Multi-dimensional intelligent early warning method for power transmission and transformation safety

Abstract

The invention provides a multi-dimensional intelligent early warning method for power transmission and transformation safety, and relates to the technical field of power transmission and transformation safety, and the method comprises the steps: building an information base of a power transmission and transformation line; establishing line collaborative association of the power transmission and transformation lines; establishing a basic linkage unit of the sensor, and establishing a weak classifier set mapped with the basic linkage unit through the basic linkage unit; establishing an anomaly recognition result; establishing a trust penalty weight of the abnormal recognition result; and carrying out cooperative authentication on the anomaly recognition result through real-time line cooperative association, establishing a cooperative authentication coefficient, inputting the cooperative authentication coefficient, the trust penalty weight and the anomaly recognition result into an anomaly analysis network, and establishing anomaly early warning. According to the invention, the technical problem that the early warning accuracy is further influenced due to the fact that the early warning mechanism is simple in the prior art can be solved, comprehensive monitoring and intelligent early warning of the operation state of the power transmission and transformation line are realized, and the technical effects of reducing the false alarm and the false alarm and improving the early warning accuracy are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of power transmission and transformation safety, and in particular to a multi-dimensional intelligent early warning method for power transmission and transformation safety. Background Art

[0002] Transmission and transformation lines are an important part of the power system, and their safe and stable operation is crucial to ensuring power supply. However, during operation, transmission and transformation lines may be affected by a variety of factors, such as weather conditions, equipment aging, and human damage, which may cause line failures and affect the normal operation of the power system.

[0003] At present, a variety of monitoring technologies and early warning methods have been developed for the safety monitoring of power transmission and transformation lines. These technologies usually include the deployment of various monitoring sensors along the power transmission and transformation lines, and the analysis of the line status by collecting the line operation data. However, the power transmission line is a complex structure with cross-connections between different parts. It relies on simple threshold judgments, which is prone to false alarms and missed alarms.

[0004] In summary, the prior art has a technical problem that due to the simple warning mechanism, false alarms and missed alarms are easily generated, which further affects the accuracy of the warning. Summary of the invention

[0005] The purpose of this application is to provide a multi-dimensional intelligent early warning method for power transmission and transformation safety, so as to solve the technical problem in the prior art that due to the simple early warning mechanism, false alarms and missed alarms are easily generated, which further affects the accuracy of the early warning.

[0006] In view of the above problems, the present application provides a multi-dimensional intelligent early warning method for power transmission and transformation safety, including: establishing an information base for power transmission and transformation lines, the information base storing line layout information and multi-dimensional monitoring sensor layout information of the power transmission and transformation lines; calling the line layout information in the information base, performing line layout information analysis, and establishing line collaborative association of the power transmission and transformation lines; establishing a basic linkage unit of the sensor with the multi-dimensional monitoring sensor layout information, and establishing a weak classifier set mapped thereto through the basic linkage unit; obtaining the line task of the power transmission and transformation line, performing line collaborative association call based on the line task, establishing real-time line collaborative association, calling the time series monitoring data of the multi-dimensional monitoring sensor, inputting the time series monitoring data into the corresponding weak classifier, performing abnormal identification of the weak classifier, and establishing an abnormal identification result; calling the time series verification window of the weak classifier set according to the abnormal identification result, and establishing a trust penalty weight of the abnormal identification result through the time series verification window; performing collaborative authentication of the abnormal identification result through real-time line collaborative association, establishing a collaborative authentication coefficient, inputting the collaborative authentication coefficient, the trust penalty weight and the abnormal identification result into the abnormal analysis network, and establishing an abnormal early warning.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: Establish an information base for power transmission and transformation lines, wherein the information base stores line layout information and multi-dimensional monitoring sensor layout information of the power transmission and transformation lines; call the line layout information in the information base, perform line layout information analysis, and establish line collaborative association of the power transmission and transformation lines; establish a basic linkage unit of the sensor with the multi-dimensional monitoring sensor layout information, and establish a weak classifier set mapped thereto through the basic linkage unit; obtain the line task of the power transmission and transformation line, perform line collaborative association call based on the line task, establish real-time line collaborative association, call the time series monitoring data of the multi-dimensional monitoring sensor, input the time series monitoring data into the corresponding weak classifier, perform abnormal identification of the weak classifier, and establish abnormal identification results; call the time series verification window of the weak classifier set according to the abnormal identification results, and establish the trust penalty weight of the abnormal identification results through the time series verification window; perform collaborative authentication of the abnormal identification results through real-time line collaborative association, establish a collaborative authentication coefficient, input the collaborative authentication coefficient, the trust penalty weight and the abnormal identification results into the abnormal analysis network, and establish an abnormal warning. By calling the information database to establish the line collaborative association and basic linkage unit of the transmission and transformation line, the corresponding weak classifier set is established based on the basic linkage unit, and the collaborative association and weak classifier are called according to the line task to identify anomalies. Combined with timing verification and collaborative authentication, anomaly warning is carried out to achieve comprehensive monitoring and intelligent early warning of the operating status of the transmission and transformation line, so as to achieve the technical effect of reducing false alarms and missed alarms and improving the accuracy of early warnings.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a flow chart of a multi-dimensional intelligent early warning method for power transmission and transformation safety in this application; Figure 2 A schematic diagram of the process of establishing line collaborative association in the multi-dimensional intelligent early warning method for power transmission and transformation safety used in this application. DETAILED DESCRIPTION

