Power system monitoring method and device, computer equipment, storage medium and computer program product

Abstract

The application relates to a power system monitoring method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring electrical quantity data, environment data and video image data of a power device in a power system to be modeled; performing preprocessing, feature extraction processing and summation processing on the electrical quantity data, the environment data and the video image data respectively to obtain a target feature vector of the power device; inputting the target feature vector into a trained device state prediction model to obtain target state information corresponding to the power device; determining visual feature information corresponding to the power device according to the target state information; constructing an initial three-dimensional model of the power system, and adjusting the initial three-dimensional model according to the visual feature information corresponding to the power device to obtain a target three-dimensional model of the power system; and monitoring the power system through the target three-dimensional model. The method can improve the monitoring accuracy of the power system.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a power system monitoring method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] Currently, in order to ensure the operational stability of the power system, accurate monitoring of the power system is of paramount importance.

[0003] In traditional technologies, two-dimensional interfaces are generally used to monitor power systems. However, this method is not intuitive enough to show the spatial relationships and real-time changes between power equipment in the power system, resulting in low accuracy of power system monitoring. Summary of the Invention

[0004] Therefore, it is necessary to provide a power system monitoring method, device, computer equipment, computer-readable storage medium, and computer program product that can improve the monitoring accuracy of power systems in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a power system monitoring method, including:

[0006] Obtain equipment data of power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment;

[0007] The electrical quantity data, the environmental data, and the video image data are preprocessed respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0008] Feature extraction processing is performed on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data respectively to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data;

[0009] Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector;

[0010] Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment.

[0011] The target feature vector is input into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0012] Based on the target state information, the visual feature information corresponding to the power equipment is determined;

[0013] An initial three-dimensional model of the power system is constructed, and the initial three-dimensional model is adjusted according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system.

[0014] The power system is monitored and processed using the target 3D model.

[0015] In one embodiment, acquiring the device data of the power equipment in the power system to be modeled includes:

[0016] Obtain the current application scenario corresponding to the power equipment in the power system to be modeled;

[0017] Based on the current application scenario, the correspondence between the application scenario and the data acquisition frequency is queried to obtain the data acquisition frequency corresponding to the current application scenario, which is used as the target data acquisition frequency for the power equipment.

[0018] The device data is acquired based on the target data acquisition frequency.

[0019] In one embodiment, determining the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector includes:

[0020] The electrical quantity data, the environmental data, and the video image data are respectively input into the trained importance prediction model to obtain the first importance corresponding to the electrical quantity data, the second importance corresponding to the environmental data, and the third importance corresponding to the video image data;

[0021] Based on the first importance, the second importance, and the third importance, the first initial weight corresponding to the first feature vector, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector are determined respectively.

[0022] The first initial weight, the second initial weight, and the third initial weight are normalized to obtain the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

[0023] In one embodiment, constructing the initial three-dimensional model of the power system includes:

[0024] Obtain the wiring diagram of the power system;

[0025] Based on the wiring diagram, the topology information of the power system is determined;

[0026] The shape and location information of the power equipment are obtained, and an initial three-dimensional model of the power system is constructed based on the shape and location information of the power equipment and the topology information of the power system.

[0027] In one embodiment, the step of performing feature extraction processing on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data includes:

[0028] The preprocessed electrical quantity data is used as the main data, and the preprocessed environmental data and the preprocessed video image data are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the first feature vector.

[0029] The preprocessed environmental data is used as the main data, and the preprocessed electrical quantity data and the preprocessed video image data are used as auxiliary data. They are input into the feature extraction model for feature extraction processing to obtain the second feature vector.

[0030] The preprocessed video image data is used as the main data, and the preprocessed electrical quantity data and the preprocessed environmental data are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the third feature vector.

[0031] In one embodiment, the trained device state prediction model is obtained by training in the following manner:

[0032] Acquire sample equipment data of sample power equipment in the sample power system; the sample equipment data includes at least sample electrical quantity data, sample environmental data, and sample video image data of the sample power equipment.

