Transformer equipment risk early warning method and device, electronic equipment and storage medium

Abstract

The invention provides a transformer equipment risk early warning method and device, electronic equipment and a storage medium, and belongs to the technical field of power risk early warning, and the method comprises the steps: carrying out the clustering of the data of each station end of a transformer based on a K-means algorithm, and obtaining first transmission data; associating a cooperative section for early warning of the transformer equipment with an index system based on the first transmission data, and generating a cooperative early warning judgment standard; determining a risk level corresponding to the first transmission data based on a collaborative early warning judgment standard; and carrying out early warning on the transformer equipment based on the risk level of the first transmission data. According to the transformer equipment risk early warning method and device, the electronic equipment and the storage medium provided by the invention, the power grid operation maintenance efficiency can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of power risk warning, and more specifically, relates to a transformer equipment risk warning method and device, electronic equipment, and storage medium. Background Art

[0002] On the one hand, during the operation of the power grid system, the reliability and scientificity of traditional troubleshooting methods are constantly declining; on the other hand, maintenance and inspection data from different sources are independent of each other, forming data islands, which makes it difficult to meet the rapidly growing market demand at this stage and reduces the efficiency of power grid operation and maintenance. Summary of the invention

[0003] The purpose of the present disclosure is to provide a transformer equipment risk early warning method and device, electronic equipment, and storage medium to improve the efficiency of power grid operation and maintenance.

[0004] A first aspect of an embodiment of the present disclosure provides a transformer equipment risk early warning method, comprising: Clustering the data at each station end of the transformer based on the K-means algorithm to obtain first transmission data; Associating the coordinated section and indicator system of transformer equipment early warning based on the first transmission data to generate a coordinated early warning judgment standard; Determining a risk level corresponding to the first transmission data based on the collaborative early warning judgment standard; An early warning is issued to the transformer equipment based on the risk level of the first transmission data.

[0005] A second aspect of the embodiments of the present disclosure provides a transformer equipment risk warning device, comprising: A clustering module, used for clustering the data of each station end of the transformer based on a K-means algorithm to obtain first transmission data; A collaborative early warning judgment module, used to associate the collaborative section and indicator system of transformer equipment early warning based on the first transmission data, and generate a collaborative early warning judgment standard; A risk level judgment module, used to determine the risk level corresponding to the first transmission data based on the collaborative early warning judgment standard; The early warning module is used to issue an early warning to the transformer equipment based on the risk level of the first transmission data.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned transformer equipment risk warning method when executing the computer program.

[0007] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned transformer equipment risk warning method are implemented.

[0008] The transformer equipment risk warning method and device, electronic device, and storage medium provided by the embodiments of the present disclosure have the beneficial effects that: the embodiments of the present disclosure obtain the first transmission data by clustering the data of each station end through the K-means algorithm, which can effectively integrate scattered data resources, explore the potential associations and laws between data, and make subsequent analysis more targeted. The collaborative warning judgment standard generated based on these data-related collaborative sections and indicator systems fully considers the comprehensive impact of different regions and multiple operating indicators, greatly improves the accuracy and comprehensiveness of the warning, and avoids the limitations of single indicators or local area judgments. Determining the risk level further quantifies the operating risk of the equipment, and provides an intuitive and clear decision-making basis for operation and maintenance personnel, so that they can quickly take corresponding measures according to the risk level. Finally, warnings based on risk levels can timely remind operation and maintenance personnel to pay attention to equipment conditions, effectively reduce the probability of transformer failures, ensure the stable operation of the power system, reduce power outage losses caused by equipment failures, and improve the safety and reliability of power grid operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of a process flow of a transformer equipment risk warning method provided by an embodiment of the present disclosure; Figure 2 A schematic diagram of a process flow of a collaborative warning retrieval model provided in one embodiment of the present disclosure; Figure 3 A structural block diagram of a transformer equipment risk warning device provided by an embodiment of the present disclosure; Figure 4 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0012] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A schematic diagram of a transformer equipment risk warning method provided by an embodiment of the present disclosure, the method comprising: S101: clustering the data at each transformer station based on a K-means algorithm to obtain first transmission data.

