order.")

    tower_dist_tip = ff.tower_cal(filtered_data_tip, start_tip, end_tip, sampling_fq_1)
    tower_dist_root = ff.tower_cal(filtered_data_root, start_root, end_root, sampling_fq_1)
    lowpass_data, fft_x, fft_y, tower_freq, tower_max = ff.process_fft(filtered_data_cen, sampling_fq)

    result_line_tip, result_scatter_tip, border_rows_tip, cycle_len_tip, min_tip \
        = data_normalize(filtered_data_tip, start_tip, end_tip)
    result_line_root, result_scatter_root, border_rows_root, cycle_len_root, min_root \
        = data_normalize(filtered_data_root, start_root, end_root)

    result_avg_tip, result_diff_tip = blade_shape(result_line_tip)
    result_avg_root, result_diff_root = blade_shape(result_line_root)

    border_rows_tip_new, angle_tip_new = coordinate_normalize(border_rows_tip, angle_tip)

    tip_r = radius_cal(border_rows_tip_new, angle_tip_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)

    pitch_angle_tip, aero_dist_tip, v_speed_tip, cen_blade_tip = (
        blade_angle_aero_dist(border_rows_tip, tip_r, cycle_len_tip, tower_dist_tip, angle_tip_new))
    pitch_angle_root, 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))

    # 将列表转换为 numpy 数组
    cen_blade_tip_array = np.array(cen_blade_tip)
    min_tip_array = np.array(min_tip)
    abs_diff = np.abs(cen_blade_tip_array - min_tip_array)  # 计算差值的绝对值
    blade_dist_tip = abs_diff * np.cos(np.deg2rad(angle_tip_new))
    blade_dist_tip.tolist()  # 如果需要将结果转换回列表

    dist_distribute = blade_dist_distribute_cal(filtered_data_tip, start_tip, end_tip,
                                                tower_dist_tip, angle_tip_new, blade_dist_tip)
    dist_distribute = [df.round(5) for df in dist_distribute]

    # 获取每个 DataFrame 第二列的最小值和最大值，以及它们对应的第一列的值，并分别保存在列表中
    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(second_col_min)
        min_keys.append(min_row.iloc[0][df.columns[0]])
        max_values.append(second_col_max)
        max_keys.append(max_row.iloc[0][df.columns[0]])

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

    for df in result_line_tip:
        first_column = df.iloc[:, 0]
        sec_column = df.iloc[:, 1]
        df.iloc[:, 0] = first_column * v_speed_tip
        df.iloc[:, 1] = sec_column * np.cos(np.deg2rad(angle_tip_new))

    for df in result_line_root:
        first_column = df.iloc[:, 0]
        sec_column = df.iloc[:, 1]
        df.iloc[:, 0] = first_column * v_speed_root
        df.iloc[:, 1] = sec_column * np.cos(np.deg2rad(angle_root))

    avg_tip = result_avg_tip.iloc[:, 0]
    result_avg_tip.iloc[:, 0] = avg_tip * v_speed_tip
    avg_root = result_avg_root.iloc[:, 0]
    result_avg_root.iloc[:, 0] = avg_root * v_speed_root

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

    sampling_num = int(0.01 * sampling_fq_1)
    data_tip.iloc[:, 0] = data_tip.iloc[:, 0] / 5000000
    data_root.iloc[:, 0] = data_root.iloc[:, 0] / 5000000
    lowpass_data.iloc[:, 0] = lowpass_data.iloc[:, 0] / 5000000


    return_list.append(time_code)
    return_list.append(wind_name)
    return_list.append(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)


