CN117520951A - Transformer health assessment method and system based on multiple characteristic quantities - Google Patents

Transformer health assessment method and system based on multiple characteristic quantities Download PDF

Info

Publication number
CN117520951A
CN117520951A CN202410021039.5A CN202410021039A CN117520951A CN 117520951 A CN117520951 A CN 117520951A CN 202410021039 A CN202410021039 A CN 202410021039A CN 117520951 A CN117520951 A CN 117520951A
Authority
CN
China
Prior art keywords
transformer
parameters
parameter
health
matching
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.)
Granted
Application number
CN202410021039.5A
Other languages
Chinese (zh)
Other versions
CN117520951B (en
Inventor
赵鲁臻
高明
贺昌
张国锋
严凌
岳龙
李子楠
林于涵
陈凯
潘庆
沈浩
黄桢
曹煜
周一挺
杨硕
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.)
Ningbo Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Original Assignee
Ningbo Power Supply Co of State Grid Zhejiang 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 Ningbo Power Supply Co of State Grid Zhejiang Electric Power Co Ltd filed Critical Ningbo Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority to CN202410021039.5A priority Critical patent/CN117520951B/en
Publication of CN117520951A publication Critical patent/CN117520951A/en
Application granted granted Critical
Publication of CN117520951B publication Critical patent/CN117520951B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/20Administration of product repair or maintenance
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06Energy or water supply
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Strategic Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Probability & Statistics with Applications (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Testing Electric Properties And Detecting Electric Faults (AREA)

Abstract

The invention provides a transformer health assessment method and a system based on multiple characteristic quantities, wherein the transformer health assessment method comprises the following steps: acquiring a normal running state of a transformer in a power grid system, acquiring a first parameter, establishing a running database, and classifying and extracting according to a first condition to acquire a second parameter; obtaining the current running state of the transformer to obtain a third parameter; classifying and extracting the third parameters to obtain a plurality of fourth parameters; inquiring a plurality of matching parameters in a power grid system; performing corresponding comparison calculation to obtain a first deviation set; performing operation simulation according to the first deviation set and the historical operation data of the transformer to obtain a simulation result; comparing the simulation result with the set health result to obtain a comparison result; judging whether the transformer is in a healthy state; if so, executing a first operation; if not, sending early warning information to the mobile terminal of the maintenance personnel. The method and the device improve convenience and accuracy of judging the health state of the transformer.

