CN120428019A - A real-time control method and system for transformer current test parameters - Google Patents
A real-time control method and system for transformer current test parametersInfo
- Publication number
- CN120428019A CN120428019A CN202510873221.8A CN202510873221A CN120428019A CN 120428019 A CN120428019 A CN 120428019A CN 202510873221 A CN202510873221 A CN 202510873221A CN 120428019 A CN120428019 A CN 120428019A
- Authority
- CN
- China
- Prior art keywords
- node
- abnormal
- transformer
- nodes
- regulation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- 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
- 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
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Protection Of Transformers (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
Abstract
本发明提供了一种变压器通流试验参数实时调控方法及系统，涉及变压器流通试验调控领域。该方法包括：采集变压器通流试验的状态数据，将状态数据以无向图的数据结构组建成状态模型；使用异常检测模型检测所述状态模型中的异常节点；在检测到异常节点时激活异常检索，并检索其他潜在异常节点，将其他潜在异常节点按照检索优先级的大小降序排列，依次采用异常检测模型检测其他节点是否异常；根据异常检测结果动态调整变压器通流试验参数：当不存在其他节点异常时，采用单节点异常调控；当存在其他节点异常时，采用多节点关联异常调控。本发明利用图模型以更低的性能负载实现多参数关联量化，相比传统方法能够提前捕捉过热趋势。
The present invention provides a method and system for real-time control of transformer current-carrying test parameters, relating to the field of transformer current-carrying test control. The method comprises: collecting status data from the transformer current-carrying test, constructing the status data into a state model using an undirected graph data structure; detecting abnormal nodes in the state model using an anomaly detection model; activating anomaly retrieval upon detecting an abnormal node, searching for other potential abnormal nodes, sorting the other potential abnormal nodes in descending order of retrieval priority, and sequentially using the anomaly detection model to detect abnormalities in the other nodes; and dynamically adjusting the transformer current-carrying test parameters based on the anomaly detection results: when no other nodes are abnormal, single-node abnormal control is adopted; when other nodes are abnormal, multi-node associated abnormal control is adopted. The present invention utilizes a graph model to achieve multi-parameter associated quantification with a lower performance load, enabling earlier detection of overheating trends compared to traditional methods.
Description
Technical Field
The invention relates to the field of transformer flow test regulation and control, in particular to a method and a system for regulating and controlling parameters of a transformer flow test in real time.
Background
The transformer through-current test needs to apply high current (up to 120% of rated current) to verify the bearing capacity of the winding, but has two major risks, namely local overheating caused by hot spot temperature sudden rise due to uneven current distribution and insulation aging caused by hot spot temperature sudden rise, and mechanical damage caused by iron core vibration exceeding standard and accumulated damage structure caused by electromagnetic force. The core contradiction of transformer through-current testing is the balance between high current requirements and equipment safety. The prior art is mainly divided into two types, namely, the traditional threshold method relies on manual experience to set a fixed threshold, and the intelligent detection method such as LSTM prediction ignores the multi-parameter coupling relation.
The method has the defects that early warning cannot be carried out at the initial stage of current harmonic, hysteresis exists, a certain test interruption rate exists, the calculation load of a multi-parameter method such as a CNN-LSTM model is too high, multi-parameter coupling is ignored, a false alarm rate exists, the multi-parameter method such as CNN extracts multi-sensor characteristics, the problem of large calculation load exists, real-time regulation and control cannot be achieved, and damage expansion is caused by response delay.
Disclosure of Invention
The invention aims to provide a method for regulating and controlling the through-flow test parameters of a transformer in real time, and further provides a system capable of running and realizing the method, so that the problems mentioned in the background art are effectively solved.
The technical scheme of the invention is as follows:
in a first aspect, a method for real-time regulation and control of a transformer through-current test parameter is provided, the method comprising the following steps:
s1, collecting state data of a transformer through-flow test, and constructing the state data into a state model by using a data structure of an undirected graph;
s2, detecting abnormal nodes in the state model by using an abnormal detection model;
s3, when abnormal nodes are detected, abnormal retrieval is activated, other potential abnormal nodes are retrieved, the other potential abnormal nodes are arranged in descending order according to the retrieval priority, and an abnormal detection model is sequentially adopted to detect whether the other nodes are abnormal;
S4, dynamically adjusting the transformer through-flow test parameters according to the abnormal detection result in the step S3:
When other node anomalies do not exist, single-node anomaly regulation is adopted;
when other nodes are abnormal, multi-node association abnormal regulation is adopted.
