CN108537414A - A kind of fault arc detection method based on LDA algorithm - Google Patents

A kind of fault arc detection method based on LDA algorithm Download PDF

Info

Publication number
CN108537414A
CN108537414A CN201810227331.7A CN201810227331A CN108537414A CN 108537414 A CN108537414 A CN 108537414A CN 201810227331 A CN201810227331 A CN 201810227331A CN 108537414 A CN108537414 A CN 108537414A
Authority
CN
China
Prior art keywords
current
electric arc
lda algorithm
class
denoted
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201810227331.7A
Other languages
Chinese (zh)
Inventor
梁昆
张轩铭
王利强
陈龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
HANGZHOU TOP TECHNOLOGY Co Ltd
Original Assignee
HANGZHOU TOP TECHNOLOGY Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by HANGZHOU TOP TECHNOLOGY Co Ltd filed Critical HANGZHOU TOP TECHNOLOGY Co Ltd
Priority to CN201810227331.7A priority Critical patent/CN108537414A/en
Publication of CN108537414A publication Critical patent/CN108537414A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
    • G06F18/21322—Rendering the within-class scatter matrix non-singular
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Computation (AREA)
  • Educational Administration (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Operations Research (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
  • Emergency Protection Circuit Devices (AREA)

Abstract

The fault electric arc recognition methods based on LDA algorithm that the invention discloses a kind of, includes the following steps：One, sample characteristics extract：Extract electric current flat shoulder time, current-jump value ratio, electric current substantially this four main features of the standard deviation of current average in the number, 1s of saltus step in 1s；Two, it is based on LDA algorithm and carries out sample training；Three, online judgment step：Judge whether to belong to fault electric arc.The fault electric arc recognition methods based on LDA algorithm of the present invention, takes full advantage of large sample, avoids the mode of artificial selected threshold.

Description

A kind of fault arc detection method based on LDA algorithm
Technical field
The invention belongs to faults to judge field, specifically a kind of fault arc detection method based on LDA algorithm.
Background technology
The fault judgment method of mainstream is typically the artificial feature for choosing current waveform at present, then by manually choosing fixation Threshold decision whether belong to fault electric arc.Fault electric arc can carry out the simulation under various scenes, various loadtypes, compare It is easy to generate a larger sample database.But by the method for manual analysis selected threshold, it is difficult to make full use of full-page proof This.
Invention content
In order to solve the above technical problems existing in the prior art, the event based on LDA algorithm that the present invention provides a kind of Hinder electric arc recognition methods, includes the following steps：
One, sample characteristics extract：Extract electric current flat shoulder time, current-jump value ratio, in 1s electric current substantially saltus step time This four main features of the standard deviation of current average in number, 1s；
Two, it is based on LDA algorithm and carries out sample training；
Three, online judgment step：Judge whether to belong to fault electric arc.
Further, the time of the current-jump in a power frequency period is denoted as tpulse, calculate from tpulseExtreme value afterwards Point, extreme point time are denoted as textreme, then the electric current flat shoulder time be:
tflat=textreme-tpulse。
Further, Δ ipulseIt is denoted as current-jump value, the sampling number in a power frequency period is P, in power frequency period Average current it is poor：Then current-jump ratio calculates as follows：
Further, the number of electric current substantially saltus step is denoted as N in 1spulse_num。
Further, if the current average in each period isThe average value being denoted as in N number of period (N=50), then the standard deviation standard deviation of current average is in 1s：
Further, step 2 is specially：N samples for including aforementioned four main feature of acquisition, preceding n1A sample category In class w1, behind n2A sample belongs to class w2；
(1) each sample mean vector m is calculatedi, i=1,2
X is sample；
(2) within class scatter matrix S is calculatediWith total within class scatter matrix Sw
Sw=S1+S2；
(3) inter _ class relationship matrix S is calculatedb
Sb=(m1-m2)(m1-m2)T；
(4) it calculatesMaximal eigenvector, be denoted as w, w is required kernel projection vector.
Further, step 3 is specially：
(1) assume that the feature for needing certain sampling is denoted as s；
(2) minimum ranges of the feature x after projection with two class samples is calculated
d1=min | wTxi-wTs|},xi∈ samples w1；
d2=min | wTxi-wTs|},xi∈ samples w2；
(3) if d1<d2Then prediction result belongs to d1Class belongs to fault electric arc；If d1>=d2Then prediction result belongs to d2Class belongs to non-faulting electric arc.
The fault electric arc recognition methods based on LDA algorithm of the present invention, takes full advantage of large sample, avoids artificial selection The mode of threshold value.
Specific implementation mode
The invention will be further described below.
The fault electric arc recognition methods based on LDA algorithm of the present invention, includes the following steps：
1. sample characteristics extract
Extract 4 main features such as following A, B, C, D：
The flat shoulder time (feature A) of electric current:Since most of scene has other loads in practice, electric current can not be directly measured The flat shoulder time.The time of current-jump in one power frequency period (20ms) is denoted as t by the present inventionpulse, then calculate from tpulseAfterwards Extreme point, the extreme point time is denoted as textreme.Then the electric current flat shoulder time is:
tflat=textreme-tpulse
Current-jump value ratio (feature B):ΔipulseIt is denoted as current-jump value, the sampling number in a power frequency period is P, the average current in power frequency period it is poor：Then saltus step ratio calculates as follows,
The number (feature C) of electric current substantially saltus step in 1s:It is each during due to the electric appliances normal use such as Switching Power Supply Period all can there is a situation where current-jumps.And a feature of usually fault electric arc is that the duration is short, intermittently, therefore Current-jump number is as a feature：Npulse_num；
The standard deviation (feature D) of current average in 1s:If the current average in each period is,Note For the average value (N=50) in N number of period, then standard deviation is：
2. the sample training (projection vector calculating step) based on LDA algorithm
N samples for including above-mentioned 4 dimensional feature of acquisition, preceding n1A sample belongs to class w1(fault electric arc), behind n2A sample Belong to class w2(non-faulting electric arc)；
(5) each sample mean vector m is calculatedi, i=1,2
(6) within class scatter matrix S is calculatediWith total within class scatter matrix Sw
Sw=S1+S2
(7) inter _ class relationship matrix S is calculatedb
Sb=(m1-m2)(m1-m2)T
(8) it calculatesMaximal eigenvector, be denoted as w, w is required kernel projection vector.
3. online judgment step (judging whether to belong to fault electric arc)
(4) assume that the feature for needing certain sampling is denoted as s；
(5) minimum ranges of the feature x after projection with two class samples is calculated
d1=min | wTxi-wTs|},xi∈ samples w1
d2=min | wTxi-wTs|},xi∈ samples w2
(6) if d1<d2Then prediction result belongs to d1Class belongs to fault electric arc；If d1>=d2Then prediction result belongs to d2Class belongs to non-faulting electric arc.

