基于机器学习和奇异值分解SVD的电池剩余使用寿命预测(Python)

采用k-最近邻KNN和随机森林算法建立预测模型。

复制代码
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC  # Support Vector Classifier
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, classification_report
from sklearn.decomposition import TruncatedSVD
from ydata_profiling import ProfileReport
from sklearn.metrics import mean_squared_error
import time


import seaborn as sns
from importlib import reload
import matplotlib.pyplot as plt
import matplotlib
import warnings




from IPython.display import display, HTML
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import plotly.io as pio


# Configure Jupyter Notebook
pd.set_option('display.max_columns', None) 
pd.set_option('display.max_rows', 500) 
pd.set_option('display.expand_frame_repr', False)
display(HTML("<style>div.output_scroll { height: 35em; }</style>"))

dataset = pd.read_csv('Battery_RUL.csv')

profile = ProfileReport(dataset)
profile

Summarize dataset:   0%|          | 0/5 [00:00<?, ?it/s]

Generate report structure:   0%|          | 0/1 [00:00<?, ?it/s]

Render HTML:   0%|          | 0/1 [00:00<?, ?it/s]

y = dataset['RUL']

x = dataset.drop(columns=['RUL'])

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=42)

Singular Value Decomposition

复制代码
# Step 5: Initialize and fit TruncatedSVD to your training data
n_components = 6  # Adjust the number of components based on your desired dimensionality
svd = TruncatedSVD(n_components=n_components, random_state=42)
X_train_svd = svd.fit_transform(X_train)




# Step 6: Transform the test data using the fitted SVD
X_test_svd = svd.transform(X_test)

K-Nearest-Neighbors

复制代码
from sklearn.neighbors import KNeighborsRegressor
start = time.time()
model = KNeighborsRegressor(n_neighbors=3).fit(X_train_svd,y_train)
end_train = time.time()
y_predictions = model.predict(X_test_svd) # These are the predictions from the test data.
end_predict = time.time()






kNN = [model.score(X_test_svd,y_test), 
       mean_squared_error(y_test,y_predictions,squared=False),
       end_train-start,
       end_predict-end_train,
       end_predict-start]


print('R-squared error: '+ "{:.2%}".format(model.score(X_test_svd,y_test)))
print('Root Mean Squared Error: '+ "{:.2f}".format(mean_squared_error(y_test,y_predictions,squared=False)))

R-squared error: 98.93%
Root Mean Squared Error: 33.30

plt.style.use('seaborn-white')
plt.rcParams['figure.figsize']=5,5 


fig,ax = plt.subplots()
plt.title('Actual vs Predicted')
plt.xlabel('Actual')
plt.ylabel('Predicted')
g = sns.scatterplot(x=y_test,
                y=y_predictions,
                s=20,
                alpha=0.6,
                linewidth=1,
                edgecolor='black',
                ax=ax)
f = sns.lineplot(x=[min(y_test),max(y_test)],
             y=[min(y_test),max(y_test)],
             linewidth=4,
             color='gray',
             ax=ax)


plt.annotate(text=('R-squared error: '+ "{:.2%}".format(model.score(X_test_svd,y_test)) +'\n' +
                  'Root Mean Squared Error: '+ "{:.2f}".format(mean_squared_error(y_test,y_predictions,squared=False))),
             xy=(0,800),
             size='medium')


xlabels = ['{:,.0f}'.format(x) for x in g.get_xticks()]
g.set_xticklabels(xlabels)
ylabels = ['{:,.0f}'.format(x) for x in g.get_yticks()]
g.set_yticklabels(ylabels)
sns.despine()

Random Forest

复制代码
%%time
from sklearn.ensemble import RandomForestRegressor
start = time.time()
model = RandomForestRegressor(n_jobs=-1,
                              n_estimators=100,
                              min_samples_leaf=1,
                              max_features='sqrt',
                              # min_samples_split=2,
                              bootstrap = True,
                              criterion='mse',
                             ).fit(X_train_svd,y_train)
end_train = time.time()
y_predictions = model.predict(X_test_svd) # These are the predictions from the test data.
end_predict = time.time()


Random_Forest = [model.score(X_test_svd,y_test), 
                                   mean_squared_error(y_test,y_predictions,squared=False),
                                   end_train-start,
                                   end_predict-end_train,
                                   end_predict-start]


print('R-squared error: '+ "{:.2%}".format(model.score(X_test_svd,y_test)))
print('Root Mean Squared Error: '+ "{:.2f}".format(mean_squared_error(y_test,y_predictions,squared=False)))

R-squared error: 99.75%
Root Mean Squared Error: 15.97
CPU times: total: 3.34 s
Wall time: 389 ms

plt.style.use('seaborn-white')
plt.rcParams['figure.figsize']=5,5 


fig,ax = plt.subplots()
plt.title('Actual vs Predicted')
plt.xlabel('Actual')
plt.ylabel('Predicted')
g = sns.scatterplot(x=y_test,
                y=y_predictions,
                s=20,
                alpha=0.6,
                linewidth=1,
                edgecolor='black',
                ax=ax)
f = sns.lineplot(x=[min(y_test),max(y_test)],
             y=[min(y_test),max(y_test)],
             linewidth=4,
             color='gray',
             ax=ax)


plt.annotate(text=('R-squared error: '+ "{:.2%}".format(model.score(X_test_svd,y_test)) +'\n' +
                  'Root Mean Squared Error: '+ "{:.2f}".format(mean_squared_error(y_test,y_predictions,squared=False))),
             xy=(0,800),
             size='medium')


xlabels = ['{:,.0f}'.format(x) for x in g.get_xticks()]
g.set_xticklabels(xlabels)
ylabels = ['{:,.0f}'.format(x) for x in g.get_yticks()]
g.set_yticklabels(ylabels)
sns.despine()

工学博士,担任《Mechanical System and Signal Processing》《中国电机工程学报》《控制与决策》等期刊审稿专家,擅长领域:现代信号处理,机器学习,深度学习,数字孪生,时间序列分析,设备缺陷检测、设备异常检测、设备智能故障诊断与健康管理PHM等。

相关推荐
superxxd1 小时前
跨平台音频IO处理库libsoundio实践
开发语言·qt·音视频
海洲探索-Hydrovo2 小时前
TTP Aether X 天通透传模块丨国产自主可控大数据双向通讯定位模组
网络·人工智能·科技·算法·信息与通信
触想工业平板电脑一体机2 小时前
【触想智能】工业安卓一体机在人工智能领域上的市场应用分析
android·人工智能·智能电视
_OP_CHEN2 小时前
C++基础:(十二)list类的基础使用
开发语言·数据结构·c++·stl·list类·list核心接口·list底层原理
Bellafu6663 小时前
selenium常用的等待有哪些?
python·selenium·测试工具
墨染天姬3 小时前
【AI】数学基础之矩阵
人工智能·线性代数·矩阵
小白学大数据4 小时前
Python爬虫常见陷阱:Ajax动态生成内容的URL去重与数据拼接
爬虫·python·ajax
2401_841495645 小时前
【计算机视觉】基于复杂环境下的车牌识别
人工智能·python·算法·计算机视觉·去噪·车牌识别·字符识别
Jonkin-Ma5 小时前
每日算法(1)之单链表
算法
zhangjipinggom5 小时前
multi-head attention 多头注意力实现细节
深度学习