CN109615086A - A kind of generation method and system of O&M assisted tag - Google Patents
A kind of generation method and system of O&M assisted tag Download PDFInfo
- Publication number
- CN109615086A CN109615086A CN201811183792.5A CN201811183792A CN109615086A CN 109615086 A CN109615086 A CN 109615086A CN 201811183792 A CN201811183792 A CN 201811183792A CN 109615086 A CN109615086 A CN 109615086A
- Authority
- CN
- China
- Prior art keywords
- label
- neural network
- data
- network model
- information
- 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
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
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The present invention relates to power supply unit O&M technologies, and in particular to a kind of generation method and system of O&M assisted tag, comprising the following steps: A) import equipment account and historical information；B) when operation maintenance personnel on-site maintenance, acquisition and upstream device information and label are arranged；C neural network model and training) are established；D) after subsequent same category of device on-site maintenance, operation maintenance personnel uploading device information and label after device information update and will substitute into the neural network model in step C, obtain model label, model accuracy in measurement period；E) if model accuracy reaches given threshold in measurement period, label is generated for whole same categories of device.The beneficial effects of the present invention are: passing through the generation and accumulation of O&M label, information guiding and experience towards O&M can be provided for subsequent same equipment and same category of device, targetedly auxiliary improves O&M efficiency, alleviates the heavy problem of the current O&M of power grid.
Description
Technical field
The present invention relates to power supply unit O&M technologies, and in particular to a kind of generation method and system of O&M assisted tag.
Background technique
The intelligent construction of power grid achieves significant progress, and automation control appliance occupies the main portion of power supply unit
Point.However automation equipment has the characteristics of strongly professional and easy break-down, and power grid O&M task is caused to increase.Provincial power network at present
The average fault ticket generated daily is more than 7000, and corresponding operation maintenance personnel quantity and skills training do not follow quickly
Development, causes operation maintenance personnel task heavy, due to being not enough familiar with new equipment, lacks experience and the decline of O&M efficiency.Urgent
O&M demand and the contradiction of relatively low O&M efficiency are increasingly prominent.It is existing to equipment due to lacking at present in worksheet
The acquisition and analysis of field data cause part without sending the work order of work to carry out sending work, waste O&M resource.Partial technical problems
Solution experience due to lacking accumulation and propagating, cause same problem to repeat investigation and solve, it is time-consuming and laborious.How electricity is quickly improved
Net O&M efficiency, the top priority built at power grid O&M.
Chinese patent CN206639241U, publication date on November 4th, 2017, a kind of power equipment O&M passive ultra-high frequency
RFID speciality label, including upper casing and lower casing, be provided in the upper casing ultrahigh frequency RFID chip and antenna, upper casing and lower casing it
Between be provided with baffle；Upper casing set is buckled in the opening of lower casing, and upper casing and lower casing constitute closed shell, and ultrahigh frequency RFID chip is
Has the function of the ultrahigh frequency RFID chip of the power equipment of device identification and data storage function；The upper casing outboard end is set
It is equipped with heavy platform, the utility model provides a kind of power equipment O&M passive ultra-high frequency RFID speciality label, structure novel；To electric power
Equipment O&M carries out special designing with ultrahigh frequency RFID speciality label, can meet power equipment O&M ultrahigh frequency RFID speciality label
Function, realize power equipment O&M plain code mark and data storage management, improve power equipment O&M management application
Efficiency；In addition the utility model supports that multiple mounting modes include gum bonding method, screw is riveted mode, metal binding belt is tied up
Mode etc..It needs to make dedicated special label body for every power supply unit, higher cost, and effective for data deficiency
Collect accumulation, it is difficult to meet the needs of improving O&M efficiency.
Summary of the invention
The technical problem to be solved by the present invention is O&M activity at present is lacked experience the technical issues of data accumulation.It proposes
A kind of is the generation side that can effectively assist improving the O&M assisted tag of O&M efficiency that equipment is arranged towards O&M label
Method and system.
