CN117574624A - Transformer state monitoring and early warning method based on digital twin technology - Google Patents
Transformer state monitoring and early warning method based on digital twin technology Download PDFInfo
- Publication number
- CN117574624A CN117574624A CN202311489752.4A CN202311489752A CN117574624A CN 117574624 A CN117574624 A CN 117574624A CN 202311489752 A CN202311489752 A CN 202311489752A CN 117574624 A CN117574624 A CN 117574624A
- Authority
- CN
- China
- Prior art keywords
- transformer
- data
- monitoring
- state
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 97
- 238000005516 engineering process Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004088 simulation Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000013461 design Methods 0.000 claims abstract description 14
- 238000013480 data collection Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012545 processing Methods 0.000 claims description 35
- 239000011159 matrix material Substances 0.000 claims description 18
- 230000009467 reduction Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 5
- 239000000463 material Substances 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 5
- 230000009466 transformation Effects 0.000 description 9
- 239000007789 gas Substances 0.000 description 8
- 238000005457 optimization Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000004867 photoacoustic spectroscopy Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000036314 physical performance Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000007707 calorimetry Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000004817 gas chromatography Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
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
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/165—Indicating that current or voltage is either above or below a predetermined value or within or outside a predetermined range of values
- G01R19/16566—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533
- G01R19/16576—Circuits and arrangements for comparing voltage or current with one or several thresholds and for indicating the result not covered by subgroups G01R19/16504, G01R19/16528, G01R19/16533 comparing DC or AC voltage with one threshold
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
- G06F2119/06—Power analysis or power optimisation
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Computer Graphics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Power Engineering (AREA)
- Housings And Mounting Of Transformers (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to a transformer state monitoring and early warning method based on a digital twin technology, which constructs a digital twin body of a transformer, namely a digital three-dimensional integral model of the transformer, which is also called a virtual model; data collection and preprocessing, wherein the types of data to be collected comprise state data, operation data and fault data; simulation design and analysis; the state monitoring and early warning are realized by monitoring and analyzing the state parameters of the transformer, the real equipment state holographic sensing is realized, the real-time monitoring of the state of the transformer is finally realized, the running state of the equipment is accurately grasped, and early warning information is timely sent out. The transformer state monitoring and early warning method based on the digital twin technology has high precision, realizes visual display and has an early warning function, and the digital modeling can be performed on the transformer through the digital twin technology, so that the accurate prediction and monitoring of the transformer state are realized; automatic monitoring and remote control are realized, and monitoring efficiency and working efficiency are improved.
Description
Technical Field
The invention relates to a transformer state monitoring method, in particular to a transformer state monitoring and early warning method based on a digital twin technology.
Background
The construction aim of the digital power grid is to construct a full-factor digital model covering the services of power transmission and transformation equipment, power transmission and transformation system test and debugging and the like, and realize the full-flow on-line management, remote equipment control and equipment dynamic monitoring of power transmission and transformation power utilization services, wherein the digital power transformation equipment state monitoring is an important ring.
The digital twin power transformation equipment health state monitoring model is built through acquisition processing, data modeling and simulation of data of the power transformation equipment, the control system and the like, the physical power system is mapped to the virtual space in a digital mode, comprehensive and accurate monitoring, state information diagnosis and prediction of the physical power transformation system can be achieved, analysis results are fed back to the physical power transformation system, optimization and adjustment of the physical power system can be effectively promoted, and the requirements of enterprise lean production, intelligent management and digital energization are met.
The Digital Twin is called Digital Twin, also called Digital mapping, digital mirror image. The digital twinning is to digitize the physical entity, and realize the dynamic mapping and interaction of the whole life cycle of the body in a visual mode. Digital twinning is a bridge connecting a digital and a reality, and physical parameters are digitized and visualized through a modeling technology, so that the mastering of a global model is realized; real-time data of the sensor is transmitted through a network, so that dynamic data management of the model and control of the whole life cycle are realized; and through an intelligent algorithm, decision is made on timely information generation judgment, prediction and guidance are provided for future scenes, and the prediction and guidance are fed back to a physical entity end to realize a complete closed loop link.
