CN107316130A - A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering - Google Patents

A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering Download PDF

Info

Publication number
CN107316130A
CN107316130A CN201710430041.8A CN201710430041A CN107316130A CN 107316130 A CN107316130 A CN 107316130A CN 201710430041 A CN201710430041 A CN 201710430041A CN 107316130 A CN107316130 A CN 107316130A
Authority
CN
China
Prior art keywords
mrow
acquisition terminal
msub
clustering
sample
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
CN201710430041.8A
Other languages
Chinese (zh)
Inventor
李中成
杨霖
吕伟嘉
李刚
卢静雅
刘浩宇
许迪
赵紫敬
张兆杰
翟术然
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.)
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Electric Power Research Institute of State Grid Tianjin Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Electric Power Research Institute of State Grid Tianjin Electric Power 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 State Grid Corp of China SGCC, State Grid Tianjin Electric Power Co Ltd, Electric Power Research Institute of State Grid Tianjin Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201710430041.8A priority Critical patent/CN107316130A/en
Publication of CN107316130A publication Critical patent/CN107316130A/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
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • G06F18/24137—Distances to cluster centroïds
    • 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Operations Research (AREA)
  • Remote Sensing (AREA)
  • Game Theory and Decision Science (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a kind of metering acquisition terminal fault diagnosis based on clustering and visable positioning method, belong to acquisition terminal FLT field.This method is extracted in filtering power information acquisition system data basis extensive, and the gathered data and historical archives information to measuring terminal are sorted out using clustering, form acquisition terminal fault diagnosis classification results, filter out terminal fault information point.According to the geographical coordinate of acquisition terminal fault message point, fault location is carried out with geospatial information data, the tracking of terminal fault information point and visual presentation are realized in GIS map, so as to realize the real time data monitoring to acquisition terminal, fault diagnosis and visualization positioning.

Description

A kind of metering acquisition terminal fault diagnosis based on clustering and visualization are positioned Method
Technical field
The invention belongs to acquisition terminal FLT field, especially a kind of metering collection based on clustering is eventually Hold fault diagnosis and visable positioning method.
Background technology
With the fast development of intelligent power grid technology at home and application, the use scale of metering acquisition terminal constantly expands Greatly, its quantity broken down and probability more and more higher.At present, there are special transformer acquisition terminal 60,000, low pressure concentrator in Efficiency in Buildings in Tianjin Area 3.9 ten thousand, nearly more than 200,000,000 datas are produced daily.Using the cleaning of effective means, invalid, unordered data are filtered, and to magnanimity Data carry out analysis classification, in time screening and positioning terminal fault message point, and assisted acquisition operation maintenance personnel is managed at it Targetedly carry out on-site terminal maintenance work in region significant.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art part, there is provided a kind of metering collection based on clustering Terminal fault is diagnosed and visable positioning method, improves metering automation terminal fault locating accuracy,
The present invention solves its technical problem and takes following technical scheme to realize：
A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering, it is characterised in that：It is suitable Sequence performs following steps：
Step is (1)：Related data is obtained, acquisition terminal characteristic index sample matrix B is built, to local all big customers The acquisition terminal for specially becoming stoichiometric point carries out real-time dynamic data collection, filtering and detected, by user profile and load nature of electricity consumed, equipment Producer and numbering, equipment address and geographical coordinate, apply to install the base profiles such as time and history gathered data difference typing number According to storehouse；
Step is (2)：To acquisition terminal feature matrix B and B0Pretreatment is normalized；
Step is (3)：The each element concentrated using mahalanobis distance method to data carries out similarity analysis；
Step is (4)：Acquisition terminal fault diagnosis classification results are obtained by clustering；
Step is (5)：According to classification results, the sample by similarity degree close to 0 is by the user base shelves in class comparison database Case and history gathered data, filter out terminal fault information point；
Step is (6)：According to the geographical coordinate of acquisition terminal fault message point, failure is carried out with geospatial information data Positioning, realizes the tracking of terminal fault information point and visual presentation in GIS map.
Moreover, the step (1) in, acquisition terminal characteristic index sample matrix B={ b1,b2…bn(i=1,2 ..., n), It is assumed that each sample biAll there is m characteristic index classification, b is represented byi=(bi1,bi2…bij,bim) (j=1,2 ..., m), Meanwhile, the standard feature index matrix for defining acquisition terminal is B0=(b01,b02…b0j,b0m), wherein b0jFor acquisition terminal data The standard reference value of j-th of characteristic value.
Moreover, the step (2) in normalization pretreatment be each characteristic index value is distributed on [0,1] interval, Specifically formula is：
In formula：bi′jFor bijValue after normalization, bimaxAnd biminIt is b respectivelyiMaximum, minimum value.
Moreover, the step (3) in, similarity analysis rule is：Characteristic value and standard feature index more more similar sample This, similarity factor absolute value is just closer to 1, and the similarity factor of not closely related sample is just closer to 0；
Similarity factor identical sample is classified as a class, first calculates the similitude system between each classification samples and standard value Measure d (b0,bj), so that it is determined that each sample and standard value B in characteristic index matrix B0Between fuzzy equivalence relation matrix D；
Using sample vector bjWith canonical reference vector b0Mahalanobis distance be：
d(b0,bj)=(b0-bj)T∑-1(b0-bj)
Calculated by mahalanobis distance function and obtain the fuzzy equivalence relation matrix D of matrix B and be：
Moreover, the step (4) in clustering be that dynamic adjustment is found and selects appropriate threshold values λ to close fuzzy equivalence It is that matrix D carries out cut, so as to obtain the classification of all samples, threshold values λ value adjustment formula is：
In formula：I >=2, represent λ from the cluster number of times of 1 to 0 reduction arrangement；λi-1And ni-1Respectively represent the i-th -1 time cluster Element number and threshold values；λiAnd niThe element number and threshold values of ith cluster are represented respectively；If in the presence ofIt is then fixed The threshold values λ of adopted ith clusteriFor optimum threshold.
Advantages and positive effects of the present invention are：
1st, the inventive method is sorted out to the gathered data and historical archives information of measuring terminal using clustering, effectively sieve Select terminal fault information point.According to the geographical coordinate of acquisition terminal fault message point, carried out with geospatial information data Fault location and visual presentation, so as to realize the real time data monitoring to acquisition terminal, fault diagnosis and visualization positioning.
2nd, the present invention provide a kind of technological means for acquisition terminal failure O＆M, can largely save collecting device O＆M into This, and tracing trouble species accuracy rate apparently higher than artificial experience and traditional statistical analysis method.Acquisition system operation maintenance Personnel have found the state of the terminal operating in institute compass of competency by directly perceived, visual mode.
Brief description of the drawings
Fig. 1 is this method flow chart.
Embodiment
Below in conjunction with the accompanying drawings and the invention will be further described by specific embodiment, following examples are descriptive , it is not limited, it is impossible to which protection scope of the present invention is limited with this.
A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering, order perform following walk Suddenly：
Step 1：Related data is obtained, acquisition terminal characteristic index sample matrix B is built, it is special to local all big customers The acquisition terminal for becoming stoichiometric point carries out real-time dynamic data collection, filtering and detected, by user profile and load nature of electricity consumed, instrument factory Family and numbering, equipment address and geographical coordinate, apply to install the base profiles such as time and the difference logging data of history gathered data Storehouse；
Wherein, acquisition terminal characteristic index sample matrix B={ b1,b2…bn(i=1,2 ..., n), it is assumed that each sample biAll there is m characteristic index classification, b is represented byi=(bi1,bi2…bij,bim) (j=1,2 ..., m).Collection is defined simultaneously The standard feature index matrix of terminal is B0=(b01,b02…b0j,b0m), wherein b0jFor j-th of characteristic value of acquisition terminal data Standard reference value；
Step 2：To acquisition terminal feature matrix B and B0Pretreatment is normalized；
Described normalization pretreatment is each characteristic index value is distributed on [0,1] interval, facilitates each characteristic to refer to Mark numerical value carries out comparative analysis on same dimension, and specific formula is：
In formula：bi′jFor bijValue after normalization, bimaxAnd biminIt is b respectivelyiMaximum, minimum value.
Step 3：, each element progress similarity analysis that data are concentrated using mahalanobis distance method；
Described similarity analysis rule is：Characteristic value and standard feature index more more similar sample, similarity factor are exhausted To value just closer to 1, and the similarity factor of not closely related sample is just closer to 0.A class can be classified as by comparing similar sample. First calculate the similitude statistic d (b between each classification samples and standard value0,bj), so that it is determined that in characteristic index matrix B Each sample and standard value B0Between fuzzy equivalence relation matrix D.
Using sample vector bjWith canonical reference vector b0Mahalanobis distance be：
d(b0,bj)=(b0-bj)T∑-1(b0-bj)
Calculated by mahalanobis distance function and obtain the fuzzy equivalence relation matrix D of matrix B and be：
Step 4：Acquisition terminal fault diagnosis classification results are obtained by clustering；
Wherein, clustering is dynamically to adjust to find to select appropriate threshold values λ to cut fuzzy equivalence relation matrix D Cut, so as to obtain the classification of all samples.Threshold values λ value adjusts formula：
In formula：I >=2, represent λ from the cluster number of times of 1 to 0 reduction arrangement；λi-1And ni-1Respectively represent the i-th -1 time cluster Element number and threshold values；λiAnd niThe element number and threshold values of ith cluster are represented respectively；If in the presence ofIt is then fixed The threshold values λ of adopted ith clusteriFor optimum threshold.
Step 5：According to classification results, the sample by similarity degree close to 0 is by the user base shelves in class comparison database Case and history gathered data, filter out terminal fault information point；
Step 6：According to the geographical coordinate of acquisition terminal fault message point, carry out failure with geospatial information data and determine Position, realizes the tracking of terminal fault information point and visual presentation in GIS map.
This method is extracted in filtering power information acquisition system data basis extensive, gathered data to measuring terminal and Historical archives information is sorted out using clustering, forms acquisition terminal fault diagnosis classification results, filters out terminal fault information Point, according to the geographical coordinate of acquisition terminal fault message point, fault location is carried out with geospatial information data, in GIS The tracking of terminal fault information point and visual presentation are realized on figure, so as to realize the real time data monitoring to acquisition terminal, failure Diagnosis and visualization positioning, effectively improve the accuracy rate of metering automation terminal fault positioning.
Although disclosing embodiments of the invention and accompanying drawing for the purpose of illustration, those skilled in the art can manage Solution：Do not departing from the present invention and spirit and scope of the appended claims in, it is various replace, change and modifications all be it is possible, Therefore, the scope of the present invention is not limited to embodiment and accompanying drawing disclosure of that.