Description

Transformer health assessment method and system based on multiple characteristic quantities
Technical Field
The invention relates to the technical field of transformers, in particular to a transformer health assessment method and system based on multiple characteristic quantities.
Background
Along with the transformer being a core device of a transformer substation, functions of voltage conversion, current conversion, voltage stabilization and the like are achieved in the whole power grid, and the health state of the transformer determines the running reliability of the power grid. Therefore, diagnosis and evaluation of the running state of the transformer are decisive factors for reliable running and reliable power supply of the power grid.
At present, a traditional transformer is often subjected to regular maintenance, and the emergency and timeliness are not achieved. The mode of regularly carrying out inspection not only can consume a large amount of manpower and material resources, but also can cause unnecessary damage to the transformer due to untimely maintenance or too short maintenance period.
The transformer state evaluation can effectively avoid the defects caused by the traditional transformer fixed inspection mode. Conventional transformer health state evaluation often uses various homologous variables such as the electrical quantity of a transformer or the gas content in oil to be unfolded and analyzed, and a single variable is difficult to fully reflect the running state and the health condition of the current transformer, so that a certain accuracy error exists.
Disclosure of Invention
Therefore, the embodiment of the invention provides the transformer health assessment method and the system based on the multiple characteristic quantities, which improve the convenience and the accuracy of the judgment of the transformer health state.
In order to solve the above problems, the present invention provides a transformer health evaluation method based on multiple feature quantities, including: acquiring a normal running state of a transformer in a power grid system to obtain a first parameter; establishing an operation database according to the first parameters, and classifying and extracting data in the operation database according to the first conditions to obtain a plurality of corresponding second parameters; acquiring the running state of the current transformer to obtain a third parameter; classifying and extracting the third parameters according to the first condition to obtain a plurality of corresponding fourth parameters; for a plurality of fourth parameters, inquiring a plurality of second parameters corresponding to the normal operation of the matching transformer in the power grid system to obtain a plurality of matching parameters; performing corresponding comparison calculation on the fourth parameters and the matching parameters to obtain a first deviation set; performing operation simulation according to the current state according to the first deviation set and the historical operation data of the transformer to obtain a simulation result; comparing the simulation result with the set health result to obtain a comparison result; judging whether the transformer is in a healthy state according to the comparison result; if the user is healthy, executing a first operation; if the mobile terminal is unhealthy, sending early warning information to the mobile terminal of the maintenance personnel.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: the operation database is built by setting and acquiring the first parameters of the transformer in the power grid system, so that the real-time state data of the transformer can be recorded, the follow-up extraction and use are convenient, and meanwhile, the data are classified, so that the follow-up use is more convenient, and the efficiency is improved. And then extract the classification to the running state of current transformer through setting up according to the same mode, obtain the matching parameter through setting up the second parameter that matches the record in the operation database through the fourth parameter after using the classification simultaneously, through comparing with historical data, and then can judge the condition of the data of current transformer fast, and then can help follow-up quick judgement transformer's health status, improve judgement efficiency, a plurality of data have also avoided the judgement error that single data caused simultaneously, have improved the accuracy of judging transformer health status. Meanwhile, the first deviation set is obtained through matching calculation of the matching parameters and the fourth parameters, and then operation simulation is carried out, so that simulation operation can be carried out through the state of the current transformer quickly, whether the current state of the transformer continuously supports the operation of the transformer or not can be obtained through the current data quickly, the health state of the current transformer can be further judged quickly, meanwhile, the simulation result and the set health result are compared, the health state of the current transformer can be judged quickly, corresponding operation is further carried out, the health state evaluation of the transformer is more convenient and quick, and meanwhile, the accuracy is high.
In one example of the present invention, classifying and extracting data in the operation database according to the first condition, and obtaining a plurality of corresponding second parameters includes: the first parameters are classified according to types, and can be specifically classified into oil gas index data, electric index data and equipment index data.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: by setting the first parameter to be divided into oil gas index data, electric index data and equipment index data according to types, the health state of the transformer can be subjected to more accurate and careful reaction through the data, the subsequent health state evaluation of the transformer is more accurate and convenient, meanwhile, the whole data and the record can be more convenient and rapid through classification, and the efficiency of the whole evaluation process is further improved.
In an example of the present invention, for a plurality of fourth parameters, querying, in the power grid system, a plurality of second parameters corresponding to the normal operation of the matching transformer, to obtain a plurality of matching parameters further includes: taking the fourth parameters as combinations, and searching similar combinations in the second parameters recorded in the power grid system; the resulting similar combination is used as a matching parameter.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: through setting up a plurality of fourth parameters as the combination to seek a plurality of second parameter corresponding combinations in the electric wire netting system, through the form of combination for seek more accurate historical state of corresponding transformer, and then it is more accurate convenient to the healthy state aassessment of current transformer, can be convenient for follow-up data support to the carrying out state aassessment of transformer through similar combination simultaneously, has improved the efficiency of carrying out the state aassessment to the transformer, has also improved the accuracy simultaneously.