Through digital twinning, physical entities in the real world can be completely inscribed in the virtual world to form a mapping relation between reality and virtual. The virtual world maps the whole life cycle of the physical world in real time and accurately so as to achieve the purposes of simulation, monitoring, prediction, optimization and the like.
The development of digital twinning goes through three main stages. The first stage is a technology accumulation period, and before the 21 st century, the appearance of two-dimensional drawing tools and simulation technologies becomes a necessary condition for digital twin development; the second stage is a concept development stage, and in 2000-2015, a series of digital twin basic concepts are provided by the industry and the aviation and military field as representatives; the third stage is an application burst period, and digital twinning is combined with the fields of aerospace, industry, energy power and the like to expand more application scenes.
The power transformer is used as a key component of a power grid, plays a role in voltage transformation in a power system, and the safety and the service life of the power transformer are important guarantees of safe, reliable and economic operation of the power system and power supply and power consumption of the whole power grid, so that the whole power system is vital. Analysis of large-area power failure accident reasons of domestic and foreign power grids shows that the self-failure of the power transformer is one of main reasons for power grid failure, and particularly, the safety of the high-voltage and ultra-high-voltage oil immersed transformer which is used as a main node of a power system is particularly critical, and economic loss caused by failure is immeasurable due to large coverage and high price. Therefore, to avoid and reduce the occurrence of faults or accidents of the high-voltage and ultra-high voltage transformers as much as possible,
the transformer detection technology is divided into two types of off-line detection and on-line monitoring. The off-line detection mainly adopts two modes of post maintenance and preventive maintenance, and is easy to cause 'sheep repair' and 'excessive maintenance', thereby causing unnecessary manpower and material resource consumption. The main methods of on-line monitoring include photoacoustic spectrometry, gas chromatography, vibration analysis, short-circuit reactance generation, and the like.
Photoacoustic spectrometry as indirect calorimetry, by measuring the amplitude of acoustic signals, the concentration of gas can be accurately measured, and gases below ppm level can be detected. And (3) finding out fault gas and fault type by analyzing and comparing the data of the dissolved gas in the transformer oil under different voltages and different times.
The vibration analysis method is mainly used for monitoring the compaction state, displacement and deformation state of an iron core and a winding in a transformer by analyzing the signal change of a vibration sensor fixed on the surface of a transformer oil tank. Because the vibration analysis method is simple, electrical connection is not needed, the normal operation of the power system is not influenced, and the method is safe and reliable, and is one of important methods for researching the online monitoring system of the current transformer.
The photoacoustic spectrometry is used as a novel transformer state monitoring technology, has high accuracy requirement on experimental equipment, needs large-scale data for modeling and result measurement, is not mature in technical route, is in a starting stage as a whole, and cannot be put into practical application on a large scale.
The power transformer state monitoring and fault diagnosis research based on the vibration analysis method is mainly realized through signal acquisition, processing and analysis, firstly, a vibration sensor is required to be installed on a transformer, data transmission and processing are performed through acquisition of vibration signals in the transformer, and then, fault characteristic parameters are extracted through processing of the data, so that a fault diagnosis model is established. In practical application, problems may exist in aspects of sensor selection, installation position, stability of data quality and the like, and accuracy of a model and accuracy of a fault mode are directly affected.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the transformer state monitoring and early warning method based on the digital twin technology, which has high precision and high efficiency and can realize visual display.
The technical scheme adopted by the invention is as follows:
a transformer state monitoring and early warning method based on a digital twin technology comprises the following steps:
step s101, constructing a transformer digital twin body, namely a transformer digital three-dimensional integral model, which is also called a virtual model;
step S102, data collection and preprocessing, wherein the types of data to be collected comprise state data, operation data and fault data;
step S103, simulating design and analysis, and designing a simulation experiment based on the constructed digital twin model and the acquired data information;
step s104, state monitoring and early warning are carried out, real equipment state holographic sensing is realized by monitoring and analyzing the state parameters of the transformer, real-time monitoring of the state of the transformer is finally realized, the running state of the equipment is accurately grasped, and early warning information is timely sent out.