[0014] The K-means algorithm is a clustering algorithm that aims to divide a given data set into K clusters so that the sum of the distances from each data point to the center of the cluster to which it belongs is minimized. In this embodiment, data such as transformer records, monitoring, operation and maintenance are collected from each station, which is the basis for subsequent analysis. The data from each station of the transformer can be regarded as a data set.

[0015] In this embodiment, the distance between each data point in the data set can be calculated, K data points are randomly selected as initial cluster centers, and each data point is assigned to the cluster where the cluster center closest to it is located. After all data points are assigned, the center of each cluster is recalculated.

[0016] Repeat the above process of allocating and updating cluster centers until the cluster centers no longer change significantly or reach a preset number of iterations. Through this process, data points with similar characteristics can be clustered together to form different clusters, and the data contained in these clusters is the first transmission data.

[0017] After clustering is completed, the obtained data is standardized into a unified format to form the first transmission data. These data can be seamlessly connected and shared between the station end and the centralized control station.

[0018] S102: Associating the coordinated section and indicator system of transformer equipment early warning based on the first transmission data to generate a coordinated early warning judgment standard.

[0019] In this embodiment, the coordination section refers to different areas or groups in which transformer equipment in a power grid area is divided according to certain rules or standards. The division of the coordination section can be based on factors such as the geographical distribution of the power grid, the importance level of the substation, and the topological structure of power transmission. For example, substations in the same power supply area or with similar power load characteristics are divided into a coordination section.

[0020] By dividing the coordinated sections, the coordinated management and control of transformer equipment in different areas can be achieved. When an abnormality occurs in a transformer in a coordinated section, the scope of its impact on surrounding equipment and the entire power grid can be quickly determined, so that corresponding emergency measures and maintenance strategies can be taken. At the same time, it is also convenient to concentrate resources to monitor and maintain equipment in key areas, improving the reliability and safety of power grid operation.

[0021] In this embodiment, the index system refers to a set of parameters and indicators used to measure the operating status of transformer equipment. The index system covers multiple parameters that can reflect the operating status of the transformer, such as electrical parameters (winding resistance, insulation resistance, core grounding current, etc.), oil chromatography parameters (gas content such as hydrogen, acetylene, and total hydrocarbons), and operating environment parameters (temperature, humidity, etc.).

[0022] The indicators are interrelated and complementary, forming a comprehensive transformer equipment operation status evaluation system. Through real-time monitoring and analysis of these indicators, abnormal conditions of transformer equipment can be discovered in time, and possible faults can be predicted based on the changing trends of the indicators.

[0023] In this embodiment, for each coordinated section, the relevant indicators in the first transmission data are matched and associated with the predefined indicator systems.

[0024] Based on historical data, industry standards, and empirical knowledge, corresponding thresholds and weights can be set for each indicator in different collaborative sections. For example, in a high-load collaborative section, the warning threshold of the winding temperature may be relatively low because the equipment is more likely to heat up under high load. By comprehensively considering the actual value, threshold, and weight of each indicator, a collaborative warning judgment standard is generated. When one or more indicators exceed their corresponding thresholds and the comprehensive weight reaches a certain level, the warning condition is triggered.

[0025] S103: Determine the risk level corresponding to the first transmission data based on the collaborative warning judgment standard.

[0026] In this embodiment, a certain risk assessment model may be used, such as a weighted average method, a fuzzy comprehensive evaluation method, etc. According to the actual conditions and corresponding weights of each indicator in the collaborative early warning judgment standard, the first transmission data is quantitatively evaluated.

[0027] Risk levels can be divided into different levels, such as low risk, medium risk, high risk, etc. For example, if most indicators are within the normal range and key indicators perform well, it can be judged as low risk; if multiple important indicators are close to or exceed the warning threshold, it can be judged as medium risk or high risk. Each risk level corresponds to different follow-up processing strategies and maintenance suggestions, providing decision-making basis for operation and maintenance personnel.

