CN112347619B - Power transformation equipment fault supervision method, system, terminal and storage medium - Google Patents
Power transformation equipment fault supervision method, system, terminal and storage medium Download PDFInfo
- Publication number
- CN112347619B CN112347619B CN202011145984.4A CN202011145984A CN112347619B CN 112347619 B CN112347619 B CN 112347619B CN 202011145984 A CN202011145984 A CN 202011145984A CN 112347619 B CN112347619 B CN 112347619B
- Authority
- CN
- China
- Prior art keywords
- power transformation
- transformation equipment
- temperature
- model
- deep learning
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- Y—GENERAL 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS 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
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems 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)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a power transformation equipment fault supervision method, a system, a terminal and a storage medium, comprising the following steps: periodically collecting monitoring data of the power transformation equipment according to a preset collecting period; inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value; marking a time stamp for the hottest point temperature value, and generating a temperature time sequence of the power transformation equipment according to the time stamp; inputting the temperature time sequence into a pre-trained Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach a fault temperature value; and if the required time reaches a preset time threshold, generating fault early warning of the power transformation equipment. The invention can effectively predict the faults of the power transformation equipment so as to timely start the dispatching scheme of the power transmission line to timely maintain the power transformation equipment with fault early warning, thereby enhancing the stability of the power transmission system.
Description
Technical Field
The invention relates to the technical field of power transmission systems, in particular to a power transformation equipment fault supervision method, a power transformation equipment fault supervision system, a power transformation equipment fault supervision terminal and a power transformation equipment fault supervision storage medium.
Background
The power transformation equipment is an important node in the power transmission system, plays a role of converting voltage and electric energy in the system, is very important and expensive power equipment in the power system, and needs very long maintenance time once overload accidents occur, so that serious influence is caused, and the safety and reliability of operation of the power transformation equipment are directly related to the safety and stability of the whole power grid. With the acceleration of power grid construction, the single capacity of the transformer is continuously increased, and the voltage level is also continuously improved. In general, the larger the capacity, the higher the voltage class, the higher the overload failure rate, and the larger the loss and the influence range due to the failure.
At present, no effective fault early warning method for the power transformation equipment exists, and only after the power transformation equipment fails, the fault is found and maintained, so that the power transmission system is unstable.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a power transformation equipment fault supervision method, a system, a terminal and a storage medium, so as to solve the technical problems.
In a first aspect, the present invention provides a method for supervising a fault of a power transformation device, including:
periodically collecting monitoring data of the power transformation equipment according to a preset collecting period;
inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value;
marking a time stamp for the hottest point temperature value, and generating a temperature time sequence of the power transformation equipment according to the time stamp;
inputting the temperature time sequence into a pre-trained Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach a fault temperature value;
and if the required time reaches a preset time threshold, generating fault early warning of the power transformation equipment.
Further, the collecting monitoring data of the power transformation device includes:
collecting the actual load of the power transformation equipment;
and collecting the ambient temperature of the power transformation equipment.
Further, the training method of the deep learning model comprises the following steps:
dividing the power transformation equipment with the same specification and the same temperature level in the power transmission system into similar power transformation equipment;
summarizing historical data of similar power transformation equipment into a deep learning model training set, wherein the historical data comprises historical collected monitoring data and corresponding hottest point temperature values;
and training the deep learning model by using the training set, and marking the trained deep learning model with corresponding power transformation equipment specifications and temperature grades.
Further, the Prophet model training method comprises the following steps:
summarizing historical sequence data of similar power transformation equipment into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation equipment;
creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters;
and training the pre-created Prophet model by using the temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
Further, the method further comprises:
acquiring the specification and the environmental temperature of the current power transformation equipment, and acquiring the temperature grade according to the environmental temperature;
and inquiring a deep learning model or a Prophet model with the matched marks according to the specification and the temperature level.
In a second aspect, the present invention provides a fault supervision system for a power transformation device, comprising:
the data acquisition unit is configured to periodically acquire monitoring data of the power transformation equipment according to a preset acquisition period;
the temperature acquisition unit is configured to input the monitoring data into a pre-trained deep learning model to acquire a corresponding hottest point temperature value;
a sequence generating unit, configured to mark a timestamp for the hottest point temperature value, and generate a temperature time sequence of the power transformation device according to the timestamp;
the time prediction unit is configured to input the temperature time sequence into a pre-trained Prophet model, and predict the time required by the hottest point temperature value of the power transformation equipment to reach a fault temperature value;
and the fault early warning unit is configured to generate fault early warning of the power transformation equipment if the required time reaches a preset time threshold.
