CN113204919B - Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment - Google Patents
Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment Download PDFInfo
- Publication number
- CN113204919B CN113204919B CN202110503178.8A CN202110503178A CN113204919B CN 113204919 B CN113204919 B CN 113204919B CN 202110503178 A CN202110503178 A CN 202110503178A CN 113204919 B CN113204919 B CN 113204919B
- Authority
- CN
- China
- Prior art keywords
- oil temperature
- trend line
- main transformer
- prediction
- conservator
- 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
Images
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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Housings And Mounting Of Transformers (AREA)
Abstract
The invention discloses a method and a device for predicting the state of a main transformer conservator based on digital twinning and electronic equipment, wherein the method comprises the following steps: establishing a digital twin main transformer conservator model; establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model; operating the digital twin main transformer conservator model and acquiring detection data; inputting the detection data into the target variable prediction model, the quantifiable influence factor prediction model and the total influence factor prediction model respectively to obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line respectively; according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line, state prediction is carried out on a main transformer conservator; the method can effectively predict and analyze the future health state of the main transformer conservator, and provides a solution for reliable operation of equipment.
Description
Technical Field
The invention relates to the technical field of operation and maintenance of electrical equipment, in particular to a method and a device for predicting a state of a main transformer conservator based on digital twinning and electronic equipment.
Background
A digital twin is a virtual model created digitally for a physical object to simulate behavior in its real-world environment, reflecting the full lifecycle process of the corresponding physical device. After the digital twin transformer substation is built, the running state of the transformer substation can be fully sensed by using an intelligent cloud platform, so that real-time monitoring is realized. The 'twin' transformer substation easily acquires power station data and performs analysis and processing, so that the problems of lack of a unified data platform, lack of data analysis, difficulty in judgment of equipment risks and the like are thoroughly solved, and the global and full-life-cycle management of the transformer substation is realized.
Due to the fact that various types of defects or faults can generate temperature rising phenomena in the operation process of the transformer, such as: the transformer bears the impact time of short-circuit current for too long, the internal pressure is increased, the mechanical damage is caused, and the like; if the short-circuit current is large, relay protection delay action even refuses action, deformation can be serious, even winding damage is caused, if the temperature continuously rises, equipment damage can be caused, abnormal power failure accidents are caused, influence is brought to personal safety and power supply stability, the temperature of a main transformer conservator is one of the most characteristic features, and the trend prediction of the temperature of the conservator is particularly important.
In traditional electric power operation and maintenance work, the health state of equipment is often judged by means such as equipment daily inspection, electric power monitoring system measurement point data acquisition and electric overhaul test, but when equipment faults are detected by means of the methods, the faults are often developed to a serious degree, great difficulty is brought to maintenance, due to the fact that predictive analysis cannot be carried out on the future health state problem of the equipment, operation and maintenance personnel can only carry out passive maintenance on the equipment, namely, a solution is provided for the occurred defects or faults, and the reliability of equipment operation is greatly influenced.
Patent document "a temperature monitoring and early warning system for transformer" (CN11584216B), it is disclosed to set up temperature sensor in the transformer conservator to and arrange temperature sensor in the transformer other positions, through the temperature information of each temperature sensor collection, carry out temperature monitoring and early warning to the transformer, however, this scheme only carries out the early warning through the control temperature, only when the oil temperature reaches the decomposition critical point soon or is about to reach the insulation failure critical point, can only be perceived, can not predict the future trend of change of the oil temperature that becomes the transformer conservator, also can not predict the state that becomes the transformer conservator.
Disclosure of Invention
The invention provides a method and a device for predicting the state of a main transformer oil conservator based on digital twins and electronic equipment, which can effectively predict and analyze the future health state of the main transformer oil conservator and provide a solution for the reliable operation of the equipment.
A main transformer oil conservator state prediction method based on digital twinning comprises the following steps:
establishing a digital twin main transformer oil conservator model;
establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model;
operating the digital twin main transformer conservator model and acquiring detection data;
inputting the detection data into the target variable prediction model, the quantifiable influence factor prediction model and the total influence factor prediction model respectively to obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line respectively;
and predicting the state of the main transformer conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line.
Further, establishing the target variable prediction model based on ideal data;
training historical sample data based on the quantifiable influence factor to obtain the quantifiable influence factor prediction model;
And training to obtain the full influence factor prediction model based on the historical sample data of the quantifiable influence factors and the historical sample data of the non-quantifiable influence factors.