[0011] This application solves the technical problem in the prior art that false alarms and missed alarms are easily generated due to the simple early warning mechanism, which further affects the accuracy of early warnings by providing a multi-dimensional intelligent early warning method for power transmission and transformation safety. By calling the information database to establish the line collaborative association and basic linkage unit of the power transmission and transformation line, a corresponding weak classifier set is established based on the basic linkage unit, and the collaborative association and weak classifier are called according to the line task for abnormal identification. Combined with timing verification and collaborative authentication for abnormal early warning, comprehensive monitoring and intelligent early warning of the operating status of the power transmission and transformation line are achieved, achieving the technical effect of reducing false alarms and missed alarms and improving the accuracy of early warnings.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] Please refer to the attached Figure 1 , this application provides a multi-dimensional intelligent early warning method for power transmission and transformation safety, which specifically includes the following steps: Step 1: Establish an information base of the power transmission and transformation line, wherein the information base stores the line layout information of the power transmission and transformation line and the layout information of the multi-dimensional monitoring sensors.

[0014] Specifically, the line layout information of the power transmission and transformation line includes basic information such as the line direction, length, tower location, conductor model, insulator configuration, etc. This information can be obtained through the design drawings, construction records, operation and maintenance archives of the power transmission and transformation line. The multi-dimensional monitoring sensor layout information includes detailed information on various sensors installed at key parts of the power transmission and transformation line, such as location, model, function, communication method, etc. The establishment of the information database can adopt a database management system such as MySQL, Oracle, etc. to facilitate the storage, query, update and maintenance of information. In the database, multiple tables can be designed to store different types of information, such as one table specifically for storing line layout information and another table for storing sensor layout information. In each table, corresponding fields can be set to correspond to different information attributes. For example, the line layout information table can have fields such as line number, starting point, end point, number of towers, etc.

[0015] In addition, in order to achieve effective management and utilization of information, a user interface can also be provided for information entry, query, statistics and analysis. For example, users can query detailed information of a certain line section through the user interface, or count the layout of sensors in a certain area. Thus, an information database of power transmission and transformation lines is established to achieve systematic and digital management of information related to power transmission and transformation lines, providing a basis for abnormal warning of power transmission and transformation lines.

[0016] Step 2: calling the line layout information in the information database, performing line layout information analysis, and establishing line coordination association of the transmission and transformation lines.

[0017] Specifically, line layout information is extracted from the information database. Line layout information analysis refers to understanding and processing line layout information in order to establish line collaborative association. The analysis process may include: analyzing the topological structure of the line to determine the connection relationship and branching of the line; identifying the length and type of the line; and statistically analyzing the operating environment of the line. To establish line collaborative association of power transmission and transformation lines, a collaborative relationship model between lines is constructed based on the parsed information. This model can reflect the mutual influence and dependency between lines. For example, the failure of a line may affect the operation of other lines connected to it; the excessive load of a line may require support from other lines that cooperate with it. The establishment of collaborative association helps to improve the reliability and economy of line operation and provide a basis for the optimal scheduling and fault handling of the line. Specifically, existing mathematical tools and methods such as graph theory and network analysis can be used, combined with professional knowledge, to establish line collaborative associations to assist in abnormal analysis and early warning of power transmission and transformation lines.