[0028] S104: issuing an early warning to the transformer equipment based on the risk level of the first transmission data.

[0029] In this embodiment, the corresponding early warning mechanism is triggered according to the determined risk level. The early warning information should include detailed risk levels, relevant abnormal indicator data, possible fault cause analysis and recommended measures. In this way, after receiving the early warning, the operation and maintenance personnel can quickly understand the problem of the equipment and take effective countermeasures, such as arranging equipment inspections, conducting further tests or timely maintenance, so as to ensure the safe and stable operation of the transformer equipment and reduce the losses caused by equipment failures.

[0030] It can be concluded from the above that this embodiment uses the K-means algorithm to cluster the data of each station to obtain the first transmission data, which can effectively integrate scattered data resources, explore the potential associations and rules between data, and make subsequent analysis more targeted. The collaborative early warning judgment standard generated based on these data-related collaborative sections and indicator systems fully considers the comprehensive impact of different regions and multiple operating indicators, greatly improves the accuracy and comprehensiveness of the early warning, and avoids the limitations of single indicators or local area judgments. Determining the risk level further quantifies the operating risk of the equipment, provides an intuitive and clear decision-making basis for operation and maintenance personnel, and enables them to quickly take corresponding measures according to the risk level. Finally, early warning based on the risk level can timely remind operation and maintenance personnel to pay attention to the equipment status, effectively reduce the probability of transformer failure, ensure the stable operation of the power system, reduce power outage losses caused by equipment failure, and improve the safety and reliability of power grid operation.

[0031] In one embodiment of the present disclosure, clustering the data of each transformer station end based on the K-means algorithm to obtain the first transmission data includes: Determine the initial cluster center corresponding to the data of each transformer station based on the K-means algorithm; Determine the K value based on the initial cluster center; Clustering is performed based on the initial cluster center and the K value to obtain first transmission data.

[0032] In this embodiment, the distance between data points in the data set can be calculated by the farthest distance method, and any data point can be selected from the data points as the initial clustering center to provide a reasonable starting point for data classification and avoid the clustering result falling into the local optimum.

[0033] Exemplarily, the farthest distance algorithm first calculates the distance between the N data objects participating in the clustering, thereby obtaining a distance matrix. The scan matrix selects the two points with the farthest distance among all objects as the first two initial cluster centers. The point with the largest sum of distances from the two selected center points among the remaining N-2 data objects is selected as the third initial cluster center. The subsequent center points are selected in this way in turn until the number of selected center points reaches the specified K value.

[0034] In this embodiment, the cosine angle can be used to calculate the similarity (distance) between vectors. The cosine angle distance calculation method is:

[0035] Where x and y represent vectors with n dimensions, Represents the values ​​of each dimension of vector x, Represents the numerical values ​​of each dimension of vector y.

[0036] In this embodiment, the K value can be determined based on a function similar to the error rate for calculating the overall performance, and the optimal solution can be found by continuously changing the K value and comparing the objective function value. Based on the total variance of the cluster mean, its change with the increase of the K value is observed, and the K value corresponding to the inflection point where the variance no longer decreases is selected to ensure the rationality and effectiveness of clustering.

[0037] The clustering operation is performed based on the determined initial cluster center and K value. Each data point is assigned to the cluster with the nearest cluster center, and the cluster center is continuously updated. After multiple iterations, the clustering result is stable, thus obtaining the first transmission data that has been sorted and classified, providing basic and representative data support for subsequent early warning analysis.

[0038] It can be concluded from the above that this embodiment can make a good start in data classification and avoid blindness by reasonably determining the initial cluster center. Based on the K value determined in this way, it is ensured that the clustering result conforms to the intrinsic structure of the data. The first transmission data finally obtained is effectively integrated and classified, and data redundancy and noise are removed, key information is highlighted, and a high-quality data foundation is provided for subsequent operations such as associating collaborative sections and indicator systems, determining risk levels, etc., thereby improving the reliability and accuracy of the entire early warning process.

