Transformer substation monitoring method and device, computer equipment and storage medium

Abstract

The invention relates to a transformer substation monitoring method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring monitoring data of a transformer substation; according to preset reference data, determining a deviation value between each piece of monitoring data and the corresponding reference data; the obtaining mode of the reference data comprises the steps of obtaining historical health data of each monitoring data identifier and a weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data comprises historical monitoring data of the transformer substation in a normal operation state; weighting the deviation value of each piece of monitoring data by using the weight coefficient to obtain a target deviation value; wherein the target deviation value is used for representing the operation state of the transformer substation. By adopting the method, the operation state of the transformer substation can be quantitatively evaluated, and the monitoring accuracy of the transformer substation is improved.

Description

Technical Field

[0001] The present application relates to the field of electrical technology, and in particular, to a monitoring method, device, computer device, storage medium, and computer program product for a substation. Background Art

[0002] With the development of electrical systems, substation fault warning technology has emerged. This technology plays an important role in the power system, aiming to detect and warn potential fault risks in a timely manner, thereby ensuring the stable operation of electrical equipment and the safety of the system. Traditional substation fault warnings often rely on manual inspections, but this method has many limitations: manual inspections are prone to errors or omissions, and real-time intelligent warnings cannot be achieved, resulting in increased safety hazards and fault risks. To improve this situation, many substations are now equipped with real-time monitoring sensors to quickly obtain various power and environmental data of the substation. Although this method can improve the monitoring ability to a certain extent, how to effectively analyze these data and accurately judge the operating state of the substation remains a major problem. Summary of the Invention

[0003] Based on this, it is necessary to provide a monitoring method, device, computer device, computer-readable storage medium, and computer program product for a substation in view of the above technical problems.

[0004] In a first aspect, the present application provides a monitoring method for a substation. The method includes:

[0005] Obtain each monitoring data of the substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power;

[0006] According to the preset reference data, determine the deviation amount between each monitoring data and the corresponding reference data; wherein, the acquisition method of the reference data includes: obtaining the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operating state of the substation;

[0007] Use the weight coefficient to perform weighted processing on the deviation amount of each monitoring data to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operating state of the substation.

[0008] In one embodiment, the reference data includes multiple reference sub-data, and the determining the deviation amount between each monitoring data and the corresponding reference data according to the preset reference data includes:

[0009] Determine the deviation amount between each of the monitoring data and the corresponding reference sub-data according to the respective reference sub-data;

[0010] Perform weighted processing on the deviation amount between each of the monitoring data and the corresponding reference sub-data respectively to obtain the deviation amount between each of the monitoring data and the corresponding reference data.

[0011] In one embodiment, the obtaining of the weight coefficient includes:

[0012] Obtain the historical health data of each monitoring data and the first weight sub-coefficient of each monitoring data identifier;

[0013] According to the historical health data, determine the positive correlation coefficient and the negative correlation coefficient between the historical health data, and use the positive correlation coefficient and the negative correlation coefficient to determine the second weight sub-coefficient of each monitoring data identifier;

[0014] Perform weighted processing on the first weight sub-coefficient and the second weight sub-coefficient to obtain the weight coefficient of each monitoring data identifier.

[0015] In one embodiment, after obtaining each monitoring data of the substation, it includes:

[0016] Generate a first warning signal when there is monitoring data outside the preset range;

[0017] Generate a second warning signal when the change amount per unit time of the monitoring data is not within the preset threshold.

[0018] In one embodiment, the obtaining of each monitoring data of the substation includes:

[0019] Obtain each environmental data and power data;

[0020] Perform normalization processing on the environmental data and power data to obtain target environmental data and target power data;

[0021] Select feature data from the target environmental data and target power data, and determine the feature data as the monitoring data; wherein, the feature data has an associated relationship with the operating state of the substation.

[0022] In one embodiment, the clustering of the historical health data according to the weight coefficient and the historical health data to determine the reference data includes:

[0023] Cluster the historical health data according to the weight coefficient and the historical health data to obtain a plurality of clustering results and corresponding clustering coefficients; wherein, the clustering coefficient is used to characterize the positive correlation between each historical health data and other historical health data in the same cluster, and the negative correlation between each historical health data and other historical health data in different clusters;

[0024] Use the clustering coefficient to select a target clustering result from the clustering results, and determine the historical health data corresponding to the target clustering result as the reference data.

[0025] In a second aspect, the present application also provides a monitoring device for a substation. The device includes:

[0026] A data acquisition module for acquiring each monitoring data of the substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power;

[0027] A deviation amount determination module for determining the deviation amount between each monitoring data and the corresponding reference data according to the preset reference data; wherein, the acquisition method of the reference data includes: acquiring the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operation state of the substation;

[0028] An operating state determination module for performing weighted processing on the deviation amounts of each monitoring data by using the weight coefficient to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operating state of the substation.

[0029] In one embodiment, the reference data includes a plurality of reference sub-data, and the deviation amount determination module is further configured to:

[0030] Determine the deviation amount between each monitoring data and each corresponding reference sub-data according to each reference sub-data;

[0031] Perform weighted processing on the deviation amounts between each monitoring data and each corresponding reference sub-data respectively to obtain the deviation amount between each monitoring data and the corresponding reference data.