[0018] Step three: establishing a basic linkage unit of sensors based on the multi-dimensional monitoring sensor deployment information, and establishing a set of weak classifiers mapped thereto through the basic linkage unit.

[0019] Specifically, the multi-dimensional monitoring sensor deployment information includes detailed information such as the specific location, type, function, and communication method of the sensor on the transmission and transformation line. A basic linkage unit of sensors is established, and the basic linkage unit includes a combination of sensors at the same location. For example, a temperature sensor and a voltage sensor at the same location can be used as a basic linkage unit.

[0020] The sensors in each basic linkage unit can share some basic information and processing logic, for example, they can use the same communication protocol for data transmission or have similar data processing algorithms. By establishing a basic linkage unit, the management and maintenance of sensors can be simplified and the efficiency of data processing can be improved.

[0021] Next, a set of weak classifiers mapped to the basic linkage unit is established. A weak classifier is a simple classifier that may not be as accurate as a strong classifier in classification problems, but is easier to train and has a lower computational cost. In machine learning, weak classifiers are often used to build ensemble learning algorithms, such as random forests or AdaBoost. Each basic linkage unit can correspond to one or more weak classifiers. These weak classifiers make a preliminary judgment on the operating status of the power transmission and transformation line based on the data features collected by the sensors. For example, the weak classifier determines whether the line has overheating, voltage anomalies, etc. based on the sensor data collected by the basic linkage unit. In this way, complex monitoring tasks can be decomposed into multiple simple classification tasks, each of which is processed by a weak classifier. Finally, the outputs of all weak classifiers are combined to obtain the final judgment on the operating status of the power transmission and transformation line, improving the monitoring accuracy and robustness while reducing the computational complexity.

[0022] Step 4: Obtain the line task of the transmission and transformation line, perform line collaborative association call based on the line task, establish real-time line collaborative association, call the time series monitoring data of the multi-dimensional monitoring sensor, input the time series monitoring data into the corresponding weak classifier, execute abnormality recognition of the weak classifier, and establish abnormality recognition results.

[0023] Specifically, the line task of the transmission and transformation line refers to the power transmission task, which is usually formulated by the power grid dispatching center or the operation and maintenance department according to the operation requirements of the power grid and the actual situation of the line, and may specifically include line branches that need to perform power transmission, etc. Line collaborative association call based on line tasks means extracting the collaborative association corresponding to the real-time line currently executing the line task from the previously established line collaborative association according to the needs of the line task, that is, the collaborative relationship of the real-time line currently executing the line task, as the real-time line collaborative association. Then, according to the real-time line collaborative association, the basic linkage unit at the corresponding position is called, and the line operation parameters are monitored through the multi-dimensional monitoring sensors in the basic linkage unit, and the time series monitoring data is generated based on the monitoring results. According to the above records, a basic linkage unit corresponds to a weak classifier set, and the time series monitoring data collected by the basic linkage unit is input into the corresponding weak classifier to perform abnormal recognition of the weak classifier. The weak classifier will judge whether the data is abnormal based on the characteristics of the data, such as change trend, amplitude, etc. The result of abnormality recognition can be binary, such as normal or abnormal; or multi-classification, such as different abnormality types and abnormality degrees, etc. The type of recognition result can be determined by professional technicians in this field to train weak classifiers.

[0024] Finally, the anomaly recognition result is established, that is, the outputs of all weak classifiers are summarized and integrated to form a final judgment on the line operation status, including the type and degree of anomaly, to achieve intelligent monitoring and health management of transmission and transformation lines, and improve the operation efficiency and reliability of the power grid.

[0025] Step 5: Call the time series verification window of the weak classifier set according to the abnormal recognition result, and establish the trust penalty weight of the abnormal recognition result through the time series verification window.

[0026] Specifically, starting from the identification node of the abnormal recognition result, the window length is set according to the size of the abnormal value of the abnormal recognition result. The larger the abnormal value, the larger the window length, so as to establish the timing verification window. Establishing the trust penalty weight of the abnormal recognition result is a process of quantifying the reliability of the abnormal recognition result. This weight can reflect the trust of the abnormal recognition result. The higher the weight, the higher the trust in the abnormal recognition result; the lower the weight, the lower the trust in the abnormal recognition result. According to the data in the timing verification window and the abnormal recognition result, the weak classifier is identified and analyzed to obtain the recognition accuracy and establish the trust penalty weight, so as to improve the accuracy and robustness of abnormal monitoring, reduce false alarms and missed alarms, and provide stronger support for the safe operation of power transmission and transformation lines.