In one example of the invention, finding similar combinations among the plurality of second parameters recorded in the grid system further comprises: matching calculation is carried out on a plurality of fourth parameters one by one; defining that when the similarity ratio of the fourth parameter and the second parameter corresponding to the fourth parameter is greater than or equal to a first threshold value, the second parameter is a matching value of the fourth parameter; when the number ratio of the matching values in the group of second parameters is larger than or equal to a second threshold value, the group of second parameters are used as matching parameters; and when the number of the matching values in any group of second parameters is not more than or equal to the second threshold value, directly uploading the data in the current fourth parameter combination to the power grid system and the mobile terminal.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: the matching calculation is carried out on a plurality of fourth parameters, the second parameters, of which the similarity ratio of the fourth parameters to the corresponding second parameters is larger than or equal to the first threshold, are used as matching values, the similarity ratio is set to rapidly judge which second parameter is the matching value, further efficiency of searching similar combinations is improved, further efficiency of subsequent evaluation of the health state of the transformer can be improved, meanwhile, when the number of the matching values in one group of second parameters is larger than or equal to the second threshold, the group of second parameters are used as the matching parameters, the fitting degree of the group of second parameters serving as the matching parameters is higher, and further the subsequent evaluation of the health state of the transformer by means of the matching parameters is more accurate. When the number of the matching values in any group of second parameters is not more than or equal to a second threshold value, the data is uploaded, and the condition that the data is abnormal or the transformer is in a different state which does not exist in the history is indicated to be verified, so that the protection and health evaluation of the transformer are more reasonable, the transformer can be better protected, and the practicability and the safety are improved.
In an embodiment of the present invention, performing corresponding comparison calculation on the plurality of fourth parameters and the plurality of matching parameters to obtain a first deviation set, and further includes: respectively carrying out difference making on the fourth parameters and the corresponding matching parameters to obtain a plurality of corresponding first difference values; and integrating the plurality of first differences to obtain a first deviation set.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: the difference is made between the fourth parameters and the corresponding matching parameters to obtain a first difference value, the first difference value is integrated, the difference between the fourth parameters and the matching parameters can be quickly known, the follow-up quick judgment of the state of the current transformer and the set difference between the state of the current transformer and the set health state can be facilitated, the quick judgment of the health state of the current transformer can be facilitated, and the health state evaluation of the transformer is more convenient and quick and more accurate.
In one embodiment of the present invention, according to the first deviation set and the historical operation data of the transformer, the operation simulation is performed according to the current state, and before the simulation result is obtained, the method further includes: carrying out loss calculation on a plurality of second parameters to obtain a loss curve corresponding to each second parameter; and obtaining a safety point of each second parameter according to the loss curve.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: the loss calculation is carried out on the plurality of second parameters to obtain the corresponding damage curve, the safety point of the current second parameters can be obtained rapidly through the loss curve, and then whether the fourth parameters are under the safety condition or not can be obtained more intuitively when the fourth parameters are judged subsequently, namely whether the current transformer health state is healthy or not, so that the evaluation efficiency of the transformer health state is improved.
In one example of the present invention, according to the first deviation set and the historical operation data of the transformer, operation simulation is performed according to the current state, so as to obtain a simulation result, and the method further includes: according to the data in the first deviation set, quickly finding out the safety point of each fourth parameter and the current position of each fourth parameter in the corresponding loss curve; judging whether the current position of each fourth parameter is positioned in front of a safety point; if the fourth parameter is in front of the safety point, simulating and calculating the time required for the fourth parameter to reach the safety point to obtain a first interval value; if the fourth parameter is located after the safety point, the fourth parameter is derived as an abnormal parameter.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: the position of the current fourth parameter on the loss curve can be rapidly judged according to the first deviation set, namely, by means of the setting of the safety point, whether the current fourth parameter is located before the safety point and the distance between the current fourth parameter and the safety point are rapidly judged, so that the health state of the transformer can be evaluated more rapidly, meanwhile, whether the parameters inside the current transformer are normal or not and the loss curve can be rapidly judged, the whole health state of the transformer can be completely evaluated, and the health state of the transformer can be evaluated more accurately.
In one example of the present invention, the simulation result is compared with the set health result to obtain a comparison result, and whether the transformer is in a health state is determined according to the comparison result, and the method further includes: if the fourth parameters which are positioned behind the safety point do not exist, and the first interval values of all the fourth parameters which are positioned in front of the safety point are larger than or equal to the set health value, judging that the transformer is healthy; if the fourth parameter which is positioned behind the safety point does not exist, but the first interval value of the fourth parameter which is positioned in front of the safety point is smaller than the set health value, judging that the transformer is unhealthy; if the fourth parameter is located after the safety point, the transformer is judged to be unhealthy.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: if the fourth parameters behind the safety point do not exist and the first interval value of all the fourth parameters before the safety point are larger than or equal to the set health value, the health of the transformer is judged, the condition that all the parameters are in the normal range at present is indicated, the transformer can normally work for a period of time, namely the transformer is in a health state, otherwise, the condition that the abnormal parameters exist in the transformer is indicated, namely the possibility that the current transformer fails is indicated, namely the health state of the current transformer is unhealthy, maintenance is needed to ensure the normal operation of the transformer, and the health state of the current transformer can be rapidly evaluated through the judgment of the set health value and the first interval value, so that the evaluation efficiency and accuracy are improved.
In an example of the present invention, if the health is judged, the first operation is executed, and if the health is judged, the mobile terminal for sending the early warning information to the maintenance personnel further includes: if the health is judged, after the first period is separated, continuing to monitor and calculate; and if the mobile terminal is unhealthy, transmitting all the fourth parameters of which the first interval value of the fourth parameters before the safety point is smaller than the set health value and all the fourth parameters after the safety point to the mobile terminal.