Claims (5)

1. a kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering, it is characterised in that：Sequentially Perform following steps：
Step is (1)：Related data is obtained, acquisition terminal characteristic index sample matrix B is built, local all big customers is specially become The acquisition terminal of stoichiometric point carries out real-time dynamic data collection, filtering and detected, by user profile and load nature of electricity consumed, equipment manufacturer And numbering, equipment address and geographical coordinate, apply to install the base profiles such as time and history gathered data difference input database；
Step is (2)：To acquisition terminal feature matrix B and B0Pretreatment is normalized；
Step is (3)：The each element concentrated using mahalanobis distance method to data carries out similarity analysis；
Step is (4)：Acquisition terminal fault diagnosis classification results are obtained by clustering；
Step is (5)：According to classification results, by sample of the similarity degree close to 0 by the user base archives in class comparison database and History gathered data, filters out terminal fault information point；
Step is (6)：According to the geographical coordinate of acquisition terminal fault message point, fault location is carried out with geospatial information data, The tracking of terminal fault information point and visual presentation are realized in GIS map.
2. metering acquisition terminal fault diagnosis and visable positioning method according to claim 1 based on clustering, It is characterized in that：The step (1) in, acquisition terminal characteristic index sample matrix B={ b1,b2…bn(i=1,2 ..., it is n), false Fixed each sample biAll there is m characteristic index classification, b is represented byi=(bi1,bi2…bij,bim) (j=1,2 ..., m), together When, the standard feature index matrix for defining acquisition terminal is B0=(b01,b02…b0j,b0m), wherein b0jFor acquisition terminal data The standard reference value of j characteristic value.
3. metering acquisition terminal fault diagnosis and visable positioning method according to claim 1 based on clustering, It is characterized in that：The step (2) in normalization pretreatment be each characteristic index value is distributed on [0,1] interval, have Body formula is：
<mrow> <msubsup> <mi>b</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> <mo>&amp;prime;</mo> </msubsup> <mo>=</mo> <mfrac> <mrow> <mo>(</mo> <msub> <mi>b</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>b</mi> <mrow> <mi>i</mi> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msub> <mi>b</mi> <mrow> <mi>i</mi> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> </msub> <mo>-</mo> <msub> <mi>b</mi> <mrow> <mi>i</mi> <mi>m</mi> <mi>i</mi> <mi>n</mi> </mrow> </msub> <mo>)</mo> </mrow> </mfrac> </mrow>
In formula：b′ijFor bijValue after normalization, bi maxAnd bi minIt is b respectivelyiMaximum, minimum value.
4. metering acquisition terminal fault diagnosis and visable positioning method according to claim 1 based on clustering, It is characterized in that：The step (3) in, similarity analysis rule is：Characteristic value and standard feature index more more similar sample, Similarity factor absolute value is just closer to 1, and the similarity factor of not closely related sample is just closer to 0；
Similarity factor identical sample is classified as a class, first calculates the similitude statistic between each classification samples and standard value d(b0,bj), so that it is determined that each sample and standard value B in characteristic index matrix B0Between fuzzy equivalence relation matrix D；
Using sample vector bjWith canonical reference vector b0Mahalanobis distance be：
d(b0,bj)=(b0-bj)T∑-1(b0-bj)
Calculated by mahalanobis distance function and obtain the fuzzy equivalence relation matrix D of matrix B and be：
5. metering acquisition terminal fault diagnosis and visable positioning method according to claim 1 based on clustering, It is characterized in that：The step (4) in clustering be that dynamic adjustment is found and selects appropriate threshold values λ to fuzzy equivalence relation Matrix D carries out cut, so as to obtain the classification of all samples, threshold values λ value adjustment formula is：
<mfenced open = "" close = ""> <mtable> <mtr> <mtd> <mrow> <msub> <mi>&amp;lambda;</mi> <mn>0</mn> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>&amp;lambda;</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> <mo>-</mo> <msub> <mi>&amp;lambda;</mi> <mi>i</mi> </msub> </mrow> <mrow> <msub> <mi>n</mi> <mi>i</mi> </msub> <mo>-</mo> <msub> <mi>n</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msub> </mrow> </mfrac> </mrow> </mtd> <mtd> <mrow> <mi>i</mi> <mo>&amp;GreaterEqual;</mo> <mn>2</mn> </mrow> </mtd> </mtr> </mtable> </mfenced>
In formula：I >=2, represent λ from the cluster number of times of 1 to 0 reduction arrangement；λi-1And ni-1The element of the i-th -1 time cluster is represented respectively Number and threshold values；λiAnd niThe element number and threshold values of ith cluster are represented respectively；If in the presence ofThen define i-th The threshold values λ of secondary clusteriFor optimum threshold.
CN201710430041.8A 2017-06-09 2017-06-09 A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering Pending CN107316130A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710430041.8A CN107316130A (en) 2017-06-09 2017-06-09 A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710430041.8A CN107316130A (en) 2017-06-09 2017-06-09 A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering

Publications (1)

Publication Number Publication Date
CN107316130A true CN107316130A (en) 2017-11-03

Family

ID=60183867

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710430041.8A Pending CN107316130A (en) 2017-06-09 2017-06-09 A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering

Country Status (1)