Further, the ideal data comprises load current, ambient temperature, ambient humidity, altitude and operation life of the main transformer conservator in an ideal operation state;
the quantifiable influence factors comprise load current, ambient temperature, ambient humidity, altitude and the operation life of main transformer conservator equipment in a non-ideal operation state;
the non-quantifiable influence factors comprise pollution characteristic parameters, vibration characteristic parameters, process characteristic parameters, material characteristic parameters, sand characteristic parameters, salt fog characteristic parameters, illumination intensity and ultrasonic effective values.
Further, according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line, the state prediction of the main transformer conservator is performed, and the method comprises the following steps:
obtaining the normal oil temperature range of the normal operation of the main transformer oil conservator according to the first oil temperature prediction trend line;
and judging whether the quantifiable influence factor of the main transformer oil conservator needs to be regulated and controlled in the future or not according to the second oil temperature prediction trend line and the normal oil temperature range.
Further, according to the second oil temperature prediction trend line and the normal range of the oil temperature, judging whether the quantifiable influence factor of the main transformer conservator needs to be regulated and controlled in the future or not, wherein the method comprises the following steps:
when the second oil temperature prediction trend line exceeds the normal range of the oil temperature, determining that the future quantitative influence factor of the main transformer conservator needs to be regulated and controlled;
and if the second oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the quantifiable influence factor of the main transformer conservator does not need to be regulated and controlled in the future.
Further, according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line, the state prediction of the main transformer conservator is performed, and the method comprises the following steps:
obtaining the normal oil temperature range of the normal operation of the main transformer oil conservator according to the first oil temperature prediction trend line;
and judging whether the main transformer oil conservator has defects or not according to the third oil temperature prediction trend line and the normal range of the oil temperature.
Further, according to the third oil temperature prediction trend line and the normal oil temperature range, determining whether the main transformer conservator has a defect includes:
when the third oil temperature prediction trend line exceeds the normal range of the oil temperature, determining that the main transformer conservator has defects;
And if the third oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the main transformer oil conservator has no defects.
Further, after confirming that there is the defect in the main change conservator, still include:
determining the time corresponding to the intersection point of the third oil temperature prediction trend line and the first oil temperature prediction trend line as the time when the fault is about to occur;
determining the time corresponding to the fact that the third oil temperature prediction trend line exceeds the first preset oil temperature as the time of entering the serious fault;
and the moment corresponding to the fact that the third oil temperature in the third oil temperature prediction trend line exceeds the second preset oil temperature is the moment when the main transformer oil conservator has the irreversible fault.
A main transformer oil conservator state prediction device based on digital twinning comprises:
the twin system establishing module is used for establishing a digital twin main transformer conservator model;
the prediction model establishing module is used for establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model;
the data acquisition module is used for operating the digital twin main transformer conservator model and acquiring detection data;
the oil temperature prediction module is used for respectively inputting the detection data into the target variable prediction model, the quantifiable influence factor prediction model and the total influence factor prediction model to respectively obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line;
And the state prediction module is used for predicting the state of the main transformer oil conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line.
An electronic device comprises a processor and a storage module, wherein the storage module stores a plurality of instructions, and the processor is used for reading the instructions and executing the method.
A computer-readable storage medium having stored thereon a plurality of instructions readable by a processor and performing the method described above.
According to the method, the device and the electronic equipment for predicting the state of the main transformer conservator based on the digital twinning, the oil temperature of the main transformer conservator is predicted according to the established model, the future health state of the main transformer conservator can be effectively predicted and analyzed, whether the quantitative influence factors need to be regulated and controlled and whether defects exist can be effectively judged, particularly, the defects can be timely found under the condition that the defects exist but the faults do not occur, the serious faults are avoided, and the reliability of the operation of the main transformer conservator is ensured to the maximum extent.
Drawings
Fig. 1 is a flowchart of an embodiment of a method for predicting a state of a main transformer conservator based on a digital twin according to the present invention.
Fig. 2 is a scene schematic diagram of a situation where quantitative influencing factors need to be regulated and controlled and defects exist in the method for predicting the state of the main transformer conservator based on the digital twinning provided by the invention.
Fig. 3 is a scene schematic diagram of the situation that quantitative influencing factors need to be regulated and controlled but no defect exists in the method for predicting the state of the main transformer conservator based on the digital twinning provided by the invention.