Compared with the prior art, the technical effect achieved by adopting the technical scheme is as follows: through setting up when judging that the transformer is healthy, detect the calculation after the interval first cycle for the transformer can periodic detection, ensure the normal operating of transformer, when setting up simultaneously and judging that the transformer is unhealthy, then all send the unusual parameter and upload to mobile terminal, directly inform maintenance personal, make it can be quick through carrying out subsequent maintenance and maintenance action to the judgement of parameter, ensure the normal operating of transformer, can not influence the normal operating of surrounding equipment.
The invention also provides a transformer health evaluation system based on the multiple characteristic quantities, wherein the transformer health evaluation method according to any one of the above is applied to the transformer health evaluation system, and the transformer health evaluation system further comprises: the acquisition module is used for acquiring the normal running state of the transformer in the power grid system, and further acquiring a first parameter, a second parameter, a third parameter and a fourth parameter; the computing module is used for computing the matching parameters and the first deviation set; the evaluation control module is used for performing simulation operation, obtaining a simulation result and a comparison result, and judging whether the transformer is healthy or not according to the comparison result.
The transformer health evaluation system has all the characteristics of the transformer health evaluation method, so that the transformer health evaluation system has the same technical effects, and is not described in detail herein.
After the technical scheme of the invention is adopted, the following technical effects can be achieved:
(1) The operation database is built by setting and acquiring the first parameters of the transformer in the power grid system, so that the real-time state data of the transformer can be recorded, the follow-up extraction and use are convenient, and meanwhile, the data are classified, so that the follow-up use is more convenient, and the efficiency is improved. And then extract the classification to the running state of current transformer through setting up according to the same mode, obtain the matching parameter through setting up the second parameter that matches the record in the operation database through the fourth parameter after using the classification simultaneously, through comparing with historical data, and then can judge the condition of the data of current transformer fast, and then can help follow-up quick judgement transformer's health status, improve judgement efficiency, a plurality of data have also avoided the judgement error that single data caused simultaneously, have improved the accuracy of judging transformer health status. Meanwhile, the first deviation set is obtained through matching calculation of the matching parameters and the fourth parameters, and then operation simulation is carried out, so that simulation operation can be carried out through the state of the current transformer quickly, whether the current state of the transformer continuously supports the operation of the transformer or not can be obtained through the current data quickly, the health state of the current transformer can be further judged quickly, meanwhile, the simulation result and the set health result are compared, the health state of the current transformer can be judged quickly, corresponding operation is further carried out, the health state evaluation of the transformer is more convenient and quick, and meanwhile, the accuracy is high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings to be used in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art;
fig. 1 is a schematic flow chart of a transformer health evaluation method based on multiple feature quantities according to an embodiment of the present invention;
fig. 2 is a schematic block diagram of a transformer health evaluation system based on multiple feature quantities according to an embodiment of the present invention.
Reference numerals illustrate:
100 is a transformer health evaluation system; 110 is an acquisition module; 120 is a calculation module; 130 is an evaluation control module.
Detailed Description
In order to make the above objects, features and advantages of the present invention more comprehensible, embodiments accompanied with present invention are described in detail with embodiments of the present invention including only some but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
[ first embodiment ]
Referring to fig. 1, the invention provides a transformer health evaluation method based on multiple characteristic quantities, which comprises the following steps:
step S100: acquiring a normal running state of a transformer in a power grid system to obtain a first parameter; establishing an operation database according to the first parameters, and classifying and extracting data in the operation database according to the first conditions to obtain a plurality of corresponding second parameters; acquiring the running state of the current transformer to obtain a third parameter; classifying and extracting the third parameters according to the first condition to obtain a plurality of corresponding fourth parameters;
step S200: for a plurality of fourth parameters, inquiring a plurality of second parameters corresponding to the normal operation of the matching transformer in the power grid system to obtain a plurality of matching parameters; performing corresponding comparison calculation on the fourth parameters and the matching parameters to obtain a first deviation set;
step S300: performing operation simulation according to the current state according to the first deviation set and the historical operation data of the transformer to obtain a simulation result; comparing the simulation result with the set health result to obtain a comparison result; judging whether the transformer is in a healthy state according to the comparison result; if the user is healthy, executing a first operation; if the mobile terminal is unhealthy, sending early warning information to the mobile terminal of the maintenance personnel.
Specifically, a record of the state of a transformer in the grid system is obtained by various detectors, such as a current detector. It can be understood that the obtaining and classifying of the first parameter may obtain the following classes, i.e. oil gas index data, electric index data and equipment index data, and may further perform other classifications, which are not described herein in detail.
Furthermore, the oil gas index data, the electric index data and the equipment index data can be subjected to refining branching, for example, the oil gas index data can be differentiated into methane content, hydrogen content and the like, and the electric index data can be differentiated into winding direct current resistance, dielectric loss maximum value, polarization index and the like; the equipment index data can be divided into operation years and the like, and all the data are acquired and uploaded through a manual or detector.
Specifically, in the daily operation of the transformer, all the detectors perform real-time data detection and upload to the power grid system, and the data obtained manually is also uploaded to the power grid system manually. And these data can be integrated into a running database.