The invention is further improved in that the step S1 of collecting the state data of the transformer through-current test comprises the steps of collecting winding current time sequence data through a current sensor, collecting hot spot temperature time sequence data through an infrared thermometer, collecting iron core vibration time sequence data through a vibration sensor, collecting discharge ripple time sequence data through an acoustic sensor and collecting environment time sequence data through an environment temperature and humidity sensor.
The invention is further improved in that the state model in step S1 is an undirected graphThe undirected graph G comprises a node set V, an edge set E, a node attribute matrix X and an adjacency matrix A, wherein the node set, wherein,The current data is represented by a graph of the current,The data of the temperature is represented and,The vibration data is represented as such,The voiceprint data is represented by a representation of the voiceprint data,Representing environmental data, the node attribute matrix, wherein,Representing dimensions asWherein d represents the total number of time steps contained in the state data during a transformer through-current test period, the ith row vector of the node attribute matrix X, wherein,Representing dimensions asReal space of (1), vectorRepresenting the ith node in undirected graph GThe attribute vector is the i-th state data acquired in a through-flow test period of the primary transformer, and the value of i is 1-5.
A further improvement of the invention is that any edge in the edge set EThe value of (2) is calculated by the following formula:
wherein, the For the ith nodeAnd the jth nodeThe value of j is 1-5,The L1 norm of the vector is represented,For the normalized coefficient to be a function of the normalized coefficient,In order to physically associate the weights with each other,Is the strength of the physical association between nodes, where, when i=1, j=2,Representing the current-temperature correlation strength, takes a value of 0.9, and when i=1, j=3,The current-vibration correlation strength is represented, the value is 0.7, and the rest.
A further development of the invention is that the adjacency matrix, wherein,Representing dimensions asIs adjacent to the matrixElements of (a)。
The invention is further improved in that the S2 comprises the following specific steps:
s21, for each node Establishing an automatic encoder anomaly detection modelThe treatment process comprises the following steps:
wherein, the Anomaly detection model for ith nodeIs provided with an encoder of the number,Anomaly detection model for ith nodeIs a decoder of (a); Is that The output result of the encoding is output,Representation ofOutputting a reconstruction result;
s22, calculating a reconstruction error, wherein the calculation formula is as follows:
Wherein k represents the kth time step;
s23, judging whether the node is abnormal or not, wherein the calculation formula is as follows:
wherein, the For the abnormality detection threshold value,Is a nodeNode risk coefficient of (2) takes on the value of,,,,;
S24, whenAnd judging that the ith node is abnormal, and triggering abnormal early warning.
The invention is further improved in that the step S3 comprises the following specific steps:
S31, when Judging that the ith node is abnormal, and activating abnormal retrieval;
s32, determining potential influence node set ;
S33, computing nodeThe calculation formula of the search priority is as follows:
wherein, the Is the ith node in undirected graph GTo the jth nodeIs the shortest path hop count of (a); is the maximum element value of the adjacency matrix A; representing the jth node Is a search priority of (1);
s34, arranging other nodes in descending order according to the size of the retrieval priority, and detecting whether the other nodes are abnormal or not by adopting an abnormality detection model in sequence.
The invention is further improved in that the step S4 comprises the following specific steps:
s41, when other node anomalies do not exist, adopting single-node anomaly regulation and control, wherein a regulation and control formula is as follows:
wherein, the In order to regulate the current after the regulation,Is the current;
S42, when other nodes are abnormal, adopting multi-node association abnormal regulation and control, wherein a regulation and control formula is as follows:
wherein, the In order to regulate the current after the regulation,As a current flow is present,Representing a current abnormal node set;
s43, when all nodes meet And the recovery test current is 0.98 times of rated current of the transformer.
