Power transmission and transformation project state analysis and active intervention system
By using data collection and processing and a state analysis model built by graph neural network in power transmission and transformation projects, combined with active intervention modules, dynamic adjustment of the real-time state of the equipment is achieved, and the insufficient response speed and decision-making accuracy in the existing technology are solved. The problem has improved the status monitoring and fault prediction capabilities of the transmission and transformation system and reduced maintenance costs.
Patent Information
- Application Number
- CN202411405042.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing active intervention technology for power transmission and transformation projects cannot dynamically adjust the intervention strategy based on the real-time status of the equipment, especially in complex operating conditions, which is difficult to meet actual needs, especially in high-voltage and large-capacity transmission systems.
Data collection and feature extraction is adopted using the data collection and processing module, the state analysis model is constructed using the graph neural network, and the active intervention module is combined with the active intervention module to conduct intelligent intervention based on real-time data, including signal decomposition, feature extraction and weighted fusion to construct input data of multi-dimensional characterization , and establish the connection relationship between devices through the graph structure mode, perform state updates and global state acquisition, and ultimately realize intelligent load regulation and active intervention.
Through data acquisition of multi-sensor networks and state analysis of graph neural networks, the accuracy and response speed of status monitoring are improved, the frequency and time of manual maintenance are reduced, the maintenance cost is reduced, and the reliability of safe operation of the system is improved.
Smart Images

Figure CN118916645A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power transmission and transformation engineering, and in particular to a power transmission and transformation engineering state analysis and active intervention system. Background Art
[0002] In recent years, with the development of sensor technology, communication technology and big data analysis technology, the condition monitoring and analysis technology of power transmission and transformation equipment has made great progress. For example, SCADA systems, online monitoring equipment and partial discharge detection technology have been widely used in power transmission and transformation projects; although these technologies can provide a certain degree of condition monitoring and fault warning, there are still many shortcomings; for example, data collection is not comprehensive enough, the analysis model is not accurate enough, and there is a lack of coordination between monitoring systems, which makes it difficult to accurately predict faults and effectively evaluate the condition; Active intervention technology is an important development direction in the field of power transmission and transformation engineering. Its purpose is to take proactive measures before a fault occurs to prevent equipment failure and power outages. However, most existing active intervention technologies rely on simple rules or preset thresholds and cannot dynamically adjust intervention strategies according to the real-time status of the equipment. In addition, when facing complex working conditions, the response speed and decision-making accuracy of active intervention in existing systems often cannot meet actual needs. This limitation is particularly prominent in high-voltage, large-capacity transmission systems. Summary of the invention
[0003] In view of the above problems, the present invention provides a power transmission and transformation project status analysis and active intervention system, which can effectively solve the problem in the above background technology that the intervention strategy cannot be dynamically adjusted according to the real-time status of the equipment.
[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a power transmission and transformation project status analysis and active intervention system, comprising: The data collection and processing module is used to collect power transmission and transformation project data and process the collected data, including: Collect data, extract features and decompose signals from the collected data, specifically: Decompose the data signal collected by the sensor into the eigenmode function, extract features from it, perform weighted fusion on the extracted features, and perform feature reorganization to achieve signal decomposition to form input data with multi-dimensional representation; and, a state analysis model building module, for building a state analysis model according to the input, including: A state analysis model is constructed based on graph neural network, and the state analysis of power transmission and transformation project is carried out using the constructed state analysis model. Specifically: Using the status of adjacent power transmission and transformation equipment, the current power transmission and transformation equipment status is updated to complete the acquisition of the global status of the power transmission and transformation system, which also includes: The active intervention module is used to actively intervene in the power transmission and transformation project according to the output results of the state analysis model.
[0005] As a preferred solution of the power transmission and transformation engineering status analysis and active intervention system of the present invention, the feature extraction of the collected data is specifically as follows: The data signal collected by each sensor Decompose and obtain the eigenmode function, then we have,
[0006] in, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Represents the residual, which is the low-frequency part of the data signal; Perform feature extraction on the decomposed intrinsic mode function, then we have,
[0007] in, Indicates indivual The energy of the modal is used to measure the energy distribution of different modes. , Respectively time series, Indicates data signal No. The eigenmode function is The sensor An intrinsic mode function.
[0008] As a preferred solution of the power transmission and transformation engineering state analysis and active intervention system of the present invention, the signal decomposition is specifically as follows: The extracted features are weighted and fused, and the features are reorganized according to the weight coefficients, then we have:
[0009] in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates indivual The energy is used to measure the energy distribution of different modes; The different The features of , and integrate the data of all sensors into the final feature matrix , then there is,
[0010]
[0011] in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Indicates different The combined multi-scale feature vector, Represents the feature matrix after integrating the data from all sensors.