[0027] Step 6: Perform collaborative authentication of anomaly identification results through real-time line collaborative association, establish a collaborative authentication coefficient, input the collaborative authentication coefficient, trust penalty weight and anomaly identification results into the anomaly analysis network, and establish an anomaly warning.

[0028] Specifically, collaborative authentication takes into account the mutual influence and dependency between the various parts of the line, and can more comprehensively evaluate abnormal situations. The abnormal identification results are analyzed using the previously established real-time line collaborative association, that is, whether the abnormal line position in the abnormal identification result has a collaborative relationship in the real-time line collaborative association. The collaborative authentication coefficient is a quantitative indicator that reflects the degree of matching between the abnormal identification result and the real-time line collaborative association. The higher the coefficient, the more reliable the abnormal identification result; the lower the coefficient, the more problems there may be in the abnormal identification result. Specifically, it can be analyzed whether the abnormal line position in the abnormal identification result is consistent with the real-time line collaborative association, that is, whether the line node with abnormalities has a connection relationship in the real-time line collaborative association. The higher the degree of consistency with the real-time line collaborative association, the larger the corresponding collaborative authentication coefficient. The proportion of abnormal nodes consistent with the real-time line collaborative association to the total number of nodes in the abnormal identification result can be counted as the collaborative authentication coefficient.

[0029] The collaborative authentication coefficient, trust penalty weight and anomaly identification result are input into the anomaly analysis network. The anomaly analysis network is a data processing model, which can be a rule-based logic model or a data-driven machine learning model. For example, if it is a rule-based logic model, the collaborative authentication coefficient and trust penalty weight can be used as weight factors to compensate and correct the anomaly identification result, and the corrected anomaly identification result can be used for anomaly warning. Specifically, warning information can be sent to management personnel to realize intelligent monitoring and early warning of transmission and transformation line anomalies, thereby improving the operation efficiency and reliability of the power grid.

[0030] Further, as attached Figure 2 As shown, step 2 of this application includes: The line topology structure is obtained according to the analysis result of the line layout information, and the line adjacency matrix is ​​established with the line topology structure; the layout environment information is called with the line layout information to extract the layout environment characteristics; the line information in the information base is read, and the line characteristics are extracted according to the line information, and the line characteristics include line length characteristics, line type characteristics, and equipment type characteristics; and the line collaborative association is established according to the line characteristics, the layout environment characteristics and the line adjacency matrix.

[0031] Specifically, first identify the key elements in the line layout information, such as the location of the pole tower, the connection method of the conductor, the branch point, etc., so as to construct the topology map of the line. This topology map reflects the connection relationship between each node in the line (such as pole towers, substations, etc.). To establish the line adjacency matrix based on the line topology structure, the topology map is converted into a matrix form, where the rows and columns of the matrix represent the nodes in the line, and the elements in the matrix represent the connection status between the nodes. If two nodes are directly connected, the corresponding matrix element is 1, otherwise it is 0. The adjacency matrix is ​​a commonly used representation in graph theory, which is convenient for mathematical calculation and analysis. To call the layout environment information with the line layout information, it is necessary to obtain the environmental parameters when the line is laid from the information database, such as terrain, climate, and vegetation as layout environment characteristics, read the line information in the information database, and extract the line characteristics according to the line information, including line length characteristics, line type characteristics, equipment type characteristics, etc. Line length characteristics may affect the resistance and inductance of the line; line type characteristics (such as AC or DC) affect the operation mode and maintenance requirements of the line; equipment type characteristics (such as insulators, conductor models) affect the electrical performance and safety factor of the line.

[0032] Finally, a line collaborative association is established based on line characteristics, layout environment characteristics and line adjacency matrix. That is, all the above information is integrated, and the line characteristics and layout environment characteristics are marked to the line adjacency matrix to obtain the connection relationship between different nodes, as well as the corresponding line type and layout environment. This is used as the line collaborative association to facilitate subsequent line anomaly analysis and improve the accuracy of anomaly analysis.

[0033] Further, step three of this application includes: Establish a location tolerance distance for the same location, authenticate the monitoring sensors at the same location through the location tolerance distance and the multi-dimensional monitoring sensor deployment information, and generate a same location authentication result; establish a historical anomaly data set for each location; establish an associated location according to the line topology, call the historical anomaly authentication data set through the associated location, and establish location anomalies and associated anomalies; perform sensor identification combination based on the location anomaly and associated anomaly, the sensor identification combination is a combination under the same location authentication result, and is the minimum number of identifiable combinations, and a basic linkage unit is established based on the sensor identification combination.