[0032] In one embodiment, the deviation amount determination module includes a weight determination sub-module for:

[0033] Acquire the historical health data of each monitoring data and the first weight sub-coefficient of each monitoring data identifier;

[0034] Based on the historical health data, determine the positive correlation coefficient and negative correlation coefficient between the historical health data, and use the positive correlation coefficient and negative correlation coefficient to determine the second weight sub - coefficient of each monitoring data identifier;

[0035] Perform a weighted process on the first weight sub - coefficient and the second weight sub - coefficient to obtain the weight coefficient of each monitoring data identifier.

[0036] In one embodiment, the device further includes an early warning sub - module, which is used for:

[0037] Generate a first early warning signal when there is monitoring data outside the preset range;

[0038] Generate a second early warning signal when the change amount of monitoring data per unit time is outside the preset threshold.

[0039] In one embodiment, the data acquisition module includes:

[0040] A data acquisition sub - module for acquiring each environmental data and power data;

[0041] A normalization sub - module for performing normalization processing on the environmental data and power data to obtain target environmental data and target power data;

[0042] Select feature data from the target environmental data and target power data, and determine the feature data as monitoring data; wherein, the feature data has an associated relationship with the operating state of the substation.

[0043] In one embodiment, the deviation amount determination module includes:

[0044] A coefficient acquisition sub - module for clustering the historical health data according to the weight coefficient and the historical health data to obtain a plurality of clustering results and corresponding clustering coefficients; wherein, the clustering coefficient is used to characterize the positive correlation of each historical health data with other historical health data in the same cluster, and the negative correlation of each historical health data with other historical health data in different clusters;

[0045] A reference data acquisition sub - module for selecting a target clustering result from the clustering results by using the clustering coefficient, and determining the historical health data corresponding to the target clustering result as reference data.

[0046] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the monitoring method of the substation as described in any one of the embodiments of the present disclosure.

[0047] Fourthly, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the monitoring method of the substation as described in any one of the embodiments of the present disclosure.

[0048] Fifthly, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the monitoring method of the substation as described in any one of the embodiments of the present disclosure.

[0049] The above-mentioned monitoring method, device, computer equipment, storage medium and computer program product of the substation determine reference data through historical health data and the weight coefficient of data identifiers, determine the deviation amount by obtaining each monitoring data of the substation, and then use the weight coefficient for weighted processing to obtain the target deviation amount, realizing the quantitative evaluation of the operation state of the substation. This method not only improves the accuracy of monitoring, but also can realize the real-time monitoring and early warning of the operation state of the substation, so as to timely discover potential fault risks and ensure the stable operation of power equipment and the safety of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a schematic flow chart of the monitoring method of the substation in an embodiment;

[0051] Figure 2 It is a schematic flow chart of the determination of the deviation amount in an embodiment;

[0052] Figure 3 It is a schematic flow chart of the acquisition of the weight coefficient in an embodiment;

[0053] Figure 4 It is a schematic flow chart of the generation of the warning signal in an embodiment;

[0054] Figure 5 It is a schematic flow chart of the normalization of the monitoring data in an embodiment;

[0055] Figure 6 It is a schematic flow chart of the acquisition of the reference data in an embodiment;

[0056] Figure 7 It is a schematic flow chart of the implementation of the monitoring method of the substation in an embodiment;

[0057] Figure 8 It is a structural block diagram of the monitoring device of the substation in an embodiment;

[0058] Figure 9 It is an internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] In one embodiment, as Figure 1 shown, a monitoring method for a substation is provided. In this embodiment, it is exemplified that the method is applied to a terminal. It can be understood that the method can also be applied to a server and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0061] Step S100, obtaining each piece of monitoring data of the substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power.

[0062] In one exemplary embodiment, a substation may include a place in a power system for transforming voltage and current, receiving electric energy, and distributing electric energy, etc.

[0063] In one exemplary embodiment, the environmental data may include data such as temperature and humidity; the power data may include data of each power device in the substation, and the power devices may include devices for receiving, converting, and distributing electric energy, etc.; specifically, the power devices may include transformers, switchgear, rectifiers, inverters, etc. In one exemplary embodiment, the power data may further include frequency, active power, reactive power, etc., and these data can comprehensively reflect the power state of the substation. In addition to temperature and humidity, the environmental data may also include air pressure, wind speed, etc., and these data help to understand whether the environmental conditions where the substation is located are suitable, etc.

[0064] Step S200, determining the deviation amount between each piece of monitoring data and the corresponding reference data according to the preset reference data; wherein, the acquisition method of the reference data includes: obtaining the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operation state of the substation.

[0065] In one exemplary embodiment, the reference data can be used to characterize the standard state when the substation is operating normally. By comparing the monitoring data with the reference data, the deviation amount can be obtained, so as to quantitatively evaluate the deviation degree between the current operation state of the substation and the normal state, etc.

[0066] In an exemplary embodiment, the deviation amount may include the Euclidean distance between the reference data and the monitoring data, etc., and the deviation amount between the reference data and the monitoring data is characterized by the Euclidean distance, etc.