[0012] As a preferred solution of the power transmission and transformation engineering state analysis and active intervention system described in the present invention, the state analysis model constructed based on the graph neural network is specifically as follows: The connection relationship between power transmission and transformation equipment is established based on the graph structure model, then, Each power transmission and transformation equipment is regarded as a node , and set the characteristic vector of the current power transmission and transformation equipment to ,in, is the index of the node, is the feature matrix after integration in the previous article; Each connection line in the power transmission and transformation network is used as the interaction relationship between devices, and an adjacency matrix is constructed , and satisfies the formula When , it indicates that the node and nodes There is a connection relationship between them, if the formula is satisfied When , it indicates that the node and nodes There is no connection between them; And the entire power transmission and transformation system is constructed as a graph structure, then we have, ,in, Represents a collection of device nodes. A collection of edges representing connections between devices.
[0013] As a preferred solution of the power transmission and transformation project state analysis and active intervention system of the present invention, the state analysis of the power transmission and transformation project by constructing a state analysis model is specifically as follows: Setting Node The initial state is , No. The state at the iteration is , using the status of adjacent nodes to update the status, specifically:
[0014] in, Representation Node In the The state after iterations, Representation Node The neighbor node set of node A set of nodes that have a connection relationship. Indicates the neighbor node in The state after iterations, Represents the bias term, which is used to correct the normal data of the node status and is set by real-time personnel according to the actual application scenario; go through After iterations, the state of each node is pooled to obtain the global state of the power transmission and transformation system. Then,
[0015] in, Indicates the status of each power transmission and transformation equipment. Represents the global status of the power transmission and transformation system; According to the calculated global state, the state prediction is performed, then,
[0016] in, Represents the weight matrix of the output layer, which is set by the implementer according to the actual application scenario. Represents the global state of the power transmission and transformation system, represents the bias term of the output layer, The distribution vector representing the state category of the power transmission and transformation project is the probability of the system state, including normal state, warning state and dangerous state.
[0017] As a preferred solution of the power transmission and transformation project status analysis and active intervention system described in the present invention, the active intervention mechanism is specifically as follows: When the state analysis model's analysis result for the power transmission and transformation project is normal, the voltage, current and temperature parameters of the current power transmission and transformation equipment are maintained according to the real-time data of the sensor, and the operation state of the current power transmission and transformation project is maintained. At the same time, the sensor's acquisition frequency is reduced, and the load of data acquisition and transmission is reduced to ensure the stable operation of the current power transmission and transformation project. When the state analysis model's analysis result for the power transmission and transformation project is in the early warning state, the real-time data of the sensors in the current power transmission and transformation project is monitored, and the fluctuation of the monitored data is analyzed. For data nodes that exceed the fluctuation range, the relevant staff is notified to perform manual maintenance and regulation to ensure that the real-time data collected by the sensors can maintain the stable operation of the power transmission and transformation project; When the analysis result of the state analysis model for the power transmission and transformation project is a fault state, the load intelligent control algorithm is used to manually intervene in the power transmission and transformation project.
[0018] As a preferred solution of the power transmission and transformation project state analysis and active intervention system described in the present invention, the manual intervention of the power transmission and transformation project using the load intelligent control algorithm is specifically as follows: According to the data of power transmission and transformation equipment collected by sensors, the load rate of each equipment is calculated and the current power of the equipment is set. And the maximum load power , and calculate the load rate, then we have,
[0019] in, Indicates the current power of the power transmission and transformation project. Indicates the maximum carrying power, Indicates the load rate calculated by the current device, which is used to determine whether the current power transmission and transformation equipment is overloaded. If yes, When the calculated load rate satisfies the formula When , it means that the current load rate of the equipment is approaching the maximum load; When the calculated load rate satisfies the formula When , it means the load rate of the current device is overloaded; When the calculated load rate satisfies the formula , it indicates that the current device is not overloaded and there is load space; Based on the load factor standard deviation and load factor average value of the equipment in the power transmission and transformation project, the load balance index of the power transmission and transformation project is determined, then:
[0020] in, Represents the standard deviation of the equipment load rate in the current power transmission and transformation project, It indicates the average value of the equipment load rate in the current power transmission and transformation project. It represents the load balance index of the power transmission and transformation project and is used to actively intervene in the power transmission and transformation project. Then, When the analysis result of the state analysis model for the power transmission and transformation project is a fault state, the load balance index of the power transmission and transformation project is adjusted to achieve active intervention in the power transmission and transformation project, specifically:
[0021] in, Represents the load balance index of the adjusted power transmission and transformation project, , Respectively represent the minimum and maximum load values of each device. It represents the total load power of the power transmission and transformation project. The active intervention of the power transmission and transformation project must ensure that the three constraints are met at the same time, which means that the active intervention of the power transmission and transformation project under the fault state is completed.