[0039] In one embodiment of the present disclosure, determining the K value based on the initial cluster center includes: The value of K is determined based on the total variance of the cluster means, which is the average of the data points in each cluster.

[0040] In this embodiment, clustering results under different K values ​​are calculated based on the initial cluster centers.

[0041] For each K value, a K-means clustering operation is performed. During the clustering process, each data point in the cluster has a cluster mean. , the cluster mean is the average value of the data points in that cluster.

[0042] Then, the total variance of the cluster means is calculated according to the total variance formula of the cluster means. The total variance formula of the cluster means is:

[0043] in, represents the total variance of the cluster means, represents the vector of the i-th object, , is the mean of the cluster to which the ith data point belongs, and N is the total number of data points.

[0044] For each object vector and the means of their clusters , calculate the mean square error E(k) of N data. Then change K, calculate two clusters first, then calculate three, and return to the K-means algorithm, with the clusters increasing in sequence until the K value is too large and the K-means algorithm is stopped. Compare the objective function values ​​by changing the K value. The principle based on which the K value is selected is that as K is increased, the variance will not decrease accordingly.

[0045] For clustering of N data objects, the number of clusters must be less than N, and the number of clusters ≤ Therefore, a K value screening method was developed in combination with the effect evaluation. The clusters were clustered according to the possible continuous K values, the total variance of the cluster means was calculated, and the K value corresponding to the inflection point value at which the total variance of the cluster means no longer decreased with the increase of K value was selected as the optimal number of clusters.

[0046] It can be concluded from the above that this embodiment can find the optimal K value by calculating the total variance of the cluster mean under different K values, thus avoiding the blindness of K value selection. Secondly, starting from a small number of clusters, gradually increasing the K value and calculating the variance ensures that the optimal number of clusters is found without over-segmenting the data, thereby improving clustering efficiency. Finally, the K value corresponding to the inflection point where the variance no longer decreases with the increase of the K value is the optimal number of clusters, which can make the data reasonably distributed in each cluster, provide an accurate basis for subsequent data processing and analysis, and ensure the reliability of data in applications such as transformer equipment risk warning.

[0047] In one embodiment of the present disclosure, the coordinated section and the indicator system of the transformer equipment early warning are associated based on the first transmission data to generate a coordinated early warning judgment standard, including: Determine the coordinated section of substation equipment early warning based on matrix algorithm; Constructing an indicator system for early warning of substation equipment based on the first transmission data; The coordinated section of substation equipment early warning and the indicator system of substation equipment early warning are associated to generate a coordinated early warning judgment standard.

[0048] In this embodiment, an improved matrix algorithm is used to determine the coordinated section of the substation equipment early warning. In this embodiment, the power grid area is divided according to the importance coefficient Q, which is composed of the substation status Q1 and the user level Q2, and the calculation formula is:

[0049] Where i = 1-2, 1 is the substation location, 2 is the user level; represents the weight of important coefficients; Represents the important coefficient.

[0050] By weighted calculation of Q1 and Q2 of different substations, the importance coefficient Q is obtained. According to the value of Q, the power grid is divided into multiple areas (first area, second area, etc.), and each area has an independent early warning target. Table 1 shows the reference setting of the importance coefficient and weight.

[0051] Table 1 Reference settings for important coefficients and weights

[0052] In this embodiment, an indicator system is constructed based on the first transmission data. The first transmission data is data after K-means algorithm clustering processing, and these data contain various operating information of the transformer equipment, such as electrical parameters, operating environment parameters, etc. A comprehensive indicator system can be constructed using these data to evaluate the operating status of the transformer equipment. Table 2 is an early warning indicator system.

[0053] Table 2 Early warning indicator system

[0054] Specifically, the oil chromatography early warning judgment standard is shown in Table 3, the electrical test early warning judgment standard is shown in Table 4, the insulating oil test early warning judgment standard is shown in Table 5, and the operating parameter early warning judgment standard is shown in Table 6.