In order to solve the above technical problems, the technical solution used in the present invention are as follows: a kind of generation side of O&M assisted tag
Method, comprising the following steps: A) establish data server, the account information and historical information of ingress area power grid power supply unit；B)
When operation maintenance personnel on-site maintenance, acquires facility information and label is set, and information and label are passed back into data server；C)
Neural network model is established, as the sample data training neural network model after top n label is associated with facility information；D)
After subsequent same category of device on-site maintenance, operation maintenance personnel uploading device information and label after device information update and will substitute into step C
In neural network model, obtain model label, model is correctly secondary if model label is identical as the label that operation maintenance personnel uploads
Number plus 1, on the contrary then model errors number, which adds 1 and operation maintenance personnel is uploaded label as objective result, adjusts neural network model；
E) if model accuracy reaches given threshold in measurement period, the information of whole same categories of device is substituted into the neural network
Model, using neural network model output result as the label of corresponding equipment.
Preferably, when the corresponding neural network model of some label is after the training of preceding (N+M) a sample data, it is correct
Rate is still below given threshold, then executes following steps: C1) H sample data, differentiation are taken out in (N+M) a sample data in the past
Data volume field and quantity of state field in sample data convert quantity of state by numerical intervals segment processing for data volume field
Whole quantity of state fields, are split into boolean's value field of n by field, n be quantity of state field can value quantity；C2) by sample
The result that the data volume field of notebook data is added between any two, subtracts each other, is divided by and is multiplied is added to new data field；C3)
Similarity of the H sample data after processing between each field is calculated, similarity is higher than the field of given threshold as joining
Examine field；C4 the reference field of (N+M) a sample data, is instructed after being associated with label as new sample data again before) obtaining
Practice neural network model, is then continued to execute from step D.
Preferably, the label reflects the apparatus characteristic information towards O&M, the label includes status label and mistake
Journey label, the status tag characterization field data feature, the process tag characterization are related to the spy of device history working condition
Sign.
Preferably, the status label is directly judged by operation maintenance personnel by device context data and account data and life
At.
Preferably, will make after status label and the newest account information association of equipment when the trained neural network model
For sample data, the training neural network model.
Preferably, the feature of the process tag characterization is the spy that device history state and presence states are collectively formed
Sign, the process label are formulated by device context status data and device history information by operation maintenance personnel and are generated.
Preferably, process label and equipment account information and history are safeguarded when the trained neural network model
Sample data, the training neural network model are used as after data correlation.
A kind of generation system of O&M assisted tag, suitable for a kind of generation method of O&M assisted tag as the aforementioned,
Including handheld terminal, memory, processor and communication device, the communication device and memory are connect with processor, described
Handheld terminal is connect by communication device with processor, and the handheld terminal receives the data that operation maintenance personnel inputs and by the number
According to the processor is transferred to, the processor executes following steps: A) data server is established, the power supply of ingress area power grid is set
Standby account information and historical information；B) when operation maintenance personnel on-site maintenance, it is arranged by handheld terminal receiving device information and label,
And information and label are passed back into data server；C neural network model) is established, top n label is associated with facility information
Afterwards as the sample data training neural network model；D) after subsequent same category of device on-site maintenance, operation maintenance personnel passes through hand-held whole
Uploading device information and label are held, after device information update and the neural network model in step C will be substituted into, obtain model mark
Label, the correct number of model adds 1 if model label is identical as the label that operation maintenance personnel uploads, otherwise model errors number adds 1
And operation maintenance personnel is uploaded into label as objective result and adjusts neural network model；E) if model accuracy reaches in measurement period
To given threshold, then the information of whole same categories of device is substituted into the neural network model, neural network model is exported into result
Label as corresponding equipment.
Substantial effect of the invention is: it can be subsequent same equipment and same by the generation and accumulation of O&M label
Class equipment provides information guiding and experience towards O&M, and targetedly auxiliary improves O&M efficiency, alleviates power grid mesh
The heavy problem of preceding O&M.
Detailed description of the invention
Fig. 1 is that O&M assisted tag generates system construction drawing.
Fig. 2 is the generation method flow diagram of O&M assisted tag.
Fig. 3 is the method flow block diagram for generating new sample data.
Fig. 4 is that label assists O&M citing.
Wherein, 100, memory, 200, processor, 300, communication device, 400, handheld terminal.
Specific embodiment
Below by specific embodiment, and in conjunction with attached drawing, a specific embodiment of the invention is further described in detail.
As shown in Figure 1, generating system construction drawing, communication device 300 and memory 100 and processing for O&M assisted tag
Device 200 connects, and handheld terminal 400 is connect by communication device 300 with processor 200, and it is defeated that handheld terminal 400 receives operation maintenance personnel
The data that enter simultaneously transfer data to processor 200, when operation maintenance personnel on-site maintenance, by 400 receiving device information of handheld terminal
And label setting, and information and label are passed back into data server.
As shown in Fig. 2, being the generation method flow diagram of O&M assisted tag, comprising the following steps: A) establish data clothes
Business device, the account information and historical information of ingress area power grid power supply unit；B) when operation maintenance personnel on-site maintenance, acquisition equipment letter
Label is ceased and be arranged, and information and label are passed back into data server；C neural network model) is established, by top n label
As the sample data training neural network model after being associated with facility information；D) after subsequent same category of device on-site maintenance, O&M
Personnel's uploading device information and label after device information update and will substitute into the neural network model in step C, obtain model mark
Label, the correct number of model adds 1 if model label is identical as the label that operation maintenance personnel uploads, otherwise model errors number adds 1
And operation maintenance personnel is uploaded into label as objective result and adjusts neural network model；E) if model accuracy reaches in measurement period
To given threshold, then the information of whole same categories of device is substituted into neural network model, using neural network model output result as
The label of corresponding equipment.
As shown in figure 3, to generate the method flow block diagram of new sample data, when the corresponding neural network mould of some label
For type after preceding (N+M) a sample data training, accuracy is still below given threshold, then executes following steps: C1) the past (N+
M H sample data) is taken out in a sample data, data volume field and quantity of state field in sample data is distinguished, by data volume
Quantity of state field, is split into boolean's value field of n by field normalized, n be quantity of state field can value quantity；
C2 the result that the data volume field of sample data is added between any two, subtracts each other, is divided by and is multiplied) is added to new data word
Section；C3 similarity of the H sample data after processing between each field, the field by similarity higher than given threshold) are calculated
As reference field；C4 the reference field of (N+M) a sample data before) obtaining, as new sample data after being associated with label
Re -training neural network model is then continued to execute from step D.The method of data volume field normalized is to take H sample
The maximum value of the data volume field in notebook data, using the ratio of the value of data volume field and the maximum value as each sample data
In the field normalization after value.By manually according to the data Distribution value of data volume field, demarcation interval, such as high, medium and low area
Between, data value is then replaced by section title, converts quantity of state field for data volume field.Quantity of state field splits citing such as
Under: the active status field of certain equipment includes open state, closed state and trouble hunting state, then splits into out the field
It opens, close and three fields of trouble hunting, which is Boolean, and after certain live O&M, equipment state is to open, then
The value of open state field is very, to close and the value of trouble hunting mode field is false.Partial data value itself is not intentional
Justice, but its locating section is meaningful, if some transformer-supplied user is 300 families, and another transformer-supplied user
For 200 families, then the label of " fault incidence is big " should all be arranged in two transformers, and operation maintenance personnel is instructed preferably to repair.If
Neural network model is imported using numerical value 300 and 200, then neural network model is difficult to be adjusted to suitable coefficient two values fortune
Result is close after calculation, but after progress data value interval division, numerical value 200 and 300 is divided into the same numerical intervals, then can
The difficulty for reducing neural network adjusting parameter, keeps result more accurate.After processing, all Booleans of device data, can
It will be not easy to the field by numerical expression, be quickly and easily converted into the data mode that neural network model is capable of handling, improved
Training effectiveness.