[0022] Beneficial effects of the present invention: The present invention collects data through a multi-sensor network, covering a wide range of equipment and lines, ensuring the comprehensiveness and real-time nature of the data, and utilizing signal decomposition and feature extraction technology to enhance the accuracy and representativeness of the data, especially under complex working conditions, which helps to improve the accuracy of state monitoring; constructing a state analysis model using a graph neural network can effectively capture the interaction between devices and the overall state of the system; through intelligent state analysis and intervention mechanisms, the system can be regulated before a fault occurs, greatly reducing the frequency and time of manual maintenance, reducing maintenance costs, and reducing the reliance of manual participation on the safe operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 The present invention is a schematic diagram of the overall structural composition of a power transmission and transformation engineering status analysis and active intervention system.
[0024] Figure 2The present invention is a schematic diagram of the state analysis logic judgment process of a power transmission and transformation project state analysis and active intervention system.
[0025] Figure 3 The present invention is a schematic diagram of an active intervention logic judgment flow of a power transmission and transformation engineering status analysis and active intervention system. DETAILED DESCRIPTION
[0026] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0028] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0029] Example 1 This embodiment provides a power transmission and transformation project status analysis and active intervention system. Figure 1 As shown, the present invention includes a data collection and processing module, a state analysis model building module and an active intervention module; Specifically, the data collection and processing module is used to collect power transmission and transformation project data and perform data processing on the collected data. The state analysis model construction module is used to construct a state analysis model based on the processed data. The active intervention module is used to perform active intervention in the power transmission and transformation project according to the output results of the state analysis model.
[0030] Furthermore, the data collection and processing module collects and processes data for the power transmission and transformation project, including a data collection unit and a data processing unit. The data collection unit collects real-time data for the power transmission and transformation project by building a multi-sensor network. The multi-sensor network deploys multiple sensors in the power transmission and transformation equipment, and the connection method between the deployed sensors is wireless connection. The multiple sensors include current sensors, temperature sensors and voltage sensors.
[0031] Specifically, the multi-transmission and transformation project collects real-time data by deploying multiple sensors to collect real-time data from the transmission equipment, and constructs the collected data into a data signal set. , then there is,
[0032] in, Indicates The sensors in The data signals collected from power transmission and transformation equipment, Represents a collection of real-time data signals collected from power transmission and transformation projects.
[0033] The data processing unit performs data preprocessing on the collected real-time data set of the power transmission and transformation project, extracts features and decomposes signals on the collected data, and sends the extracted feature data to the state analysis model construction module to provide input data for the subsequent state analysis model. The data preprocessing is to collect the real-time data set. Preprocessing operations are performed to ensure the accuracy of the data, including data cleaning, data deduplication, and outlier removal. Data preprocessing is an existing conventional technology disclosed in the art and will not be described in detail in this embodiment.
[0034] The feature extraction and signal decomposition of the collected data is to extract features based on the processed data, and decompose the extracted feature data into signal features at different time scales, thereby improving the multi-dimensional representation of the data and providing accurate data input, i.e., input data, for the subsequent state analysis model. The specific implementation process is as follows: The data signal collected by each sensor Decompose and obtain the eigenmode function, then we have,
[0035] in, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Represents the residual, which is the low-frequency part of the data signal; Perform feature extraction on the decomposed intrinsic mode function, then we have,
[0036] in, Indicates indivual The energy of the modal is used to measure the energy distribution of different modes. , Respectively time series, Indicates data signal No. The eigenmode function is The sensor Intrinsic mode functions; The extracted features are weighted and fused, and the features are reorganized according to the weight coefficients, then we have:
[0037] in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates indivual The energy is used to measure the energy distribution of different modes; The different The features of , and integrate the data of all sensors into the final feature matrix , then there is,
[0038]
[0039] in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Indicates different The combined multi-scale feature vector, Represents the feature matrix after integrating the data from all sensors.