In a second aspect, a real-time regulation and control system for transformer through-current test parameters is provided, wherein the system comprises a model building module, an abnormal retrieval module, a secondary retrieval module and a parameter adjustment module;
The model building module is used for collecting state data of a transformer through-flow test and building the state data into a state model by using a data structure of an undirected graph;
The abnormality retrieval module is used for detecting abnormal nodes in the state model by using the abnormality detection model;
The secondary retrieval module is used for activating abnormal retrieval when abnormal nodes are detected, retrieving other potential abnormal nodes, arranging the other potential abnormal nodes in descending order according to the retrieval priority, and sequentially detecting whether the other nodes are abnormal or not by adopting an abnormal detection model;
the parameter adjustment module is used for dynamically adjusting the through-flow test parameters of the transformer according to the abnormality detection result, wherein when other node abnormalities do not exist, single-node abnormal regulation is adopted, and when other node abnormalities exist, multi-node associated abnormal regulation is adopted.
The beneficial effects are that:
(1) According to the invention, through collecting winding current time sequence data, hot spot temperature time sequence data, iron core vibration time sequence data, discharge voiceprint time sequence data and environment time sequence data and through multi-physical quantity cross verification, the hysteresis of the traditional single parameter threshold method is obviously solved, and the false alarm rate is reduced.
(2) According to the invention, state data of a transformer through-flow test is associated and quantized in an undirected graph form, and compared with a traditional CNN-LSTM model, the method realizes multi-parameter coupling with lower performance load.
(3) According to the invention, the automatic encoder anomaly detection model is established for each node in the undirected graph, the anomaly detection model is utilized to detect the anomaly node and activate anomaly retrieval, and the transformer through-flow test parameters are dynamically adjusted, so that the overheat trend can be captured in advance.
(4) According to the invention, through a hierarchical dynamic regulation strategy, when other node anomalies are not existed, single-node anomaly regulation is adopted, and when other node anomalies are existed, multi-node association anomaly regulation is adopted, so that the traditional 'one-cut' type power failure is avoided.
Drawings
Fig. 1 is a flow chart of a method for real-time regulation and control of transformer through-current test parameters according to embodiment 1 of the present invention.
Fig. 2 is a schematic structural diagram of a real-time regulation and control system for through-current test parameters of a transformer according to embodiment 2 of the present invention.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced without one or more of these details. In other instances, well-known features have not been described in detail in order to avoid obscuring the invention.
Example 1:
The embodiment constructs a real-time regulation and control method for the transformer through-flow test parameters, which comprises the steps of collecting state data of a transformer through-flow test, constructing a state model, detecting abnormal nodes in the state model by using an abnormal detection model, activating abnormal retrieval when the abnormal nodes are detected, retrieving other potential abnormal nodes, and dynamically regulating the transformer through-flow test parameters according to an abnormal detection result. The graph model carries out multi-parameter association quantification, and captures overheat trend in advance than the existing method, the priority retrieval mechanism compresses calculated amount, and current gradual adjustment of closed loop regulation can avoid test interruption.
Fig. 1 shows specific steps of a method for regulating and controlling parameters of a through-current test of a transformer in this embodiment in real time:
s1, collecting state data of a transformer through-flow test, and constructing the state data into a state model by using a data structure of an undirected graph;
s2, detecting abnormal nodes in the state model by using an abnormal detection model;
s3, when abnormal nodes are detected, abnormal retrieval is activated, other potential abnormal nodes are retrieved, the other potential abnormal nodes are arranged in descending order according to the retrieval priority, and an abnormal detection model is sequentially adopted to detect whether the other nodes are abnormal;
S4, dynamically adjusting the transformer through-flow test parameters according to the abnormal detection result in the step S3:
When other node anomalies do not exist, single-node anomaly regulation is adopted;
when other nodes are abnormal, multi-node association abnormal regulation is adopted.
In the embodiment, the step S1 of collecting state data of a transformer through-current test comprises the steps of collecting winding current time sequence data through a current sensor, collecting hot spot temperature time sequence data through an infrared thermometer, collecting iron core vibration time sequence data through a vibration sensor, collecting discharge ripple time sequence data through an acoustic sensor and collecting environment time sequence data through an environment temperature and humidity sensor.
In the present embodiment, the state model in S1 is an undirected graphThe undirected graph G comprises a node set V, an edge set E, a node attribute matrix X and an adjacent matrix A, and the node set, wherein,The current data is represented by a graph of the current,The data of the temperature is represented and,The vibration data is represented as such,The voiceprint data is represented by a representation of the voiceprint data,Representing environmental data, node attribute matrix, wherein,Representing dimensions asWherein d represents the total number of time steps contained in the state data in a transformer through-current test period, the ith row vector of the node attribute matrix X, wherein,Representing dimensions asReal space of (1), vectorRepresenting the ith node in undirected graph GThe attribute vector is the i-th state data acquired in a through-flow test period of the primary transformer, and the value of i is 1-5.