[0055] Table 3 Oil chromatography early warning judgment criteria

[0056] Table 4 Electrical test warning judgment standard

[0057] Table 5 Insulating oil test warning judgment standard

[0058] Table 6 Operation parameter warning judgment criteria

[0059] In this embodiment, the determined coordinated section of the substation equipment early warning is associated with the constructed indicator system. For example, in a specific coordinated section, according to the characteristics and importance of the area, combined with the corresponding indicator system, a coordinated early warning judgment standard suitable for the area is formulated. This means that in different power grid areas, due to their different importance and equipment characteristics, the judgment standard of early warning will also be different, thereby achieving more accurate equipment early warning.

[0060] For example, assuming that the warning function in the Nth region is a, if the warning index is met, the element in the information matrix is ​​represented by 1; if the warning index is not met, the element in the information matrix is ​​recorded as -1. The grid areas to be coordinated in different regions can be represented as:

[0061] Different data information forms a diagonal, which is recorded as the information diagonal W, and the output area to be coordinated is recorded as u, then the position function of the area to be coordinated can be:

[0062] In the formula For the area to be coordinated, is the early warning information of the area to be coordinated. The formula for the area to be coordinated is:

[0063] The matrix information reflects the coordinated warning section, allowing users to select the coordinated warning section according to the control warning dimension, such as according to different parameters such as oil chromatography, electrical test, insulating oil test, and operation status. These data parameters are assumed to be denoted as o, and the coordinated warning section where the data parameters are located is , then the following mathematical relationship exists:

[0064] The area to be warned is associated with the warning dimension and the importance coefficient in the above manner.

[0065] It can be concluded from the above that this embodiment determines the coordinated section based on the matrix algorithm and can reasonably divide the power grid area. Secondly, the indicator system is constructed using the first transmission data to comprehensively evaluate the equipment status. Finally, the coordinated section is associated with the indicator system to generate a judgment standard, so that the early warning standard is targeted and can more accurately provide risk early warning for transformer equipment in different areas.

[0066] In one embodiment of the present disclosure, providing an early warning for a transformer device based on a risk level of the first transmission data includes: Assign corresponding weights to different risk levels; Performing a weighted summation on the weights corresponding to the risk levels of the first transmission data to obtain a comprehensive risk level; Provide early warning for transformer equipment based on comprehensive risk level.

[0067] In this embodiment, a risk level mechanism is set, and a warning value is set for the danger identification mechanism.

[0068] First, set the risk data.

[0069] In this embodiment, the risk levels can be divided into four levels. For the convenience of calculation, the corresponding values ​​are set as follows: normal: 4, caution: 3, abnormal: 2, and severe: 1.

[0070] Then set the weights.

[0071] In this embodiment, the risk level weights can be calculated by Matlab software, as shown in Table 7: Table 7 Risk level weights

[0072] Then the weighted average calculation is performed, the formula is as follows: Comprehensive risk level = (level 1 value * level 1 weight) + (level 2 value * level 2 weight) + ... + (level n value * level n weight) Finally, risk level classification is carried out.

[0073] According to the threshold range of the comprehensive risk level value A, the comprehensive risk level of the equipment is obtained, such as the comprehensive risk level shown in Table 8. The judgment basis is shown in the table: Table 8 Comprehensive risk level

[0074] It can be concluded from the above that this embodiment makes risk assessment more scientific and quantitative by assigning weights to different risk levels and obtaining a comprehensive risk level by weighted summation. Secondly, the risk level is subdivided into four levels, and corresponding clear values ​​and weights are obtained. With the assistance of Matlab software, the calculation process is accurate and efficient. Finally, different threshold intervals and corresponding diagnostic suggestions are divided according to the comprehensive risk level, which enables operation and maintenance personnel to intuitively understand the equipment status, take reasonable countermeasures in time, and effectively ensure the stable operation of transformer equipment.

[0075] In one embodiment of the present disclosure, it also includes: The risk level corresponding to the first transmission data is optimized to obtain a target risk level corresponding to the first transmission data.

[0076] In one embodiment of the present disclosure, optimizing the risk level corresponding to the first transmission data to obtain the target risk level corresponding to the first transmission data includes: Construct collaborative warning retrieval model; The risk level corresponding to the first transmission data is optimized based on the collaborative early warning retrieval model to obtain a target risk level corresponding to the first transmission data.