[0040] Reference Figure 2 , which is a schematic diagram of the state analysis logic judgment process, provides a detailed state analysis process, and the state analysis module is to build a state analysis model and integrate the feature matrix of all sensor data As the input of the model, the state analysis of the power transmission and transformation project is carried out. At the same time, the historical data of the power transmission and transformation project is used as the control group of the state analysis model to ensure the accuracy of the state analysis of the power transmission and transformation project. The state analysis model is constructed based on the deep learning algorithm, and the specific construction is as follows: The connection relationship between power transmission and transformation equipment is established based on the graph structure model, then, Each power transmission and transformation equipment is regarded as a node , and set the characteristic vector of the current power transmission and transformation equipment to ,in, is the index of the node, is the feature matrix after integration in the previous article; Each connection line in the power transmission and transformation network is used as the interaction relationship between devices, and an adjacency matrix is constructed , and satisfies the formula When , it indicates that the node and nodes There is a connection relationship between them, if the formula is satisfied When , it indicates that the node and nodes There is no connection between them; And the entire power transmission and transformation system is constructed as a graph structure, then we have, ,in, Represents a collection of device nodes. A set of edges representing connections between devices; Build a message passing mechanism between nodes so that the status of the nodes can be updated. Then, Setting Node The initial state is , No. The state at the iteration is , using the status of adjacent nodes to update the status, specifically:
[0041] in, Representation Node In the The state after iterations, Representation Node The neighbor node set of node A set of nodes that have a connection relationship. Indicates the neighbor node in The state after iterations, Represents the bias term, which is used to correct the normal data of the node status and is set by real-time personnel according to the actual application scenario; go through After iterations, the state of each node is pooled to obtain the global state of the power transmission and transformation system. Then,
[0042] in, Indicates the status of each power transmission and transformation equipment. Represents the global status of the power transmission and transformation system; According to the calculated global state, the state prediction is performed, then,
[0043] in, Represents the weight matrix of the output layer, which is set by the implementer according to the actual application scenario. Represents the global state of the power transmission and transformation system, represents the bias term of the output layer, The distribution vector representing the state category of the power transmission and transformation project is the probability of the system state, including normal state, warning state and dangerous state; According to the predicted state probability, the maximum probability , The state probability of the largest category in the system state and the corresponding category label are used to locate the state of the power transmission and transformation equipment of the current system; After the status of the power transmission and transformation equipment of the current system is located, the historical data of the power transmission and transformation project is used for comparison and verification, and then,
[0044] in, Indicates the status category, including normal status, warning status and dangerous status. Indicates the control data obtained using historical data. Indicates the positioning result of the power transmission and transformation equipment status of the current system. Represents the prediction loss function of the state analysis model. When the prediction loss satisfies the formula It indicates that the accuracy of the current state analysis model meets the requirements for state analysis of power transmission and transformation projects. If the formula is not satisfied, the nodes of the constructed state analysis model are re-iterated until the requirements are met. For the specific formula requirement value of the loss function, no specific numerical limit is made in this embodiment, and it is set by the implementer according to actual needs.
[0045] Reference Figure 3, is a schematic diagram of the active intervention logic judgment process, which provides a detailed active intervention process. The active intervention module is based on the output results of the state analysis model to actively intervene to ensure the stable operation of the power transmission and transformation project. The active intervention based on the output results of the state analysis model is to actively intervene in the power transmission and transformation project by formulating an active intervention mechanism. The specific intervention process is as follows: When the state analysis model's analysis result for the power transmission and transformation project is normal, the voltage, current and temperature parameters of the current power transmission and transformation equipment are maintained according to the real-time data of the sensor, and the operation state of the current power transmission and transformation project is maintained. At the same time, the sensor's acquisition frequency is reduced, and the load of data acquisition and transmission is reduced to ensure the stable operation of the current power transmission and transformation project. When the state analysis model's analysis result for the power transmission and transformation project is in the early warning state, the real-time data of the sensors in the current power transmission and transformation project is monitored, and the fluctuation of the monitored data is analyzed. For data nodes that exceed the fluctuation range, the relevant staff is notified to perform manual maintenance and regulation to ensure that the real-time data collected by the sensors can maintain the stable operation of the power transmission and transformation project; When the state analysis model's analysis result for the power transmission and transformation project is a fault state, the load intelligent control algorithm is used to manually intervene in the power transmission and transformation project, as follows: According to the data of power transmission and transformation equipment collected by sensors, the load rate of each equipment is calculated and the current power of the equipment is set. And the maximum load power , and calculate the load rate, then we have,