[0067] In an exemplary embodiment, the weight coefficient may characterize the importance degree of each monitoring data when evaluating the operation state of the substation. Different monitoring data may have different influences on the operation state of the substation. Therefore, by assigning different weight coefficients to each monitoring data, the actual operation state of the substation can be reflected more accurately. For example, for the monitoring data with a greater influence on the operation state of the substation, a larger weight coefficient may be assigned, while for the monitoring data with a smaller influence, a smaller weight coefficient may be assigned. In this way, when calculating the deviation amount and performing weighted processing, the operation state of the substation can be evaluated more precisely, and the accuracy of monitoring can be improved.

[0068] In an exemplary embodiment, the weight coefficient may include a subjective weight coefficient and an objective weight coefficient, etc.; the subjective weight coefficient can be subjectively weighted by using AHP; the objective coefficient can be obtained through the CRITIC algorithm, etc., and the subjective weight coefficient and the objective weight coefficient are weighted and summed to obtain the weight coefficient, etc.

[0069] In an exemplary embodiment, the historical health data may include each monitoring data during the normal operation of the substation in the past period of time. These data can be screened and processed to ensure their accuracy and representativeness. By performing cluster analysis on the historical health data and combining the weight coefficient, the reference data closer to the actual operation state of the substation can be determined, thereby providing a more accurate basis for subsequent deviation amount calculation and operation state evaluation, etc.

[0070] In an exemplary embodiment, fuzzy C - clustering may be adopted for the clustering, and the historical health data is clustered by using the weight coefficient and the historical health data. After obtaining the clustering result, one or more clustering results can be selected as the target clustering result as the normal operation mode, and the historical health data corresponding to the normal operation mode is the reference data, etc. In the actual use process, the clustering effect can also be evaluated by calculating the silhouette index, so as to select the normal operation mode, etc.

[0071] Step S300: Using the weight coefficient, perform weighted processing on the deviation amounts of the monitoring data to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operation state of the substation.

[0072] In an exemplary embodiment, the weight coefficient may include the weight coefficient of the data identifier. By using the weight coefficient, each monitoring data is weighted and summed to obtain the target deviation amount. It can be understood that the larger the target deviation amount, the higher the probability that the operation mode of the substation is abnormal, etc.

[0073] In an exemplary embodiment, the operation state may include a normal operation state, an abnormal operation state, and a warning state. Among them, the normal operation state means that all monitoring data of the substation are within the preset range and the deviation amount is small; the abnormal operation state means that some monitoring data of the substation exceed the preset range, or the deviation amount is large, and the substation may need to be inspected or repaired; the warning state means that although some monitoring data of the substation have not exceeded the preset range, their change trend may indicate that an abnormality is about to occur, and attention needs to be paid and measures need to be taken in time for prevention. By quantitatively evaluating the operation state of the substation, the operation and maintenance personnel can more intuitively understand the operation situation of the substation, and thus make more accurate judgments and decisions.

[0074] In the above monitoring method of the substation, the reference data is determined through the historical health data and the weight coefficient of the data identifier. By obtaining each monitoring data of the substation, determining the deviation amount according to the reference data, and then using the weight coefficient for weighted processing to obtain the target deviation amount, the quantitative evaluation of the operation state of the substation is realized. This method not only improves the accuracy of monitoring, but also can realize the real-time monitoring and warning of the operation state of the substation, so as to timely discover potential fault risks and ensure the stable operation of power equipment and the safety of the system.

[0075] In one embodiment, as Figure 2 shown, the reference data includes a plurality of reference sub-data. The determining of the deviation amount between each of the monitoring data and the corresponding reference data according to the preset reference data includes:

[0076] Step S201, determining the deviation amount between each of the monitoring data and each corresponding reference sub-data according to each reference sub-data.

[0077] Step S202, respectively performing weighted processing on the deviation amounts between each of the monitoring data and each corresponding reference sub-data to obtain the deviation amounts between each of the monitoring data and the corresponding reference data.

[0078] In an exemplary embodiment, multiple normal operation modes and corresponding reference data can be obtained through clustering. The deviation amount can be calculated by using the monitoring data and each reference data, and each deviation amount is weighted and summed to obtain the deviation amount, etc.

[0079] In an exemplary embodiment, during the weighting process, weights can be assigned according to the degree of influence of different monitoring data on the overall operating state of the substation. The greater the degree of influence of the monitoring data, the higher the corresponding weight given to its deviation amount during the weighting process. In this way, the obtained target deviation amount can more accurately reflect the actual operating conditions of the substation, etc.

[0080] In an exemplary embodiment, after using the weight coefficient to perform a weighting process on the deviation amounts of the monitoring data to obtain the target deviation amount, it may further include further analyzing and judging the target deviation amount to determine whether it is necessary to issue a more detailed warning prompt or take corresponding maintenance measures, etc., in order to better ensure the stable operation of the substation and the safety of the power system.

[0081] In this embodiment, by determining the deviation amounts between the monitoring data and each reference sub-data and performing a weighting process, the deviation amounts between each monitoring data and the reference data are obtained. By confirming the deviation amounts with multiple reference sub-data, the accuracy and comprehensiveness of the substation operating state assessment are improved. At the same time, a comprehensive analysis of the deviation amounts between each monitoring data and the reference data is realized to more accurately evaluate the operating state of the substation.