[0077] In this embodiment, a collaborative early warning retrieval model is first constructed, which can integrate more relevant information and factors to more accurately evaluate and optimize the risk level.

[0078] During the construction process, factors such as the operating characteristics of power grids in different regions, historical fault data of transformer equipment, and current trends in operating environment parameter changes can be considered, and these factors can be integrated into the model in appropriate mathematical forms and logical relationships.

[0079] When optimizing the risk level corresponding to the first transmission data based on the constructed collaborative early warning retrieval model, the model can re-analyze and calculate the input first transmission data and its corresponding initial risk level according to the rules and algorithms set internally.

[0080] For example, Figure 2 As shown in Figure 1, a collaborative early warning retrieval model is constructed, assuming that the power grid regional nodes are M groups, and the retrieval scale is represented by l. The dynamic retrieval scale can be described as , dynamically adjust the search specifications, realize dynamic calculation of the search scale, and thus achieve global optimization. The dynamic retrieval scale formula is:

[0081] Among them, l0 is the initial scale of the power grid area retrieval scale; s is the number of iterations when searching multiple power grid area nodes; is the maximum number of repetitions during the retrieval period; during the continuous data retrieval process, the energy decay value is calculated by presented in the form of.

[0082] In order to achieve the effectiveness of regional coordinated early warning, it is necessary to find and .in, Indicates the power grid area nodes before the dynamic retrieval scale is li, The grid area node after li has the following relationship when obtaining the best search value:

[0083] If equation (1) is applicable, then ; If equation (1) does not apply, then

[0084] If equation (2) is applicable, then .

[0085] In this way, the calculation is performed repeatedly, so that equation (1) and equation (2) are connected together until the value obtained is the largest.

[0086] Through continuous iterative calculation, the optimal iteration value is obtained. , F is the optimal solution for risk diagnosis after collaborative early warning.

[0087] From the above, it can be concluded that this embodiment can break through the limitation of single data by constructing a collaborative early warning retrieval model and integrating multiple factors such as the characteristics of power grids in different regions, historical fault data, and changing trends of environmental parameters. In the process of model optimization, dynamic adjustment of retrieval scale and iterative calculation can analyze risks more accurately. The final target risk level is more in line with the actual condition of the equipment, which greatly improves the accuracy of risk warning, helps to take effective maintenance measures in time, and ensures the stable operation of the transformer.

[0088] Corresponding to the transformer equipment risk early warning method in the above embodiment, Figure 3 This is a structural block diagram of a transformer equipment risk warning device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 3 The transformer equipment risk warning device 20 includes: a clustering module 21, a collaborative warning judgment module 22, a risk level judgment module 23, and a warning module 24.

[0089] The clustering module 21 is used to cluster the data of each station end of the transformer based on the K-means algorithm to obtain the first transmission data; A collaborative early warning judgment module 22, used to associate the collaborative section and indicator system of the transformer equipment early warning based on the first transmission data, and generate a collaborative early warning judgment standard; A risk level determination module 23, configured to determine a risk level corresponding to the first transmission data based on a collaborative warning determination standard; The early warning module 24 is used to issue an early warning to the transformer equipment based on the risk level of the first transmission data.

[0090] In one embodiment of the present disclosure, the clustering module 21 is specifically used for: Determine the initial cluster center corresponding to the data of each transformer station based on the K-means algorithm; Determine the K value based on the initial cluster center; Clustering is performed based on the initial cluster center and the K value to obtain first transmission data.

[0091] In one embodiment of the present disclosure, the clustering module 21 is further configured to: The value of K is determined based on the total variance of the cluster means, which is the average of the data points in each cluster.

[0092] In one embodiment of the present disclosure, the collaborative early warning judgment module 22 is specifically used to: Determine the coordinated section of substation equipment early warning based on matrix algorithm; Constructing an indicator system for early warning of substation equipment based on the first transmission data; The coordinated section of substation equipment early warning and the indicator system of substation equipment early warning are associated to generate a coordinated early warning judgment standard.