Preferably, the step of establishing the digital model of the transformer is as follows:
step s201, analyzing the structure and principle of the transformer, and collecting relevant data of the transformer main body;
step S202, constructing a mathematical model of the transformer, modeling the geometric form, material characteristics and motion state information of the transformer into a digital twin platform based on a three-dimensional modeling technology, wherein the mathematical model accurately characterizes the physical form and the electrical characteristics of the transformer;
and step s203, accurately simulating and optimizing the digital model of the transformer.
Preferably, the status data, the operation data, and the fault data flow include:
step 301, collecting various state information in the transformer in real time through a sensor, wherein the state data comprise temperature, humidity, oil level, load and gas concentration;
step S302, acquiring transformer history and real-time operation data including voltage, current, active power, reactive power and frequency electrical performance indexes from power grid company data;
step S303, fault data comprise information such as fault type, fault phenomenon, fault time, fault position and the like of the transformer, a fault database is constructed based on the information, and a processing operation flow when the transformer breaks down is stored to form a fault processing operation set;
step S304, a transformer state database is constructed based on the state data, the operation data, the fault data and other information, all states are numbered, and corresponding indexes and parameter threshold intervals are defined; for example, the transformer overload protection is named E01, the transformer input voltage anomaly is named E02, etc.; the state database can be subsequently optimized and updated based on business needs.
Step S305, data cleaning, namely performing preliminary processing on the acquired original data to remove dirty data and abnormal value interference factors;
step S306, extracting features, namely extracting features of the cleaned data, selecting key indexes and carrying out normalization processing to reduce the difference between the features;
step s307, performing data dimension reduction, in which dimension reduction processing is performed on the extracted feature information based on Principal Component Analysis (PCA) technology in order to reduce the calculation amount and improve the classification effect; principal component analysis is to map high-dimensional data into a low-dimensional space for representation by some linear projection, and expect that the variance of the data is maximum in the projected dimension, so that fewer data dimensions are used, and meanwhile, the characteristics of more original data points are reserved, and the steps of dimension reduction processing are as follows:
(1) The preprocessed transformer monitoring data is represented in the form of a matrix, and each element in the matrix represents a certain index of a monitoring point, such as voltage, current, active power, reactive power, temperature, pressure and the like.
(2) And calculating a covariance matrix of the monitoring data, calculating eigenvalues and eigenvectors of the covariance matrix, and sorting according to the magnitude of the eigenvalues.
(3) And selecting the feature vectors corresponding to the first k largest feature values to construct a new feature matrix.
(4) And mapping the original monitoring data into a new feature matrix to realize dimension reduction processing.
Through the steps, the transformer monitoring data can be mapped from a high-dimensional space to a low-dimensional space, so that the dimension reduction processing of the data is realized. The dimension reduction processing method can effectively reduce the dimension of the data, simultaneously retain main information in the data, and is beneficial to improving the efficiency of data analysis and processing.
Step s308, a mapping is established.
Preferably, the simulation design and analysis, based on the constructed digital twin model and the collected data information, designs a simulation experiment including:
step s401, inputting the preprocessed data into a digital model, processing and analyzing the data based on algorithms such as machine learning, deep learning and the like, designing different simulation experiments based on different working states, and comparing and analyzing;
step s402, the data obtained by the simulation experiment are effectively processed and analyzed, and compared, analyzed and converted with the data in the state database. For example, by testing transformers under different load conditions, the accuracy of the digital twin technology prediction results is verified;
step S403, system testing, namely applying the established digital twin model to an actual transformer state monitoring system, and performing experimental testing; performance evaluation, namely evaluating the performance of the digital twin technology in transformer state monitoring according to data obtained by experimental tests;
step s404, optimizing and improving, according to the evaluation result, optimizing and improving the digital model, and improving the stability and the precision of the digital model; for example, improvements are made to problems that occur in practical applications of digital twinning techniques, such as optimization algorithms, improved sensor accuracy, increased data samples, and the like.