[0046] in, Indicates the current power of the power transmission and transformation project. Indicates the maximum carrying power, Indicates the load rate calculated by the current device, which is used to determine whether the current power transmission and transformation equipment is overloaded. If yes, When the calculated load rate satisfies the formula When , it means that the current load rate of the equipment is approaching the maximum load; When the calculated load rate satisfies the formula When , it means the load rate of the current device is overloaded; When the calculated load rate satisfies the formula , it indicates that the current device is not overloaded and there is load space; Based on the load factor standard deviation and load factor average value of the equipment in the power transmission and transformation project, the load balance index of the power transmission and transformation project is determined, then:
[0047] in, Represents the standard deviation of the equipment load rate in the current power transmission and transformation project, It indicates the average value of the equipment load rate in the current power transmission and transformation project. It represents the load balance index of the power transmission and transformation project and is used to actively intervene in the power transmission and transformation project. Then, When the analysis result of the state analysis model for the power transmission and transformation project is a fault state, the load balance index of the power transmission and transformation project is adjusted to achieve active intervention in the power transmission and transformation project, specifically:
[0048] in, Represents the load balance index of the adjusted power transmission and transformation project, , Respectively represent the minimum and maximum load values of each device. It represents the total load power of the power transmission and transformation project. The active intervention of the power transmission and transformation project must ensure that the three constraints are met at the same time, which means that the active intervention of the power transmission and transformation project under the fault state is completed.
[0049] Furthermore, if the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the system described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.
[0050] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0051] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0052] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment may not be described (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those features that are not relevant to implementing the invention).
[0053] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.
[0054] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A power transmission and transformation project status analysis and active intervention system, comprising: The data collection and processing module is used to collect power transmission and transformation project data and process the collected data. It is characterized by: including: Collect data, extract features and decompose signals from the collected data, specifically: Decompose the data signal collected by the sensor into the eigenmode function, extract features from it, perform weighted fusion on the extracted features and perform feature reorganization to achieve signal decomposition and form input data with multi-dimensional representation; and, a state analysis model building module, used to build a state analysis model based on input data, including: A state analysis model is constructed based on graph neural network, and the state analysis of power transmission and transformation project is carried out using the constructed state analysis model. Specifically: Using the status of adjacent power transmission and transformation equipment, the current power transmission and transformation equipment status is updated to complete the acquisition of the global status of the power transmission and transformation system; Also includes: The active intervention module is used to actively intervene in the power transmission and transformation project according to the output results of the state analysis model.
2. The power transmission and transformation project status analysis and active intervention system according to claim 1, characterized in that: The feature extraction of the collected data is specifically as follows: The data signal collected by each sensor Decompose and obtain the eigenmode function, then we have, in, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Represents the residual, which is the low-frequency part of the data signal; Perform feature extraction on the decomposed intrinsic mode function, then we have, in, Indicates indivual The energy of the modal is used to measure the energy distribution of different modes. , Respectively time series, Indicates data signal No. The eigenmode function is The sensor An intrinsic mode function.
3. A power transmission and transformation project status analysis and active intervention system according to claim 2, characterized in that: The signal decomposition is as follows: The extracted features are weighted and fused, and the features are reorganized according to the weight coefficients, then, in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates indivual The energy is used to measure the energy distribution of different modes; The different The features of , and integrate the data of all sensors into the final feature matrix , then there is, in, Represents the weight coefficient after weighted fusion, which is indivual The weight coefficient corresponding to the energy of Indicates the corresponding sensor serial number, Indicates the upper limit of the number of sensors. represents the sequence number of the intrinsic mode function, represents the upper limit of the number of modal functions, Indicates data signal No. The eigenmode function is The sensor The intrinsic mode functions, Indicates different The combined multi-scale feature vector, Represents the feature matrix after integrating the data from all sensors.
4. The power transmission and transformation project status analysis and active intervention system according to claim 3 is characterized by: The state analysis model constructed based on the graph neural network is specifically as follows: The connection relationship between power transmission and transformation equipment is established based on the graph structure model, then, Each power transmission and transformation equipment is regarded as a node , and set the characteristic vector of the current power transmission and transformation equipment to ,in, is the index of the node, is the integrated feature matrix in the previous article; Each connection line in the power transmission and transformation network is used as the interaction relationship between devices, and an adjacency matrix is constructed , and satisfies the formula When , it indicates that the node and nodes There is a connection relationship between them, if the formula is satisfied When , it indicates that the node and nodes There is no connection between them; And the entire power transmission and transformation system is constructed as a graph structure, then we have, ,in, Represents a collection of device nodes. A collection of edges representing connections between devices.
