cloud
226 lines
9.7 KiB
Python
226 lines
9.7 KiB
Python
import sys
|
||
print("Python 解释器路径:", sys.executable)
|
||
print("已安装的包路径:", sys.path)
|
||
import data
|
||
import pandas as pd
|
||
import numpy as np
|
||
import matplotlib.pyplot as plt
|
||
from pathlib import Path
|
||
|
||
# ----------------------
|
||
# 配置参数
|
||
# ----------------------
|
||
RAW_DATA_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01 原始数据.xlsx')
|
||
CLEANED_DATA_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01cleaned_scada_data.xlsx')
|
||
#中间保存路径
|
||
AFTER_LIMIT_POWER_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_limit_power_cleaning.xlsx')
|
||
AFTER_TIP_SPEED_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_tip_speed_cleaning.xlsx')
|
||
AFTER_SPEED_POWER_PATH = Path(r'D:\经手项目\数据分析项目\哈萨克斯坦项目\CHUZHIBAO\T01\T01after_speed_power_cleaning.xlsx')
|
||
RESULT_TABLE_PATH = Path(r'F:\风速区间功率均值表.xlsx')
|
||
RESULT_PLOT_PATH = Path(r'F:\风速功率曲线.png')
|
||
RATED_POWER = 4800 # 额定功率
|
||
RATED_WIND_SPEED = 18# 额定风速
|
||
POWER_STEP = 5
|
||
WIND_SPEED_STEP = 0.25 # 风速区间步长
|
||
WIND_SPEED_CHANGE_THRESHOLD = 1
|
||
#TIME_THRESHOLD = pd.Timedelta(hours=2)
|
||
IQR_MULTIPLIER1 = 1.8
|
||
IQR_MULTIPLIER2 = 2
|
||
MINIMUM_GENERATOR_SPEED = 1
|
||
K = 0.9 # k值：删除小于k倍最小发电机转速的点
|
||
|
||
|
||
# ----------------------
|
||
# 工具函数：定义保存数据
|
||
def save_intermediate_data(data,file_path,step_name):
|
||
"""保存中间数据的专用函数，仅做保存"""
|
||
try:
|
||
if data.empty:
|
||
print(f"⚠️{step_name}为空，不保存")
|
||
return
|
||
#创建目录（如果不存在）
|
||
file_path.parent.mkdir(parents=True, exist_ok=True)
|
||
#保存数据
|
||
data.to_excel(file_path, index=False,engine='openpyxl')
|
||
print(f"✅ {step_name}已保存（{len(data)}条）至：{file_path}")
|
||
except Exception as e:
|
||
print(f"❌ 保存{step_name}失败：{str(e)}")
|
||
|
||
# ----------------------
|
||
# 数据清洗函数
|
||
# ----------------------
|
||
|
||
def load_data(file_path):
|
||
try:
|
||
if not file_path.exists():
|
||
raise FileNotFoundError(f"文件不存在: {file_path}")
|
||
data = pd.read_excel(file_path, engine='openpyxl')
|
||
print(f"成功读取数据，共{len(data)}条记录")
|
||
return data
|
||
except Exception as e:
|
||
print(f"数据读取错误: {str(e)}")
|
||
return None
|
||
|
||
|
||
def clean_scada_data(raw_data):
|
||
if raw_data is None or raw_data.empty:
|
||
print("无数据可清洗")
|
||
return None
|
||
|
||
data = raw_data.copy()
|
||
|
||
# 1. 基础过滤：删除停机数据
|
||
initial_count = len(data)
|
||
data = data[data['平均有功功率'] > 0].copy()
|
||
|
||
#1.5 删除小于最小发电机转速的点
|
||
if not data.empty and '平均发电机转速' in data.columns:
|
||
# 计算阈值：k倍最小发电机转速
|
||
speed_threshold = K * MINIMUM_GENERATOR_SPEED
|
||
# 过滤数据
|
||
data = data[data['平均发电机转速'] >= speed_threshold].copy()
|
||
removed_count = initial_count - len(data)
|
||
print(f"发电机转速过滤后保留 {len(data)} 条数据（移除{removed_count}条低转速数据，阈值: {speed_threshold:.2f}）")
|
||
initial_count = len(data)
|
||
|
||
# 2. 时间列处理
|
||
if '时间' not in data.columns:
|
||
print("警告：数据中未找到'时间'列，无法进行限功率点识别")
|
||
return data
|
||
|
||
data['时间'] = pd.to_datetime(data['时间'], errors='coerce')
|
||
time_invalid_count = data['时间'].isna().sum()
|
||
data = data.dropna(subset=['时间'])
|
||
print(f"时间处理后保留 {len(data)} 条数据（移除{time_invalid_count}条无效时间数据）")
|
||
|
||
# 3. 识别并移除限功率点
|
||
|
||
if not data.empty:
|
||
min_power = data['平均有功功率'].min()
|
||
power_intervals = np.arange(min_power, RATED_POWER, POWER_STEP)
|
||
limit_power_points = []
|
||
|
||
for interval in power_intervals:
|
||
mask = (data['平均有功功率'] >= interval) & (data['平均有功功率'] < interval + POWER_STEP)
|
||
interval_data = data[mask]
|
||
if interval_data.empty:
|
||
continue
|
||
|
||
grouped = interval_data.groupby(interval_data['时间'].dt.date)
|
||
for date, group in grouped:
|
||
group_sorted = group.sort_values('时间')
|
||
wind_speed_range = group_sorted['平均风速'].max()-group_sorted['平均风速'].min()
|
||
if wind_speed_range > WIND_SPEED_CHANGE_THRESHOLD:
|
||
limit_power_points.extend(group_sorted.index)
|
||
|
||
data = data.drop(limit_power_points,errors='ignore')
|
||
print(f"限功率识别后保留{len(data)}条数据(移除{len(limit_power_points)}条限功率数据)")
|
||
save_intermediate_data(data,AFTER_LIMIT_POWER_PATH,"限功率清洗后的数据")
|
||
|
||
|
||
|
||
# 4. 计算并清洗叶尖速比
|
||
if not data.empty and '平均风速' in data.columns :
|
||
data = data[data['平均风速'] > 0].copy()
|
||
print(f"移除风速为0的数据后保留 {len(data)} 条数据")
|
||
|
||
data['叶尖速比'] =data['平均发电机转速']*3.14*162*78*30/data['平均风速']
|
||
#data['叶尖速比']= data['叶轮转速']*100/data['平均风速']
|
||
|
||
if not data.empty:
|
||
wind_speed_min = data['平均风速'].min()
|
||
wind_speed_max = data['平均风速'].max()
|
||
wind_speed_intervals = np.arange(wind_speed_min, wind_speed_max, WIND_SPEED_STEP)
|
||
cleaned_data_list = []
|
||
|
||
for interval in wind_speed_intervals:
|
||
mask = (data['平均风速'] >= interval) & (data['平均风速'] < interval + WIND_SPEED_STEP)
|
||
interval_data = data[mask]
|
||
|
||
if len(interval_data) >= 4:
|
||
q1 = interval_data['叶尖速比'].quantile(0.25)
|
||
q3 = interval_data['叶尖速比'].quantile(0.75)
|
||
iqr = q3 - q1
|
||
lower = q1 - IQR_MULTIPLIER1 * iqr
|
||
upper = q3 + IQR_MULTIPLIER2 * iqr
|
||
interval_cleaned = interval_data[(interval_data['叶尖速比'] >= lower) &
|
||
(interval_data['叶尖速比'] <= upper)]
|
||
|
||
else:
|
||
interval_cleaned = interval_data
|
||
|
||
cleaned_data_list.append(interval_cleaned)
|
||
|
||
data = pd.concat(cleaned_data_list)
|
||
print(f"叶尖速比清洗后保留 {len(data)} 条数据")
|
||
save_intermediate_data(data,AFTER_TIP_SPEED_PATH,"叶尖速比清洗后的数据")
|
||
|
||
# 5. 风速-功率关系清洗
|
||
if not data.empty and '平均风速' in data.columns and '平均有功功率' in data.columns:
|
||
wind_speed_min = data['平均风速'].min()
|
||
wind_speed_max = data['平均风速'].max()
|
||
wind_speed_intervals = np.arange(wind_speed_min, wind_speed_max, WIND_SPEED_STEP)
|
||
final_cleaned_list = []
|
||
|
||
for interval in wind_speed_intervals:
|
||
mask = (data['平均风速'] >= interval) & (data['平均风速'] < interval + WIND_SPEED_STEP)
|
||
interval_data = data[mask]
|
||
|
||
if len(interval_data) >= 4:
|
||
q1 = interval_data['平均有功功率'].quantile(0.25)
|
||
q3 = interval_data['平均有功功率'].quantile(0.75)
|
||
iqr = q3 - q1
|
||
lower_limit = q1 - IQR_MULTIPLIER1 * iqr
|
||
upper_limit = q3 + IQR_MULTIPLIER2 * iqr
|
||
|
||
interval_cleaned = interval_data[(interval_data['平均有功功率'] >= lower_limit) &
|
||
(interval_data['平均有功功率'] <= upper_limit)]
|
||
else:
|
||
interval_cleaned = interval_data
|
||
final_cleaned_list.append(interval_cleaned)
|
||
|
||
data = pd.concat(final_cleaned_list)
|
||
print(f"风速-功率清洗后保留 {len(data)} 条数据")
|
||
save_intermediate_data(data, AFTER_SPEED_POWER_PATH, "风速功率清洗后的数据")
|
||
|
||
# 6. 高风速区二次过滤
|
||
#if not data.empty and '平均风速' in data.columns:
|
||
#high_wind_mask = data['平均风速'] >= RATED_WIND_SPEED
|
||
#high_wind_data = data[high_wind_mask]
|
||
|
||
#if len(high_wind_data) > 0:
|
||
#robust_mean = high_wind_data['平均有功功率'].median()
|
||
#high_wind_filtered = high_wind_data[
|
||
#(high_wind_data['平均有功功率'] >= robust_mean * 0.98) &
|
||
#(high_wind_data['平均有功功率'] <= robust_mean * 1.02)
|
||
#]
|
||
|
||
#low_wind_data = data[~high_wind_mask]
|
||
#data = pd.concat([low_wind_data, high_wind_filtered])
|
||
#print(f"高风速区二次过滤后保留 {len(data)} 条数据")
|
||
return data
|
||
|
||
|
||
# ----------------------
|
||
# 主程序：执行数据清洗并保存结果
|
||
# ----------------------
|
||
if __name__ == "__main__":
|
||
# 加载原始数据
|
||
raw_data = load_data(RAW_DATA_PATH)
|
||
|
||
# 清洗数据
|
||
cleaned_data = clean_scada_data(raw_data)
|
||
|
||
# 保存清洗后的数据到指定路径
|
||
if cleaned_data is not None and not cleaned_data.empty:
|
||
try:
|
||
# 创建保存目录（如果不存在）
|
||
CLEANED_DATA_PATH.parent.mkdir(parents=True, exist_ok=True)
|
||
|
||
# 保存为Excel文件
|
||
cleaned_data.to_excel(CLEANED_DATA_PATH, index=False, engine='openpyxl')
|
||
print(f"清洗后的数据已成功保存到: {CLEANED_DATA_PATH}")
|
||
except Exception as e:
|
||
print(f"保存数据时出错: {str(e)}")
|
||
else:
|
||
print("没有可保存的清洗后数据") |