Preferably, the transformer state monitoring includes:
(1) Monitoring the temperature; the temperature monitoring has important significance for judging whether the transformer runs normally or not, a temperature parameter threshold table is established according to different factors such as the type, the model, the voltage level and the like of the transformer, corresponding transformer states such as normal and overheat are set, and when the system detects that the oil temperature exceeds a threshold value, early warning can be carried out.
(2) Load monitoring; in the operation of the transformer, the digital model needs to monitor the operation load in real time, and generally, the load monitoring threshold of the main transformer is set to be a plurality of, such as 80%, 85%, 90%, 95% of rated load, so as to accurately grasp the real-time load state of the transformer, and when the load of the transformer is in different intervals, different colors are displayed to perform corresponding early warning.
(3) Monitoring voltage; the threshold value of the voltage fluctuation range is set in the range from-20% to +5% of rated voltage, and when the voltage fluctuation range exceeds, real-time early warning is carried out.
(4) And monitoring partial discharge. And monitoring and diagnosing partial discharge of the transformer based on the digital model, and timely finding potential faults.
Preferably, the relevant data of the transformer main body comprises physical parameters, structural parameters, electrical parameters, operation parameters and civil engineering data information, and the principle, structure and parameters of the transformer are analyzed and confirmed.
Compared with the prior art, the invention has the beneficial effects that:
the transformer state monitoring and early warning method based on the digital twin technology has the advantages of high precision, high efficiency, visual display realization, high data processing capacity, capability of digitally modeling the transformer through the digital twin technology and inputting the data acquired in real time into the model, thereby realizing the accurate prediction and monitoring of the transformer state; the digital twin technology can realize automatic monitoring and remote control, so that the labor cost and the time cost are reduced, and the monitoring efficiency and the working efficiency are improved; the digital twin technology can visually display the obtained data in the forms of charts, curves and the like, so that a user can conveniently analyze and judge the data; the digital twin technology can timely send out early warning information, prevent accidents in advance and guarantee safe operation of the power grid; the digital twin technology can process and analyze the acquired data through algorithms such as machine learning, deep learning and the like, and extract key information such as transformer state parameters including temperature, humidity, gas concentration and the like.
Drawings
FIG. 1 is a control flow diagram of a method for monitoring and pre-warning transformer conditions based on digital twinning technology;
FIG. 2 is a flow chart of a control process for establishing a digital model of a transformer based on a method for monitoring and early warning the state of the transformer by a digital twin technology;
FIG. 3 is a flow chart of state data, operation data, fault data of a transformer state monitoring and early warning method based on a digital twinning technique;
fig. 4 is a flow chart of simulation design and analysis of a transformer state monitoring and early warning method based on digital twinning technology.
Detailed Description
The invention is described in detail below with reference to the attached drawings and examples:
the digital twin technology is a technology for modeling, simulating and visualizing a physical system, and is a digital and compound engineering entity design and manufacturing method. The method has the core principle that data in the real world is acquired through a digital technology, a entity is modeled, and simulation, optimization and control of the entity are realized.
The digital twin technology mainly comprises three steps: model establishment, simulation and optimization, and feedback adjustment.
The model is built, and the step is to collect information data related to the entity, such as CAD design drawing, sensor detection data and the like, input the information data into a computer, and build a digital model of the entity.
And simulating and optimizing, namely carrying out numerical simulation experiments under various conditions through a digital model, analyzing physical performance performances under different conditions, finding out bottlenecks restricting the physical performance, and carrying out corresponding optimization design.
And (3) feedback adjustment, wherein the step is based on the calculation result of machine learning, performs difference analysis by comparing different conditions, gathers the difference result, inputs the difference result and feeds the difference result back into the model, continuously iterates, continuously optimizes the digital model, and gradually improves the efficiency and accuracy of the digital model.
1-4, a transformer state monitoring and early warning method based on digital twin technology comprises the following steps:
step s101, constructing a transformer digital twin body, namely a transformer digital three-dimensional integral model, which is also called a virtual model;
step S102, data collection and preprocessing, wherein the types of data to be collected comprise state data, operation data and fault data;
step S103, simulating design and analysis, and designing a simulation experiment based on the constructed digital twin model and the acquired data information;
step s104, state monitoring and early warning are carried out, real equipment state holographic sensing is realized by monitoring and analyzing the state parameters of the transformer, real-time monitoring of the state of the transformer is finally realized, the running state of the equipment is accurately grasped, and early warning information is timely sent out.