In this embodiment, any edge in edge set EThe value of (2) is calculated by equation (1):
wherein, the For the ith nodeAnd the jth nodeThe value of j is 1-5,The L1 norm of the vector is represented,For the normalized coefficient to be a function of the normalized coefficient,In order to physically associate the weights with each other,Is the strength of the physical association between nodes, where, when i=1, j=2,Representing the current-temperature correlation strength, takes a value of 0.9, and when i=1, j=3,The current-vibration correlation strength is represented, the value is 0.7, and the rest。
In the present embodiment, the adjacency matrix, wherein,Representing dimensions asIs adjacent to the matrixElements of (a)。
In this embodiment, S2 includes the following specific steps:
s21, for each node Establishing an automatic encoder anomaly detection modelThe treatment process is shown in the formula (2) and the formula (3):
wherein, the Anomaly detection model for ith nodeIs provided with an encoder of the number,Anomaly detection model for ith nodeIs a decoder of (a); Is that The output result of the encoding is output,Representation ofOutputting a reconstruction result;
s22, calculating a reconstruction error according to the following formula (4):
Wherein k represents the kth time step;
s23, judging whether the node is abnormal or not, wherein a calculation formula is shown in the following formula (5):
wherein, the For the abnormality detection threshold value,Is a nodeNode risk coefficient of (2) takes on the value of,,,,;
S24, whenAnd judging that the ith node is abnormal, and triggering abnormal early warning.
In this embodiment, S3 includes the following specific steps:
S31, when Judging that the ith node is abnormal, and activating abnormal retrieval;
s32, determining potential influence node set ;
S33, computing nodeThe calculation formula of the search priority is shown in the following formula (6):
wherein, the Is the ith node in undirected graph GTo the jth nodeIs the shortest path hop count of (a); is the maximum element value of the adjacency matrix A; representing the jth node Is a search priority of (1);
s34, arranging other nodes in descending order according to the size of the retrieval priority, and detecting whether the other nodes are abnormal or not by adopting an abnormality detection model in sequence.
In this embodiment, S4 includes the following specific steps:
S41, when other node anomalies do not exist, adopting single-node anomaly regulation, wherein a regulation formula is shown in a formula (7):
wherein, the In order to regulate the current after the regulation,Is the current;
S42, when other nodes are abnormal, adopting multi-node association abnormal regulation, wherein a regulation formula is shown in a formula (8):
wherein, the In order to regulate the current after the regulation,As a current flow is present,Representing a current abnormal node set;
s43, when all nodes meet And the recovery test current is 0.98 times of rated current of the transformer.
Example 2:
the embodiment provides a real-time regulation and control system for transformer through-flow test parameters, which comprises a model building module, an abnormal retrieval module, a secondary retrieval module and a parameter adjustment module as shown in fig. 2.
The model building module is used for collecting state data of the transformer through-flow test and building a state model;
The abnormality retrieval module is used for detecting abnormal nodes in the state model by using the abnormality detection model;
the secondary retrieval module is used for activating abnormal retrieval when abnormal nodes are detected, and retrieving other potential abnormal nodes;
The parameter adjustment module is used for dynamically adjusting the through-flow test parameters of the transformer according to the abnormal detection result.
In the embodiment, the state data of the transformer through-current test is collected by collecting winding current time sequence data through a current sensor, collecting hot spot temperature time sequence data through an infrared thermometer, collecting iron core vibration time sequence data through a vibration sensor, collecting discharge ripple time sequence data through an acoustic sensor and collecting environment time sequence data through an environment temperature and humidity sensor.
The steps for realizing the corresponding functions of each parameter and each unit module in the transformer through-current test parameter real-time regulation system according to the present invention can refer to each parameter and each step in the embodiment of the transformer through-current test parameter real-time regulation method in the above embodiment 1.
Such as:
The state data of the transformer through-current test comprises winding current time sequence data collected through a current sensor, hot spot temperature time sequence data collected through an infrared thermometer, iron core vibration time sequence data collected through a vibration sensor, discharge ripple time sequence data collected through an acoustic sensor and environment time sequence data collected through an environment temperature and humidity sensor.