Preferably, an operation database is built by setting and acquiring the first parameters of the transformer in the power grid system, so that the real-time state data of the transformer can be recorded, the subsequent extraction and use are facilitated, and meanwhile, the data are classified, so that the subsequent use is more convenient, and the efficiency is improved. And then extract the classification to the running state of current transformer through setting up according to the same mode, obtain the matching parameter through setting up the second parameter that matches the record in the operation database through the fourth parameter after using the classification simultaneously, through comparing with historical data, and then can judge the condition of the data of current transformer fast, and then can help follow-up quick judgement transformer's health status, improve judgement efficiency, a plurality of data have also avoided the judgement error that single data caused simultaneously, have improved the accuracy of judging transformer health status. Meanwhile, the first deviation set is obtained through matching calculation of the matching parameters and the fourth parameters, and then operation simulation is carried out, so that simulation operation can be carried out through the state of the current transformer quickly, whether the current state of the transformer continuously supports the operation of the transformer or not can be obtained through the current data quickly, the health state of the current transformer can be further judged quickly, meanwhile, the simulation result and the set health result are compared, the health state of the current transformer can be judged quickly, corresponding operation is further carried out, the health state evaluation of the transformer is more convenient and quick, and meanwhile, the accuracy is high.
Specifically, classifying and extracting the data in the operation database according to the first condition to obtain a plurality of corresponding second parameters, wherein the steps include: the first parameters are classified according to types, and can be specifically classified into oil gas index data, electric index data and equipment index data.
Preferably, the first parameter is divided into the oil gas index data, the electric index data and the equipment index data according to the types, so that the health state of the transformer can be subjected to more accurate and careful reaction through the data, the subsequent health state evaluation of the transformer is more accurate and convenient, meanwhile, the whole data and the record can be more convenient and quick through classification, and the efficiency of the whole evaluation process is further improved.
Specifically, for the fourth parameters, querying the power grid system for the second parameters corresponding to the normal operation of the matching transformer, and obtaining the matching parameters further includes: taking the fourth parameters as combinations, and searching similar combinations in the second parameters recorded in the power grid system; the resulting similar combination is used as a matching parameter.
Preferably, a plurality of fourth parameters are used as combinations to search for a plurality of combinations corresponding to the second parameters in the power grid system, and the history state of the corresponding transformer is searched more accurately through the combination mode, so that the current state of health evaluation of the transformer is more accurate and convenient, meanwhile, the data support can be conveniently made for the subsequent state evaluation of the transformer through similar combinations, the state evaluation efficiency of the transformer is improved, and meanwhile, the accuracy is also improved.
Specifically, searching for similar combinations among the plurality of second parameters recorded in the grid system further includes: matching calculation is carried out on a plurality of fourth parameters one by one; defining that when the similarity ratio of the fourth parameter and the second parameter corresponding to the fourth parameter is greater than or equal to a first threshold value, the second parameter is a matching value of the fourth parameter; when the number ratio of the matching values in the group of second parameters is larger than or equal to a second threshold value, the group of second parameters are used as matching parameters; and when the number of the matching values in any group of second parameters is not more than or equal to the second threshold value, directly uploading the data in the current fourth parameter combination to the power grid system and the mobile terminal.
Specifically, the first threshold and the second threshold are set values for human beings, and can be changed according to actual conditions. Wherein the similarity ratio is calculated as the ratio of the second parameter to the fourth parameter, and the first threshold value sets a safety range, for example [0.85,1.14], i.e. the second parameter and the fourth parameter of which the ratio falls within the region match each other. And when the number ratio of the matching values in the group of second parameters is larger than or equal to the second threshold value, the matching degree is high, and the second parameters are reorganized into matching parameters. It can be understood that when the number of the matching values in any group of second parameters is not more than the second threshold, the data in the current fourth parameter combination is directly uploaded to the power grid system and the mobile terminal, and the data can be sent and marked separately for the second parameters and the fourth parameters which are already matched and the second parameters and the fourth parameters which are not matched, so that a maintainer can recognize the difference at the first time and the reaction efficiency can be improved.
Preferably, the matching calculation is performed on a plurality of fourth parameters, the second parameters of which the similarity ratio of the fourth parameters to the corresponding second parameters is larger than or equal to the first threshold value are used as matching values, the similarity ratio is set to rapidly judge which second parameter is the matching value, further efficiency of searching similar combinations is improved, further efficiency of subsequent evaluation of the health state of the transformer can be improved, meanwhile, when the number of the matching values in one group of second parameters is larger than or equal to the second threshold value, the group of second parameters are used as the matching parameters, the fitting degree of the group of second parameters serving as the matching parameters is higher, and further the subsequent evaluation of the health state of the transformer by means of the matching parameters is more accurate. When the number of the matching values in any group of second parameters is not more than or equal to a second threshold value, the data is uploaded, and the condition that the data is abnormal or the transformer is in a different state which does not exist in the history is indicated to be verified, so that the protection and health evaluation of the transformer are more reasonable, the transformer can be better protected, and the practicability and the safety are improved.
Specifically, the corresponding comparison calculation is performed on the fourth parameters and the matching parameters to obtain a first deviation set, and the method further includes: respectively carrying out difference making on the fourth parameters and the corresponding matching parameters to obtain a plurality of corresponding first difference values; and integrating the plurality of first differences to obtain a first deviation set.
Preferably, the difference is made between the fourth parameters and the corresponding matching parameters to obtain a first difference value, the first difference value sets are obtained by integrating the first difference values, how large the difference between the current fourth parameters and the matching parameters is can be quickly known by making the difference, and further, the follow-up quick judgment of the state of the current transformer and the set difference between the state of the current transformer can be facilitated, the quick judgment of the health state of the current transformer can be facilitated, and further, the health state evaluation of the transformer is more convenient and quick, and meanwhile, the method is more accurate.