Further, the training method of the deep learning model comprises the following steps:
dividing the power transformation equipment with the same specification and the same temperature level in the power transmission system into similar power transformation equipment;
summarizing historical data of similar power transformation equipment into a deep learning model training set, wherein the historical data comprises historical collected monitoring data and corresponding hottest point temperature values;
and training the deep learning model by using the training set, and marking the trained deep learning model with corresponding power transformation equipment specifications and temperature grades.
Further, the Prophet model training method comprises the following steps:
summarizing historical sequence data of similar power transformation equipment into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation equipment;
creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters;
and training the pre-created Prophet model by using the temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
In a third aspect, a terminal is provided, including:
a processor, a memory, wherein,
the memory is used for storing a computer program,
the processor is configured to call and run the computer program from the memory, so that the terminal performs the method of the terminal as described above.
In a fourth aspect, there is provided a computer storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of the above aspects.
The invention has the advantages that,
according to the power transformation equipment fault supervision method, system, terminal and storage medium, the hottest point temperature values of the power transformation equipment are obtained according to the monitoring data of the power transformation equipment through the deep learning model, then a temperature time sequence is generated according to all the hottest point temperature values, and time required for reaching the fault temperature values is predicted according to the temperature time sequence by utilizing the trained Prophet model, wherein the temperature threshold corresponds to the temperature during fault. Therefore, the fault of the power transformation equipment can be effectively predicted, so that a dispatching scheme of the power transmission line can be started in time to maintain the power transformation equipment with fault early warning in time, and the stability of a power transmission system is enhanced.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a schematic flow chart of a method of one embodiment of the invention.
FIG. 2 is a schematic block diagram of a system of one embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
FIG. 1 is a schematic flow chart of a method of one embodiment of the invention. The execution body of fig. 1 may be a fault supervision system of a power transformation device.
As shown in fig. 1, the method includes:
step 110, periodically collecting monitoring data of the power transformation equipment according to a preset collection period;
step 120, inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value;
step 130, marking a time stamp for the hottest point temperature value, and generating a temperature time sequence of the power transformation equipment according to the time stamp;
step 140, inputting the temperature time sequence into a pre-trained Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach a fault temperature value;
and 150, if the required time reaches a preset time threshold, generating fault early warning of the power transformation equipment.
In order to facilitate understanding of the present invention, the present invention further describes the fault supervision method for power transformation equipment according to the principles of the fault supervision method for power transformation equipment according to the present invention, in combination with the process of fault supervision for power transformation equipment in the embodiment.
Specifically, the power transformation equipment fault supervision method comprises the following steps:
s1, periodically collecting monitoring data of the power transformation equipment according to a preset collection period.
The acquisition period is set to be 1h, and the actual load and the environmental temperature of the power transformation equipment are acquired every 1 h.
And calculating the average value of the environmental temperature of the power transformation equipment within 24 hours every 24 hours, updating the average value to be the average environmental temperature, and clearing the historical average environmental temperature.
S2, inputting the monitoring data into a pre-trained deep learning model, and obtaining a corresponding hottest point temperature value.
Firstly, equipment codes of all power transformation equipment in a power transmission system are obtained, a database is created in each equipment code, and monitoring data of the power transformation equipment are stored in the corresponding database.
The specification parameters (such as rated load) and average environmental temperature of all the power transformation equipment are collected, 5 ℃ is set to be one grade, for example, 0-5 ℃ is set to be one grade, 5-10 ℃ is set to be one grade, 10-15 ℃ is set to be one grade, and the like.
Firstly, according to specification parameters, the power transformation devices with the same specification parameters are divided into the same group, then the power transformation devices in each group are classified according to the average environment temperature, and the power transformation devices with the same average environment temperature are divided into the same class. The similar power transformation equipment is the power transformation equipment with the same specification parameters and the same average ambient temperature level.
And summarizing the historical actual load and the corresponding actual hottest point temperature value of the similar power transformation equipment to generate a training set for training the deep learning model, and marking the specification and the temperature grade of the corresponding power transformation equipment after the deep learning model is trained. That is, each type of power transformation device corresponds to one deep learning model.
When a fault is predicted on a certain power transformation device, the specification parameters and the temperature grade of the power transformation device are collected, then a deep learning model with a matching mark is searched, the actual load of the power transformation device is input into the matching deep learning model, and the hottest point temperature value monitored at the time is obtained.
And S3, marking a time stamp for the hottest point temperature value, and generating a temperature time sequence of the power transformation equipment according to the time stamp.