[0034] Specifically, the location tolerance distance is a threshold value that defines the maximum distance difference between two sensor locations that are considered to be at the same location. For example, if the location tolerance distance is set to 5 meters, then sensors with a distance less than or equal to 5 meters will be considered to be deployed at the same location. The specific distance can be determined by professional and technical personnel in this field based on actual experience. Compare the actual location of each sensor with the location of other sensors to determine whether it is within the location tolerance distance. If so, these sensors are certified as sensors at the same location. Generate a same-location certification result, that is, a list of all sensors certified as at the same location. Collect and organize the abnormal data that occurred at each location over a period of time in the past to form a historical abnormal data set for each location. If necessary, this data may include fault records, maintenance logs, monitoring data, etc. The establishment of a historical abnormal data set helps to analyze the abnormal patterns and trends of each location and provide data support for subsequent abnormality identification and prediction.

[0035] Establishing associated locations based on the line topology structure refers to analyzing the electrical connection relationship and physical layout of the line to determine which locations have direct or indirect associations in power transmission or fault propagation. For example, adjacent towers, nodes in the same line ring network, etc. may be defined as associated locations. Associated locations are locations where the line topology structure has a connection relationship.

[0036] By calling the historical anomaly authentication data set by associating the location, we can analyze the anomaly propagation and mutual influence between these locations, establish location anomalies and associated anomalies, and the location anomaly is the line node where the anomaly occurs. The associated anomaly refers to the line node with anomaly correlation, that is, to analyze whether the anomaly at a certain location is associated with the anomaly at other locations. Specifically, the correlation between anomalies at different locations can be analyzed through existing management analysis methods. Combining sensor identification with location anomalies and associated anomalies means determining the number of sensors for anomaly identification at the same location based on the historical anomaly authentication data set. The sensor identification combination should be a combination under the same location authentication result, and it should be the minimum number of combinations that can be identified to reduce the complexity and cost of data analysis.

[0037] Finally, a basic linkage unit is established based on sensor identification and combination, that is, the sensors that need to work together are used as a basic linkage unit. Such a basic linkage unit can more effectively perform abnormal monitoring and fault diagnosis, improve the accuracy and efficiency of the monitoring system, and provide guarantee for the safe operation of the transmission and transformation lines.

[0038] Furthermore, the present application also includes the following steps: The historical monitoring data set of the basic linkage unit is called; the historical abnormal data set is used to perform supervision identification of the historical monitoring data set, and a training data set and a verification data set are established according to the supervision identification results; the basic model adaptation decision of the basic linkage unit is performed through the decision channel, and the weak classifier set is constructed based on the adaptation decision results and the training data set and the verification data set.

[0039] Specifically, after establishing the basic linkage unit, it is also necessary to establish a set of weak classifiers mapped to it. The specific steps are as follows: Calling the historical monitoring data set of the basic linkage unit refers to obtaining the historical monitoring data corresponding to the historical abnormal data set, which may include time series data such as temperature, voltage, and current collected by sensors. The historical abnormal data set includes abnormality type, abnormality degree, etc., which means using the information in the historical abnormal data set to mark the data in the historical monitoring data set. The results of the supervision identification can be different types of abnormalities and abnormality degrees. The training data set and the verification data set are established according to the results of the supervision identification in order to train and verify the machine learning model. The training data set is used to train the model, and the verification data set is used to evaluate the performance of the model. Usually, the training data set and the verification data set are divided from the original data set according to a certain proportion, such as 70% of the data is used for training and 30% of the data is used for verification.

[0040] Making basic model adaptation decisions for basic linkage units through decision channels refers to selecting appropriate machine learning models or algorithms based on the characteristics of the basic linkage units. Factors that may be considered in the adaptation decision include data characteristics, model complexity, etc. Specifically, professional and technical personnel in this field can select a variety of machine learning models and configure corresponding data features for each machine learning model, so as to match the basic model according to the data features of the sensors corresponding to the basic linkage units, and use the training data set and the verification data set to train the model, and obtain a converged model to form a weak classifier set. Construct a weak classifier set suitable for the characteristics of the basic linkage unit to improve the accuracy and efficiency of abnormal monitoring and fault diagnosis.