Label reflects the apparatus characteristic information towards O&M, and label includes status label and process label, status label list
Field data feature is levied, process tag characterization is related to the feature of device history working condition.Status label is by operation maintenance personnel by setting
Standby field data and account data directly judge and generate.It is when training neural network model, status label and equipment is newest
Sample data, training neural network model are used as after account information association.
The feature of process tag characterization is the feature that is collectively formed of device history state and presence states, process label by
Operation maintenance personnel is formulated by device context status data and device history information and is generated.When training neural network model, by process
Sample data, training neural network model are used as after label and equipment account information and history maintenance data correlation.
As shown in figure 4, work order 1 is the user of intelligent electric meter active reporting to explain how label assists the citing of O&M
Power-off fault, but be associated with " arrearage " label after being checked by operation maintenance personnel on the user, then other smart machines of the user
The power-off fault of upload can show " arrearage " label, and worksheet process personnel save O&M resource by not sending work to handle.
Work order 2 is entire platform area power-off fault, but by operation maintenance personnel or business personnel in advance will " operation expanding construction in " label with
The platform area power-off fault work order that whole smart machines report in the area this Qu Guanlian, Ze Gaitai can show the label, at work order
It manages process personnel to handle by work order hang-up, row observes conditions and handles again after standby service expansion construction.Work order 3 sets for user
Standby failure, when operation maintenance personnel last time send work scene O&M by the user-association label of " preferred process rank height ", then this
Fault ticket preferentially can send work to handle, and improve specific aim and whole O&M efficiency, reduce loss.
Above-mentioned embodiment is only a preferred solution of the present invention, not the present invention is made in any form
Limitation, there are also other variations and modifications on the premise of not exceeding the technical scheme recorded in the claims.
Claims (10)
1. a kind of generation method of O&M assisted tag, which is characterized in that
The following steps are included:
A data server, the account information and historical information of ingress area power grid power supply unit) are established；
B it) when operation maintenance personnel on-site maintenance, acquires facility information and label is set, and information and label are passed back into data clothes
Business device；
C neural network model) is established, as the sample data training neural network after top n label is associated with facility information
Model；
D) after subsequent same category of device on-site maintenance, operation maintenance personnel uploading device information and label will be after device information updates and generation
Enter the neural network model in step C, obtains model label, the model if model label is identical as the label that operation maintenance personnel uploads
Correct number adds 1, and on the contrary then model errors number, which adds 1 and operation maintenance personnel is uploaded label as objective result, adjusts neural network
Model；
E) if model accuracy reaches given threshold in measurement period, the information of whole same categories of device is substituted into the nerve
Network model, using neural network model output result as the label of corresponding equipment.
2. a kind of generation method of O&M assisted tag according to claim 1, which is characterized in that
When the corresponding neural network model of some label is after the training of preceding (N+M) a sample data, accuracy in measurement period
Lower than given threshold, then following steps are executed:
C1 H sample data) is taken out in (N+M) a sample data in the past, distinguishes data volume field and state in sample data
Field is measured, quantity of state field is converted by numerical intervals segment processing for data volume field, whole quantity of state fields is split into n
A boolean's value field, n be quantity of state field can value quantity；
C2 the result that the data volume field of sample data is added between any two, subtracts each other, is divided by and is multiplied) is added to new number
According to field；
C3 similarity of the H sample data after processing between each field, the field by similarity higher than given threshold) are calculated
As reference field；
C4 the reference field of (N+M) a sample data before) obtaining, as new sample data re -training mind after being associated with label
Through network model, then continued to execute from step D.
3. a kind of generation method of O&M assisted tag according to claim 1 or 2, which is characterized in that
The label reflects the apparatus characteristic information towards O&M, and the label includes status label and process label, described existing
Shape tag characterization field data feature, the process tag characterization are related to the feature of device history working condition.
4. a kind of generation method of O&M assisted tag according to claim 3, which is characterized in that
The status label is directly judged and is generated by device context data and account data by operation maintenance personnel.