Fig. 4 is a scene schematic diagram of a situation that a quantifiable influence factor does not need to be regulated and controlled but has a defect in the method for predicting the state of the main transformer conservator based on the digital twinning provided by the invention.
Fig. 5 is a scene schematic diagram of the main transformer conservator state prediction method based on digital twinning, which is provided by the invention, wherein the quantitative influence factors do not need to be regulated and controlled and no defect exists.
Fig. 6 is a schematic structural diagram of an embodiment of a main transformer conservator state prediction device based on a digital twin according to the present invention.
Detailed Description
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 1, the present embodiment provides a method for predicting a state of a main transformer conservator based on a digital twin, including:
s1, establishing a digital twin main transformer conservator model;
S2, establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model;
s3, operating the digital twin main transformer conservator model and acquiring detection data;
s4, inputting the detection data into the target variable prediction model, the quantifiable influence factor prediction model and the total influence factor prediction model respectively, and obtaining a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line respectively;
and S5, predicting the state of the main transformer conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line.
Specifically, in step S1, the main transformer conservator component is digitally modeled by using techniques such as laser point cloud and oblique photography, so as to obtain a digital twin main transformer conservator model, which has an access capability of supporting various standard communication protocols and can simulate the operation of physical equipment.
Further, in step S2, the target variable prediction model is established based on ideal data, where the ideal data includes relevant operation data generated by the main transformer conservator in an ideal operation state, including but not limited to load current, ambient temperature, ambient humidity, altitude, operation age of the main transformer conservator device in the ideal operation state, and the ideal operation state refers to an operation environment state in which the device is very healthy and is not interfered by any external factor, and the target variable prediction model is an ideal prediction model, and aims to find a fluctuation range of the oil temperature under an ideal external condition, and the fluctuation range can be used as a reference for determining that the health condition of the device is normal.
And training based on historical sample data of the quantifiable influence factor to obtain the quantifiable influence factor prediction model. The quantifiable influence factor is a parameter capable of accurately giving a specific value, and the influence factor can directly cause the oil temperature to change, and the quantifiable influence factor includes but is not limited to load current, ambient temperature, ambient humidity, altitude, the operation life of main transformer conservator equipment and the like in a non-ideal state. The quantifiable impact factor has two layers of meanings, one is that the data corresponding to the impact factor is not caused by defect reasons, and the other is that the data has a specific quantification value, and the two must be satisfied at the same time.
The ideal data and the quantifiable influence factor data are similar and refer to laboratory environments, but the difference is that the ideal data are based on the contents of industry standard, equipment production manufacturing guide rules and the like, the normal fluctuation range of the equipment operation data of the equipment under the laboratory conditions is framed, the quantifiable influence factor is an actual data change curve after the equipment discharges external interference, and the operation data may exceed the normal fluctuation range.
The oil temperature prediction model only considers the quantifiable influence factor, is established based on a laboratory environment, sets the non-quantifiable influence factor to be in an ideal state, and finds out the dynamic mathematical relationship between the oil temperature and the variable influence factor.
The non-quantifiable influence factor is a parameter which gives no specific numerical value, or a phenomenon or data characteristic parameter caused by a certain defect reason, including but not limited to a pollution characteristic parameter, a vibration characteristic parameter, a process characteristic parameter, a material characteristic parameter, a sand characteristic parameter, a salt fog characteristic parameter, illumination intensity and an ultrasonic effective value.
The non-quantifiable impact factors are factors except the quantifiable impact factors which are classified into the non-quantifiable impact factors, and comprise data factors which are not caused by defects but cannot be quantified or characteristic parameter factors (whether numerical values can be quantified or not) caused by some defect reasons.
The full influence factor comprises a quantifiable influence factor and a non-quantifiable influence factor, and the full influence factor prediction model is obtained based on historical sample data of the quantifiable influence factor and historical sample data of the non-quantifiable influence factor.
The full influence factor prediction model is used for predicting the future change trend of the oil temperature under the actual action of all the current quantifiable influence factors and non-quantifiable influence factors, and the prediction has strong guiding significance for judging whether the equipment has defect problems or not and the development degree change of the defect problems.
Further, in step S3, operating the digital twin main transformer conservator model, and acquiring detection data, where the detection data includes: load current, ambient temperature, ambient humidity, altitude and the operation life of the main transformer conservator under the operation state.
Further, in step S4, the detection data is input into the target variable prediction model, a time sequence of the main transformer conservator temperature measurement points in an ideal external environment can be obtained, the temperature measurement points are connected to obtain a first oil temperature prediction trend line, and the first oil temperature prediction trend line is an oil temperature range of the main transformer conservator under a normal condition.
And inputting the detection data into the quantifiable influence factor prediction model to obtain a time sequence of the temperature measuring points of the main transformer oil conservator under the influence of the quantifiable influence factor, and connecting the temperature measuring points to obtain a second oil temperature prediction trend line.
And inputting the detection data into the total influence factor prediction model to obtain a time sequence of main transformer conservator temperature measuring points under the influence of quantifiable influence factors and non-quantifiable factors, and connecting the temperature measuring points to obtain a third oil temperature prediction trend line.
Further, in step S5, the predicting a state of the main transformer conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line, and the third oil temperature prediction trend line includes:
Obtaining the normal oil temperature range of the normal operation of the main transformer oil conservator according to the first oil temperature prediction trend line;
judging whether the quantifiable influence factors of the main transformer oil conservator need to be regulated and controlled in the future or not according to the second oil temperature forecasting trend line and the normal range of the oil temperature;
and judging whether the main transformer oil conservator has defects or not according to the third oil temperature prediction trend line and the normal range of the oil temperature.
Wherein, according to the second oil temperature prediction trend line and the normal range of the oil temperature, whether the quantifiable influence factor of the main transformer oil conservator needs to be regulated and controlled in the future is judged, and the method comprises the following steps:
when the second oil temperature prediction trend line exceeds the oil temperature normal range, determining that the future regulation and control of the quantifiable influence factor of the main transformer oil conservator are required;
and if the second oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the quantifiable influence factors of the main transformer oil conservator do not need to be regulated and controlled in the future.
And determining that the quantifiable influence factor needs to be regulated and controlled, and changing the parameter of the quantifiable influence factor by means of regulation and control, so that the main transformer oil conservator can enter a normal operation state.
According to the third oil temperature prediction trend line and the normal range of the oil temperature, judging whether the main transformer oil conservator has defects or not, wherein the method comprises the following steps:
When the third oil temperature prediction trend line exceeds the normal range of the oil temperature, determining that the main transformer conservator has defects;
and if the third oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the main transformer conservator has no defect.
Specifically, referring to fig. 2 to 5, where K1 is a first oil temperature prediction trend line, K2 is a second oil temperature prediction trend line, K3 is a third oil temperature prediction trend line, and the first oil temperature prediction trend line K1 is an oil temperature range of the main transformer conservator under normal conditions, in fig. 2, the second oil temperature prediction trend line K2 partially exceeds the first oil temperature prediction trend line K1, so that the quantifiable influence factor of the main transformer conservator needs to be adjusted and controlled in the future, and the third oil temperature prediction trend line K3 exceeds the first oil temperature prediction trend line K1, so that the main transformer conservator has a defect. In fig. 3, the second oil temperature prediction trend line K2 partially exceeds the first oil temperature prediction trend line K1, so that the quantifiable influence factor of the main transformer conservator needs to be adjusted and controlled in the future, and the third oil temperature prediction trend line K3 does not exceed the first oil temperature prediction trend line K1, so that the main transformer conservator does not have defects. In fig. 4, the second oil temperature prediction trend line K2 does not exceed the first oil temperature prediction trend line K1, so that the quantifiable influence factor of the main transformer conservator does not need to be adjusted in the future, and the third oil temperature prediction trend line K3 exceeds the first oil temperature prediction trend line K1, so that the main transformer conservator has a defect. In fig. 5, the second oil temperature prediction trend line K2 does not exceed the first oil temperature prediction trend line K1, so that the quantifiable influence factor of the main transformer conservator does not need to be adjusted, and the third oil temperature prediction trend line K3 does not exceed the first oil temperature prediction trend line K1, so that the main transformer conservator does not have defects.
If the main transformer conservator has defects, faults can be caused in a future period of time, therefore, fault prediction can be carried out through a third oil temperature prediction trend line, and after the main transformer conservator is determined to have defects, the method further comprises the following steps:
determining the time corresponding to the intersection point of the third oil temperature prediction trend line and the first oil temperature prediction trend line as the time when the fault is about to occur;
determining the time corresponding to the third oil temperature prediction trend line exceeding the first preset oil temperature as the time of entering the serious fault;
and determining the moment corresponding to the second preset oil temperature exceeded in the third oil temperature prediction trend line as the moment when the main transformer conservator has the irreversible fault, wherein the power failure fault can be caused at the moment.