[0041] Furthermore, step five of this application includes: Obtain an identification node of an abnormal identification result, and use the identification node as a timing zero point; read an abnormal value of the abnormal identification result, determine a window length based on the abnormal value, and build a timing verification window based on the window length and the timing zero point; determine an abnormality type according to the abnormal identification result, and configure an influence weight of the abnormality type; perform identification analysis of a weak classifier within the timing verification window through the abnormality type and influence weight, and establish a trust penalty weight.

[0042] Specifically, the identification node in the anomaly recognition result is used as the timing zero point, that is, the starting point of the window. The anomaly value of the anomaly recognition result is read, that is, the degree of anomaly in the anomaly recognition result is extracted, such as the amplitude and duration of the anomaly. The purpose of determining the window length based on the anomaly value is to construct a time window for more in-depth analysis. The determination of the window length can be determined according to the size of the anomaly value. The window length is proportional to the anomaly value. Specifically, the correspondence between the anomaly value and the window length can be configured by professional and technical personnel in this field based on experience. The timing verification window is constructed based on the window length and the timing zero point, that is, the timing zero point is used as the starting point of the window, and the corresponding time length is extended backward to form a time period, which is the timing verification window.

[0043] Determining the anomaly type based on the anomaly identification results and configuring the impact weight of the anomaly type is to conduct more targeted analysis within the timing verification window. Different anomaly types may have different impacts on the power grid, so it is necessary to assign an impact weight to each anomaly type to reflect its importance and urgency. Specifically, historical abnormal accidents corresponding to different anomaly types can be collected, the scope of impact and the losses caused by historical abnormal accidents can be analyzed, and different impact weights can be configured for different anomaly types. The specific configuration can be made by experts in this field based on their experience.

[0044] Through the abnormal type and impact weight, the weak classifier is identified and analyzed in the time series verification window, that is, the weak classifier is used to process and analyze the data in the window, and the identification results corresponding to the continuous time nodes are output. Under normal circumstances, the output results are basically the same. Therefore, the identification results are identified differently, the degree of difference is obtained, and the difference is weighted with the impact weight to generate the final trust penalty weight. This weight reflects the reliability of the abnormal identification result. The higher the weight, the higher the trust in the abnormal identification result; the lower the weight, the lower the trust in the abnormal identification result. Achieve in-depth analysis and verification of abnormal identification results, and improve the accuracy and robustness of abnormal monitoring.

[0045] Furthermore, the present application also includes the following steps: Establish a basic impact weight, where the basic impact weight is an impact weight of a non-abnormal type; perform identification and analysis of weak classifiers within a timing verification window based on the basic impact weight, and establish a trust penalty weight based on the identification and analysis results of the abnormal type and the identification and analysis results of the non-abnormal type.

[0046] Specifically, the establishment of basic impact weights, that is, determining the impact weights of non-abnormal types, is to perform identification and analysis of non-abnormal types within the timing verification window to compare and verify the identification results of abnormal types. Non-abnormal types refer to the normal operation of the line. The basic impact weight reflects the degree of influence of non-abnormal conditions on the operation of the power grid. The corresponding basic impact weight can be generated by collecting historical line operation records under non-abnormal conditions for correlation impact analysis. According to the basic impact weights, weak classifier identification and analysis are performed within the timing verification window, that is, the non-abnormal type data within the window is processed and analyzed using weak classifiers. The purpose of this step is to evaluate the performance of the system under non-abnormal conditions and the system's monitoring ability for normal operating conditions. Trust penalty weights are established based on the identification and analysis results of abnormal types and non-abnormal types, that is, the identification results of abnormal types and non-abnormal types are comprehensively considered, and a trust weight is assigned to the abnormal identification results. Exemplarily, the identification error of the weak classifier for non-abnormal types is statistically calculated, weighted in combination with the basic impact weight, and averaged with the trust penalty weight established by the identification and analysis of the weak classifier in the timing verification window through the abnormal type and the impact weight, to obtain the final trust penalty weight, thereby improving the reliability of abnormal warning.

[0047] Furthermore, the present application also includes the following steps: An abnormal warning threshold is set, and the abnormal warning threshold is constructed by a historical abnormal data set of the power transmission and transformation line; the abnormal warning is triggered and judged by the abnormal warning threshold; a response strategy is established according to the trigger judgment result, and abnormal warning management is performed based on the response strategy.

