当前课程知识点:Big Data of Smart Grid >  Chapter 7 Prospect of BDSG >  Intelligent Disaster or Failure Recognition Means——Related Literature of Electric Power Vision Big Data >  6.3 Fault correlation analysis of power grid control system equipment

返回《Big Data of Smart Grid》慕课在线视频课程列表

6.3 Fault correlation analysis of power grid control system equipment在线视频

返回《Big Data of Smart Grid》慕课在线视频列表

6.3 Fault correlation analysis of power grid control system equipment课程教案、知识点、字幕

Ok, welcome back.
好的,欢迎回来

This lecture will start to learn Section 6.3
这节课我们将要开始学习6.3节

This section is about the analysis of equipment accident correlation of power grid control system based on frequent item set
本节是关于基于频繁项集的电网控制系统设备事故相关性分析

Daily load forecasting of large users
大型用户的每日负载预测

We will introduce the research methods and analysis results of this part
我们将对这部分的研究方法和分析结果示例进行介绍

The feature selection of equipment accident correlation
设备事故关联特征选取

Based on the data of accident equipment object, accident occurrence time
基于事故设备对象、事故发生时间

accident end time, accident occurrence type, accident cause type, line trip, line coincidence and so on
事故结束时间、事故发生类型、事故原因类型、线路跳闸情况、线路重合情况等数据

by selecting the equipment accident correlation features
通过选取设备事故关联特征

the frequent item set of equipment accidents and the equipment accident correlation examples are formed
形成设备事故发生的频繁项集和设备事故的关联实例

According to the different data types
根据数据类型的不同

the correlation features are selected from the following aspects
从以下几个方面选择关联特征

The first is equipment features
首先是设备特征

it is mainly from equipment account and equipment accident data
它主要来自设备台账、设备事故数据

used to analyze the distribution rule of heavy overload area under different equipment types
用于分析不同设备类型、不同事故类型

accident types and user proportion
不同用户构成比例下的重过载台区分布规律

The second aspect is time series characteristics
第二是时序特征

it is used to analyze the cause proportion and correlation trend law of equipment accident period, important weather and holidays changing with time
它用于分析设备事故时段、重要天气、节假日随时间变化的原因占比、关联趋势规律

The last aspect is about associated features
最后一点是关于伴生特征的

they are used to analyze the half life factors of equipment accidents
它们用于分析设备发生事故的半生因素

including the relationship between equipment accidents and equipment category, weather, cause type and other factors
包括设备发生事故与设备类别、天气、原因类型等因素的关联关系

Equipment accident correlation evaluation
设备事故关联关系评估

Based on the above frequent item set of equipment accidents and the example of equipment accidents association
基于上述设备事故发生频繁项集和设备事故关联实例

in addition to using the three common indicators
除了使用关联分析中常见的三个指标

support, confidence and promotion in association analysis to evaluate the association degree
支持度、置信度、提升度来评估关联程度

new derivative comprehensive indicators can also be defined
还可以定义新的衍生综合指标

Now,let's talk about analysis results of line accident correlation
现在,让我们来讨论线路事故关联关系分析成果

We will select three most representative analysis results of line accidents for display
我们将选取线路事故最具有代表性的3个分析成果进行展示

The first is about correlation analysis of multiple accident associated factors
首先是关于事故多伴生因素关联分析

The analysis results are as shown in Table 6.1
分析结果如表6.1所示

The correlation degree between the cause types (front item)
属于不同伴生因素的原因类型(前项)

and the accident types (back item) of different associated factors is different
与事故类型(后项)关联程度不同

From the analysis results
由分析结果可推断出

it can be inferred that the line accident in the accident type has strong correlation with the lightning stroke in the cause type
故类型中的线路事故与原因类型中的雷击具有强相关性

The second part is the analysis of the causes of the types of accidents
第二部分是事故类型的原因占比分析

The analysis results are shown in Fig. 6.7
分析结果如图6.7所示

in which each node shows the influence degree of different cause types on the occurrence of the accident
图中通过各个节点表示不同原因类型对事故发生的影响程度

and it can be seen that typhoon, external force damage, foreign matters, lightning stroke, etc.
可看出台风、外力破坏及异物、雷击等

are the main causes of the occurrence of the line accident
是发生线路事故的主要成因

The third part is about accident type association analysis
第三部分是关于事故类型关联分析

Some analysis results are shown in table 6.2
部分分析结果如表6.2所示

It can be seen that the probability of line accident and unit accident occurring at the same time is very high
看出线路事故与机组事故同时发生的概率很大

Generally speaking
综合来看

the strong relevant factors of line accidents in the places where the above accidents occur
以上事故发生地的线路事故强相关因素

include lightning stroke, burning mountain, typhoon, external force damage and foreign matters
包括原因类型中的雷击、火烧山、台风、外力破坏及异物

and often form cascading accident response together with unit accidents and bus accidents
且往往与机组事故、母线事故等共同形成级联事故反应

Ok, that’s all for this lecture
好的,这就是本节课的全部内容

Next time we will move on to section 6.4
下次,我们将继续第6.4节

Hope to see you again
希望能再次见到你

Big Data of Smart Grid课程列表:

Chapter 1 What is Big Data

-Course Introduction and Overview of Big Data

-Chapter 1

-Big data review literature

Chapter 2 Big Data of Smart Grid(BDSG)

-2.1 Why Electirc Power + Big Data? 2.2 Applications

-Chapter 2

-An important application of big data in electric power——literature on the identification of small targets such as faults

Chapter 3 Main Application Fields of BDSG

-3.1 Grid Operation and Development

-3.2 Power Consumers

-3.3 Society and Government

-Chapter3

-Related literature on big data applications from the user perspective

Chapter 4 Technology System of BDSG

-4.1 Data Acquisition+4.2 Data Storage

-4.3 Data Processing

-4.4 Data Analysis and Mining

-4.5 Data Visualization

-4.6 Data Security and Privacy Protection

-Chapter4

-Load forecasting technology related literature

Chapter 5 Research Methods and Application Methods of BDSG

-5.1.1Platform Construction: Demand Analysis

-5.1.2Platform Construction: Design (1)

-5.1.2Platform Construction: Design (2)

-5.2 Data collection and management

-5.3.1 Data Aggregation and Fusion: Scheme and process

-5.3.2 Data Aggregation and Fusion: Application Practice

-5.4.1 Analysis and Mining: Scheme and process

-5.4.2 Analysis and Mining: Use-case analysis

-Chapter5

-Commonly used electric power big data deep learning method——application literature of transfer learning

Chapter 6 Project Cases of BDSG

-6.1 Heavy overload prediction of station area

-6.2 Daily load forecasting of large users

-6.3 Fault correlation analysis of power grid control system equipment

-6.4 Reliability of relay protection equipment family-

-6.5Application of random matrix in big data analysis of smart grid

-Chapter6

-Literature on Power Vision Data Processing Technology

Chapter 7 Prospect of BDSG

-Development trend and suggestions for BDIG

-Chapter7

-Intelligent Disaster or Failure Recognition Means——Related Literature of Electric Power Vision Big Data

6.3 Fault correlation analysis of power grid control system equipment笔记与讨论

也许你还感兴趣的课程:

© 柠檬大学-慕课导航 课程版权归原始院校所有,
本网站仅通过互联网进行慕课课程索引,不提供在线课程学习和视频,请同学们点击报名到课程提供网站进行学习。