For another example:
The state model constructed by the model construction module is an undirected graph The undirected graph G includes a node set V, an edge set E, a node attribute matrix X, and an adjacency matrix A.
The node set, wherein,The current data is represented by a graph of the current,The data of the temperature is represented and,The vibration data is represented as such,The voiceprint data is represented by a representation of the voiceprint data,Representing environmental data, the node attribute matrix, wherein,Representing dimensions asWherein d represents the total number of time steps contained in the state data during a transformer through-current test period, the ith row vector of the node attribute matrix X, wherein,Representing dimensions asReal space of (1), vectorRepresenting the ith node in undirected graph GThe attribute vector is the i-th state data acquired in a through-flow test period of the primary transformer, and the value of i is 1-5.
Any edge in edge set EThe value of (2) is calculated by the formula (1) in example 1, and is not described here.
Adjacency matrix, wherein,Representing dimensions asIs adjacent to the matrixElements of (a)。
For another example:
The anomaly retrieval module first calculates for each node Establishing an automatic encoder anomaly detection modelThe processing procedure is shown in the formula (2) and the formula (3) in the embodiment 1, and is not repeated here.
Then, the reconstruction error is calculated according to the formula (4) in the embodiment 1, then whether the node is abnormal or not is judged according to the formula (5) in the embodiment 1, and the abnormality early warning is triggered when the abnormality of a certain node is judged.
For another example:
The implementation of the secondary retrieval module comprises the specific steps of activating exception retrieval when the ith node is determined to be abnormal, and then determining a set of potential influencing nodes Further, a node is calculated according to the formula (6) in embodiment 1And finally, arranging other nodes in descending order according to the size of the retrieval priority, and sequentially detecting whether other nodes are abnormal by adopting an abnormality detection model.
For another example:
The parameter adjustment module is used for dynamically adjusting the through-flow test parameters of the transformer according to the abnormality detection result, wherein when no other node abnormality exists, single-node abnormality regulation is adopted, and a regulation formula is shown as a formula (7) in the embodiment 1. When other node anomalies exist, multi-node-associated anomaly regulation is adopted, and a regulation formula is shown in a formula (8) in the embodiment 1.
Example 3
The embodiment provides electronic equipment which comprises a processor and a memory, wherein a computer program which can be called by the processor is stored in the memory, and the processor executes the real-time regulation and control method for the transformer through-flow test parameters by calling the computer program stored in the memory.
The electronic device may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, where at least one computer program is stored in the memories, and the computer program is loaded and executed by the processors to implement a method for real-time regulation and control of a transformer through-current test parameter provided by the above method embodiment. The electronic device can also include other components for implementing the functions of the device, for example, the electronic device can also have wired or wireless network interfaces, input-output interfaces, and the like, for inputting and outputting data. The present embodiment is not described herein.
Those skilled in the art will appreciate that the present invention may be implemented as a system, method, or computer program product. Accordingly, the present disclosure may be embodied in either entirely hardware, entirely software (including firmware, resident software, micro-code, etc.), or in a combination of hardware and software, referred to herein generally as a "circuit," module, "or" system. Furthermore, in some embodiments, the invention may also be embodied in the form of a computer program product in one or more computer-readable media, which contain computer-readable program code.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer-readable storage medium include an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The present invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow or block of the flowchart illustrations and block diagrams, and combinations of flows and blocks in the flowchart illustrations or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and block diagram block or blocks.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are all within the protection of the present invention.
Claims (10)
1. The real-time regulation and control method for the through-flow test parameters of the transformer is characterized by comprising the following steps:
s1, collecting state data of a transformer through-flow test, and constructing the state data into a state model by using a data structure of an undirected graph;
s2, detecting abnormal nodes in the state model by using an abnormal detection model;
s3, when abnormal nodes are detected, abnormal retrieval is activated, other potential abnormal nodes are retrieved, the other potential abnormal nodes are arranged in descending order according to the retrieval priority, and an abnormal detection model is sequentially adopted to detect whether the other nodes are abnormal;
S4, dynamically adjusting the transformer through-flow test parameters according to the abnormal detection result in the step S3:
When other node anomalies do not exist, single-node anomaly regulation is adopted;
when other nodes are abnormal, multi-node association abnormal regulation is adopted.