    # 将return_list转换为DataFrame并追加到CSV文件
    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_tip.iloc[:, 0].tolist()[::sampling_num],
                'ydata': data_tip.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()),
                'ymin': min(lowpass_data['distance_filtered'].tolist())
            },
            'fft': {
                'xdata': fft_x,
                'ydata': fft_y,
                'xmax': max(fft_x),
                'xmin': min(fft_x),
                'ymax': max(fft_y),
                'ymin': min(fft_y)
            }
        },
        'blade_tip': {
            'first_blade': {
                'xdata': result_line_tip[0].iloc[:, 0].tolist(),
                'ydata': result_line_tip[0].iloc[:, 1].tolist()
            },
            'second_blade': {
                'xdata': result_line_tip[1].iloc[:, 0].tolist(),
                'ydata': result_line_tip[1].iloc[:, 1].tolist()
            },
            'third_blade': {
                'xdata': result_line_tip[2].iloc[:, 0].tolist(),
                'ydata': result_line_tip[2].iloc[:, 1].tolist()
            },
            'avg_blade': {
                'xdata': result_avg_tip.iloc[:, 0].tolist(),
                'ydata': result_avg_tip.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
            }
        }
    }

    # 获取当前程序的绝对路径
    python_interpreter_path = sys.executable
    project_directory = os.path.dirname(python_interpreter_path)
    data_folder = os.path.join(project_directory, 'data')
    # 检查data文件夹是否存在，如果不存在则创建
    if not os.path.exists(data_folder):
        os.makedirs(data_folder)

    # CSV文件路径
    csv_file_path = os.path.join(data_folder, 'history_data.csv')
    # 检查CSV文件是否存在，如果不存在则创建一个空的CSV文件
    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):

    """
    打开、解决时间重置、按时间清洗异常值、分列数据
    """

    # 读取第2、4、9列的数据
    data = pd.read_csv(file_path, usecols=[1, 3, 8], header=None, engine='c')
    data = data.head(int(len(data) * 0.95))

    # 找到第一列中最大值和最小值的位置
    max_value = data.iloc[:, 0].max()
    max_index = data.iloc[:, 0].idxmax()
    min_index = data.iloc[:, 0].idxmin()

    # 检查最小值的位置是否是最大值位置的下一个
    if min_index == max_index + 1:
        # 将最小值及其之后的所有值都加上最大值
        data.iloc[min_index:, 0] += max_value

    # 按时间列筛选清洗异常值
    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)
    # 计算最小值
    min_time = data.iloc[:, 0].min()
    data.iloc[:, 0] -= min_time

    # 分为两组数据
    data_1 = data.iloc[:, [0, 1]]
    data_2 = data.iloc[:, [0, 2]]

    # 分别命名列
    data_1.columns = ['time', 'distance']
    data_2.columns = ['time', 'distance']

    return data_1, data_2


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

    """
    对轮毂中心数据进行降噪，和前项填充
    :param data_group: process_data计算完成后轮毂中心的数据。
    :param noise_threshold: 去掉占比小于noise_threshold的数据。
    :return: filtered_data：降噪后的数据
    """

    time.sleep(1)

    # 计算distance的分布
    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

    # 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 - 20) | (
            data_group['distance'] > mean_values * 1.1), 'distance'] = np.nan

    # 前向填充
    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):

    """
    对数据进行降噪，和前项填充；计算数据的周期节点，叶片前缘突变点、后缘突变点
    :param data_group: process_data计算完成后的数据。
    :param noise_threshold: 去掉占比小于noise_threshold的数据。
    :param min_distance: 区分叶片和塔筒的距离差值。
    :return: start_points：周期开始点, end_points：周期结束点, filtered_data：降噪后的数据
    """

    time.sleep(1)

    # 计算distance的分布
    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

    # 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 - 20) | (
            data_group['distance'] > mean_values * 1.1), 'distance'] = np.nan


    # 前向填充
    data_group['distance'] = data_group['distance'].fillna(method='ffill')
    filtered_data = data_group

    # 计算相邻两行distance的差值
    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()

    # 遍历所有差值大于的行
    for idx in large_diff_indices:
        # 获取当前行的 distance 值
        current_distance = filtered_data.loc[idx, 'distance']

        next_rows_large = filtered_data.loc[idx - 1000: idx - 1]

        # 检查是否任意 distance 的值小于 current_distance - 2
        if next_rows_large['distance'].le(current_distance - min_distance).all():
            # 如果都小于，则将当前行和下一行添加到 special_points 中
            end_points = pd.concat([end_points, filtered_data.loc[[idx - 1]]])

    for idx in small_diff_indices:
        # 获取当前行的 distance 值
        current_distance = filtered_data.loc[idx - 1, 'distance']

        next_rows_small = filtered_data.iloc[idx: idx + 1000]