[0082] In one embodiment, as Figure 3 shown, the obtaining of the weight coefficient includes:

[0083] Step S211, obtain the historical health data of each monitoring data and the first weight sub-coefficient of each monitoring data identifier.

[0084] Step S212, according to the historical health data, determine the positive correlation coefficient and negative correlation coefficient between the historical health data, and use the positive correlation coefficient and negative correlation coefficient to determine the second weight sub-coefficient of each monitoring data identifier.

[0085] Step S213, perform a weighting process on the first weight sub-coefficient and the second weight sub-coefficient to obtain the weight coefficient of each monitoring data identifier.

[0086] In an exemplary embodiment, the first weight sub-coefficient may include subjective weighting, etc. Specifically, the APH algorithm can be used for subjective weighting, etc. In another exemplary embodiment, the second weight sub-coefficient may include objective weighting, etc. Specifically, the CRITIC algorithm can be used to obtain the second weight sub-coefficient, etc.

[0087] In one exemplary embodiment, a positive correlation coefficient can be used to indicate the degree of consistency in the changing trends between two historical health data sets—that is, when one data set increases, the other data set also tends to increase. A negative correlation coefficient, on the other hand, can indicate the degree of opposition in the changing trends between two data sets—that is, when one data set increases, the other data set tends to decrease. By calculating the positive and negative correlation coefficients between each set of historical health data, a second weighting sub-coefficient can be further determined for each monitoring data set identifier to reflect its relative importance in the overall operational status assessment. After obtaining the first and second weighting sub-coefficients, they can be weighted to obtain the final weighting coefficient. The weighting method can be flexibly selected based on actual circumstances, such as equal-weighted averaging or weighted averaging. By comprehensively considering the results of subjective and objective weighting, the resulting weighting coefficient can more accurately reflect the contribution of each monitoring data set to the substation operational status assessment. In another exemplary embodiment, other factors, such as the stability, reliability, and availability of the monitoring data, can also be considered in determining the weighting coefficient. These factors may have a certain impact on the determination of the weighting coefficient, and therefore, in practical applications, comprehensive consideration and analysis based on specific circumstances are required.

[0088] In this embodiment, by combining the first weight coefficient and the second weight coefficient, the importance of each monitoring data in the substation operation status assessment can be more comprehensively considered, thereby improving the accuracy and rationality of the weight coefficient determination, improving the accuracy of the deviation amount, and further improving the accuracy of the substation operation status and monitoring.

[0089] In one embodiment, Figure 4 As shown, after obtaining the monitoring data of the substation, the following steps are included:

[0090] Step S101: When the monitoring data is outside the preset range, a first warning signal is generated.

[0091] Step S102: When the change in the monitoring data per unit time is not within a preset threshold, a second warning signal is generated.

[0092] In an exemplary embodiment, the preset range can be set based on historical health data and substation operating specifications to determine whether the monitoring data is within a normal range. When the monitoring data exceeds the preset range, it may indicate that the substation's operating status is abnormal. In this case, a first warning signal is generated to alert personnel and prompt appropriate action.

[0093] In an exemplary embodiment, the preset threshold can be set according to the changing trend of historical health data and the operation specifications of the substation, and is used to determine whether the change amount of the monitoring data per unit time is normal. When the change amount of the monitoring data per unit time exceeds the preset threshold, it may indicate that the operation state of the substation has changed significantly in a short period of time. At this time, a second warning signal is generated to remind the staff to pay attention and conduct fault troubleshooting and handling in a timely manner.

[0094] In this embodiment, by generating the first warning signal and the second warning signal, real-time monitoring and warning of the operation state of the substation can be achieved, so as to timely discover potential fault risks and ensure the stable operation of power equipment and the safety of the system. At the same time, according to different warning signals, the staff can take different handling measures to better ensure the stable operation of the substation and the safety of the power system.

[0095] In one embodiment, as Figure 5 shown, the obtaining of each monitoring data of the substation includes:

[0096] Step S111, obtain each environmental data and power data.

[0097] Step S112, perform normalization processing on the each environmental data and power data to obtain target environmental data and target power data.

[0098] Step S113, select feature data from the target environmental data and target power data, and determine the feature data as the monitoring data; wherein, the feature data has an associated relationship with the operation state of the substation.

[0099] In an exemplary embodiment, the environmental data may include temperature, humidity, etc.; the power data may include voltage, current, power, etc. The feature data may include key information that can reflect the operation state of the substation, such as the extreme values, average values or changing trends of data such as temperature, humidity, voltage, current, etc. By analyzing and processing these feature data, the operation state of the substation can be understood more accurately, abnormal situations can be discovered in a timely manner, and strong support can be provided for subsequent warning and fault troubleshooting. When selecting feature data, it can be flexibly selected according to the actual situation and operation requirements of the substation to ensure the accuracy and effectiveness of the monitoring data, etc.