5. a kind of generation method of O&M assisted tag according to claim 4, which is characterized in that
When the trained neural network model, sample data, instruction will be used as after status label and the newest account information association of equipment
Practice the neural network model.
6. a kind of generation method of O&M assisted tag according to claim 3, which is characterized in that
The feature of the process tag characterization is the feature that device history state and presence states are collectively formed, the process mark
Label are formulated by device context status data and device history information by operation maintenance personnel and are generated.
7. a kind of generation method of O&M assisted tag according to claim 4, which is characterized in that
The feature of the process tag characterization is the feature that device history state and presence states are collectively formed, the process mark
Label are formulated by device context status data and device history information by operation maintenance personnel and are generated.
8. a kind of generation method of O&M assisted tag according to claim 3, which is characterized in that
When the trained neural network model, by conduct after process label and equipment account information and history maintenance data correlation
Sample data, the training neural network model.
9. a kind of generation method of O&M assisted tag according to claim 4, which is characterized in that
When the trained neural network model, by conduct after process label and equipment account information and history maintenance data correlation
Sample data, the training neural network model.
10. a kind of generation system of O&M assisted tag is suitable for such as a kind of described in any item O&M auxiliary of claim 1-9
The generation method of label, which is characterized in that
Including handheld terminal, memory, processor and communication device, the communication device and memory are connect with processor,
The handheld terminal is connect by communication device with processor, and the handheld terminal receives the data that operation maintenance personnel inputs and by institute
It states data and is transferred to the processor, the processor executes following steps:
A data server, the account information and historical information of ingress area power grid power supply unit) are established；
B) when operation maintenance personnel on-site maintenance, it is arranged by handheld terminal receiving device information and label, and information and label is returned
Pass to data server；
C neural network model) is established, as the sample data training neural network after top n label is associated with facility information
Model；
D) after subsequent same category of device on-site maintenance, operation maintenance personnel is believed equipment by handheld terminal uploading device information and label
After breath updates and the neural network model in step C is substituted into, obtains model label, if the mark that model label and operation maintenance personnel upload
Sign identical, the correct number of model adds 1, and on the contrary then model errors number adds 1 and operation maintenance personnel is uploaded label as objective result
Adjust neural network model；
E) if model accuracy reaches given threshold in measurement period, the information of whole same categories of device is substituted into the nerve
Network model, using neural network model output result as the label of corresponding equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811183792.5A CN109615086B (en) | 2018-10-11 | 2018-10-11 | Method and system for generating operation and maintenance auxiliary label |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811183792.5A CN109615086B (en) | 2018-10-11 | 2018-10-11 | Method and system for generating operation and maintenance auxiliary label |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109615086A true CN109615086A (en) | 2019-04-12 |
| CN109615086B CN109615086B (en) | 2020-10-20 |
Family
ID=66002388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811183792.5A Active CN109615086B (en) | 2018-10-11 | 2018-10-11 | Method and system for generating operation and maintenance auxiliary label |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109615086B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275210A (en) * | 2020-01-14 | 2020-06-12 | 国网山西省电力公司电力科学研究院 | Transformer substation auxiliary equipment ledger information sharing method and device |
| CN111340326A (en) * | 2019-12-24 | 2020-06-26 | 国网浙江省电力有限公司嘉兴供电公司 | Power terminal monitoring method and device based on neural network fault prediction |
| CN112258068A (en) * | 2020-10-30 | 2021-01-22 | 武汉理工光科股份有限公司 | Security activity scheme generation and dynamic update method and device |