        # 检查是否任意 distance 的值小于 current_distance - 2
        if next_rows_small['distance'].le(current_distance - min_distance).all():
            # 如果都小于，则将当前行和下一行添加到 special_points 中
            start_points = pd.concat([start_points, filtered_data.loc[[idx]]])

    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) \
        -> Tuple[List[pd.DataFrame], List[pd.DataFrame], List[pd.DataFrame], int, list]:

    """
    提取每个叶片的数据并归一化，输出散点图和拟合图
    :param data_group: cycle_calculate计算完成后的数据。
    :param start_points: 所有每个周期开始点，叶片前缘突变点。
    :param end_points: 叶片后缘突变点。
    :return: turbines_processed: 每个叶片的拟合数据，
             turbines_scattered: 每个叶片的散点数据，
             border_rows: 每个叶片的2个边缘数据，
             normalize_cycle: 周期长度
    """

    time.sleep(1)

    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()
    time.sleep(1)

    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)]

    # 遍历所有起始时间点
    for i in range(0, len(start_times), 2):

        # 获取当前起始和结束时间点
        start_time = start_times[i]
        end_time = start_times[i + 1]

        # 根据当前起始时间点和结束时间点对数据进行分段
        segment = data_group[(data_group['time'] > start_time) & (data_group['time'] <= end_time)]

        if segment is None:
            pass
        else:
            # 周期归一化
            ratio = (end_time - start_time) / normalize_cycle
            segment.loc[:, 'time'] = (segment['time'] - start_time) / ratio

            # 将结果添加到相应的 turbine 数据框中
            turbines[i % 3] = pd.concat([turbines[i % 3], segment])

    # 数据分组清洗、求平均
    turbines_processed = []
    turbines_scattered = []
    min_list = []
    sd_time = [-1, -1]
    time_list = list(range(0, normalize_cycle, 1000))

    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()), 1000))
        # 原始代码
        # bins = list(range(int(first_time), int(turbine_sorted['time'].max()) + len(start_times), int(fs / 50)))
        grouped = turbine_sorted.groupby(pd.cut(turbine_sorted['time'], bins=bins, right=False))

        # 初始化一个空的 DataFrame 用于存储处理后的数据
        processed_df = pd.DataFrame()
        scattered_df = pd.DataFrame()
        mean_points = []
        diff_points = []

        # 对每个组进行处理
        for _, group in grouped:
            # 去除 distance 最大和最小的前5%
            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)]

            # 计算均值
            mean_point = filtered_group['distance'].mean()
            mean_points.append(mean_point)

        # 遍历 mean_points 列表，计算每个元素与其下一个元素的差值
        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))

        # 找到第一个和最后一个小于 sdr_diff 的序号
        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):

            # 去除 distance 最大和最小的前5%
            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:  # 如果斜率小于，则认为该组数据不是突变点

                # 计算中点
                mid_point = filtered_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]
                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

        # 找到time列的最小值和最大值
        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

        # 将处理后的 DataFrame 添加到列表中
        turbines_processed.append(processed_df)
        turbines_scattered.append(scattered_df)

    border_rows = []
    for i, turbine in enumerate(turbines_processed):
        # 找到离 sd_time[0] 最近的行的索引
        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]

        # 找到离 sd_time[1] 最近的行的索引
        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]

        # 切片 turbine，从 closest_index_0 到 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)

    time.sleep(1)

    return turbines_processed, turbines_scattered, border_rows, full_cycle, min_list


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

    """
    计算叶片平均形状、叶片形状偏差。
    :param turbines_processed:叶片拟合曲线数据，来自data_normalize
    :return: 叶片平均形状、叶片形状偏差
    """