[0100] In an exemplary embodiment, since the dimensions and value ranges of different monitoring data may vary, it may be difficult to directly compare and analyze them. Therefore, through normalization processing, each monitoring data can be converted into data under the same scale for subsequent analysis and processing. The normalization method can be flexibly selected according to the actual situation. For example, methods such as min-max normalization and Z-score normalization can be used. After obtaining the normalized target environmental data and target power data, characteristic data associated with the operation status of the substation can be selected from these data as monitoring data for subsequent analysis and processing. The selection of characteristic data can be flexibly determined according to the actual situation. For example, data closely related to the operation status of the substation can be selected, or selected based on experience. By selecting characteristic data, the processing and analysis process of the monitoring data can be further simplified, and the monitoring efficiency and accuracy can be improved.

[0101] In this embodiment, by normalizing each monitoring data of the substation and selecting characteristic data, the consistency and relevance of the monitoring data can be ensured, providing a reliable basis for subsequent analysis and processing. At the same time, by monitoring and analyzing the characteristic data, the operation status of the substation can be more accurately reflected, potential fault risks can be detected in a timely manner, and a strong guarantee for the stable operation of the power system can be provided.

[0102] In one embodiment, as Figure 6 shown, clustering the historical health data according to the weight coefficient and the historical health data to determine the reference data includes:

[0103] Step S221, clustering the historical health data according to the weight coefficient and the historical health data to obtain a plurality of clustering results and corresponding clustering coefficients; wherein, the clustering coefficient is used to characterize the positive correlation of each historical health data with other historical health data in the same cluster, and the negative correlation of each historical health data with other historical health data in different clusters.

[0104] Step S222, using the clustering coefficient, selecting a target clustering result from the clustering results, and determining the historical health data corresponding to the target clustering result as the reference data.

[0105] In an exemplary embodiment, by introducing a weight coefficient, the importance of each historical health data in the clustering process can be more accurately reflected, thereby improving the accuracy and reliability of clustering. Specifically, the weight coefficient can be determined according to the historical health data of each monitoring data and the corresponding weight sub - coefficient to reflect the relative importance of each historical health data in the overall operation state evaluation. Then, using clustering algorithms such as K - means, hierarchical clustering, etc., cluster the historical health data to obtain multiple clustering results and corresponding clustering coefficients. The clustering coefficient can be used to characterize the positive correlation of each historical health data with other historical health data in the same cluster and the negative correlation of each historical health data with other historical health data in different clusters. By comparing the clustering coefficients of different clustering results, the target clustering result with the best clustering effect can be selected, and the historical health data corresponding to the target clustering result is determined as the reference data. The reference data can be used to characterize the standard state during the normal operation of the substation, providing strong support for subsequent state evaluation and early warning. During the clustering process, other evaluation indicators such as the Silhouette Coefficient can also be used to evaluate the clustering effect, so as to select the optimal clustering result as the reference data. In this way, the accuracy and reliability of the substation operation state evaluation can be further improved.

[0106] In an exemplary embodiment, during the clustering process, in addition to considering the weight coefficient and the clustering coefficient, expert experience or domain knowledge can also be combined to further optimize and adjust the clustering result. For example, experts can evaluate the rationality and accuracy of the clustering result based on in - depth understanding and experience judgment of the substation operation state to ensure that the selected reference data can truly reflect the normal operation state of the substation. In addition, with the continuous monitoring of the substation operation state and the continuous accumulation of data, the reference data can be updated and optimized regularly to adapt to the changes in the substation operation state and new monitoring requirements. In this way, the accuracy and timeliness of the substation operation state evaluation can be continuously improved, providing a more reliable guarantee for the safe and stable operation of the power system.

[0107] In an exemplary embodiment, the clustering coefficient may include metrics such as intra-cluster cohesion and inter-cluster separation. Among them, the intra-cluster cohesion is used to measure the similarity degree, that is, the positive correlation, among historical health data within the same cluster; while the inter-cluster separation is used to measure the difference degree, that is, the negative correlation, among historical health data between different clusters. By comprehensively considering the intra-cluster cohesion and inter-cluster separation, the clustering effect can be evaluated more comprehensively, so as to select the optimal clustering result as reference data. In specific implementation, a suitable clustering algorithm and evaluation metrics can be adopted, combined with weight coefficients for clustering processing, and the clustering results can be screened and optimized according to evaluation metrics such as the clustering coefficient. In this way, the accuracy and reliability of the substation operation state assessment can be further improved, providing more powerful support for the safe and stable operation of the power system. Specifically, the clustering coefficient may include metrics such as the sihouette index to characterize the clustering coefficient.

[0108] In this embodiment, by introducing weight coefficients and combining with a clustering algorithm to perform clustering processing on historical health data, more accurate and reliable reference data can be obtained. These reference data can truly reflect the standard state during the normal operation of the substation, providing strong support for subsequent state assessment and early warning. At the same time, by comprehensively considering metrics such as intra-cluster cohesion and inter-cluster separation, the clustering effect can be comprehensively evaluated to ensure that the selected reference data is representative and accurate.

[0109] In an exemplary embodiment, the detection method of the substation can be applied to the schematic diagram as Figure 7 shown, specifically including:

[0110] Step S401. Select representative parameters of the substation. Each substation monitoring master station collects and processes the corresponding monitoring data, and each substation digital twin terminal processes the corresponding data and transmits the processed data back to the integrated remote operation and maintenance platform.

