CN-121689542-B - On-line monitoring method, system, equipment and storage medium for operation state of secondary equipment of transformer substation

CN121689542BCN 121689542 BCN121689542 BCN 121689542BCN-121689542-B

Abstract

The invention discloses a method, a system, equipment and a storage medium for monitoring the operation state of secondary equipment of a transformer substation on line, which belong to the technical field of power system monitoring, and are characterized in that the state type of the secondary equipment is obtained, a secondary loop model is constructed, theoretical values of all monitoring points are calculated through the model, residual vectors are obtained by comparing the theoretical values with actual values, the operation state is judged based on the residual vectors, a target fault set is screened through similarity analysis of fault feature vectors corresponding to the virtual faults and the residual vectors, the relevance index of all the virtual faults is determined based on the relevance between the disturbance vectors and the residual vectors in the target fault set, and a suspected fault set is selected according to the relevance index, the fault strength of all the virtual faults is calculated through constructing a fault positioning model in the suspected fault set, and the virtual faults with the fault strength larger than a strength set value are used as detection results to early warn the operation state of the secondary equipment.

Inventors

SHI HENGCHU
CHEN JING
YOU HAO
XU SHOUDONG
CHEN XIAOFAN
HU XIAO
DING XIAOLI
YANG QIAOWEI
LI YINYIN
YANG YUANHANG

Assignees

云南电网有限责任公司

Dates

Publication Date: 20260505
Application Date: 20260210

Claims (7)

1. The on-line monitoring method for the operation state of the secondary equipment of the transformer substation is characterized by comprising the following steps of, Acquiring state types of secondary equipment, constructing a secondary loop model, calculating theoretical values of all monitoring points through the secondary loop model, comparing the theoretical values with actual measurement values to obtain residual vectors, and judging an operation state based on the residual vectors; Screening a target fault set through similarity analysis of fault feature vectors and residual vectors corresponding to virtual faults, determining correlation indexes of the virtual faults based on correlation between disturbance vectors and residual vectors in the target fault set, and selecting a suspected fault set according to the correlation indexes; Screening a target fault set through similarity analysis of fault feature vectors and residual vectors corresponding to virtual faults, wherein the screening comprises the steps of pre-constructing a virtual fault library, wherein the virtual fault library comprises fault types of secondary equipment; By applying disturbance to the virtual faults, fault feature vectors corresponding to the virtual faults are obtained, including, Operating the secondary loop model in a reference state to obtain a reference value of each monitoring point; applying preset disturbance to secondary equipment corresponding to the virtual fault, keeping the state types of other secondary equipment unchanged, and running the secondary loop model again to obtain disturbance values of all monitoring points; constructing a fault characteristic vector of the virtual fault based on the difference value between the disturbance value and the reference value; based on similarity calculation of the fault feature vector and the residual vector, determining a similarity index of each virtual fault; Screening a target fault set according to the similarity index; the selecting the suspected fault set according to the correlation index comprises the steps of normalizing the correlation index of each virtual fault and arranging the correlation indexes according to the sequence from large to small; Calculating the sum of the first K correlation indexes, and increasing K by 1 in response to the fact that the sum of the correlation indexes is smaller than an index set value until the sum of the correlation indexes is not smaller than the index set value, wherein virtual faults corresponding to the first K correlation indexes are used as suspected fault sets; and in the suspected fault set, calculating the fault intensity of each virtual fault by constructing a fault positioning model, and taking the virtual fault with the fault intensity larger than the intensity set value as a detection result to early warn the running state of the secondary equipment.
2. The method for on-line monitoring of the operation state of secondary equipment of a transformer substation according to claim 1 is characterized by comprising the steps of obtaining the state type of each secondary equipment and constructing a secondary circuit model, wherein the step of obtaining the state type of each secondary equipment through image input, and the step of constructing a numerical model reflecting the actual operation state of the secondary circuit based on the connection relation and the electrical characteristics of the secondary equipment.
3. The method for on-line monitoring of operation states of secondary equipment of a transformer substation according to claim 2, wherein the state type comprises at least one of a pressing plate state, a switching handle state, an air switch state, a connection state of a current terminal, a connection state of a voltage terminal, a connection state of cables in a cabinet, a connection state of cables between cabinets and a connection state of optical fibers.
4. The method for on-line monitoring of operation state of secondary equipment of transformer substation according to claim 3, wherein said virtual fault with fault intensity greater than intensity set value is used as detection result, and comprises comparing fault intensity with intensity set value; And obtaining a virtual fault with the fault strength exceeding the strength set value, and outputting the corresponding secondary equipment and the fault type as detection results.
5. An online monitoring system for the operation state of secondary equipment of a transformer substation, which is applied to the online monitoring method for the operation state of the secondary equipment of the transformer substation according to any one of claims 1-4, is characterized by comprising an acquisition module, a calculation module and a calculation module, wherein the acquisition module is used for acquiring the state types of the secondary equipment and constructing a secondary loop model; the calculation module is used for calculating theoretical values of all monitoring points through the secondary loop model, comparing the theoretical values with actual measurement values to obtain residual vectors, and judging the running state based on the residual vectors; The screening module is used for screening the target fault set through similarity analysis of fault feature vectors and residual vectors corresponding to the virtual faults, determining correlation indexes of the virtual faults based on the correlation between the disturbance vectors and the residual vectors, and selecting the suspected fault set according to the correlation indexes; and the output module is used for obtaining a fault detection result based on the fault intensity and carrying out early warning on the running state of the secondary equipment.
6. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of a substation secondary device operation state online monitoring method according to any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of a method for on-line monitoring of the operating status of a secondary device of a substation according to any one of claims 1 to 4.