[0033] The sample electrical quantity data, the sample environmental data, and the sample video image data are preprocessed respectively to obtain preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data.

[0034] Feature extraction processing is performed on the preprocessed sample electrical quantity data, the preprocessed sample environmental data, and the preprocessed sample video image data respectively to obtain a first sample feature vector corresponding to the preprocessed sample electrical quantity data, a second sample feature vector corresponding to the preprocessed sample environmental data, and a third sample feature vector corresponding to the preprocessed sample video image data.

[0035] Determine the first target sample weight corresponding to the first sample feature vector, the second target sample weight corresponding to the second sample feature vector, and the third target sample weight corresponding to the third sample feature vector;

[0036] Based on the first target sample weight, the second target sample weight, and the third target sample weight, the first sample feature vector, the second sample feature vector, and the third sample feature vector are summed to obtain the target sample feature vector of the sample power equipment.

[0037] The target sample feature vector is input into the equipment state prediction model to be trained to obtain the predicted state information corresponding to the sample power equipment.

[0038] Obtain the actual state information corresponding to the sample power equipment, and iteratively train the equipment state prediction model to be trained based on the difference between the predicted state information and the actual state information to obtain the trained equipment state prediction model.

[0039] Secondly, this application also provides a power system monitoring device, comprising:

[0040] The data acquisition module is used to acquire equipment data of the power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment;

[0041] The data processing module is used to preprocess the electrical quantity data, the environmental data and the video image data respectively to obtain preprocessed electrical quantity data, preprocessed environmental data and preprocessed video image data;

[0042] The feature extraction module is used to perform feature extraction processing on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data respectively, to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data;

[0043] The weight determination module is used to determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector;

[0044] The vector summation module is used to sum the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain the target feature vector of the power equipment.

[0045] The state prediction module is used to input the target feature vector into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0046] The information determination module is used to determine the visual feature information corresponding to the power equipment based on the target state information;

[0047] The model processing module is used to construct an initial three-dimensional model of the power system and adjust the initial three-dimensional model according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system.

[0048] The system monitoring module is used to monitor and process the power system using the target 3D model.

[0049] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0050] Obtain equipment data of power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment;

[0051] The electrical quantity data, the environmental data, and the video image data are preprocessed respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0052] Feature extraction processing is performed on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data respectively to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data;

[0053] Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector;

[0054] Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment.

[0055] The target feature vector is input into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0056] Based on the target state information, the visual feature information corresponding to the power equipment is determined;

[0057] An initial three-dimensional model of the power system is constructed, and the initial three-dimensional model is adjusted according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system.

[0058] The power system is monitored and processed using the target 3D model.

[0059] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0060] Obtain equipment data of power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment;

[0061] The electrical quantity data, the environmental data, and the video image data are preprocessed respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0062] Feature extraction processing is performed on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data respectively to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data;

[0063] Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector;

[0064] Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment.

[0065] The target feature vector is input into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0066] Based on the target state information, the visual feature information corresponding to the power equipment is determined;

[0067] An initial three-dimensional model of the power system is constructed, and the initial three-dimensional model is adjusted according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system.

[0068] The power system is monitored and processed using the target 3D model.

[0069] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0070] Obtain equipment data of power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment;

[0071] The electrical quantity data, the environmental data, and the video image data are preprocessed respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0072] Feature extraction processing is performed on the preprocessed electrical quantity data, the preprocessed environmental data, and the preprocessed video image data respectively to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data;

[0073] Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector;

[0074] Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment.

[0075] The target feature vector is input into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0076] Based on the target state information, the visual feature information corresponding to the power equipment is determined;

[0077] An initial three-dimensional model of the power system is constructed, and the initial three-dimensional model is adjusted according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system.

[0078] The power system is monitored and processed using the target 3D model.