[0093] In one embodiment of the present disclosure, the risk level determination module 23 is specifically used to: Assign corresponding weights to different risk levels; Performing a weighted summation on the weights corresponding to the risk levels of the first transmission data to obtain a comprehensive risk level; Provide early warning for transformer equipment based on comprehensive risk level.

[0094] In one embodiment of the present disclosure, the transformer equipment risk warning device 20 further includes: an optimization module; the optimization module is specifically used to: The risk level corresponding to the first transmission data is optimized to obtain a target risk level corresponding to the first transmission data.

[0095] In one embodiment of the present disclosure, the optimization module is further configured to: Construct collaborative warning retrieval model; The risk level corresponding to the first transmission data is optimized based on the collaborative early warning retrieval model to obtain a target risk level corresponding to the first transmission data.

[0096] See also Figure 4 , Figure 4 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 4The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 3 The functions of modules 21 to 24 are shown.

[0097] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0098] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0099] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0100] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the transformer equipment risk warning method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0101] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0102] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0105] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0107] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0108] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A transformer equipment risk early warning method, characterized in that: include: Clustering the data at each station end of the transformer based on the K-means algorithm to obtain first transmission data; Based on the first transmission data, the coordinated section and indicator system of transformer equipment early warning are associated to generate a coordinated early warning judgment standard; Determining a risk level corresponding to the first transmission data based on the collaborative warning judgment standard; An early warning is issued to the transformer equipment based on the risk level of the first transmitted data.

2. The transformer equipment risk early warning method according to claim 1, characterized in that: The clustering of the data of each transformer station end based on the K-means algorithm to obtain the first transmission data includes: Determine the initial cluster center corresponding to the data of each transformer station based on the K-means algorithm; Determine the K value based on the initial cluster center; Clustering is performed based on the initial cluster center and the K value to obtain first transmission data.

3. The transformer equipment risk early warning method according to claim 2, characterized in that: The step of determining the K value based on the initial cluster center includes: The value of K is determined based on the total variance of the cluster means, which is the average of the data points in each cluster.

4. The transformer equipment risk early warning method according to claim 1, characterized in that: The step of associating the coordinated section and indicator system of transformer equipment early warning based on the first transmission data to generate a coordinated early warning judgment standard includes: Determine the coordinated section of substation equipment early warning based on matrix algorithm; Constructing an indicator system for early warning of substation equipment based on the first transmission data; The coordinated section of the substation equipment early warning and the indicator system of the substation equipment early warning are associated to generate a coordinated early warning judgment standard.

5. The transformer equipment risk early warning method according to claim 1, characterized in that: The step of providing an early warning to the transformer device based on the risk level of the first transmission data includes: Assign corresponding weights to different risk levels; Performing a weighted summation on the weights corresponding to the risk levels of the first transmission data to obtain a comprehensive risk level; An early warning is issued for transformer equipment based on the comprehensive risk level.

6. The transformer equipment risk early warning method according to claim 1, characterized in that: Also includes: The risk level corresponding to the first transmission data is optimized to obtain a target risk level corresponding to the first transmission data.

7. The transformer equipment risk early warning method according to claim 6, characterized in that: The optimizing the risk level corresponding to the first transmission data to obtain a target risk level corresponding to the first transmission data includes: Construct collaborative warning retrieval model; The risk level corresponding to the first transmission data is optimized based on the collaborative early warning retrieval model to obtain a target risk level corresponding to the first transmission data.

8. A transformer equipment risk warning device, characterized in that: include: A clustering module, used for clustering the data of each station end of the transformer based on a K-means algorithm to obtain first transmission data; A collaborative early warning judgment module, used to associate the collaborative section and indicator system of transformer equipment early warning based on the first transmission data to generate a collaborative early warning judgment standard; A risk level judgment module, used to determine the risk level corresponding to the first transmission data based on the collaborative warning judgment standard; An early warning module is used to issue an early warning to the transformer equipment based on the risk level of the first transmission data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images