Specifically, according to the first deviation set and the historical operation data of the transformer, operation simulation is performed according to the current state, and before the simulation result is obtained, the method further comprises the steps of: carrying out loss calculation on a plurality of second parameters to obtain a loss curve corresponding to each second parameter; and obtaining a safety point of each second parameter according to the loss curve.
Specifically, the loss curve may be a curve generated by corresponding the consumption amount and time of the historical operation data reaction, for example, in an oil gas index data index, a curve chart of the methane content changing along with time, and through experimental analysis on each signal loss curve, different critical values corresponding to different data can be obtained, the critical values are safety points, and when the critical values are exceeded, the data are abnormal, that is, the transformer is abnormal, and repair or maintenance is required.
Preferably, the loss calculation is performed on the plurality of second parameters to obtain a corresponding damage curve, the safety point of the current second parameter can be quickly obtained through the loss curve, and then, when the fourth parameter is judged later, whether the fourth parameter is under the safety condition or not, namely, whether the current health state of the transformer is healthy or not can be intuitively obtained, so that the evaluation efficiency of the health state of the transformer is improved.
Specifically, according to the first deviation set and the historical operation data of the transformer, operation simulation is performed according to the current state, and a simulation result is obtained, and the method further comprises the following steps: according to the data in the first deviation set, quickly finding out the safety point of each fourth parameter and the current position of each fourth parameter in the corresponding loss curve; judging whether the current position of each fourth parameter is positioned in front of a safety point; if the fourth parameter is in front of the safety point, simulating and calculating the time required for the fourth parameter to reach the safety point to obtain a first interval value; if the fourth parameter is located after the safety point, the fourth parameter is derived as an abnormal parameter.
Preferably, the position of the current fourth parameter on the loss curve can be rapidly judged according to the first deviation set, namely, by means of the setting of the safety point, whether the current fourth parameter is located before the safety point and the distance between the current fourth parameter and the safety point are rapidly judged, so that the health state of the transformer can be evaluated more rapidly, meanwhile, whether the parameter inside the current transformer is normal or not and the loss curve can be rapidly judged, the whole health state of the transformer can be completely evaluated, and the health state of the transformer can be evaluated more accurately.
Specifically, comparing the simulation result with the set health result to obtain a comparison result, and judging whether the transformer is in a health state according to the comparison result, and further comprising: if the fourth parameters which are positioned behind the safety point do not exist, and the first interval values of all the fourth parameters which are positioned in front of the safety point are larger than or equal to the set health value, judging that the transformer is healthy; if the fourth parameter which is positioned behind the safety point does not exist, but the first interval value of the fourth parameter which is positioned in front of the safety point is smaller than the set health value, judging that the transformer is unhealthy; if the fourth parameter is located after the safety point, the transformer is judged to be unhealthy.
Preferably, if the fourth parameter after the safety point does not exist and the first interval value of all the fourth parameters before the safety point is greater than or equal to the set health value, the health of the transformer is judged, the condition that all the parameters are in a normal range at present is indicated, the transformer can still work normally for a period of time, namely the healthy state is indicated, otherwise, the condition that the abnormal parameter exists in the transformer is indicated, namely the possibility of failure exists in the current transformer is indicated, namely the healthy state of the current transformer is unhealthy, maintenance is needed to ensure the normal operation of the transformer, the healthy state of the current transformer can be rapidly evaluated through the judgment of the set health value and the first interval value, and the evaluation efficiency and accuracy are improved.
Specifically, if the health is judged, the first operation is executed, and if the health is judged, the mobile terminal for sending the early warning information to the maintenance personnel further comprises: if the health is judged, after the first period is separated, continuing to monitor and calculate; and if the mobile terminal is unhealthy, transmitting all the fourth parameters of which the first interval value of the fourth parameters before the safety point is smaller than the set health value and all the fourth parameters after the safety point to the mobile terminal.
Specifically, the first period is a time set manually, and can be adjusted actually according to actual conditions.
Preferably, when the transformer is judged to be healthy, detection calculation is performed after the first period is spaced, so that the transformer can be periodically detected, normal operation of the transformer is guaranteed, meanwhile, when the transformer is judged to be unhealthy, abnormal parameters are sent and uploaded to the mobile terminal, and maintenance personnel are directly notified, so that the transformer can quickly perform subsequent maintenance and maintenance actions through judgment of the parameters, normal operation of the transformer is guaranteed, and normal operation of surrounding equipment is not affected.
[ second embodiment ]
Referring to fig. 2, the present invention further provides a transformer health evaluation system 100 based on multiple feature quantities, where the transformer health evaluation method according to any one of the above is applied to the transformer health evaluation system 100, and the transformer health evaluation system 100 further includes: the acquisition module 110 is configured to acquire a normal operation state of a transformer in the power grid system, thereby acquiring a first parameter, a second parameter, a third parameter and a fourth parameter; the calculating module 120, the calculating module 120 is used for calculating the matching parameter and the first deviation set; the evaluation control module 130, the evaluation control module 130 is used for performing simulation operation to obtain a simulation result and a comparison result, and judging whether the transformer is healthy or not according to the comparison result.
In a specific embodiment, the obtaining module 110, the calculating module 120, and the evaluation control module 130 cooperate to implement the transformer health evaluation method described above, which is not described herein.
The transformer health evaluation system 100 has all the features of the above-mentioned transformer health evaluation method, and therefore has the same technical effects, and will not be described in detail herein.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (10)