[0111] In an exemplary embodiment, voltage, current, and power can be selected as representatives, and then the corresponding monitoring data of each substation is collected and data cleaning is performed to handle missing values and outliers in the data. The data model of the substation digital twin can extract the operation data and environmental data of each physical node, and extract the characteristic parameters of the target feature fields from the operation data and environmental data of each physical node according to the physical node category. Transmit the above processed data back to the integrated remote operation and maintenance platform, etc.

[0112] Step S402, perform preliminary early warning for the thresholds and trends of single parameters.

[0113] In an exemplary embodiment, it is possible to check whether each parameter in the real-time monitoring data transmitted back by each substation exceeds a preset threshold. If a parameter exceeds the preset threshold, a warning is issued. Calculate the change amount of the parameter within a preset time period, determine whether the change amount of the parameter exceeds a preset change amount threshold, and issue a warning through the parameter change trend. If the change amount of the parameter exceeds the preset threshold, a warning is issued.

[0114] Step S403: Perform weighted fuzzy C-clustering on the historical normal data of each substation respectively to obtain the normal operation mode of each substation.

[0115] In an exemplary embodiment, it is possible to perform weighted fuzzy C-clustering on the historical normal data of each substation respectively to obtain the normal operation mode of each substation, etc. Specifically, it may include: performing max-min normalization processing on each parameter, and the formula is as follows:

[0116] (1)

[0117] Wherein, X represents the normalized historical normal data, x represents the historical normal data, min(x) represents the smallest historical normal data, and max(x) represents the largest historical normal data; the AHP method can be used to subjectively assign weights to the indicators first; Represents the priority weight vector of the second-layer index with respect to the first-layer total index. =[], 0 < <1 satisfies . Construct a judgment matrix and solve it using the root method , and perform a consistency test. The steps for performing a consistency test are as follows: calculate the consistency index , look up the corresponding average random consistency index in Table 2, calculate the consistency ratio , where m is the order of the judgment matrix, is the largest eigenvalue of the judgment matrix. When, accept the judgment matrix, otherwise modify the judgment matrix. The meanings of each level of scale can be as shown in Table 1:

[0118] Table 1

[0119]

[0120] Table 2

[0121]

[0122] The CRITIC method can be used to objectively assign weights to indicators. Since the dimensions of the indicators are different, it is necessary to standardize the indicators. Thus, from the indicator matrix S (with dimensions m×n, where m is the number of samples and n is the number of indicators), the standardized matrix .

[0123] Calculation method for normalizing positive indicators:

[0124] (2)

[0125] where represents the data in the i-th row and j-th column of the standardized matrix; represents the data in the i-th row and j-th column of matrix S;

[0126] Calculation method for normalizing negative indicators:

[0127] (3)

[0128] Calculation method for normalizing interval-type indicators. Let the optimal indicator value be , and the indicator range be , :

[0129] (4)

[0130] The CRITIC method reflects the differences and conflicts among indicators using the standard deviation and correlation coefficient. The calculation formulas for the standard deviation of each indicator and the correlation coefficient between indicators in the standardized matrix are respectively:

[0131] j = 1, 2, 3...n (5) i, j = 1, 2, …, n (6)

[0132] where is the standard deviation of the j-th indicator; is the correlation coefficient between the i-th indicator and the j-th indicator; are respectively the i-th and j-th columns of the standardized matrix . represents the information content contained in the indicator. The larger it is, the greater the weight of the indicator in the evaluation system. The information content contained in the j-th indicator is calculated as:

[0133] (7)

[0134] Taking the proportion of the information content of the j-th indicator in the total information content as the objective weight of this indicator, its calculation formula is:

[0135] (8)

[0136] The calculation formula for the combined weight W of AHP and CRITIC based on the least squares method is as follows:

[0137] (9)

[0138] s.t. 、 (10)

[0139] Among them, W represents the combined weight, φ represents the subjective weight, σ represents the objective weight, and s represents the index value; the subscript i represents the substation number, and j represents the index number. Taking the matrix Y and the weight vector W as inputs, assuming the number of clusters is c (2 c ), the weighted coefficient m of the membership degree is taken as 2, and c rows of data are randomly selected from the Y matrix as the initial cluster center matrix V = … … , = , the initial industrial load membership degree matrix is determined , , the number of iterations l = 0, represents the membership degree of the i-th sample belonging to the j-th class, , = 1, is the Euclidean distance from the i-th sample to the center of the j-th class. Through formulas (12)(13):

[0140] , i = 1, 2, …, c (11)

[0141] , i, j (12)

[0142] Perform repeated iterative solution for the clustering objective: , until for a given ε, there is J(l) - J(l - 1) ε holds,

[0143] J(l) = , j = 1, 2, …, c (13)

[0144] Among them, v and y correspond to the elements in the matrix V and the matrix Y respectively, and other variables have corresponding explanations. Formulas (12) to (14) - see the fuzzy C clustering process for details. If , then the sample i belongs to the j-th class.