5. A power transmission and transformation project status analysis and active intervention system according to claim 4, characterized in that: The state analysis of the power transmission and transformation project by constructing a state analysis model is specifically as follows: Setting Node The initial state is , No. The state at the iteration is , using the status of adjacent nodes to update the status, specifically: in, Representation Node In the The state after iterations, Representation Node The neighbor node set of node A set of nodes that have a connection relationship. Indicates the neighbor node in The state after iterations, Represents the bias term, which is used to correct the normal data of the node status and is set by real-time personnel according to the actual application scenario; go through After iterations, the state of each node is pooled to obtain the global state of the power transmission and transformation system. Then, in, Indicates the status of each power transmission and transformation equipment. Represents the global status of the power transmission and transformation system; According to the calculated global state, the state prediction is performed, then, in, Represents the weight matrix of the output layer, which is set by the implementer according to the actual application scenario. Represents the global state of the power transmission and transformation system, represents the bias term of the output layer, The distribution vector representing the state category of the power transmission and transformation project is the probability of the system state, including normal state, warning state and dangerous state.
6. A power transmission and transformation project status analysis and active intervention system according to claim 5, characterized in that: The active intervention module performs active intervention based on the output results of the state analysis model, as follows: When the state analysis model's analysis result for the power transmission and transformation project is normal, the voltage, current and temperature parameters of the current power transmission and transformation equipment are maintained according to the real-time data of the sensor, and the operation state of the current power transmission and transformation project is maintained. At the same time, the sensor's acquisition frequency is reduced, and the load of data acquisition and transmission is reduced to ensure the stable operation of the current power transmission and transformation project. When the state analysis model's analysis result for the power transmission and transformation project is in the early warning state, the real-time data of the sensors in the current power transmission and transformation project is monitored, and the fluctuation of the monitored data is analyzed. For data nodes that exceed the fluctuation range, the relevant staff is notified to perform manual maintenance and regulation to ensure that the real-time data collected by the sensors can maintain the stable operation of the power transmission and transformation project; When the analysis result of the state analysis model for the power transmission and transformation project is a fault state, the load intelligent control algorithm is used to manually intervene in the power transmission and transformation project.
7. A power transmission and transformation project status analysis and active intervention system according to claim 6, characterized in that: The specific details of using the load intelligent control algorithm to manually intervene in the power transmission and transformation project are as follows: According to the data of power transmission and transformation equipment collected by sensors, the load rate of each equipment is calculated and the current power of the equipment is set. And the maximum load power , and calculate the load rate, then we have, in, Indicates the current power of the power transmission and transformation project. Indicates the maximum carrying power, Indicates the load rate calculated by the current device, which is used to determine whether the current power transmission and transformation equipment is overloaded. If yes, When the calculated load rate satisfies the formula When , it means that the current load rate of the equipment is approaching the maximum load; When the calculated load rate satisfies the formula When , it means the load rate of the current device is overloaded; When the calculated load rate satisfies the formula , it indicates that the current device is not overloaded and there is load space; Based on the load factor standard deviation and load factor average value of the equipment in the power transmission and transformation project, the load balance index of the power transmission and transformation project is determined, then: in, Represents the standard deviation of the equipment load rate in the current power transmission and transformation project, It indicates the average value of the equipment load rate in the current power transmission and transformation project. It represents the load balance index of the power transmission and transformation project and is used to actively intervene in the power transmission and transformation project. Then, When the analysis result of the state analysis model for the power transmission and transformation project is a fault state, the load balance index of the power transmission and transformation project is adjusted to achieve active intervention in the power transmission and transformation project, specifically: in, Represents the load balance index of the adjusted power transmission and transformation project, , Respectively represent the minimum and maximum load values of each device. It represents the total load power of the power transmission and transformation project. The active intervention of the power transmission and transformation project must ensure that the three constraints are met at the same time, which means that the active intervention of the power transmission and transformation project under the fault state is completed.
Citation Information
Patent Citations
Full-station capacitive equipment online monitoring method and system based on intelligent group association
CN117134507A
Power grid equipment operation state monitoring method based on multi-modal data joint representation and dynamic weight learning
CN117172413A
Electric power data large model construction method and system
CN117520599A
Power distribution management method and system based on power flow and stability analysis
CN117559445A
Power equipment state monitoring method and system based on multi-source data fusion
CN117874467A