2. The method for regulating and controlling the transformer through-current test parameters in real time according to claim 1 is characterized in that the state data of the transformer through-current test in the step S1 comprises the steps of collecting winding current time sequence data through a current sensor, collecting hot spot temperature time sequence data through an infrared thermometer, collecting iron core vibration time sequence data through a vibration sensor, collecting discharge ripple time sequence data through an acoustic sensor and collecting environment time sequence data through an environment temperature and humidity sensor.
3. The method for real-time regulation and control of transformer through-current test parameters according to claim 2, wherein the state data is represented by undirected graphThe data structure of (2) is built into a state model, wherein V is a node set, E is an edge set, X is a node attribute matrix, and A is an adjacency matrix.
4. The method for real-time regulation and control of transformer through-current test parameters according to claim 3, wherein the node set, wherein,From the time-series data of the winding current,From the time series data of the temperature of the hot spot,From the time series data of the vibration of the iron core,From the discharge voiceprint time series data,Derived from the environmental time series data.
5. The method for real-time regulation and control of transformer through-current test parameters according to claim 3, wherein the node attribute matrix, wherein,Representing dimensions asD represents the total number of time steps contained in the state data in a through-flow test period of the primary transformer;
The ith row vector of the node attribute matrix X , wherein,Representing dimensions asReal space, vector of (a)Representing the ith node in undirected graph GThe attribute vector is the ith state data collected in a transformer through-flow test period.
6. The method for real-time regulation and control of transformer through-current test parameters according to claim 3, wherein any side in the side set EThe value of (2) is calculated by the following formula:
in the formula, For the ith nodeAnd the jth nodeThe value of j is 1-5 on the edge between the two sides; an L1 norm representing the vector; Is a normalized coefficient; Is a physical association weight; is the strength of the physical association between nodes, where, when i=1, j=2, Representing the current-temperature correlation strength, takes a value of 0.9, and when i=1, j=3,The current-vibration correlation strength is represented, the value is 0.7, and the rest;
The adjacency matrix, wherein,Representing dimensions asIs adjacent to the matrixElements of (a)。
7. The method for real-time regulation and control of transformer through-current test parameters according to claim 6, wherein step S2 specifically comprises:
s21, for each node Establishing an automatic encoder anomaly detection modelThe treatment process comprises the following steps:
wherein, the Anomaly detection model for ith nodeIs provided with an encoder of the number,Anomaly detection model for ith nodeIs a decoder of (a); Is that The output result of the encoding is output,Representation ofOutputting a reconstruction result;
s22, calculating reconstruction errors :
Wherein k represents the kth time step;
s23, judging whether the node is abnormal or not, wherein the calculation formula is as follows:
wherein, the For the abnormality detection threshold value,Is a nodeNode risk coefficient of (2) takes on the value of,,,,;
When (when)And judging that the ith node is abnormal, and triggering abnormal early warning.
8. The method for real-time regulation and control of transformer through-current test parameters according to claim 7, wherein step S3 specifically comprises:
S31, when Judging that the ith node is abnormal, and activating abnormal retrieval;
s32, determining potential influence node set ;
S33, computing nodeSearch priority of (f):
;
Wherein, the Is the ith node in undirected graph GTo the jth nodeIs the shortest path hop count of (a); is the maximum element value of the adjacency matrix A; representing the jth node Is a search priority of (1);
s34, arranging other nodes in descending order according to the size of the retrieval priority, and detecting whether the other nodes are abnormal or not by adopting an abnormality detection model in sequence.
9. The method for real-time regulation and control of transformer through-current test parameters according to claim 8, wherein step S4 specifically comprises:
s41, when other node anomalies do not exist, adopting single-node anomaly regulation and control, wherein a regulation and control formula is as follows:
wherein, the In order to regulate the current after the regulation,Is the current;
S42, when other nodes are abnormal, adopting multi-node association abnormal regulation and control, wherein a regulation and control formula is as follows:
wherein, the In order to regulate the current after the regulation,As a current flow is present,Representing a current abnormal node set;
s43, when all nodes meet And the recovery test current is 0.98 times of rated current of the transformer.