[0145] The optimal number of clusters k is determined by the weighted Silhouette index. The larger the index, the better the clustering effect. a(x) is the weighted average distance between the sample x in the cluster and all other samples within the cluster; b(x) is the minimum weighted average distance from the sample x to all samples in non - same clusters. The calculation formula is as follows:

[0146] (14)

[0147] Step S404: According to the normal operation modes of each substation, an abnormal severity index is proposed for comprehensive early warning.

[0148] In an exemplary embodiment, comprehensive early warning can be performed according to the obtained normal operation modes of each substation. An abnormal severity index is proposed, that is, the sum of weighted Euclidean distances d from the sample points to the nearest cluster centers, which reflects the degree of deviation of the sample points from the normal operation modes of the substations. Let the threshold be L. If d > L, this point can be regarded as an abnormal point or having a safety risk, so as to perform intelligent early warning, etc.

[0149] Step S405: The edge device makes a preliminary intelligent early warning judgment on the collected data according to the preset threshold and trend analysis algorithm. The edge device performs comprehensive early warning and uploads the clustering results or abnormal data to the central server.

[0150] ​In an exemplary embodiment, edge computing devices can be deployed at the edge nodes of a substation. These devices can be high-performance embedded systems, industrial computers, or dedicated edge servers, with strong computing and storage capabilities. The edge devices are directly connected to the sensors, smart meters, monitoring systems, etc. of the substation to collect power data in real time (such as voltage, current, power, temperature, etc.). The edge devices first preprocess the collected data, including operations such as data cleaning, denoising, and normalization, to reduce the data transmission volume and the complexity of subsequent processing. It can be understood that the edge devices perform preliminary intelligent early warning judgments on the collected data according to preset thresholds and trend analysis algorithms. This step can be completed on the edge devices, reducing the dependence on the central server and reducing latency. The edge devices perform weighted fuzzy C-means clustering (FCM) on the preprocessed data to obtain various normal operation modes of the substation. Since the clustering algorithm has a large amount of computation, the edge devices can complete this computing task locally and only upload the clustering results or abnormal data to the central server, reducing the data transmission volume. When the edge devices detect abnormal data or complex situations that cannot be processed, they upload the abnormal data or clustering results to the cloud or the central server for further analysis. The cloud server can perform more complex model training, pattern recognition, and global optimization. The cloud server trains and optimizes the model based on global data and sends the updated model parameters or early warning rules to the edge devices. The edge devices perform real-time early warning according to the new model parameters to ensure the accuracy and real-time nature of the early warning system. Sensitive data is stored and processed locally on the edge devices, reducing the need to upload data to the cloud and protecting user privacy and data security. At the same time, the data transmission between the edge devices and the cloud uses encryption protocols (such as TLS / SSL) to ensure the security of data during transmission. As the power system expands, new edge devices can be easily deployed in new substations or distribution rooms, and the system has good scalability. The edge devices can be dynamically adjusted according to requirements to adapt to power networks of different scales. The edge devices have a certain fault tolerance ability. Even in the case of network interruption or the unavailability of the cloud server, the edge devices can still perform early warning and processing based on local data to ensure the reliability of the system. Since the edge devices are close to the data source, they can perform real-time computing and early warning locally, reducing the latency of data transmission and ensuring a quick response when abnormalities occur in the power system. Multiple edge devices can process the data of different substations in parallel, and the distributed computing architecture can effectively share the computing load, avoid single-point bottlenecks, and improve the overall computing efficiency of the system.

[0151] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0152] Based on the same inventive concept, an embodiment of the present application also provides a monitoring device for a substation for implementing the monitoring method of the substation involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the monitoring device for the substation provided below can refer to the limitations on the monitoring method of the substation in the above text, and will not be repeated here.

[0153] In one embodiment, as Figure 8 shown, a monitoring device 100 for a substation is provided, including: a data acquisition module 101, a deviation amount determination module 102, and an operating state determination module 103, where:

[0154] The data acquisition module is used to acquire various monitoring data of the substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power.

[0155] The deviation amount determination module is used to determine the deviation amount between each of the monitoring data and the corresponding reference data according to the preset reference data; wherein, the acquisition method of the reference data includes: acquiring the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operating state of the substation.

[0156] The operating state determination module is used to perform weighted processing on the deviation amounts of each of the monitoring data by using the weight coefficient to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operating state of the substation.

[0157] In one of the embodiments, the reference data includes multiple reference sub-data, and the deviation amount determination module is further used for:

[0158] Determine the deviation amount between each of the monitored data and the corresponding reference sub-data according to the respective reference sub-data;

[0159] Perform weighted processing on the deviation amounts between each of the monitored data and the corresponding reference sub-data respectively to obtain the deviation amounts between each of the monitored data and the corresponding reference data.

[0160] In one embodiment, the deviation amount determination module includes a weight determination sub-module for:

[0161] Obtain the historical health data of each monitored data and the first weight sub-coefficient of each monitored data identifier;

[0162] Determine the positive correlation coefficient and the negative correlation coefficient between the historical health data according to the historical health data, and use the positive correlation coefficient and the negative correlation coefficient to determine the second weight sub-coefficient of each monitored data identifier;

[0163] Perform weighted processing on the first weight sub-coefficient and the second weight sub-coefficient to obtain the weight coefficient of each monitored data identifier.