Description

On-line monitoring method, system, equipment and storage medium for operation state of secondary equipment of transformer substation Technical Field The invention relates to the technical field of power system monitoring, in particular to a method, a system, equipment and a storage medium for online monitoring of the operation state of secondary equipment of a transformer substation. Background The transformer substation is a pivot node for the operation of the power system, the higher the voltage level of the transformer substation is, the larger the function of the transformer substation is, the higher the safety and reliability are required, and the secondary equipment of the intelligent transformer substation is the basis for the safe and stable operation of the power grid and the primary equipment of the transformer substation. At present, the patent application document with the publication number of CN119557740A discloses a transformer substation secondary equipment fault positioning method based on a space-time diagram convolution network model, wherein the method comprises the steps of obtaining historical data of secondary equipment, constructing a fault feature set comprising running state information, SV/GOOSE receiving state information and sampling values, sequencing the fault feature data according to a time sequence, corresponding to corresponding secondary equipment faults one by one, extracting and screening fault features with high correlation, constructing a screened fault feature set, carrying out multi-mode feature fusion processing on data of the fault feature set based on the time sequence to obtain fault feature fusion data, constructing a STGCN model comprising a three-layer 1D-CNN network and a one-layer GCN network for simultaneously learning space and time features of the feature map data, dividing the fault feature fusion data into a training set and a test set, using the training set for model learning, using the test set for evaluating performance and accuracy of the model, obtaining a trained STGCN model, setting a dynamic threshold value of the number of the fault feature information of self-adaptive conditions to detect the faults of the secondary equipment, when the faults of the secondary equipment are detected, carrying out multi-mode feature fusion processing on the data based on the time sequence, and carrying out fault position and positioning and reasoning on the fault position of the fault feature data, and if the fault position of the fault position is well-positioned by the fault positioning model is judged to be the fault position-fault positioning rules and the fault positioning method is well-inferred. According to the method, fault characteristics are screened, fusion data are constructed according to the screened fault characteristic sets, fault detection of the secondary equipment is achieved according to the fusion data and a complex STGCN model, however, the number of the secondary equipment in the secondary circuit is large, when the secondary circuit breaks down, the secondary equipment with the fault is a small number, the fusion data of all the secondary equipment are collected to achieve fault detection of the secondary equipment, the calculated amount of fault detection can be greatly increased, and the monitoring efficiency of the operation state of the secondary equipment is low. Disclosure of Invention In view of the problems, the invention provides a method, a system, equipment and a storage medium for online monitoring of the operation state of secondary equipment of a transformer substation. Therefore, the invention solves the technical problems that how to solve the problems that the number of secondary devices in a secondary circuit is large, when the secondary circuit fails, the failed secondary devices are a few parts, the fusion data of all the secondary devices are collected to realize the failure detection of the secondary devices, the calculated amount of the failure detection is obviously greatly increased, and the monitoring efficiency of the operation state of the secondary devices is lower. In order to solve the technical problems, the invention provides the technical scheme that the on-line monitoring method for the operation state of the secondary equipment of the transformer substation comprises the following steps of, Acquiring state types of secondary equipment, constructing a secondary loop model, calculating theoretical values of all monitoring points through the secondary loop model, comparing the theoretical values with actual measurement values to obtain residual vectors, and judging an operation state based on the residual vectors; screening a target fault set through similarity analysis of fault feature vectors and residual vectors corresponding to virtual faults; in the target fault set, determining a correlation index of each virtual fault based on the correlation between the disturbance vector and the residual vector