Marking the time stamp of the hottest point temperature value monitored by the power transformation equipment each time, and generating a power transformation equipment temperature time sequence in the last month according to the time stamp, for example (T) 1 ,T 2 ,…，T n ) Wherein T is 1 ,T 2 ,…，T n Is the hottest spot temperature value ordered in time sequence.
S4, inputting the temperature time sequence into a pre-trained Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach a fault temperature value.
Historical sequence data of the similar power transformation devices are summarized into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation devices (the temperature time sequence is the temperature time sequence from the start of use to the transmission of faults of the power transformation devices). And creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters. And training a pre-created Prophet model by using a temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
And similar to the step S3, inquiring and matching the Prophet model according to the specification parameters and average environmental temperature of the power transformation equipment, inputting the temperature time sequence of the power transformation equipment into the matched Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach the fault temperature value.
And S5, if the required time reaches a preset time threshold, generating fault early warning of the power transformation equipment.
And if the time predicted in the step S4 is less than 1h, generating fault early warning of the power transformation equipment. And selecting an alternative variable point line according to the fault early warning power transmission system, and immediately overhauling early warning power transformation equipment.
As shown in fig. 2, the system 200 includes:
the data acquisition unit 210 is configured to periodically acquire monitoring data of the power transformation device according to a preset acquisition period;
a temperature obtaining unit 220, configured to input the monitoring data into a pre-trained deep learning model, and obtain a corresponding hottest point temperature value;
a sequence generating unit 230, configured to timestamp the hottest point temperature value, and generate a temperature time sequence of the power transformation device according to the timestamp;
a time prediction unit 240, configured to input the temperature time sequence into a pre-trained Prophet model, and predict a time required for the hottest point temperature value of the power transformation device to reach a fault temperature value;
and the fault early warning unit 250 is configured to generate fault early warning of the power transformation equipment if the required time reaches a preset time threshold.
Optionally, as an embodiment of the present invention, the training method of the deep learning model includes:
dividing the power transformation equipment with the same specification and the same temperature level in the power transmission system into similar power transformation equipment;
summarizing historical data of similar power transformation equipment into a deep learning model training set, wherein the historical data comprises historical collected monitoring data and corresponding hottest point temperature values;
and training the deep learning model by using the training set, and marking the trained deep learning model with corresponding power transformation equipment specifications and temperature grades.
Optionally, as an embodiment of the present invention, the training method of the propset model includes:
summarizing historical sequence data of similar power transformation equipment into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation equipment;
creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters;
and training the pre-created Prophet model by using the temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
Fig. 3 is a schematic structural diagram of a terminal 300 according to an embodiment of the present invention, where the terminal 300 may be used to execute the fault supervision method of a power transformation device according to the embodiment of the present invention.
The terminal 300 may include: a processor 310, a memory 320 and a communication unit 330. The components may communicate via one or more buses, and it will be appreciated by those skilled in the art that the configuration of the server as shown in the drawings is not limiting of the invention, as it may be a bus-like structure, a star-like structure, or include more or fewer components than shown, or may be a combination of certain components or a different arrangement of components.
The memory 320 may be used to store instructions for execution by the processor 310, and the memory 320 may be implemented by any type of volatile or non-volatile memory terminal or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk. The execution of the instructions in memory 320, when executed by processor 310, enables terminal 300 to perform some or all of the steps in the method embodiments described below.
The processor 310 is a control center of the storage terminal, connects various parts of the entire electronic terminal using various interfaces and lines, and performs various functions of the electronic terminal and/or processes data by running or executing software programs and/or modules stored in the memory 320, and invoking data stored in the memory. The processor may be comprised of an integrated circuit (Integrated Circuit, simply referred to as an IC), for example, a single packaged IC, or may be comprised of a plurality of packaged ICs connected to the same function or different functions. For example, the processor 310 may include only a central processing unit (Central Processing Unit, simply CPU). In the embodiment of the invention, the CPU can be a single operation core or can comprise multiple operation cores.
And a communication unit 330 for establishing a communication channel so that the storage terminal can communicate with other terminals. Receiving user data sent by other terminals or sending the user data to other terminals.
The present invention also provides a computer storage medium in which a program may be stored, which program may include some or all of the steps in the embodiments provided by the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random-access memory (random access memory, RAM), or the like.
Therefore, the invention obtains the hottest point temperature value of the power transformation equipment according to the monitoring data of the power transformation equipment through the deep learning model, then generates a temperature time sequence according to all the hottest point temperature values, and predicts the time required for reaching the fault temperature value according to the temperature time sequence by utilizing the trained Prophet model, wherein the temperature threshold corresponds to the temperature during the fault. Therefore, the faults of the power transformation equipment can be effectively predicted, so that a dispatching scheme of the power transmission line can be started in time to maintain the power transformation equipment with fault early warning in time, the stability of the power transmission system is enhanced, and the technical effects achieved by the embodiment can be described in the above and are not repeated here.