[0079] The aforementioned power system monitoring method, device, computer equipment, storage medium, and computer program product first acquire electrical quantity data, environmental data, and video image data of the power equipment in the power system to be modeled, all of which are used as equipment data of the power equipment in the power system to be modeled. The electrical quantity data, environmental data, and video image data are then preprocessed to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data. Feature extraction processing is then performed on the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data. The first feature vector is then used to determine the... The system first assigns a first target weight, a second target weight corresponding to a second feature vector, and a third target weight corresponding to a third feature vector. Then, based on these weights, the first, second, and third feature vectors are summed to obtain the target feature vector of the power equipment. This target feature vector is then input into the trained equipment state prediction model to obtain the target state information of the power equipment. Next, based on the target state information, the visual feature information corresponding to the power equipment is determined, and an initial three-dimensional model of the power system is constructed. Based on the visual feature information of the power equipment, the initial three-dimensional model is adjusted to obtain the target three-dimensional model of the power system. Finally, the power system is monitored using the target three-dimensional model. In this way, during the monitoring of the power system, through a series of processes such as preprocessing, feature extraction, and model processing of various equipment data of the power equipment in the power system to be modeled, the target state information corresponding to the power equipment can be accurately obtained. This allows for a more accurate determination of the visual feature information of the power equipment. Combined with the initial 3D model of the power system, the target 3D model of the power system can be obtained more accurately, which is beneficial to improving the monitoring accuracy of the power system. Moreover, by using a 3D model to monitor the power system, this method avoids the shortcomings of using a 2D interface monitoring method, which makes it difficult to intuitively display the spatial relationships and real-time changes between power equipment in the power system, resulting in low monitoring accuracy. This further improves the monitoring accuracy of the power system. Attached Figure Description

[0080] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0081] Figure 1 This is a flowchart illustrating a power system monitoring method in one embodiment;

[0082] Figure 2 This is a flowchart illustrating a power system monitoring method in another embodiment;

[0083] Figure 3 This is a flowchart illustrating a power system visualization monitoring method based on a time series mapping model in one embodiment.

[0084] Figure 4 This is a structural block diagram of a power system monitoring device in one embodiment;

[0085] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0086] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0088] In one exemplary embodiment, such as Figure 1 As shown, a power system monitoring method is provided. This embodiment illustrates the method by applying it to a server. It is understood that this method can also be applied to a terminal, or to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smartphones, and tablets; the server can be a standalone server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0089] Step S101: Obtain equipment data of the power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment.

[0090] The power system is equipped with a variety of monitoring devices, such as SCADA (Supervisory Control and Data Acquisition) systems, PMU (Phasor Measurement Unit) devices, infrared thermometers, and video surveillance cameras.

[0091] Among them, power equipment includes power generation equipment (such as thermal power generation equipment and hydropower generation equipment), power transformation equipment (such as transformers and circuit breakers), power transmission equipment (such as transmission lines and substations), and power distribution equipment (such as distribution cabinets and distribution boxes).

[0092] The equipment data includes at least electrical quantity data of the power equipment, environmental data, and video image data.

[0093] The electrical quantities include voltage, current, and power. Voltage reflects the voltage level at different nodes in the power system; current is used to monitor the load on transmission lines or equipment; and power includes active and reactive power, used to analyze equipment energy efficiency and grid operational stability.

[0094] The environmental data includes temperature, humidity, and smoke concentration. Temperature and humidity reflect the operating environment of the equipment and help identify potential failures caused by deteriorating environmental conditions; smoke concentration helps identify early signs of equipment overheating or fire.

[0095] Among them, video image data is obtained from real-time images of monitoring cameras of key equipment (such as transformers and circuit breakers) to assist in judging equipment status and troubleshooting.

[0096] For example, the server collects electrical quantity data, environmental data, and video image data of the power equipment in the power system to be modeled in real time through monitoring equipment deployed on the power system to be modeled, and uses the electrical quantity data, environmental data, and video image data as equipment data of the power equipment in the power system to be modeled.

[0097] Step S102: Preprocess the electrical quantity data, environmental data, and video image data respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0098] Preprocessing includes data cleaning, data calibration, data standardization, and data synchronization.

[0099] Among them, the preprocessed electrical quantity data refers to the electrical quantity data after preprocessing.