Referring to FIGS. 2 and 4, t1The time at which the fault is about to occur, t2Will exceed the first preset oil temperature T at any moment1To enter a critical failure time, t3Will exceed the second preset oil temperature T at any moment2And the moment when the main transformer conservator has irreversible faults.
Further, after determining that the main transformer conservator has a defect, the method further comprises the following steps:
and determining the defect reason according to a pre-established knowledge graph of the main transformer conservator.
Each device defect cause may produce one or more phenomenon characteristics (e.g., sound, image, smell, etc.), although there may be 2 different defect causes with the same phenomenon characteristics or data characteristics. And also by one or more data characteristics (sensor data, test data, secondary relay protection data, etc.). By extracting the defect case information, finding out which phenomenon characteristics and data characteristics correspond to each defect reason, and a judging method, a judging logic, a solution and measures corresponding to the defect reasons, and establishing a structured knowledge base table containing the information, the main transformer conservator knowledge graph can be generated, and the query of a knowledge entity is facilitated.
According to the method provided by the embodiment, the oil temperature of the main transformer conservator is predicted according to the established model, the future health state of the main transformer conservator can be effectively predicted and analyzed, whether quantitative influence factors need to be regulated and controlled and whether defects exist can be effectively judged, particularly, the defects can be timely found under the condition that the defects exist but the faults do not occur, the serious faults are avoided, and the reliability of the operation of the main transformer conservator is ensured to the maximum extent.
Referring to fig. 6, in some embodiments, there is also provided a digital twin-based main transformer conservator state prediction device, including:
the twin system establishing module 201 is used for establishing a digital twin main transformer conservator model;
the prediction model establishing module 202 is used for establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model;
the data acquisition module 203 is used for operating the digital twin main transformer conservator model and acquiring detection data;
the oil temperature prediction module 204 is configured to input the detection data into the target variable prediction model, the quantifiable impact factor prediction model and the total impact factor prediction model respectively, and obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line respectively;
And the state prediction module 205 is configured to predict a state of the main transformer conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line, and the third oil temperature prediction trend line.
Specifically, the prediction model establishment module 202 establishes the target variable prediction model based on ideal data; training historical sample data based on the quantifiable influence factor to obtain the quantifiable influence factor prediction model; and training to obtain the full influence factor prediction model based on the historical sample data of the quantifiable influence factor and the historical sample data of the non-quantifiable influence factor.
The state prediction module 205 is further configured to obtain a normal oil temperature range of the main transformer conservator in normal operation according to the first oil temperature prediction trend line; judging whether the quantifiable influence factors of the main transformer oil conservator need to be regulated and controlled in the future or not according to the second oil temperature forecasting trend line and the normal range of the oil temperature; and judging whether the main transformer oil conservator has defects or not according to the third oil temperature prediction trend line and the normal range of the oil temperature.
The state prediction module 205 is further configured to determine that the quantifiable influence factor of the main transformer conservator needs to be adjusted and controlled in the future when the second oil temperature prediction trend line exceeds the normal oil temperature range; and if the second oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the quantifiable influence factor of the main transformer conservator does not need to be regulated and controlled in the future.
The state prediction module 205 is further configured to determine that the main transformer conservator has a defect when the third oil temperature prediction trend line exceeds the oil temperature normal range; and if the third oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the main transformer oil conservator has no defects.
The state prediction module 205 is further configured to determine a time corresponding to an intersection of the third oil temperature prediction trend line and the first oil temperature prediction trend line as a time when the fault is about to occur; determining the time corresponding to the third oil temperature prediction trend line exceeding the first preset oil temperature as the time of entering the serious fault; and the time corresponding to the third oil temperature prediction trend line exceeding the second preset oil temperature is the time when the main transformer conservator has irreversible faults.
The device provided by the embodiment predicts the oil temperature of the main transformer conservator according to the established model, can effectively predict and analyze the future health state of the main transformer conservator, comprises the steps of determining whether the influence factors need to be regulated and controlled and effectively judging whether defects exist, can timely discover the defects particularly under the condition that the defects exist but the faults do not occur, avoids serious faults, and ensures the reliability of the operation of the main transformer conservator to the maximum extent.