Preferably, the step of establishing the digital model of the transformer is as follows:
step s201, analyzing the structure and principle of the transformer, and collecting relevant data of the transformer main body;
step S202, constructing a mathematical model of the transformer, modeling the geometric form, material characteristics and motion state information of the transformer into a digital twin platform based on a three-dimensional modeling technology, wherein the mathematical model accurately characterizes the physical form and the electrical characteristics of the transformer;
and step s203, accurately simulating and optimizing the digital model of the transformer.
Preferably, the data collection and preprocessing includes that the data types to be collected include status data, operation data, and fault data, including:
step 301, collecting various state information in the transformer in real time through a sensor, wherein the state data comprise temperature, humidity, oil level, load and gas concentration;
step S302, acquiring transformer history and real-time operation data including voltage, current, active power, reactive power and frequency electrical performance indexes from power grid company data;
step S303, fault data comprise information such as fault type, fault phenomenon, fault time, fault position and the like of the transformer, a fault database is constructed based on the information, and a processing operation flow when the transformer breaks down is stored to form a fault processing operation set;
step S304, a transformer state database is constructed based on the state data, the operation data, the fault data and other information, all states are numbered, and corresponding indexes and parameter threshold intervals are defined; for example, the transformer overload protection is named E01, the transformer input voltage anomaly is named E02, etc.; the state database can be subsequently optimized and updated based on business needs.
Step S305, data cleaning, namely performing preliminary processing on the acquired original data to remove dirty data and abnormal value interference factors;
step S306, extracting features, namely extracting features of the cleaned data, selecting key indexes and carrying out normalization processing to reduce the difference between the features;
step s307, performing data dimension reduction, in which dimension reduction processing is performed on the extracted feature information based on Principal Component Analysis (PCA) technology in order to reduce the calculation amount and improve the classification effect; principal component analysis is to map high-dimensional data into a low-dimensional space for representation by some linear projection, and expect that the variance of the data is maximum in the projected dimension, so that fewer data dimensions are used, and meanwhile, the characteristics of more original data points are reserved, and the steps of dimension reduction processing are as follows:
(1) The preprocessed transformer monitoring data is represented in the form of a matrix, and each element in the matrix represents a certain index of a monitoring point, such as voltage, current, active power, reactive power, temperature, pressure and the like.
(2) And calculating a covariance matrix of the monitoring data, calculating eigenvalues and eigenvectors of the covariance matrix, and sorting according to the magnitude of the eigenvalues.
(3) And selecting the feature vectors corresponding to the first k largest feature values to construct a new feature matrix.
(4) And mapping the original monitoring data into a new feature matrix to realize dimension reduction processing.
Through the steps, the transformer monitoring data can be mapped from a high-dimensional space to a low-dimensional space, so that the dimension reduction processing of the data is realized. The dimension reduction processing method can effectively reduce the dimension of the data, simultaneously retain main information in the data, and is beneficial to improving the efficiency of data analysis and processing.
Step s308, a mapping is established.
Preferably, the simulation design and analysis, based on the constructed digital twin model and the collected data information, designs a simulation experiment including:
step s401, inputting the preprocessed data into a digital model, processing and analyzing the data based on algorithms such as machine learning, deep learning and the like, designing different simulation experiments based on different working states, and comparing and analyzing;
step s402, the data obtained by the simulation experiment are effectively processed and analyzed, and compared, analyzed and converted with the data in the state database. For example, by testing transformers under different load conditions, the accuracy of the digital twin technology prediction results is verified;
step S403, system testing, namely applying the established digital twin model to an actual transformer state monitoring system, and performing experimental testing; performance evaluation, namely evaluating the performance of the digital twin technology in transformer state monitoring according to data obtained by experimental tests;
step s404, optimizing and improving, according to the evaluation result, optimizing and improving the digital model, and improving the stability and the precision of the digital model; for example, improvements are made to problems that occur in practical applications of digital twinning techniques, such as optimization algorithms, improved sensor accuracy, increased data samples, and the like.