| CN114284939A (en) * | 2021-12-27 | 2022-04-05 | 国网北京市电力公司 | Power distribution network operation and maintenance inspection method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484761A (en) * | 2014-12-17 | 2015-04-01 | 孙翔 | Service life processing system of equipment |
| US20150213108A1 (en) * | 2013-08-16 | 2015-07-30 | Tencent Technology (Shenzhen) Company Limited | Multidimensional data process method and device thereof |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
-
2018
- 2018-10-11 CN CN201811183792.5A patent/CN109615086B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150213108A1 (en) * | 2013-08-16 | 2015-07-30 | Tencent Technology (Shenzhen) Company Limited | Multidimensional data process method and device thereof |
| CN104484761A (en) * | 2014-12-17 | 2015-04-01 | 孙翔 | Service life processing system of equipment |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN108174165A (en) * | 2018-01-17 | 2018-06-15 | 重庆览辉信息技术有限公司 | Electric power safety operation and O＆M intelligent monitoring system and method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111340326A (en) * | 2019-12-24 | 2020-06-26 | 国网浙江省电力有限公司嘉兴供电公司 | Power terminal monitoring method and device based on neural network fault prediction |
| CN111275210A (en) * | 2020-01-14 | 2020-06-12 | 国网山西省电力公司电力科学研究院 | Transformer substation auxiliary equipment ledger information sharing method and device |
| CN111275210B (en) * | 2020-01-14 | 2023-05-02 | 国网山西省电力公司电力科学研究院 | Method and device for sharing account information of auxiliary equipment of transformer substation |
| CN112258068A (en) * | 2020-10-30 | 2021-01-22 | 武汉理工光科股份有限公司 | Security activity scheme generation and dynamic update method and device |
| CN112258068B (en) * | 2020-10-30 | 2022-03-29 | 武汉理工光科股份有限公司 | Security activity scheme generation and dynamic update method and device |
| CN114284939A (en) * | 2021-12-27 | 2022-04-05 | 国网北京市电力公司 | Power distribution network operation and maintenance inspection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109615086B (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615086A (en) | A kind of generation method and system of O&M assisted tag | |
| CN106505731B (en) | A kind of intelligent substation and scheduling are to test case intelligent generating system and a method | |
| CN107180314B (en) | Operation and maintenance business model modeling method based on primary and secondary system incidence relation | |
| CN109977535A (en) | A kind of line loss abnormality diagnostic method, device, equipment and readable storage medium storing program for executing | |
| CN110889466B (en) | Transformer area line loss analysis method based on line loss classifier | |
| CN105137215B (en) | Medical equipment cost-benefit wireless monitoring analysis system and medical equipment cost-benefit wireless monitoring analysis method | |
| CN108898239A (en) | A kind of site selection method for distribution transformer based on data analysis | |
| CN114049235A (en) | Agricultural information management system based on Internet of things | |
| CN109738723A (en) | A kind of electric energy meter three-phase automatic identification method | |
| CN107612592A (en) | A kind of efficiency interactive system based on power line transmission | |
| CN112905670B (en) | Electric energy meter system for indoor power failure fault research and judgment and indoor power failure fault research and judgment method | |
| CN111126825B (en) | Intelligent charge-discharge energy-saving management system for visual battery and control method thereof | |
| de Macedo et al. | Opportunities and challenges of DSM in smart grid environment | |
| CN204010288U (en) | A kind of power information remote wireless terminal collector | |
| CN103578043B (en) | Device, method and system for processing power grid data | |
| CN105631552A (en) | Power distribution automation engineering economic benefit assessment method based on whole life cycle | |
| CN105021054A (en) | Intelligent electric furnace combining internet-of-things technology and mobile management application | |
| CN112003374B (en) | Wireless monitoring system for power quality | |
| CN114200203A (en) | Fault monitoring method and system for metering device of transformer substation | |
| CN202904690U (en) | Intelligent patrol system of switching station | |
| CN112560908A (en) | Cloud-end cooperative load identification system and method | |
| CN104268677A (en) | Energy consumption benchmarking computerization handheld terminal system and benchmarking computerization method | |
| CN210015512U (en) | Line loss statistical analysis device and system | |
| CN211086454U (en) | Enterprise production state monitoring system based on NB-IOT | |
| CN116310258B (en) | Three-dimensional construction management system and method based on transformer substation live-action |
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 |