[0048] Specifically, the abnormal warning threshold is set to accurately determine when an alarm needs to be issued when an abnormal situation is detected. The abnormal warning threshold is constructed by analyzing the historical abnormal data set of the power transmission and transformation line, including statistical analysis and trend analysis of the historical abnormal data, to determine the minimum abnormal value that will cause the line failure, and set it as the abnormal warning threshold. The abnormal warning is triggered and judged by the abnormal warning threshold, that is, the abnormal value of the abnormal warning exceeds or reaches the abnormal warning threshold, triggering the abnormal warning. Establishing a response strategy based on the trigger judgment result means formulating corresponding response measures according to the type and severity of the abnormality. The response strategy may include notifying the operation and maintenance personnel, starting the backup equipment, adjusting the operating parameters, etc., which needs to be determined in combination with the actual early warning response strategy. Different response strategies can be configured for different abnormal types and abnormal degrees by professional and technical personnel in this field based on actual experience. When the abnormal warning is triggered, the response strategy is generated according to the abnormal type and abnormal degree. Abnormal warning management based on the response strategy means that after the abnormality is detected and the warning is triggered, the relevant staff is notified to handle it according to the predetermined response strategy, so as to achieve timely early warning and effective management of abnormalities in the power transmission and transformation line, and improve the operation efficiency and safety of the power grid.

[0049] Furthermore, the present application also includes the following steps: The abnormal warning is recorded and continuous abnormal identification is established; the line fault of the power transmission and transformation line is reported through the continuous abnormal identification, and the power transmission and transformation line is managed according to the line fault.

[0050] Specifically, recording the abnormal warning means recording the relevant warning information after the abnormal warning, including the time, location, abnormal type, degree of abnormality, etc. The warning record is helpful for subsequent fault analysis and processing, and also provides a basis for the management and analysis of historical data. The warning records are arranged in chronological order to generate continuous abnormality identification results. The line fault of the transmission and transformation line is reported through continuous abnormality identification, that is, when the abnormal situation is detected continuously, a fault alarm is issued, that is, the line fault is reported. The method of reporting the line fault can include any form of sound, light and electricity to remind relevant personnel to respond to and effectively manage the transmission and transformation line fault in a timely manner to ensure the stable operation and safety of the power grid.

[0051] In summary, the multi-dimensional intelligent early warning method for power transmission and transformation safety provided by this application has the following technical effects: Establish an information base for power transmission and transformation lines, wherein the information base stores line layout information and multi-dimensional monitoring sensor layout information of the power transmission and transformation lines; call the line layout information in the information base, perform line layout information analysis, and establish line collaborative association of the power transmission and transformation lines; establish a basic linkage unit of the sensor with the multi-dimensional monitoring sensor layout information, and establish a weak classifier set mapped thereto through the basic linkage unit; obtain the line task of the power transmission and transformation line, perform line collaborative association call based on the line task, establish real-time line collaborative association, call the time series monitoring data of the multi-dimensional monitoring sensor, input the time series monitoring data into the corresponding weak classifier, perform abnormal identification of the weak classifier, and establish abnormal identification results; call the time series verification window of the weak classifier set according to the abnormal identification results, and establish the trust penalty weight of the abnormal identification results through the time series verification window; perform collaborative authentication of the abnormal identification results through real-time line collaborative association, establish a collaborative authentication coefficient, input the collaborative authentication coefficient, the trust penalty weight and the abnormal identification results into the abnormal analysis network, and establish an abnormal warning. By calling the information database to establish the line collaborative association and basic linkage unit of the transmission and transformation line, the corresponding weak classifier set is established based on the basic linkage unit, and the collaborative association and weak classifier are called according to the line task to identify anomalies. Combined with timing verification and collaborative authentication, anomaly warning is carried out to achieve comprehensive monitoring and intelligent early warning of the operating status of the transmission and transformation line, so as to achieve the technical effect of reducing false alarms and missed alarms and improving the accuracy of early warnings.