Preferably, the transformer state monitoring includes:
(1) Monitoring the temperature; the temperature monitoring has important significance for judging whether the transformer runs normally or not, a temperature parameter threshold table is established according to different factors such as the type, the model, the voltage level and the like of the transformer, corresponding transformer states such as normal and overheat are set, and when the system detects that the oil temperature exceeds a threshold value, early warning can be carried out.
(2) Load monitoring; in the operation of the transformer, the digital model needs to monitor the operation load in real time, and generally, the load monitoring threshold of the main transformer is set to be a plurality of, such as 80%, 85%, 90%, 95% of rated load, so as to accurately grasp the real-time load state of the transformer, and when the load of the transformer is in different intervals, different colors are displayed to perform corresponding early warning.
(3) Monitoring voltage; the threshold value of the voltage fluctuation range is set in the range from-20% to +5% of rated voltage, and when the voltage fluctuation range exceeds, real-time early warning is carried out.
(4) And monitoring partial discharge. And monitoring and diagnosing partial discharge of the transformer based on the digital model, and timely finding potential faults.
Preferably, the relevant data of the transformer main body comprises physical parameters, structural parameters, electrical parameters, operation parameters and civil engineering data information, and the principle, structure and parameters of the transformer are analyzed and confirmed.
The transformer state monitoring and early warning method based on the digital twin technology has the advantages of high precision, high efficiency, visual display realization, high data processing capacity, capability of digitally modeling the transformer through the digital twin technology and inputting the data acquired in real time into the model, thereby realizing the accurate prediction and monitoring of the transformer state; the digital twin technology can realize automatic monitoring and remote control, so that the labor cost and the time cost are reduced, and the monitoring efficiency and the working efficiency are improved; the digital twin technology can visually display the obtained data in the forms of charts, curves and the like, so that a user can conveniently analyze and judge the data; the digital twin technology can timely send out early warning information, prevent accidents in advance and guarantee safe operation of the power grid; the digital twin technology can process and analyze the acquired data through algorithms such as machine learning, deep learning and the like, and extract key information such as transformer state parameters including temperature, humidity, gas concentration and the like.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the structure of the present invention in any way. Any simple modification, equivalent variation and modification of the above embodiments according to the technical substance of the present invention fall within the technical scope of the present invention.
Claims (7)
1. The transformer state monitoring and early warning method based on the digital twin technology is characterized by comprising the following steps of:
step s101, constructing a transformer digital twin body, namely a transformer digital three-dimensional integral model;
step S102, data collection and preprocessing, wherein the collected data types comprise state data, operation data and fault data;
step S103, simulating design and analysis, and designing a simulation experiment based on the constructed digital twin model and the acquired data information;
step s104, state monitoring and early warning are carried out, real equipment state holographic sensing is realized by monitoring and analyzing the state parameters of the transformer, real-time monitoring of the state of the transformer is finally realized, the running state of the equipment is accurately grasped, and early warning information is timely sent out.
2. The method for monitoring and early warning the state of a transformer based on the digital twin technology according to claim 1, wherein the method is characterized by comprising the following steps:
the step of establishing the transformer digital model is as follows:
step s201, analyzing the structure and principle of the transformer, and collecting relevant data of the transformer main body;
step S202, constructing a mathematical model of the transformer, modeling the geometric form, material characteristics and motion state information of the transformer into a digital twin platform based on a three-dimensional modeling technology, wherein the mathematical model accurately characterizes the physical form and the electrical characteristics of the transformer;
and step s203, accurately simulating and optimizing the digital model of the transformer.