It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solution in the embodiments of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium such as a U-disc, a mobile hard disc, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, etc. various media capable of storing program codes, including several instructions for causing a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention.
The same or similar parts between the various embodiments in this specification are referred to each other. In particular, for the terminal embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference should be made to the description in the method embodiment for relevant points.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
Although the present invention has been described in detail by way of preferred embodiments with reference to the accompanying drawings, the present invention is not limited thereto. Various equivalent modifications and substitutions may be made in the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and it is intended that all such modifications and substitutions be within the scope of the present invention/be within the scope of the present invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A power transformation equipment fault supervision method, characterized by comprising:
periodically collecting monitoring data of the power transformation equipment according to a preset collecting period;
inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value;
marking a time stamp for the hottest point temperature value, and generating a temperature time sequence of the power transformation equipment according to the time stamp;
inputting the temperature time sequence into a pre-trained Prophet model, and predicting the time required for the hottest point temperature value of the power transformation equipment to reach a fault temperature value;
if the required time reaches a preset time threshold, generating fault early warning of the power transformation equipment;
the collecting monitoring data of the power transformation equipment comprises the following steps:
collecting the actual load of the power transformation equipment;
collecting the ambient temperature of the power transformation equipment;
the training method of the deep learning model comprises the following steps:
according to the specification parameters, dividing the power transformation equipment with the same specification parameters into the same group, classifying the power transformation equipment in each group according to the average environment temperature, and dividing the power transformation equipment with the average environment temperature at the same temperature level into the same class;
summarizing the historical actual loads and corresponding actual hottest point temperature values of all similar power transformation devices in each group aiming at the similar power transformation devices in the group, generating a training set for training a deep learning model, and marking the specification and temperature grade of the corresponding power transformation devices after the deep learning model is trained;
inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value, wherein the method comprises the following steps: and searching a deep learning model with a matching mark, and inputting the actual load in the monitoring data into the matching deep learning model to obtain a corresponding hottest point temperature value.
2. The method of claim 1, wherein the propset model training method comprises:
summarizing historical sequence data of similar power transformation equipment into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation equipment;
creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters;
and training the pre-created Prophet model by using the temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
3. The method according to claim 1 or 2, characterized in that the method further comprises:
acquiring the specification and the environmental temperature of the current power transformation equipment, and acquiring the temperature grade according to the environmental temperature;
and inquiring a deep learning model or a Prophet model with the matched marks according to the specification and the temperature level.
4. A power transformation equipment fault supervision system, comprising:
the data acquisition unit is configured to periodically acquire monitoring data of the power transformation equipment according to a preset acquisition period;
the temperature acquisition unit is configured to input the monitoring data into a pre-trained deep learning model to acquire a corresponding hottest point temperature value;
a sequence generating unit, configured to mark a timestamp for the hottest point temperature value, and generate a temperature time sequence of the power transformation device according to the timestamp;
the time prediction unit is configured to input the temperature time sequence into a pre-trained Prophet model, and predict the time required by the hottest point temperature value of the power transformation equipment to reach a fault temperature value;
the fault early warning unit is configured to generate fault early warning of the power transformation equipment if the required time reaches a preset time threshold;
the training method of the deep learning model comprises the following steps:
according to the specification parameters, dividing the power transformation equipment with the same specification parameters into the same group, classifying the power transformation equipment in each group according to the average environment temperature, and dividing the power transformation equipment with the average environment temperature at the same temperature level into the same class;
summarizing the historical actual loads and corresponding actual hottest point temperature values of all similar power transformation devices in each group aiming at the similar power transformation devices in the group, generating a training set for training a deep learning model, and marking the specification and temperature grade of the corresponding power transformation devices after the deep learning model is trained;
inputting the monitoring data into a pre-trained deep learning model to obtain a corresponding hottest point temperature value, wherein the method comprises the following steps: and searching a deep learning model with a matching mark, and inputting the actual load in the monitoring data into the matching deep learning model to obtain a corresponding hottest point temperature value.
5. The system of claim 4, wherein the propset model training method comprises:
summarizing historical sequence data of similar power transformation equipment into a temperature training set, wherein the historical sequence data comprises a temperature time sequence from the start of use to the occurrence of faults of the power transformation equipment;
creating a Prophet model, and setting model parameters of the Prophet model, wherein the model parameters comprise trend item variable point parameters, period item parameters and holiday item parameters;
and training the pre-created Prophet model by using the temperature training set, and marking the trained Prophet model with corresponding power transformation equipment specifications and temperature grades.
