Fundamental Concept
SCADA: Supervisory control and data acquisition data acquisition and monitoring control system
Parameters being monitored include
generator rpm, generator bearing temperatures, oil temperature, pitch angle,
yaw system, wind speeds
GUI： graphical user interfaces 图形用户界面
professional phrases
wind curtailment
outlier outlier/outlier
power grid power company
histogram histogram
Regression model regression model
DPI: Stands for “Dots Per Inch.” DPI is used to measure the resolution of an image both on screen and in print.
Raw Data Description
Program 1 2018 Scada data of A Wind Turbine
Analysis object: wind power generator power
Goal: Construct wind power output power curve model Model
influencing factors: data screening and processing method, wind power curve, optimal decision-making selection
Solution: regression models regression analysis model
objective functions optimization objective function
characteristics of wind power generation: andomness and intermittency
Wind speed - output power curve
Note：A typical wind turbine power curve has three main characteristic speeds:
- cut-in (Vc ); 2) rated (Vr ); and 3) cut-out (Vs) speeds. 1)
Start-up wind speed; No-load speed; 2) Rated speed 3) Cut-out wind speed (consider fan safety, stop running speed)
Influencing factors of actual wind speed-power curve
the empirical power curves could be substantially different from the theoretical ones due to
- the location of the turbine,
- air density,
- wind velocity distribution,
- wind direction,
- mechanical and control issues,
- uncertainties in measurements.
the data shows
In Wind Turbines, Scada Systems measure and save data’s like wind speed, wind direction, generated power etc. for 10 minutes intervals. This file was taken from a wind turbine’s scada system that is working and generating power in Turkey.
The data’s in the file are:
Date/Time (for 10 minutes intervals)
LV ActivePower (kW): The power generated by the turbine for that moment
Wind Speed (m/s): The wind speed at the hub height of the turbine (the wind speed that turbine use for electricity generation)
TheoreticalPowerCurve (KWh): The theoretical power values that the turbine generates with that wind speed which is given by the turbine manufacturer, and
Wind Direction (°): The wind direction at the hub height of the turbine (wind turbines turn to this direction automaticly)
model building route
1. Data processing
2. Power model establishment
Preprocessing of data
man-made approaches,
statistic-based models
learning-based models.
Four-step method for data preprocessing
validity check, data validity check
data scaling, data range scaling
missing data preprocessing, missing data preprocessing
lag removal.? ? ? ? ?
three kinds of representative outliers
1、The first type ： the value of wind power tends to zero when the corresponding wind speed is greater than the cut-in wind speed but less than the cut-out wind speed.
Cause：Wind turbine maintenance and wind curtailment .
2、The second type ：outlier are also far from their ideal power data on the power curve, but do not equal to zero.
Cause： wind curtailment and dirt, bugs, or ice on blades, pitch malfunction and other factors.
3、The final type： the value of wind power exceeds the physical limitation of the wind turbine.
error1:
Solving: add pip install windrose
Python Package
matplotlib
pyplot—— drawing
basic structure
# coding=utf-8
from matplotlib import pyplot as plt# 导包
x=range(2,26,2)
y=[15,13,14,6,16,19,22,9,11.5,16,19,21]
# 绘图，展示图形
plt.plot(x,y)
plt.show()
Question 1 : Matplotlib Chinese fonts are not displayed
Set Chinese fonts
from matplotlib.font_manager import FontProperties
font= FontProperties(fname=r"C:\Windows\Fonts\simhei.ttf", size=10) # 此文件路径为windows自带的字体路径，需要什么字体都可以此路径下找
plt.xticks(list(x)[::3],_xtick_labels[::3],rotation=(45),fontproperties=font)#rotation 旋转坐标刻度角度
# 注意fontproperties=font，其中这个font是用户自定义的预使用字体代号
Question 2 : The error
actually means that the number of x and y data does not correspond. Note: range (a, b) cannot marry b! ! ! !
Add horizontal and vertical guides
import matplotlib.pyplot as plt
plt.axhline(y=0.5, color='r', linestyle='-')
plt.show()
numpy
reshape/flatten
random
round
dtype
(24,1) is different from (24,), the former is a two-dimensional array, the latter is one-dimensional
Axis
One-dimensional array 0 axis
Two-dimensional array 0, 1 axis
Three-dimensional array 0, 1, 2 axis
numpy read data
CSV type
predict
KNeighborsRegressor: By finding the k nearest neighbors of a sample and assigning the average value of a certain (some) attributes of these neighbors to the sample, the value of the corresponding attribute of the sample can be obtained.
DecisionTreeRegressor: The data type of the regression tree leaf nodes is continuous, while the data type of the classification tree leaf nodes is discrete.
The regression tree leaf nodes are specific values, while the classification tree leaf nodes are the predicted categories determined according to the training sample categories.
The leaf nodes of a regression tree return the mean of a "clump" of training data rather than specific, continuous predictions.
ExtraTreesRegressor():
EDPR Wind Farm
professional phrases
met mast. (measuring tower)
long-term projected life span; long-term projected life
cumulative fatigue cumulative fatigue
down time downtime
supervised learning (supervised learning)
Thesis Learning-Machine Learning for Predictive Maintenance on Wind Turbines
Core aim
1、predictive maintenance on wind turbines
2、big data analysis
3、machine learning algorithms
The main objective of this thesis project is to enhance the current body of knowledge regarding
predictive maintenance on wind turbines by implementing a big data analysis on a real world data set.
wind turbine
subsystem failure
big data life cycle
Common Fault Diagnosis Methods for Wind Power Generators
Review of Fault Diagnosis Technology for Wind Turbine Gearbox
Zhou Zekun
(Shanghai Institute of Electrical Engineering, Shanghai 200240)
data preprocessing
According to the form of the quartile method , the data will be eliminated due to the problems caused by the system components during the operation process
Fusion of SCADA data based on deep variational autoencoder network
Wind power gearbox fault warning