10. A real-time regulation and control system for a transformer through-flow test parameter, for executing the real-time regulation and control method for a transformer through-flow test parameter according to any one of claims 1 to 9, characterized in that the real-time regulation and control system for a transformer through-flow test parameter comprises:
The model construction module is used for collecting state data of a transformer through-flow test and constructing the state data into a state model by a data structure of an undirected graph;
an anomaly retrieval module for detecting an anomaly node in the state model using the anomaly detection model;
The secondary retrieval module is used for activating abnormal retrieval when abnormal nodes are detected, retrieving other potential abnormal nodes, arranging the other potential abnormal nodes in descending order according to the retrieval priority, and sequentially detecting whether the other nodes are abnormal or not by adopting an abnormal detection model;
the parameter adjustment module is used for dynamically adjusting the through-flow test parameters of the transformer according to the abnormality detection result, wherein when other node abnormalities do not exist, single-node abnormal regulation is adopted, and when other node abnormalities exist, multi-node associated abnormal regulation is adopted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510873221.8A CN120428019B (en) | 2025-06-27 | 2025-06-27 | Real-time regulation and control method and system for through-current test parameters of transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510873221.8A CN120428019B (en) | 2025-06-27 | 2025-06-27 | Real-time regulation and control method and system for through-current test parameters of transformer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120428019A true CN120428019A (en) | 2025-08-05 |
| CN120428019B CN120428019B (en) | 2025-09-26 |
Family
ID=96556275
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510873221.8A Active CN120428019B (en) | 2025-06-27 | 2025-06-27 | Real-time regulation and control method and system for through-current test parameters of transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120428019B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020042024A1 (en) * | 2018-08-29 | 2020-03-05 | 区链通网络有限公司 | Node abnormality detection method and device based on graph algorithm and storage device |
| US20200089874A1 (en) * | 2018-09-17 | 2020-03-19 | General Electric Company | Local and global decision fusion for cyber-physical system abnormality detection |
| US20200167787A1 (en) * | 2018-11-26 | 2020-05-28 | Bank Of America Corporation | System for anomaly detection and remediation based on dynamic directed graph network flow analysis |
| US20210271711A1 (en) * | 2020-02-27 | 2021-09-02 | Oracle International Corporation | Vectorized queues for shortest-path graph searches |
| US20220327204A1 (en) * | 2021-04-12 | 2022-10-13 | General Electric Company | Unified multi-agent system for abnormality detection and isolation |
| CN117539223A (en) * | 2023-11-30 | 2024-02-09 | 西安好博士医疗科技有限公司 | Intelligent electric heating control system and method for incubator |
| CN117554723A (en) * | 2023-11-13 | 2024-02-13 | 江苏省送变电有限公司 | Preventive rising current test method and test device for high voltage transformer |
| CN118157326A (en) * | 2024-05-09 | 2024-06-07 | 国能大渡河检修安装有限公司 | Power station transformer operating state adjustment method, device, medium and electronic equipment |
| CN221174850U (en) * | 2023-12-01 | 2024-06-18 | 辽宁省送变电工程有限公司 | Primary through-flow pressurization test device for transformer and sleeve current transformer |
| CN118367682A (en) * | 2024-06-19 | 2024-07-19 | 赛润电气(杭州)有限公司 | A method and system for intelligent state identification and control of electrical equipment |
| CN118982164A (en) * | 2024-07-05 | 2024-11-19 | 北方联合电力有限责任公司包头第二热电厂 | A mixed water intelligent heating control system |
| CN119644972A (en) * | 2025-02-18 | 2025-03-18 | 浙江小趣信息技术有限公司 | Industrial equipment real-time monitoring system based on edge calculation |
| CN119939456A (en) * | 2024-12-31 | 2025-05-06 | 广东电网有限责任公司东莞供电局 | A method for identifying abnormalities in multi-modal data of main transformer operation |
-
2025
- 2025-06-27 CN CN202510873221.8A patent/CN120428019B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020042024A1 (en) * | 2018-08-29 | 2020-03-05 | 区链通网络有限公司 | Node abnormality detection method and device based on graph algorithm and storage device |
| US20200089874A1 (en) * | 2018-09-17 | 2020-03-19 | General Electric Company | Local and global decision fusion for cyber-physical system abnormality detection |