[0164] In one embodiment, the device further includes an early warning sub-module for:

[0165] Generate a first early warning signal when there is monitored data outside the preset range;

[0166] Generate a second early warning signal when the change amount per unit time of the monitored data is outside the preset threshold.

[0167] In one embodiment, the data acquisition module includes:

[0168] A data acquisition sub-module for acquiring each environmental data and power data;

[0169] A normalization sub-module for performing normalization processing on the environmental data and power data to obtain target environmental data and target power data;

[0170] Select feature data from the target environmental data and target power data, and determine the feature data as the monitored data; wherein, the feature data has an association relationship with the operating state of the substation.

[0171] In one embodiment, the deviation amount determination module includes:

[0172] A coefficient acquisition sub-module, configured to cluster the historical health data according to the weight coefficient and the historical health data, to obtain a plurality of clustering results and corresponding clustering coefficients; wherein the clustering coefficient is used to characterize the positive correlation between each piece of historical health data and other historical health data in the same cluster, and the negative correlation between each piece of historical health data and other historical health data in different clusters;

[0173] A reference data acquisition sub-module, configured to select a target clustering result from the clustering results by using the clustering coefficient, and determine the historical health data corresponding to the target clustering result as reference data.

[0174] Each module in the monitoring device of the above substation can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0175] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in Figure 9 The figure shows. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store monitoring data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a monitoring method for a substation.

[0176] Those skilled in the art can understand that Figure 9 The structure shown in is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0177] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0178] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., and are not limited thereto.

[0179] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0180] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A monitoring method for a substation, characterized in that, The method includes: Obtaining each piece of monitoring data of the substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power. Determining the deviation amount between each piece of the monitoring data and the corresponding reference data according to the preset reference data; wherein, the obtaining method of the reference data includes: obtaining the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operation state of the substation. Using the weight coefficient to perform weighted processing on the deviation amount of each piece of the monitoring data to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operation state of the substation.

2. The method according to claim 1, characterized in that The reference data includes multiple reference sub-data, and the determining the deviation amount between each piece of the monitoring data and the corresponding reference data according to the preset reference data includes: Determining the deviation amount between each piece of the monitoring data and each corresponding reference sub-data according to each reference sub-data. Performing weighted processing on the deviation amount between each piece of the monitoring data and each corresponding reference sub-data respectively to obtain the deviation amount between each piece of the monitoring data and the corresponding reference data.

3. The method according to claim 1, wherein The obtaining of the weight coefficient includes: Obtaining the historical health data of each piece of monitoring data and the first weight sub-coefficient of each monitoring data identifier. Determining the positive correlation coefficient and negative correlation coefficient between each piece of the historical health data according to the historical health data, and using the positive correlation coefficient and negative correlation coefficient to determine the second weight sub-coefficient of each monitoring data identifier. Performing weighted processing on the first weight sub-coefficient and the second weight sub-coefficient to obtain the weight coefficient of each monitoring data identifier.

4. The method according to claim 1, wherein After obtaining each piece of monitoring data of the substation, it includes: Generating a first warning signal when there is monitoring data not within the preset range. Generating a second warning signal when the change amount of the monitoring data per unit time is not within the preset threshold.

5. The method according to claim 1, wherein The obtaining of each piece of monitoring data of the substation includes: Obtaining each piece of environmental data and power data. Performing normalization processing on the environmental data and power data to obtain target environmental data and target power data. Selecting characteristic data from the target environmental data and target power data, and determining the characteristic data as the monitoring data; wherein, the characteristic data has an associated relationship with the operation state of the substation.

6. The method according to claim 1, wherein The clustering the historical health data according to the weight coefficient and the historical health data to determine the reference data includes: Clustering the historical health data according to the weight coefficient and the historical health data to obtain multiple clustering results and corresponding clustering coefficients; wherein, the clustering coefficient is used to characterize the positive correlation of each historical health data with other historical health data in the same cluster, and the negative correlation of each historical health data with other historical health data in different clusters. Using the clustering coefficient, select a target clustering result from the clustering results, and determine the historical health data corresponding to the target clustering result as the reference data.

7. A monitoring device for a substation, characterized in that, The device includes: a data acquisition module, configured to acquire various monitoring data of a substation; wherein, the monitoring data includes power data and environmental data; the power data includes at least one of the following: current, voltage, power; a deviation amount determination module, configured to determine the deviation amount between each of the monitoring data and the corresponding reference data according to a preset reference data; wherein, the acquisition method of the reference data includes: acquiring the historical health data of each monitoring data identifier and the weight coefficient of each monitoring data identifier, clustering the historical health data according to the weight coefficient and the historical health data, and determining the reference data; the historical health data includes each historical monitoring data in the normal operation state of the substation; an operating state determination module, configured to perform weighted processing on the deviation amounts of each of the monitoring data by using the weight coefficient to obtain a target deviation amount; wherein, the target deviation amount is used to characterize the operating state of the substation.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, 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 6 are implemented.

10. A computer program product, comprising 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 6 are implemented.

Images