1. The transformer health assessment method based on the multiple characteristic quantities is characterized by comprising the following steps of:
acquiring a normal running state of a transformer in a power grid system to obtain a first parameter;
establishing an operation database according to the first parameters, and classifying and extracting data in the operation database according to a first condition to obtain a plurality of corresponding second parameters;
acquiring the running state of the current transformer to obtain a third parameter;
classifying and extracting the third parameters according to the first condition to obtain a plurality of corresponding fourth parameters;
for the fourth parameters, inquiring and matching the second parameters corresponding to the normal operation of the transformer in the power grid system to obtain matching parameters;
performing corresponding comparison calculation on the plurality of fourth parameters and the plurality of matching parameters to obtain a first deviation set;
performing operation simulation according to the current state according to the first deviation set and the historical operation data of the transformer to obtain a simulation result;
comparing the simulation result with a set health result to obtain a comparison result;
judging whether the transformer is in a healthy state according to a comparison result;
if the user is healthy, executing a first operation;
if the mobile terminal is unhealthy, sending early warning information to the mobile terminal of the maintenance personnel.
2. The multi-feature-based transformer health assessment method according to claim 1, wherein the classifying and extracting the data in the operation database according to the first condition to obtain the corresponding plurality of second parameters comprises:
the first parameters are classified according to types, and can be specifically classified into oil gas index data, electric index data and equipment index data.
3. The method for evaluating the health of a transformer based on multiple feature quantities according to claim 1, wherein the querying the power grid system for matching the multiple second parameters corresponding to the normal operation of the transformer for the multiple fourth parameters further comprises:
searching similar combinations in the second parameters recorded in the power grid system by taking the fourth parameters as combinations;
and taking the obtained similar combination as the matching parameter.
4. The multi-feature based transformer health assessment method of claim 3, wherein said finding similar combinations among said plurality of second parameters recorded in said grid system further comprises:
matching calculation is carried out on the fourth parameters one by one;
defining that when the similarity ratio of the fourth parameter to the corresponding second parameter falls within a first threshold, the second parameter is a matching value of the fourth parameter;
when the number ratio of the matched values in the group of second parameters is larger than or equal to a second threshold value, the group of second parameters are used as the matched parameters;
and when the number of the matching values in any group of second parameters is not more than or equal to a second threshold value, directly uploading the data in the current fourth parameter combination to the power grid system and the mobile terminal.
5. The method for evaluating the health of a transformer based on multiple feature quantities according to claim 1, wherein the performing corresponding comparison calculation on the multiple fourth parameters and the multiple matching parameters to obtain a first deviation set further comprises:
respectively differencing the fourth parameters with the corresponding matching parameters to obtain a plurality of corresponding first difference values;
and integrating the plurality of first differences to obtain the first deviation set.
6. The multi-feature-based transformer health assessment method according to claim 1, wherein the performing the operation simulation according to the current state according to the first bias set and the historical operation data of the transformer, before obtaining the simulation result, further comprises:
performing loss calculation on the plurality of second parameters to obtain a loss curve corresponding to each second parameter;
and obtaining a safety point of each second parameter according to the loss curve.
7. The method for evaluating the health of a transformer based on multiple characteristic quantities according to claim 6, wherein the performing the operation simulation according to the current state according to the first deviation set and the historical operation data of the transformer to obtain a simulation result, further comprises:
according to the data in the first deviation set, quickly finding out the safety point of each fourth parameter and the current position of each fourth parameter in the corresponding loss curve;
judging whether the position of each fourth parameter is positioned before a safety point or not;
if the fourth parameter is in front of the safety point, simulating and calculating the time required for the fourth parameter to reach the safety point to obtain a first interval value;
if the fourth parameter is located after the safety point, the fourth parameter is derived as an abnormal parameter.
8. The method for evaluating the health of a transformer based on multiple feature quantities according to claim 7, wherein comparing the simulation result with a set health result to obtain a comparison result, and determining whether the transformer is in a health state according to the comparison result, further comprises:
if the fourth parameters which are positioned behind the safety point do not exist, and the first interval values of all the fourth parameters which are positioned in front of the safety point are larger than or equal to the set health value, judging that the transformer is healthy;
if the fourth parameter which is positioned behind the safety point does not exist, but the first interval value of the fourth parameter which is positioned in front of the safety point is smaller than the set health value, judging that the transformer is unhealthy;
and if the fourth parameter which is positioned behind the safety point exists, judging that the transformer is unhealthy.
9. The method for evaluating the health of a transformer based on multiple feature values according to claim 8, wherein the step of executing the first operation if the transformer is healthy and sending the early warning information to the mobile terminal of the maintenance person if the transformer is unhealthy further comprises:
if the health is judged, after the first period is separated, continuing to monitor and calculate;
and if the mobile terminal is unhealthy, transmitting all the fourth parameters of which the first interval value of the fourth parameters before the safety point is smaller than the set health value and all the fourth parameters after the safety point to the mobile terminal.
10. A multi-feature-based transformer health assessment system, wherein the transformer health assessment method according to any one of claims 1 to 9 is applied to the transformer health assessment system, the transformer health assessment system further comprising:
the acquisition module is used for acquiring the normal running state of the transformer in the power grid system, and further acquiring the first parameter, the second parameter, the third parameter and the fourth parameter;
the calculating module is used for calculating the matching parameters and the first deviation set;
and the evaluation control module is used for performing simulation operation, obtaining the simulation result and the comparison result, and judging whether the transformer is healthy or not according to the comparison result.
CN202410021039.5A 2024-01-08 2024-01-08 Transformer health assessment method and system based on multiple characteristic quantities Active CN117520951B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410021039.5A CN117520951B (en) 2024-01-08 2024-01-08 Transformer health assessment method and system based on multiple characteristic quantities