| US20200167787A1 (en) * | 2018-11-26 | 2020-05-28 | Bank Of America Corporation | System for anomaly detection and remediation based on dynamic directed graph network flow analysis |
| US20210271711A1 (en) * | 2020-02-27 | 2021-09-02 | Oracle International Corporation | Vectorized queues for shortest-path graph searches |
| US20220327204A1 (en) * | 2021-04-12 | 2022-10-13 | General Electric Company | Unified multi-agent system for abnormality detection and isolation |
| CN117554723A (en) * | 2023-11-13 | 2024-02-13 | 江苏省送变电有限公司 | Preventive rising current test method and test device for high voltage transformer |
| CN117539223A (en) * | 2023-11-30 | 2024-02-09 | 西安好博士医疗科技有限公司 | Intelligent electric heating control system and method for incubator |
| CN221174850U (en) * | 2023-12-01 | 2024-06-18 | 辽宁省送变电工程有限公司 | Primary through-flow pressurization test device for transformer and sleeve current transformer |
| CN118157326A (en) * | 2024-05-09 | 2024-06-07 | 国能大渡河检修安装有限公司 | Power station transformer operating state adjustment method, device, medium and electronic equipment |
| CN118367682A (en) * | 2024-06-19 | 2024-07-19 | 赛润电气(杭州)有限公司 | A method and system for intelligent state identification and control of electrical equipment |
| CN118982164A (en) * | 2024-07-05 | 2024-11-19 | 北方联合电力有限责任公司包头第二热电厂 | A mixed water intelligent heating control system |
| CN119939456A (en) * | 2024-12-31 | 2025-05-06 | 广东电网有限责任公司东莞供电局 | A method for identifying abnormalities in multi-modal data of main transformer operation |
| CN119644972A (en) * | 2025-02-18 | 2025-03-18 | 浙江小趣信息技术有限公司 | Industrial equipment real-time monitoring system based on edge calculation |
Non-Patent Citations (1)
| Title |
|---|
| 许毅;陆斌;乐俊;: "变压器温升和异常状态试验的自动测量与控制系统", 计算机测量与控制, no. 08, 25 August 2015 (2015-08-25), pages 2654 - 2567 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120428019B (en) | 2025-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884199B (en) | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium | |
| CN118706192B (en) | A fire protection monitoring method and system for circuit protection of electrical cabinet | |
| CN120414885A (en) | A quality monitoring and optimization method and system for ensuring power supply | |
| CN115632486B (en) | A method and system for electricity safety management based on Internet of Things | |
| CN119181192A (en) | A fire monitoring method, device and system for an electrical cabinet | |
| CN113570473A (en) | Equipment fault monitoring method and device, computer equipment and storage medium | |
| CN118686751A (en) | A wind turbine cabin fire early warning optimization control method and system | |
| CN117706258A (en) | Fault detection system based on big data processing | |
| CN119938437A (en) | A multifunctional intelligent sensing immersion liquid cooling monitoring method and system | |
| CN120428019B (en) | Real-time regulation and control method and system for through-current test parameters of transformer | |
| CN119397878B (en) | Temperature warning method and device for bus duct, terminal and storage medium | |
| CN119782301B (en) | Data quality monitoring storage system based on equipment electrical state evaluation | |
| CN120951186A (en) | A method and system for early warning of faults in a synchronous condenser excitation system | |
| CN119765854B (en) | Intelligent power supply adjustment method, system and storage medium based on voltage | |
| KR100340967B1 (en) | Method and apparatus for detecting fault using General Regression Neural Network | |
| CN120711689A (en) | Heat dissipation strategy determination method, device, electronic device and non-volatile storage medium | |
| CN120124448A (en) | A relay protection simulation system | |
| CN118970825A (en) | A main transformer overload protection method and system based on power factor | |
| CN118551172A (en) | Thyristor-level health state assessment method based on multi-parameter analysis and storage medium | |
| CN118523448A (en) | A method for suppressing the spread of thermal runaway in a battery energy storage system | |
| CN118249479A (en) | A super-capacity energy storage method and system with intelligent temperature management | |
| CN117639282A (en) | A frequency domain response processing method and system for the end screen voltage divider of the converter valve side casing | |
| CN119181885B (en) | Energy storage cabinet operation monitoring system and method | |
| CN119961873B (en) | A fault diagnosis method, device, medium and equipment based on charging data | |
| CN120703625A (en) | Variable load demagnetization power supply testing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |