导入依赖库并加载数据
# 导入依赖库
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
from tensorflow import keras
from keras import models
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn import metrics
from sklearn.metrics import accuracy_score
# 加载数据集
detection = pd.read_csv('detect_dataset.csv')
df_class = pd.read_csv('classData.csv')
电力故障检测--二分类
数据预处理
detection.head()
| Output (S) | Ia | Ib | Ic | Va | Vb | Vc | Unnamed: 7 | Unnamed: 8 | |
|---|---|---|---|---|---|---|---|---|---|
| 0 | 0 | -170.472196 | 9.219613 | 161.252583 | 0.054490 | -0.659921 | 0.605431 | NaN | NaN |
| 1 | 0 | -122.235754 | 6.168667 | 116.067087 | 0.102000 | -0.628612 | 0.526202 | NaN | NaN |
| 2 | 0 | -90.161474 | 3.813632 | 86.347841 | 0.141026 | -0.605277 | 0.464251 | NaN | NaN |
| 3 | 0 | -79.904916 | 2.398803 | 77.506112 | 0.156272 | -0.602235 | 0.445963 | NaN | NaN |
| 4 | 0 | -63.885255 | 0.590667 | 63.294587 | 0.180451 | -0.591501 | 0.411050 | NaN | NaN |
# 移除空值
detection.drop(detection.iloc[:,[7,8]], axis=1, inplace=True)
detection.shape
(12001, 7)
数据可视化
fig, axs = plt.subplots(1, 3, figsize=(15, 5))
axs[0].scatter(detection['Ia'], detection['Va'])
axs[0].set_xlabel("Ia")
axs[0].set_ylabel("Va")
axs[1].scatter(detection['Ib'], detection['Vb'], color = "red")
axs[1].set_xlabel("Ib")
axs[1].set_ylabel("Vb")
axs[2].scatter(detection['Ic'], detection['Vc'], color = "green")
axs[2].set_xlabel("Ic")
axs[2].set_ylabel("Vc")
plt.tight_layout()
plt.show()
# 绘制有故障和无故障的图表
fault = detection[detection['Output (S)'] == 1]
no_fault = detection[detection['Output (S)'] == 0]
fig, axs = plt.subplots(3, 2, figsize=(10, 10))
axs[0, 0].scatter(no_fault['Ia'], no_fault['Va'])
axs[0, 0].set_xlabel("Ia")
axs[0, 0].set_ylabel("Va")
axs[0, 0].set_title("No Fault")
axs[0, 1].scatter(fault['Ia'], fault['Va'])
axs[0, 1].set_xlabel("Ia")
axs[0, 1].set_ylabel("Va")
axs[0, 1].set_title("Fault")
axs[1, 0].scatter(no_fault['Ib'], no_fault['Vb'], color = "red")
axs[1, 0].set_xlabel("Ib")
axs[1, 0].set_ylabel("Vb")
axs[1, 0].set_title("No Fault")
axs[1, 1].scatter(fault['Ib'], fault['Vb'], color = "red")
axs[1, 1].set_xlabel("Ib")
axs[1, 1].set_ylabel("Vb")
axs[1, 1].set_title("Fault")
axs[2, 0].scatter(no_fault['Ic'], no_fault['Vc'], color = "green")
axs[2, 0].set_xlabel("Ic")
axs[2, 0].set_ylabel("Vc")
axs[2, 0].set_title("No Fault")
axs[2, 1].scatter(fault['Ic'], fault['Vc'], color = "green")
axs[2, 1].set_xlabel("Ic")
axs[2, 1].set_ylabel("Vc")
axs[2, 1].set_title("Fault")
plt.tight_layout()
plt.show()
# 检测空值
detection.isna().sum()
Output (S) 0 Ia 0 Ib 0 Ic 0 Va 0 Vb 0 Vc 0 dtype: int64
# 设置特征和真值
y = detection.iloc[:,0]
X = detection.iloc[:,1:7]
# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=1)
# 创建神经网络模型
detection_model = models.Sequential()
detection_model.add(keras.layers.Dense(6,
input_shape=(6,),
name='Input_layer',
activation='relu'))
detection_model.add(keras.layers.Dense(16,
name='Hidden_layer1',
activation='relu'))
detection_model.add(keras.layers.Dense(1,
name='Output_layer',
activation='sigmoid'))
detection_model.compile(optimizer = keras.optimizers.Adam(),
loss = keras.losses.binary_crossentropy,
metrics = keras.metrics.binary_accuracy)
# 训练NN模型
detection_model.fit(X_train, y_train, epochs=15)
Epoch 1/15 300/300 [==============================] - 1s 977us/step - loss: 2.0507 - binary_accuracy: 0.6274 Epoch 2/15 300/300 [==============================] - 0s 945us/step - loss: 0.2647 - binary_accuracy: 0.9384 Epoch 3/15 300/300 [==============================] - 0s 918us/step - loss: 0.1595 - binary_accuracy: 0.9759 Epoch 4/15 300/300 [==============================] - 0s 927us/step - loss: 0.1106 - binary_accuracy: 0.9831 Epoch 5/15 300/300 [==============================] - 0s 980us/step - loss: 0.0885 - binary_accuracy: 0.9845 Epoch 6/15 300/300 [==============================] - 0s 878us/step - loss: 0.0759 - binary_accuracy: 0.9848 Epoch 7/15 300/300 [==============================] - 0s 930us/step - loss: 0.0688 - binary_accuracy: 0.9850 Epoch 8/15 300/300 [==============================] - 0s 884us/step - loss: 0.0638 - binary_accuracy: 0.9861 Epoch 9/15 300/300 [==============================] - 0s 964us/step - loss: 0.0601 - binary_accuracy: 0.9864 Epoch 10/15 300/300 [==============================] - 0s 928us/step - loss: 0.0577 - binary_accuracy: 0.9869 Epoch 11/15 300/300 [==============================] - 0s 969us/step - loss: 0.0558 - binary_accuracy: 0.9873 Epoch 12/15 300/300 [==============================] - 0s 920us/step - loss: 0.0538 - binary_accuracy: 0.9875 Epoch 13/15 300/300 [==============================] - 0s 1ms/step - loss: 0.0515 - binary_accuracy: 0.9882 Epoch 14/15 300/300 [==============================] - 0s 959us/step - loss: 0.0511 - binary_accuracy: 0.9883 Epoch 15/15 300/300 [==============================] - 0s 913us/step - loss: 0.0493 - binary_accuracy: 0.9887
<keras.src.callbacks.History at 0x1f18102bcd0>
# 模型预测
y_pred = detection_model.predict(X_test)
y_pred = np.where(y_pred>0.5, 1, 0)
76/76 [==============================] - 0s 734us/step
模型性能
print(classification_report(y_test, y_pred))
precision recall f1-score support
0 0.98 1.00 0.99 1297
1 1.00 0.98 0.99 1104
accuracy 0.99 2401
macro avg 0.99 0.99 0.99 2401
weighted avg 0.99 0.99 0.99 2401
print(f'Accuracy Score : {accuracy_score(y_test, y_pred)*100:.02f}%')
Accuracy Score : 99.04%
# 混淆矩阵
fig, ax = plt.subplots()
class_names=[0,1]
tick_marks = np.arange(len(class_names))
plt.xticks(tick_marks, class_names)
plt.yticks(tick_marks, class_names)
cnf_matrix = metrics.confusion_matrix(y_test, y_pred)
sns.heatmap(pd.DataFrame(cnf_matrix), annot=True, cmap="YlGnBu" ,fmt='g')
ax.xaxis.set_label_position("top")
plt.tight_layout()
plt.title('Confusion matrix', y=1.1)
plt.ylabel('Actual label')
plt.xlabel('Predicted label')
Text(0.5, 427.9555555555555, 'Predicted label')
电力故障检测--多分类
数据预处理
df_class.head()
| G | C | B | A | Ia | Ib | Ic | Va | Vb | Vc | |
|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | 0 | 0 | 1 | -151.291812 | -9.677452 | 85.800162 | 0.400750 | -0.132935 | -0.267815 |
| 1 | 1 | 0 | 0 | 1 | -336.186183 | -76.283262 | 18.328897 | 0.312732 | -0.123633 | -0.189099 |
| 2 | 1 | 0 | 0 | 1 | -502.891583 | -174.648023 | -80.924663 | 0.265728 | -0.114301 | -0.151428 |
| 3 | 1 | 0 | 0 | 1 | -593.941905 | -217.703359 | -124.891924 | 0.235511 | -0.104940 | -0.130570 |
| 4 | 1 | 0 | 0 | 1 | -643.663617 | -224.159427 | -132.282815 | 0.209537 | -0.095554 | -0.113983 |
df_class.shape
(7861, 10)
输出：[G C B A]
[0 0 0 0] - 无故障
[1 0 0 1] - LG 故障（A 相与地之间）
[0 0 1 1] - LL 故障（A 相和 B 相之间）
[1 0 1 1] - LLG 故障（A、B 相与接地之间）
[0 1 1 1] - LLL 故障（所有三相之间）
[1 1 1 1] - LLLG 故障（三相对称故障）
# 为故障类型创建新列
df_class['faultType'] = (df_class['G'].astype(str) +
df_class['C'].astype(str) +
df_class['B'].astype(str) +
df_class['A'].astype(str))
df_class.head()
| G | C | B | A | Ia | Ib | Ic | Va | Vb | Vc | faultType | |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 1 | 0 | 0 | 1 | -151.291812 | -9.677452 | 85.800162 | 0.400750 | -0.132935 | -0.267815 | 1001 |
| 1 | 1 | 0 | 0 | 1 | -336.186183 | -76.283262 | 18.328897 | 0.312732 | -0.123633 | -0.189099 | 1001 |
| 2 | 1 | 0 | 0 | 1 | -502.891583 | -174.648023 | -80.924663 | 0.265728 | -0.114301 | -0.151428 | 1001 |
| 3 | 1 | 0 | 0 | 1 | -593.941905 | -217.703359 | -124.891924 | 0.235511 | -0.104940 | -0.130570 | 1001 |
| 4 | 1 | 0 | 0 | 1 | -643.663617 | -224.159427 | -132.282815 | 0.209537 | -0.095554 | -0.113983 | 1001 |
df_class["faultType"].unique()
array(['1001', '1011', '0110', '0111', '1111', '0000'], dtype=object)
数据可视化
values = list(df_class["faultType"].value_counts())
faults =['No Fault', 'LLG Fault', 'LLLG Fault', 'LG Fault', 'LLL Fault', 'LL Fault']
plt.bar(faults, values, width=0.6)
<BarContainer object of 6 artists>
plt.pie(df_class['faultType'].value_counts(), autopct='%1.1f%%', labels=faults)
plt.show()
创建模型
# 设置数据特征
x = df_class.iloc[:,4:10]
# 设置数据真值
y = df_class['faultType']
enc = LabelEncoder()
y = enc.fit_transform(y)
y = keras.utils.to_categorical(y,6)
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.20)
class_model = keras.models.Sequential()
class_model.add(keras.layers.Dense(128,
input_shape=(6,),
name='Input_layer',
activation='relu'))
class_model.add(keras.layers.Dense(240,
name='Hidden_layer1',
activation='relu'))
class_model.add(keras.layers.Dense(240,
name='Hidden_layer2',
activation='tanh'))
class_model.add(keras.layers.Dense(6,
name='output_layer',
activation='softmax'))
class_model.compile(
loss='categorical_crossentropy',
metrics = ['accuracy']
)
class_model.fit(x_train, y_train, epochs=50, batch_size=64, validation_split=0.2)
Epoch 1/50 79/79 [==============================] - 1s 4ms/step - loss: 1.1702 - accuracy: 0.5807 - val_loss: 1.0718 - val_accuracy: 0.5890 Epoch 2/50 79/79 [==============================] - 0s 2ms/step - loss: 0.9922 - accuracy: 0.6412 - val_loss: 0.9843 - val_accuracy: 0.6455 Epoch 3/50 79/79 [==============================] - 0s 2ms/step - loss: 0.9151 - accuracy: 0.6598 - val_loss: 0.9624 - val_accuracy: 0.6216 Epoch 4/50 79/79 [==============================] - 0s 2ms/step - loss: 0.8811 - accuracy: 0.6610 - val_loss: 0.8986 - val_accuracy: 0.5946 Epoch 5/50 79/79 [==============================] - 0s 2ms/step - loss: 0.8151 - accuracy: 0.6843 - val_loss: 0.8542 - val_accuracy: 0.6550 Epoch 6/50 79/79 [==============================] - 0s 2ms/step - loss: 0.7482 - accuracy: 0.7000 - val_loss: 1.0069 - val_accuracy: 0.5485 Epoch 7/50 79/79 [==============================] - 0s 2ms/step - loss: 0.6781 - accuracy: 0.7252 - val_loss: 0.6106 - val_accuracy: 0.7361 Epoch 8/50 79/79 [==============================] - 0s 2ms/step - loss: 0.6297 - accuracy: 0.7378 - val_loss: 0.5969 - val_accuracy: 0.7591 Epoch 9/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5815 - accuracy: 0.7567 - val_loss: 0.5684 - val_accuracy: 0.7695 Epoch 10/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5764 - accuracy: 0.7553 - val_loss: 0.5504 - val_accuracy: 0.7377 Epoch 11/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5567 - accuracy: 0.7604 - val_loss: 0.5000 - val_accuracy: 0.7830 Epoch 12/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5384 - accuracy: 0.7672 - val_loss: 0.5533 - val_accuracy: 0.7496 Epoch 13/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5350 - accuracy: 0.7728 - val_loss: 0.4889 - val_accuracy: 0.7846 Epoch 14/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5124 - accuracy: 0.7660 - val_loss: 0.5275 - val_accuracy: 0.7599 Epoch 15/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5131 - accuracy: 0.7708 - val_loss: 0.5131 - val_accuracy: 0.7456 Epoch 16/50 79/79 [==============================] - 0s 2ms/step - loss: 0.5079 - accuracy: 0.7724 - val_loss: 0.5055 - val_accuracy: 0.7623 Epoch 17/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4781 - accuracy: 0.7815 - val_loss: 0.5120 - val_accuracy: 0.7719 Epoch 18/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4848 - accuracy: 0.7732 - val_loss: 0.4581 - val_accuracy: 0.7957 Epoch 19/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4703 - accuracy: 0.7867 - val_loss: 0.5137 - val_accuracy: 0.7424 Epoch 20/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4674 - accuracy: 0.7869 - val_loss: 0.5217 - val_accuracy: 0.7512 Epoch 21/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4635 - accuracy: 0.7849 - val_loss: 0.4628 - val_accuracy: 0.7933 Epoch 22/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4618 - accuracy: 0.7873 - val_loss: 0.4528 - val_accuracy: 0.8045 Epoch 23/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4564 - accuracy: 0.7903 - val_loss: 0.4700 - val_accuracy: 0.7814 Epoch 24/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4549 - accuracy: 0.7922 - val_loss: 0.4851 - val_accuracy: 0.7893 Epoch 25/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4494 - accuracy: 0.7905 - val_loss: 0.4289 - val_accuracy: 0.7822 Epoch 26/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4493 - accuracy: 0.7913 - val_loss: 0.4805 - val_accuracy: 0.7838 Epoch 27/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4351 - accuracy: 0.7970 - val_loss: 0.5136 - val_accuracy: 0.7822 Epoch 28/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4352 - accuracy: 0.7950 - val_loss: 0.4145 - val_accuracy: 0.7878 Epoch 29/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4265 - accuracy: 0.7994 - val_loss: 0.4031 - val_accuracy: 0.8108 Epoch 30/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4187 - accuracy: 0.8036 - val_loss: 0.4390 - val_accuracy: 0.7790 Epoch 31/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4201 - accuracy: 0.7913 - val_loss: 0.4498 - val_accuracy: 0.8029 Epoch 32/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4107 - accuracy: 0.8028 - val_loss: 0.4140 - val_accuracy: 0.7981 Epoch 33/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4176 - accuracy: 0.8046 - val_loss: 0.4122 - val_accuracy: 0.8029 Epoch 34/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4027 - accuracy: 0.8034 - val_loss: 0.3649 - val_accuracy: 0.8172 Epoch 35/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4072 - accuracy: 0.8016 - val_loss: 0.5376 - val_accuracy: 0.7361 Epoch 36/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4193 - accuracy: 0.7930 - val_loss: 0.3750 - val_accuracy: 0.8092 Epoch 37/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3911 - accuracy: 0.8113 - val_loss: 0.3858 - val_accuracy: 0.8100 Epoch 38/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3897 - accuracy: 0.8129 - val_loss: 0.3601 - val_accuracy: 0.8140 Epoch 39/50 79/79 [==============================] - 0s 2ms/step - loss: 0.4003 - accuracy: 0.8054 - val_loss: 0.3973 - val_accuracy: 0.8116 Epoch 40/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3877 - accuracy: 0.8141 - val_loss: 0.4003 - val_accuracy: 0.8140 Epoch 41/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3887 - accuracy: 0.8135 - val_loss: 0.3980 - val_accuracy: 0.7989 Epoch 42/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3887 - accuracy: 0.8105 - val_loss: 0.3622 - val_accuracy: 0.8172 Epoch 43/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3902 - accuracy: 0.8087 - val_loss: 0.3714 - val_accuracy: 0.8140 Epoch 44/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3800 - accuracy: 0.8054 - val_loss: 0.4569 - val_accuracy: 0.7989 Epoch 45/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3788 - accuracy: 0.8121 - val_loss: 0.3890 - val_accuracy: 0.8037 Epoch 46/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3760 - accuracy: 0.8175 - val_loss: 0.3601 - val_accuracy: 0.8116 Epoch 47/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3663 - accuracy: 0.8177 - val_loss: 0.3666 - val_accuracy: 0.7941 Epoch 48/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3760 - accuracy: 0.8119 - val_loss: 0.3720 - val_accuracy: 0.8021 Epoch 49/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3749 - accuracy: 0.8219 - val_loss: 0.3885 - val_accuracy: 0.8164 Epoch 50/50 79/79 [==============================] - 0s 2ms/step - loss: 0.3639 - accuracy: 0.8262 - val_loss: 0.4709 - val_accuracy: 0.7734
<keras.src.callbacks.History at 0x1f1838f8be0>
y_pred_prob = class_model.predict(x_test)
y_pred = np.argmax(y_pred_prob, axis=1)
y_test = np.argmax(y_test,axis=1)
50/50 [==============================] - 0s 963us/step
模型性能
print(classification_report(y_test, y_pred, zero_division=0))
precision recall f1-score support
0 0.99 1.00 0.99 465
1 0.79 0.62 0.70 217
2 0.43 0.89 0.58 209
3 0.93 0.98 0.95 243
4 0.85 0.93 0.89 212
5 0.00 0.00 0.00 227
accuracy 0.78 1573
macro avg 0.66 0.74 0.68 1573
weighted avg 0.71 0.78 0.73 1573
print(f'Accuracy Score : {accuracy_score(y_test, y_pred)*100:.02f}%')
Accuracy Score : 77.81%