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

    # 创建一个新的data.frame用于保存结果
    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]

    # 遍历每一行
    for i in range(num_rows):
        distances = [df.loc[i, 'distance'] for df in turbines_processed]  # 获取每个data.frame的distance列的值
        avg_distance = sum(distances) / len(distances)  # 计算distance列的平均值
        time_value = turbines_processed[0].loc[i, 'time']  # 获取time列的值
        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]

    time.sleep(10)

    return turbine_avg, turbine_diff


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

    """
    将叶尖测量数据和叶根、轮毂中心的测量原点归一化。
    :param tip_border_rows: 3个叶尖边缘数据
    :param tip_angle: 叶尖测量俯仰角
    :return: 归一化后叶尖数据，叶尖俯仰角
    """

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


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

    """
    计算测量点处的旋转半径。
    :param border_rows: 三个叶片的边界
    :param meas_angle: 回波俯仰角
    :param cen_dist: 轮毂中心距离
    :param cen_angle: 轮毂中心俯仰角
    :param angle_main: 主轴倾角
    :param angle_rotate: 锥角
    :return: 旋转半径
    """

    aero_dist = (pd.concat([df['distance'] for df in border_rows]).mean())
    cen_x = np.cos(np.deg2rad(cen_angle)) * cen_dist
    cen_y = np.sin(np.deg2rad(cen_angle)) * cen_dist
    aero_x = np.cos(np.deg2rad(meas_angle)) * aero_dist
    aero_y = np.sin(np.deg2rad(meas_angle)) * aero_dist
    theta_4 = np.tan(np.pi - np.deg2rad(angle_main))
    theta_5 = np.tan(np.pi / 2 - np.deg2rad(angle_main) + np.deg2rad(angle_rotate))

    if np.abs(np.deg2rad(angle_main) - np.deg2rad(angle_rotate)) < 0.0001:
        radius = np.abs((cen_y - aero_y) - theta_4 * (cen_x - aero_x))

    else:
        radius = (np.abs((theta_4 * (cen_x - aero_x) - (cen_y - aero_y)) / (theta_4 - theta_5))
                  * (1 + theta_5 ** 2) ** 0.5)
    return radius


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

    """
    计算叶片相对桨距角和叶片净空距离。
    :param border_rows: 三个叶片的边界
    :param radius: 旋转半径
    :param full_cycle: 全周期
    :param tower_dist: 塔筒距离
    :param v_angle: 俯仰角度
    :return: 绝对桨距角，净空距离，叶片线速度
    """

    v_speed = 2 * np.pi * radius / full_cycle  # 叶片线速度m/(1计时器单位）
    pitch_angle_list = []
    aero_dist_list = []
    cen_blade = []
    for turbine in border_rows:
        diff_time = turbine.iloc[1, 0] - turbine.iloc[0, 0]

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

        pitch_angle = np.degrees(np.arctan(diff_len / (diff_time * v_speed)))
        pitch_angle_list.append(pitch_angle)
        aero_dist_list.append(aero_dist)
        cen_blade.append(mean_col2)
    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))
    aero_dist_list.append(np.mean(aero_dist_list))
    pitch_angle_list = [round(num, 2) for num in pitch_angle_list]
    aero_dist_list = [round(num, 2) for num in aero_dist_list]

    return pitch_angle_list, aero_dist_list, v_speed, cen_blade


def find_param(path: str):

    """
    根据文件路径获取参数
    """

    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):

    """
    计算每个叶片每个周期的转速和净空距离
    :param data_group: cycle_calculate计算完成后的数据。
    :param start_points: 所有每个周期开始点，叶片前缘突变点。
    :param end_points: 叶片后缘突变点。
    :param tower_dist: 塔筒距离。
    :param v_angle: 测量俯仰角度。
    :param blade_cen_dist: 叶片内部距离。
    """

    time.sleep(1)

    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()

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

    # 遍历所有起始时间点
    for i in range(0, len(start_times) - 2, 2):
        # 获取当前起始和结束时间点
        start_time = start_times[i]
        end_time = start_times[i + 1]

        # 根据当前起始时间点和结束时间点对数据进行分段
        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 = (start_times[i + 2] - start_times[i]) * 3 / 5000000

        # 周期归一化
        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]
        })

        # 将结果添加到相应的 turbine 数据框中
        tower_clearance[i % 3] = pd.concat([tower_clearance[i % 3], new_df])

    return tower_clearance