6. A terminal, comprising:
a processor;
a memory for storing execution instructions of the processor;
wherein the processor is configured to perform the method of any of claims 1-3.
7. A computer readable storage medium storing a computer program, which when executed by a processor implements the method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011145984.4A CN112347619B (en) | 2020-10-23 | 2020-10-23 | Power transformation equipment fault supervision method, system, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011145984.4A CN112347619B (en) | 2020-10-23 | 2020-10-23 | Power transformation equipment fault supervision method, system, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112347619A CN112347619A (en) | 2021-02-09 |
| CN112347619B true CN112347619B (en) | 2023-08-11 |
Family
ID=74359876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011145984.4A Active CN112347619B (en) | 2020-10-23 | 2020-10-23 | Power transformation equipment fault supervision method, system, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112347619B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109284863A (en) * | 2018-09-04 | 2019-01-29 | 南京理工大学 | A kind of power equipment temperature predicting method based on deep neural network |
| CN110460454A (en) * | 2018-05-04 | 2019-11-15 | 上海伽易信息技术有限公司 | Network equipment port intelligent fault prediction technique and principle based on deep learning |
| CN110739637A (en) * | 2019-10-14 | 2020-01-31 | 国网山东省电力公司潍坊供电公司 | power transmission line monitoring method, system, terminal and storage medium |
| CN111176575A (en) * | 2019-12-28 | 2020-05-19 | 苏州浪潮智能科技有限公司 | SSD (solid State disk) service life prediction method, system, terminal and storage medium based on Prophet model |
-
2020
- 2020-10-23 CN CN202011145984.4A patent/CN112347619B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110460454A (en) * | 2018-05-04 | 2019-11-15 | 上海伽易信息技术有限公司 | Network equipment port intelligent fault prediction technique and principle based on deep learning |
| CN109284863A (en) * | 2018-09-04 | 2019-01-29 | 南京理工大学 | A kind of power equipment temperature predicting method based on deep neural network |
| CN110739637A (en) * | 2019-10-14 | 2020-01-31 | 国网山东省电力公司潍坊供电公司 | power transmission line monitoring method, system, terminal and storage medium |
| CN111176575A (en) * | 2019-12-28 | 2020-05-19 | 苏州浪潮智能科技有限公司 | SSD (solid State disk) service life prediction method, system, terminal and storage medium based on Prophet model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112347619A (en) | 2021-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109729131B (en) | Application request processing method and device and router | |
| CN111368890A (en) | Fault detection method and device and information physical fusion system | |
| CN106327033B (en) | Power system cascading failure analysis method based on Markov process | |
| CN103296750B (en) | Apparatus and method for correcting error of acquired data | |
| CN113590370A (en) | Fault processing method, device, equipment and storage medium | |
| CN112087334A (en) | Alarm root cause analysis method, electronic device and storage medium | |
| CN110556920A (en) | Distribution automation monitoring method, system, terminal and storage medium | |
| CN116502166B (en) | Method, device, equipment and medium for predicting faults of target equipment | |
| CN116231871B (en) | Power grid situation supervision method, system and storage medium based on digital twinning | |
| CN113704018A (en) | Application operation and maintenance data processing method and device, computer equipment and storage medium | |
| CN113779328B (en) | Power supply monitoring data integration processing method, system, terminal and storage medium | |
| CN108039971A (en) | A kind of alarm method and device | |
| CN112347619B (en) | Power transformation equipment fault supervision method, system, terminal and storage medium | |
| CN113987724A (en) | Power grid risk identification method and system based on topology analysis | |
| CN111062503B (en) | Power grid monitoring alarm processing method, system, terminal and storage medium | |
| CN116996363A (en) | Fault early warning method and related device for power distribution network | |
| CN115561700B (en) | Metering standard analysis method and device for direct-current electric energy meter | |
| CN111611097A (en) | Fault detection method, device, equipment and storage medium | |
| CN110838940A (en) | Underground cable inspection task configuration method and device | |
| CN116307705A (en) | Power distribution network line section fault risk evaluation method, device and storage medium | |
| CN113922343A (en) | Power distribution network protection fixed value setting method, terminal equipment and storage medium | |
| CN110232482B (en) | Equipment management method and device based on neural network | |
| CN115858324B (en) | AI-based IT equipment fault processing method, apparatus, equipment and medium | |
| CN114781674B (en) | Method and device for positioning faults of wind power equipment, storage medium and electronic equipment | |
| CN117216495A (en) | Transformer monitoring method, system, terminal and storage medium based on immune mechanism |
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 |