In some embodiments, an electronic device is further provided, which includes a processor and a storage module, the storage module stores a plurality of instructions, and the processor is configured to read the instructions and execute the method described above.
In some embodiments, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a plurality of instructions, which can be read by a processor and execute the above-mentioned method.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention. It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (7)
1. A main transformer conservator state prediction method based on digital twinning is characterized by comprising the following steps:
Establishing a digital twin main transformer oil conservator model;
establishing a target variable prediction model, a quantifiable influence factor prediction model and a total influence factor prediction model, establishing the target variable prediction model based on ideal data, obtaining the quantifiable influence factor prediction model based on historical sample data training of the quantifiable influence factor, and obtaining the total influence factor prediction model based on historical sample data of the quantifiable influence factor and historical sample data training of a non-quantifiable influence factor;
operating the digital twin main transformer conservator model and acquiring detection data;
respectively inputting the detection data into the target variable prediction model, the quantitative influence factor prediction model and the total influence factor prediction model to respectively obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line;
according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line, state prediction is carried out on a main transformer oil conservator;
according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line, the state prediction of the main transformer oil conservator is carried out, and the method comprises the following steps:
Obtaining the normal oil temperature range of the normal operation of the main transformer oil conservator according to the first oil temperature prediction trend line;
judging whether the quantifiable influence factors of the main transformer oil conservator need to be regulated and controlled in the future or not according to the second oil temperature forecasting trend line and the normal range of the oil temperature;
and judging whether the main transformer oil conservator has defects or not according to the third oil temperature prediction trend line and the normal range of the oil temperature.
2. The method of claim 1, wherein the ideal data comprises load current, ambient temperature, ambient humidity, altitude and operational life of the main transformer conservator equipment at an ideal operating state;
the quantifiable influence factors comprise load current, ambient temperature, ambient humidity, altitude and the commissioning life of main transformer oil conservator equipment in a non-ideal operation state;
the non-quantifiable influence factors comprise pollution characteristic parameters, vibration characteristic parameters, process characteristic parameters, material characteristic parameters, sand characteristic parameters, salt mist characteristic parameters, illumination intensity and ultrasonic effective values.
3. The method of claim 2, wherein determining whether a quantifiable impact factor of the main conservator needs to be adjusted in the future based on the second predicted trend line for oil temperature and the normal range for oil temperature comprises:
When the second oil temperature prediction trend line exceeds the oil temperature normal range, determining that the future regulation and control of the quantifiable influence factor of the main transformer oil conservator are required;
and if the second oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the quantifiable influence factors of the main transformer oil conservator do not need to be regulated and controlled in the future.
4. The method of claim 1, wherein determining whether the main transformer conservator has a fault based on the third oil temperature prediction trend line and the normal range of oil temperature comprises:
when the third oil temperature prediction trend line exceeds the normal range of the oil temperature, determining that the main transformer conservator has defects;
and if the third oil temperature prediction trend line does not exceed the normal range of the oil temperature, determining that the main transformer oil conservator has no defects.
5. The method of claim 4, wherein after determining that the main conservator is defective, further comprising:
determining the time corresponding to the intersection point of the third oil temperature prediction trend line and the first oil temperature prediction trend line as the time when the fault is about to occur;
determining the time corresponding to the third oil temperature prediction trend line exceeding the first preset oil temperature as the time of entering the serious fault;
And the moment corresponding to the fact that the third oil temperature in the third oil temperature prediction trend line exceeds the second preset oil temperature is the moment when the main transformer oil conservator has the irreversible fault.