Claims (7)

1. a kind of fault electric arc recognition methods based on LDA algorithm, includes the following steps：
One, sample characteristics extract：Extract electric current flat shoulder time, current-jump value ratio, in 1s electric current substantially saltus step number, 1s This four main features of the standard deviation of interior current average；
Two, it is based on LDA algorithm and carries out sample training；
Three, online judgment step：Judge whether to belong to fault electric arc.
2. the fault electric arc recognition methods based on LDA algorithm as described in claim 1, it is characterised in that：
The time of current-jump in one power frequency period is denoted as tpulse, calculate from tpulseExtreme point afterwards, extreme point time It is denoted as textreme, then the electric current flat shoulder time be:
tflat=textreme-tpulse。
3. the fault electric arc recognition methods based on LDA algorithm as described in claim 1, it is characterised in that：
ΔipulseIt is denoted as current-jump value, the sampling number in a power frequency period is P, and the average current in power frequency period is poor：Then current-jump ratio calculates as follows：
4. the fault electric arc recognition methods based on LDA algorithm as described in claim 1, it is characterised in that：
The number of electric current substantially saltus step is denoted as N in 1spulse_num。
5. the fault electric arc recognition methods based on LDA algorithm as described in claim 1, it is characterised in that：
If the current average in each period is The average value (N=50) being denoted as in N number of period, then in 1s The standard deviation standard deviation of current average is：
6. the fault electric arc recognition methods based on LDA algorithm as described in claim 1, it is characterised in that：
Step 2 is specially：N samples for including aforementioned four main feature of acquisition, preceding n1A sample belongs to class w1, behind n2It is a Sample belongs to class w2；
(1) each sample mean vector m is calculatedi, i=1,2
X is sample；
(2) within class scatter matrix S is calculatediWith total within class scatter matrix Sw
Sw=S1+S2；
(3) inter _ class relationship matrix S is calculatedb
Sb=(m1-m2)(m1-m2)T；
(4) it calculatesMaximal eigenvector, be denoted as w, w is required kernel projection vector.
7. the fault electric arc recognition methods based on LDA algorithm as claimed in claim 6, it is characterised in that：
Step 3 is specially：
(1) assume that the feature for needing certain sampling is denoted as s；
(2) minimum ranges of the feature x after projection with two class samples is calculated
d1=min | wTxi-wTs|},xi∈ samples w1；
d2=min | wTxi-wTs|},xi∈ samples w2；
(3) if d1<d2Then prediction result belongs to d1Class belongs to fault electric arc；If d1>=d2Then prediction result belongs to d2 Class belongs to non-faulting electric arc.
CN201810227331.7A 2018-03-19 2018-03-19 A kind of fault arc detection method based on LDA algorithm Pending CN108537414A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810227331.7A CN108537414A (en) 2018-03-19 2018-03-19 A kind of fault arc detection method based on LDA algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810227331.7A CN108537414A (en) 2018-03-19 2018-03-19 A kind of fault arc detection method based on LDA algorithm