3. The method for monitoring and early warning the state of a transformer based on the digital twin technology according to claim 1, wherein the method is characterized by comprising the following steps:
the state data, the operation data and the fault data flow comprise:
step 301, acquiring state information in the transformer in real time through a sensor, wherein the state data comprises temperature, humidity, oil level, load and gas concentration;
step S302, acquiring transformer history and real-time operation data including voltage, current, active power, reactive power and frequency electrical performance indexes from power grid company data;
step S303, fault data comprise information such as fault type, fault phenomenon, fault time, fault position and the like of the transformer, a fault database is constructed based on the information, and a processing operation flow when the transformer breaks down is stored to form a fault processing operation set;
step S304, a transformer state database is constructed based on the state data, the operation data, the fault data and other information, all states are numbered, and corresponding indexes and parameter threshold intervals are defined; for example, the transformer overload protection is named E01, the transformer input voltage anomaly is named E02, etc.; the state database can be optimized and updated based on the service requirement later;
step S305, data cleaning, namely performing preliminary processing on the acquired original data to remove dirty data and abnormal value interference factors;
step S306, extracting features, namely extracting features of the cleaned data, selecting key indexes and carrying out normalization processing to reduce the difference between the features;
step s307, performing data dimension reduction, namely performing dimension reduction processing on the extracted characteristic information based on a principal component analysis technique; the principal component analysis is to map high-dimensional data into a low-dimensional space for representation by linear projection, and expect the maximum variance of the data in the projected dimension, thereby using fewer data dimensions while preserving the characteristics of the original data points;
step s308, a mapping is established.
4. The method for monitoring and early warning the state of a transformer based on the digital twin technology according to claim 1, wherein the method is characterized by comprising the following steps:
the simulation design and analysis are based on the constructed digital twin model and the acquired data information, and the design simulation experiment comprises the following steps:
step s401, inputting the preprocessed data into a digital model, processing and analyzing the data based on algorithms such as machine learning, deep learning and the like, designing different simulation experiments based on different working states, and comparing and analyzing;
step S402, processing and analyzing the data obtained by the simulation experiment, and comparing, analyzing and converting the data with the data in the state database;
step S403, system testing, namely applying the established digital twin model to an actual transformer state monitoring system, and performing experimental testing; performance evaluation, namely evaluating the performance of the digital twin technology in transformer state monitoring according to data obtained by experimental tests;
step s404, optimizing and improving, according to the evaluation result, optimizing and improving the digital model, and improving the stability and the precision of the digital model;
5. the method for monitoring and early warning the state of a transformer based on the digital twin technology according to claim 1, wherein the method is characterized by comprising the following steps:
the transformer condition monitoring includes:
(1) Monitoring the temperature; according to different factors such as the type, the model, the voltage level and the like of the transformer, a temperature parameter threshold value table is established, a corresponding transformer state is set, and when the system detects that the oil temperature exceeds a threshold value, early warning is carried out;
(2) Load monitoring; in the operation of the transformer, the digital model needs to monitor the operation load in real time, the load monitoring threshold value of the main transformer is set to 80%, 85%, 90% or 95% of rated load, and when the load of the transformer is in different intervals, different colors are displayed for corresponding early warning;
(3) Monitoring voltage; setting the threshold value of the voltage fluctuation range within the range from-20% to +5% of rated voltage, and carrying out real-time early warning when the voltage fluctuation range exceeds;
(4) Monitoring partial discharge; monitoring and diagnosing partial discharge of the transformer based on the digital model, and finding potential faults;
6. the method for monitoring and early warning the state of a transformer based on the digital twin technology according to claim 1, wherein the method is characterized by comprising the following steps:
the related data of the transformer main body comprise physical parameters, structural parameters, electrical parameters, operation parameters and civil engineering data information, and the principle, the structure and the parameters of the transformer are analyzed and confirmed.