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410021039.5A CN117520951B (en) 2024-01-08 2024-01-08 Transformer health assessment method and system based on multiple characteristic quantities

Publications (2)

Publication Number Publication Date
CN117520951A true CN117520951A (en) 2024-02-06
CN117520951B CN117520951B (en) 2024-05-24

Family

ID=89742448

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410021039.5A Active CN117520951B (en) 2024-01-08 2024-01-08 Transformer health assessment method and system based on multiple characteristic quantities

Country Status (1)

Country Link
CN (1) CN117520951B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117828512A (en) * 2024-03-04 2024-04-05 天津通安变压器有限公司 Rapid evaluation and prediction method for operation risk of oil immersed transformer

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106199305A (en) * 2016-07-01 2016-12-07 太原理工大学 Underground coal mine electric power system dry-type transformer insulation health state evaluation method
CN106841846A (en) * 2016-12-19 2017-06-13 广东电网有限责任公司电力调度控制中心 A kind of transformer state analysis and fault diagnosis method and system
CN111322732A (en) * 2020-02-24 2020-06-23 杨子靖 Air conditioner health state analysis method and system
CN113935562A (en) * 2020-07-14 2022-01-14 东南大学 Intelligent rating and automatic early warning method for health condition of power equipment
US20220137612A1 (en) * 2020-11-05 2022-05-05 Wuhan University Transformer fault diagnosis and positioning system based on digital twin
WO2023082298A1 (en) * 2021-11-10 2023-05-19 广东电网有限责任公司广州供电局 Transformer health index evaluation method and apparatus, computer device, and storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106199305A (en) * 2016-07-01 2016-12-07 太原理工大学 Underground coal mine electric power system dry-type transformer insulation health state evaluation method
CN106841846A (en) * 2016-12-19 2017-06-13 广东电网有限责任公司电力调度控制中心 A kind of transformer state analysis and fault diagnosis method and system
CN111322732A (en) * 2020-02-24 2020-06-23 杨子靖 Air conditioner health state analysis method and system
CN113935562A (en) * 2020-07-14 2022-01-14 东南大学 Intelligent rating and automatic early warning method for health condition of power equipment
US20220137612A1 (en) * 2020-11-05 2022-05-05 Wuhan University Transformer fault diagnosis and positioning system based on digital twin
WO2023082298A1 (en) * 2021-11-10 2023-05-19 广东电网有限责任公司广州供电局 Transformer health index evaluation method and apparatus, computer device, and storage medium

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
耿艳;崔慧军;于洋;张奇;: "基于辅助决策专家库的设备健康水平预测研究", 华北电力技术, no. 11, 1 November 2017 (2017-11-01) *
苏译;: "基于特征量变化的变压器状态评估方法", 现代制造技术与装备, no. 09, 15 September 2017 (2017-09-15) *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117828512A (en) * 2024-03-04 2024-04-05 天津通安变压器有限公司 Rapid evaluation and prediction method for operation risk of oil immersed transformer

Also Published As

Publication number Publication date
CN117520951B (en) 2024-05-24

Similar Documents

Publication Publication Date Title
CN117520951B (en) Transformer health assessment method and system based on multiple characteristic quantities
CN112561736A (en) Fault diagnosis system and method for relay protection device of intelligent substation
CN108828406A (en) The fault recognition method and its system of non-intrusion type user power utilization
CN114252749B (en) Transformer partial discharge detection method and device based on multiple sensors
CN118137682B (en) Active detection system and method for hardware faults of power distribution automation master station
CN117612345A (en) Power equipment state monitoring and alarming system and method
CN116520068B (en) Diagnostic method, device, equipment and storage medium for electric power data
CN112417763B (en) Defect diagnosis method, device and equipment for power transmission line and storage medium
CN117289162A (en) Battery health prediction method and system based on group end convergence method
CN116184265A (en) Lightning arrester leakage current detection method and system based on multi-classification SVM
CN113177646A (en) Power distribution equipment online monitoring method and system based on self-adaptive edge proxy
CN117807155B (en) Method, equipment and storage medium for generating multi-dimensional early warning prompt information
CN117491813A (en) Insulation abnormality detection method for power battery system of new energy automobile
CN113671287B (en) Intelligent detection method, system and readable storage medium for power grid automation terminal
CN114971308A (en) Transformer health condition assessment method based on multi-dimensional data analysis
CN111986469A (en) Intelligent diagnosis method for field terminal fault
CN106154122A (en) A kind of retrospective power cable detecting and controlling system
CN111487562B (en) Early warning and decision-making assisting method for power transformer state
CN117093904B (en) Transformer substation fire detection data acquisition method
CN118604681B (en) Short circuit diagnosis method and system based on 4G Internet of things
CN118783636A (en) Power quality assessment method and system based on private transformer acquisition terminal
CN116945906A (en) Battery management system and fault early warning method for mining new energy vehicle
CN117825895A (en) Comprehensive monitoring device and method for partial discharge and oil chromatography linkage of transformer
CN118777970A (en) State monitoring system of electric energy metering device
CN118706192A (en) Electrical cabinet circuit protection fireproof monitoring method and system

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
GR01 Patent grant
GR01 Patent grant