Country Link
CN (1) CN107316130A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109885021A (en) * 2019-02-15 2019-06-14 中国电力科学研究院有限公司 A kind of method and system that acquisition equipment is monitored based on real-time data collection
CN111160652A (en) * 2019-12-31 2020-05-15 安徽海螺信息技术工程有限责任公司 Knowledge-sensing-based equipment abnormal state comprehensive judgment and operation and maintenance method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103345639A (en) * 2013-07-01 2013-10-09 河海大学常州校区 Support vector machine high-voltage circuit breaker fault diagnosis method based on fuzzy clustering
US20130282336A1 (en) * 2010-12-27 2013-10-24 Hitachi, Ltd. Anomaly Sensing and Diagnosis Method, Anomaly Sensing and Diagnosis System, Anomaly Sensing and Diagnosis Program and Enterprise Asset Management and Infrastructure Asset Management System
CN105372557A (en) * 2015-12-03 2016-03-02 国家电网公司 Power grid resource fault diagnosis method based on association rules

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130282336A1 (en) * 2010-12-27 2013-10-24 Hitachi, Ltd. Anomaly Sensing and Diagnosis Method, Anomaly Sensing and Diagnosis System, Anomaly Sensing and Diagnosis Program and Enterprise Asset Management and Infrastructure Asset Management System
CN103345639A (en) * 2013-07-01 2013-10-09 河海大学常州校区 Support vector machine high-voltage circuit breaker fault diagnosis method based on fuzzy clustering
CN105372557A (en) * 2015-12-03 2016-03-02 国家电网公司 Power grid resource fault diagnosis method based on association rules

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李笑等: "改进模糊聚类算法在浙江旱栽优势作物核心种质研究中的应用", 《浙江农业学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109885021A (en) * 2019-02-15 2019-06-14 中国电力科学研究院有限公司 A kind of method and system that acquisition equipment is monitored based on real-time data collection
CN111160652A (en) * 2019-12-31 2020-05-15 安徽海螺信息技术工程有限责任公司 Knowledge-sensing-based equipment abnormal state comprehensive judgment and operation and maintenance method

Similar Documents

Publication Publication Date Title
CN106022592B (en) Electricity consumption behavior abnormity detection and public security risk early warning method and device
CN109977535B (en) Line loss abnormality diagnosis method, device, equipment and readable storage medium
Xiao et al. Data mining in building automation system for improving building operational performance
CN113011481B (en) Electric energy meter function abnormality assessment method and system based on decision tree algorithm
CN110264107B (en) Large data technology-based abnormal diagnosis method for line loss rate of transformer area
CN110503256A (en) Short-term load forecasting method and system based on big data technology
CN108758357B (en) A kind of localization of bursted pipe method based on the analysis of water supply network change value of pressure
Du Toit et al. Customer segmentation using unsupervised learning on daily energy load profiles
CN107870275A (en) Arrester evaluation of running status method based on big data
CN111486555A (en) Method for carrying out energy-saving regulation and control on central air conditioner by artificial intelligence AI expert system
CN115081795A (en) Enterprise energy consumption abnormity cause analysis method and system under multidimensional scene
CN106875613A (en) A kind of fire alarm Situation analysis method
CN107316130A (en) A kind of metering acquisition terminal fault diagnosis and visable positioning method based on clustering
CN104715156A (en) Building energy-saving potential dynamic assessment method
CN116148753A (en) Intelligent electric energy meter operation error monitoring system
CN112615428A (en) Line loss analysis and treatment system and method
CN116796403A (en) Building energy saving method based on comprehensive energy consumption prediction of commercial building
CN110426996B (en) Environmental pollution monitoring method based on big data and artificial intelligence
CN112307675B (en) Neural network-based temperature-sensitive load separation identification method and system
CN117559443A (en) Ordered power utilization control method for large industrial user cluster under peak load
WO2024001253A1 (en) Fault detection method and apparatus for air conditioner, air conditioner and electronic device
CN112365082A (en) Public energy consumption prediction method based on machine learning
CN108446783A (en) A kind of prediction of new fan operation power and monitoring method
CN104318316A (en) Method of measuring user electricity utilization in real time
CN113723671B (en) Data clustering analysis method based on electricity consumption condition big data

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20171103