[0052] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0053] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A multi-dimensional intelligent early warning method for power transmission and transformation safety, characterized in that: The multi-dimensional intelligent early warning method for power transmission and transformation safety includes: Establishing an information base of power transmission and transformation lines, wherein the information base stores line layout information of the power transmission and transformation lines and layout information of multi-dimensional monitoring sensors; Calling the line layout information in the information database, performing line layout information analysis, and establishing line coordination association of the power transmission and transformation lines; Establishing a basic linkage unit of sensors with the multi-dimensional monitoring sensor deployment information, and establishing a set of weak classifiers mapped thereto through the basic linkage unit; Acquire the line task of the power transmission and transformation line, perform line collaborative association call based on the line task, establish real-time line collaborative association, call the time series monitoring data of the multi-dimensional monitoring sensor, input the time series monitoring data into the corresponding weak classifier, perform abnormality recognition of the weak classifier, and establish abnormality recognition results; Calling the time series verification window of the weak classifier set according to the abnormal recognition result, and establishing the trust penalty weight of the abnormal recognition result through the time series verification window; Through real-time line collaborative association, collaborative authentication of anomaly identification results is performed, a collaborative authentication coefficient is established, and the collaborative authentication coefficient, trust penalty weight and anomaly identification results are input into the anomaly analysis network to establish an anomaly warning.

2. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 1, characterized in that: The executing line layout information analysis and establishing line coordination association of the power transmission and transformation lines also includes: Acquire a line topology structure according to the analysis result of the line layout information, and establish a line adjacency matrix based on the line topology structure; Using the line layout information to call layout environment information and extract layout environment features; Reading line information in the information database, and extracting line features according to the line information, wherein the line features include line length features, line type features, and equipment type features; A line collaborative association is established according to the line characteristics, the layout environment characteristics and the line adjacency matrix.

3. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 1, characterized in that: The basic linkage unit for establishing sensors based on the multi-dimensional monitoring sensor layout information also includes: Establishing a position tolerance distance for the same position, performing monitoring sensor authentication at the same position through the position tolerance distance and multi-dimensional monitoring sensor deployment information, and generating a same position authentication result; Build historical anomaly datasets for each location; Establishing an associated position according to the line topology structure, calling a historical abnormality authentication data set through the associated position, and establishing a position abnormality and an associated abnormality; A sensor identification combination is performed based on the position anomaly and the associated anomaly. The sensor identification combination is a combination under the same position authentication result and is the minimum number of identifiable combinations. A basic linkage unit is established based on the sensor identification combination.

4. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 3, characterized in that: The step of establishing a weak classifier set mapped thereto through the basic linkage unit also includes: Call the historical monitoring data set of the basic linkage unit; Using the historical abnormal data set to perform supervisory identification on the historical monitoring data set, and establishing a training data set and a verification data set according to the supervisory identification results; The basic model adaptation decision of the basic linkage unit is made through the decision channel, and the weak classifier set is constructed based on the adaptation decision results and the training data set and the verification data set.

5. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 1, characterized in that: The step of calling the time series verification window of the weak classifier set according to the abnormal recognition result and establishing the trust penalty weight of the abnormal recognition result through the time series verification window further includes: Obtaining an identification node of an abnormal identification result, and taking the identification node as a timing zero point; Reading an abnormal value of an abnormal recognition result, determining a window length based on the abnormal value, and constructing a timing verification window based on the window length and the timing zero point; Determine the abnormality type according to the abnormality identification result, and configure the impact weight of the abnormality type; The identification and analysis of the weak classifier is performed within the time series verification window through the abnormal type and the impact weight, and the trust penalty weight is established.

6. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 5, characterized in that: The multi-dimensional intelligent early warning method for power transmission and transformation safety also includes: Establishing a basic influence weight, wherein the basic influence weight is an influence weight of a non-abnormal type; The weak classifier identification analysis within the time series verification window is performed according to the basic impact weight, and the trust penalty weight is established according to the identification analysis results of the abnormal type and the identification analysis results of the non-abnormal type.

7. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 1, characterized in that: The multi-dimensional intelligent early warning method for power transmission and transformation safety also includes: Setting an abnormal warning threshold, wherein the abnormal warning threshold is constructed by using a historical abnormal data set of the power transmission and transformation line; Triggering and judging the abnormal warning by using the abnormal warning threshold; Establish a response strategy based on the trigger identification results, and perform abnormal warning management based on the response strategy.

8. The multi-dimensional intelligent early warning method for power transmission and transformation safety according to claim 1, characterized in that: The multi-dimensional intelligent early warning method for power transmission and transformation safety also includes: Record the abnormal warning and establish continuous abnormality recognition; The line fault of the power transmission and transformation line is reported through the continuous abnormal identification, and the power transmission and transformation line is managed according to the line fault.

Images