6. A main transformer conservator state prediction device based on digital twinning is characterized by comprising:
the twin system establishing module is used for establishing a digital twin main transformer conservator model;
the prediction model establishing module is used for establishing a target variable prediction model, a quantitative influence factor prediction model and a total influence factor prediction model;
the data acquisition module is used for operating the digital twin main transformer conservator model and acquiring detection data;
the oil temperature prediction module is used for respectively inputting the detection data into the target variable prediction model, the quantifiable influence factor prediction model and the total influence factor prediction model to respectively obtain a first oil temperature prediction trend line, a second oil temperature prediction trend line and a third oil temperature prediction trend line;
the state prediction module is used for predicting the state of the main transformer conservator according to the first oil temperature prediction trend line, the second oil temperature prediction trend line and the third oil temperature prediction trend line;
the prediction model establishing module establishes the target variable prediction model based on ideal data; training historical sample data based on the quantifiable influence factor to obtain the quantifiable influence factor prediction model; training to obtain the full influence factor prediction model based on historical sample data of a quantifiable influence factor and historical sample data of a non-quantifiable influence factor;
The state prediction module is further used for obtaining a normal oil temperature range of normal operation of the main transformer oil conservator according to the first oil temperature prediction trend line; judging whether the quantifiable influence factors of the main transformer oil conservator need to be regulated and controlled in the future or not according to the second oil temperature forecasting trend line and the normal range of the oil temperature; and judging whether the main transformer oil conservator has defects or not according to the third oil temperature prediction trend line and the normal range of the oil temperature.
7. An electronic device comprising a processor and a memory module, the memory module storing a plurality of instructions, the processor being configured to read the plurality of instructions and execute the method according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110503178.8A CN113204919B (en) | 2021-05-10 | 2021-05-10 | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110503178.8A CN113204919B (en) | 2021-05-10 | 2021-05-10 | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113204919A CN113204919A (en) | 2021-08-03 |
CN113204919B true CN113204919B (en) | 2022-07-08 |
Family
ID=77030530
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110503178.8A Active CN113204919B (en) | 2021-05-10 | 2021-05-10 | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113204919B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114358719B (en) * | 2021-12-24 | 2023-01-17 | 宁波欧依安盾安全科技有限公司 | Nuclear power station digital twin visualization instrument control electrical operation regulation method and system |
CN117113729B (en) * | 2023-10-20 | 2024-01-23 | 国网吉林省电力有限公司长春供电公司 | Digital twinning-based power equipment online state monitoring system |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112685949A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer health prediction method based on digital twinning |
CN112765873A (en) * | 2020-11-30 | 2021-05-07 | 中国南方电网有限责任公司超高压输电公司广州局 | LSTM algorithm-based power transformation equipment heating prediction method |
-
2021
- 2021-05-10 CN CN202110503178.8A patent/CN113204919B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112685949A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer health prediction method based on digital twinning |
CN112765873A (en) * | 2020-11-30 | 2021-05-07 | 中国南方电网有限责任公司超高压输电公司广州局 | LSTM algorithm-based power transformation equipment heating prediction method |
Also Published As
Publication number | Publication date |
---|---|
CN113204919A (en) | 2021-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7275018B2 (en) | Method of condition monitoring | |
CN113204919B (en) | Method and device for predicting state of main transformer conservator based on digital twinning and electronic equipment | |
CN111241154A (en) | Storage battery fault early warning method and system based on big data | |
CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
CN113537415A (en) | Convertor station inspection method and device based on multi-information fusion and computer equipment | |
CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
CN113742993B (en) | Method, device, equipment and storage medium for predicting life loss of dry-type transformer | |
CN110703743A (en) | Equipment failure prediction and detection system and method | |
CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
CN117590159A (en) | Tunnel cable power supply state monitoring method and system based on deep learning | |
CN117828512B (en) | Rapid evaluation and prediction method for operation risk of oil immersed transformer | |
CN117639228A (en) | Power distribution network running state prediction method and system based on digital twin | |
CN116993166A (en) | Park safety risk monitoring method | |
CN116611953A (en) | Electric energy meter production and manufacturing real-time data management method and system based on Internet of things | |
CN116956187A (en) | Fault prediction method and device for power supply module, storage medium and processor | |
CN116679139A (en) | Cable replacement monitoring system and method | |
CN115935135A (en) | Top-layer oil temperature prediction method for extra-high voltage converter transformer and storage medium | |
CN112747413B (en) | Air conditioning system load prediction method and device | |
CN114357181A (en) | Photovoltaic panel fault detection method and system based on knowledge graph | |
CN114066163A (en) | Power equipment state analysis method and device based on three-layer architecture mode | |
CN113705076A (en) | Wind turbine generator gearbox state monitoring method and control device based on partial least square method | |
CN118132996B (en) | Adaptive production scheduling optimization method based on industrial digital twin | |
CN118091406B (en) | Motor detection and repair method and device, electronic equipment and storage medium | |
CN117875946B (en) | Man-machine collaborative autonomous infrared inspection method for operation and maintenance of transformer substation equipment | |
CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence |
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 |