Publications (1)

Publication Number Publication Date
CN108537414A true CN108537414A (en) 2018-09-14

Family

ID=63484168

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810227331.7A Pending CN108537414A (en) 2018-03-19 2018-03-19 A kind of fault arc detection method based on LDA algorithm

Country Status (1)

Country Link
CN (1) CN108537414A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110244198A (en) * 2019-05-09 2019-09-17 山东优柏电子科技有限公司 Resistive load serial arc detection method and application based on compound criterion

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105403816A (en) * 2015-10-30 2016-03-16 国家电网公司 Identification method of DC fault electric arc of photovoltaic system
CN106326915A (en) * 2016-08-10 2017-01-11 北京理工大学 Improved-Fisher-based chemical process fault diagnosis method
CN106707094A (en) * 2015-11-12 2017-05-24 沈阳工业大学 Classification recognition method of arc fault of low voltage power supply and distribution line
CN106961248A (en) * 2017-04-25 2017-07-18 西安交通大学 Mix the photovoltaic system fault arc detection method of quadratic form time-frequency distributions feature and the analysis of self adaptation multiplicative function

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105403816A (en) * 2015-10-30 2016-03-16 国家电网公司 Identification method of DC fault electric arc of photovoltaic system
CN106707094A (en) * 2015-11-12 2017-05-24 沈阳工业大学 Classification recognition method of arc fault of low voltage power supply and distribution line
CN106326915A (en) * 2016-08-10 2017-01-11 北京理工大学 Improved-Fisher-based chemical process fault diagnosis method
CN106961248A (en) * 2017-04-25 2017-07-18 西安交通大学 Mix the photovoltaic system fault arc detection method of quadratic form time-frequency distributions feature and the analysis of self adaptation multiplicative function

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘湘澎: "电弧故障断路器的故障电弧电流特性研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110244198A (en) * 2019-05-09 2019-09-17 山东优柏电子科技有限公司 Resistive load serial arc detection method and application based on compound criterion
CN110244198B (en) * 2019-05-09 2022-03-01 山东优柏电子科技有限公司 Resistive load series arc detection method based on composite criterion and application

Similar Documents

Publication Publication Date Title
CN108562835A (en) A kind of fault arc detection method based on BP neural network
CN104237750B (en) GIS insulation defect partial discharge fault graph drawing method
CN110069886A (en) The identification of cable initial failure and classification method based on VMD and CNN
CN105606944B (en) The fault line selection method for single-phase-to-ground fault and device of distribution system
CN110108992B (en) Cable partial discharge fault identification method and system based on improved random forest algorithm
CN106154163B (en) Battery life state identification method
CN104198899B (en) Partial discharge type identifying method for transformer under multi-discharge source situation
CN114636900B (en) Power distribution network multiple fault diagnosis method
CN107153150A (en) A kind of power distribution network over-voltage fault type recognition method and device
CN106970302B (en) Power distribution network high-resistance fault positioning and simulating method based on integrated empirical mode decomposition
CN105403816A (en) Identification method of DC fault electric arc of photovoltaic system
CN109284938A (en) A kind of comprehensive estimation method and device of power cable line state
CN110543921A (en) cable early fault identification method based on waveform learning
CN107491783B (en) Transformer fault type classification method based on improved density peak value clustering algorithm
CN109116196A (en) A kind of power cable fault discharging sound intelligent identification Method
CN108075437A (en) A kind of voltage sag source identification method based on wavelet transformation
CN103683198A (en) Excitation surge current fast identification method based on planar adjacent point distances formed by differential current adjacent order difference
CN114414942A (en) Power transmission line fault identification classifier, identification method and system based on transient waveform image identification
CN106526468A (en) Breaker state detection method based on waveform characteristics identification
CN110490428A (en) Job of air traffic control method for evaluating quality and relevant apparatus
CN108537414A (en) A kind of fault arc detection method based on LDA algorithm
CN107247962A (en) A kind of real-time electrical appliance recognition and system based on sliding window
CN106355249A (en) Relay protection equipment status identification method based on BP neural network
CN107219494A (en) A kind of electric energy meter testing results system
CN105183612B (en) The appraisal procedure of server free memory abnormal growth and operation conditions

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20180914

RJ01 Rejection of invention patent application after publication