7. The transformer state monitoring and early warning method based on the digital twin technology according to claim 3, wherein the step of dimension reduction processing is as follows:
(1) The preprocessed transformer monitoring data are expressed in a matrix form, and each element in the matrix represents a certain index of a monitoring point;
(2) Calculating a covariance matrix of the monitoring data, calculating eigenvalues and eigenvectors of the covariance matrix, and sorting according to the magnitude of the eigenvalues;
(3) Selecting feature vectors corresponding to the first k largest feature values, and constructing a new feature matrix;
(4) And mapping the original monitoring data into a new feature matrix to realize dimension reduction processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489752.4A CN117574624A (en) | 2023-11-09 | 2023-11-09 | Transformer state monitoring and early warning method based on digital twin technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489752.4A CN117574624A (en) | 2023-11-09 | 2023-11-09 | Transformer state monitoring and early warning method based on digital twin technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117574624A true CN117574624A (en) | 2024-02-20 |
Family
ID=89861676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311489752.4A Pending CN117574624A (en) | 2023-11-09 | 2023-11-09 | Transformer state monitoring and early warning method based on digital twin technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117574624A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117977586A (en) * | 2024-04-02 | 2024-05-03 | 深圳供电局有限公司 | Power failure early warning method and device based on three-dimensional digital twin model and electronic equipment |
| CN118395362A (en) * | 2024-06-28 | 2024-07-26 | 上海凌至物联网有限公司 | Digital twinning-based transformer bushing internal fault diagnosis method |
| CN118566796A (en) * | 2024-05-24 | 2024-08-30 | 国网青海省电力公司黄化供电公司 | Method for detecting fault state of converter transformer winding |
| CN118657000A (en) * | 2024-08-20 | 2024-09-17 | 安徽继远软件有限公司 | Visual reconstruction standard modeling method based on power transformation equipment component |
-
2023
- 2023-11-09 CN CN202311489752.4A patent/CN117574624A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117977586A (en) * | 2024-04-02 | 2024-05-03 | 深圳供电局有限公司 | Power failure early warning method and device based on three-dimensional digital twin model and electronic equipment |
| CN118566796A (en) * | 2024-05-24 | 2024-08-30 | 国网青海省电力公司黄化供电公司 | Method for detecting fault state of converter transformer winding |
| CN118395362A (en) * | 2024-06-28 | 2024-07-26 | 上海凌至物联网有限公司 | Digital twinning-based transformer bushing internal fault diagnosis method |
| CN118657000A (en) * | 2024-08-20 | 2024-09-17 | 安徽继远软件有限公司 | Visual reconstruction standard modeling method based on power transformation equipment component |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117574624A (en) | Transformer state monitoring and early warning method based on digital twin technology | |
| CN111784175A (en) | Distribution transformer risk assessment method and system based on multi-source information | |
| CN106054104A (en) | Intelligent ammeter fault real time prediction method based on decision-making tree | |
| CN113420162B (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN113466597A (en) | Intelligent detection method for equipment state of rail transit power supply system | |
| CN104933477A (en) | Method for optimizing maintenance strategy by using risk assessment of power transmission and transformation equipment | |
| CN112884089A (en) | Power transformer fault early warning system based on data mining | |
| CN102539325A (en) | Method for monitoring structural damage of coke tower based on strain monitoring | |
| CN116975566A (en) | Intelligent transformer monitoring system and method based on multi-source parameter analysis and diagnosis | |
| CN113902241A (en) | Power grid equipment maintenance strategy system and method based on comprehensive state evaluation | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN112966990A (en) | Comprehensive state evaluation method for power transformation equipment | |
| CN117807659A (en) | Building structure defect detection and correction method and system | |
| CN110262460B (en) | Concrete piston fault prediction method for extracting features by combining clustering idea | |
| CN112085233A (en) | Power digital information model based on station domain BIM data fusion multi-source information | |
| CN116258467A (en) | Electric power construction management and control system | |
| CN116298659A (en) | Power distribution network fault identification method based on distributed current monitoring data mining | |
| CN115936663A (en) | Maintenance method and device for power system | |
| CN115600695A (en) | Fault diagnosis method of metering equipment | |
| CN114971308A (en) | Transformer health condition assessment method based on multi-dimensional data analysis | |
| CN114332515A (en) | Online evaluation method for operation safety of coal mill based on intuition fuzzy clustering | |
| CN114066163A (en) | Power equipment state analysis method and device based on three-layer architecture mode | |
| CN114878942A (en) | Design method of high-voltage cable intelligent monitoring center system | |
| Jiafeng et al. | Research and Application of State Identification Technology for Live Operation of Distribution Lines | |
| CN114583833B (en) | Fusion analysis method and device based on centralized monitoring remote signaling and remote measurement |
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 |