[0100] Among them, preprocessed environmental data refers to environmental data after preprocessing.

[0101] Among them, preprocessed video image data refers to video image data after preprocessing.

[0102] For example, the server performs preprocessing on electrical quantity data, environmental data, and video image data, including data cleaning, data calibration, data standardization, and data synchronization, to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0103] Step S103: Perform feature extraction processing on the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data respectively to obtain the first feature vector corresponding to the preprocessed electrical quantity data, the second feature vector corresponding to the preprocessed environmental data, and the third feature vector corresponding to the preprocessed video image data.

[0104] The first feature vector refers to the feature vector corresponding to the preprocessed electrical quantity data.

[0105] The second feature vector refers to the feature vector corresponding to the preprocessed environmental data.

[0106] The third feature vector refers to the feature vector corresponding to the preprocessed video image data.

[0107] For example, the server inputs the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data into the feature extraction model. The feature extraction model performs feature extraction processing on the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data to obtain the first feature vector corresponding to the preprocessed electrical quantity data, the second feature vector corresponding to the preprocessed environmental data, and the third feature vector corresponding to the preprocessed video image data.

[0108] Step S104: Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

[0109] Here, the first target weight refers to the weight ultimately assigned to the first feature vector.

[0110] The second target weight refers to the weight ultimately assigned to the second feature vector.

[0111] The third target weight refers to the weight ultimately assigned to the third feature vector.

[0112] For example, the server inputs the first feature vector, the second feature vector, and the third feature vector into the attention mechanism model, and obtains the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector through the attention mechanism model.

[0113] Step S105: Based on the first target weight, the second target weight, and the third target weight, sum the first feature vector, the second feature vector, and the third feature vector to obtain the target feature vector of the power equipment.

[0114] The target feature vector refers to the feature vector obtained by summing the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight.

[0115] For example, the server performs verification processing on the first target weight, the second target weight, and the third target weight to obtain the verification result; if the verification result indicates that the first target weight, the second target weight, and the third target weight all meet the preset threshold, the server sums the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain the target feature vector of the power equipment.

[0116] Step S106: Input the target feature vector into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0117] Among them, the equipment state prediction model refers to a network model that can use the target feature vector of the power equipment to obtain the target state information of the power equipment, such as the convolutional neural network model and the recurrent neural network model.

[0118] Among them, target status information refers to the status information of power equipment, including normal operation status, overload status and fault status.

[0119] For example, the server inputs the target feature vector into the trained device state prediction model to obtain the predicted probability of the power equipment under each preset state information; then, the server selects the preset state information with the highest predicted probability from each preset state information as the target state information corresponding to the power equipment.

[0120] Step S107: Determine the visual feature information corresponding to the power equipment based on the target status information.

[0121] Visual feature information is used to represent the colors of electrical equipment in the 3D model, such as green, red, and gray. It should be noted that different target state information corresponds to different visual feature information. For example, normal operation corresponds to green, overload state corresponds to red, and fault state corresponds to gray.

[0122] For example, the server queries the correspondence between the target state information and the visual feature information based on the target state information, and obtains the visual feature information corresponding to the target state information as the visual feature information corresponding to the power equipment.

[0123] Step S108: Construct an initial three-dimensional model of the power system, and adjust the initial three-dimensional model according to the visual feature information of the power equipment to obtain the target three-dimensional model of the power system.

[0124] The initial 3D model is used to represent the initial 3D model of the power system.

[0125] The target 3D model is used to represent the final 3D model of the power system.

[0126] For example, in response to the command to build a 3D model of the power system, the server builds an initial 3D model of the power system; then, the server renders the initial 3D model according to the visual feature information of the power equipment to obtain the rendered initial 3D model, which serves as the target 3D model of the power system.

[0127] Step S109: Monitor the power system using the target 3D model.

[0128] For example, the server generates video information corresponding to the target 3D model based on the monitoring instructions for the power system; then, the server performs monitoring processing on the power system based on the video information corresponding to the target 3D model.

[0129] In the aforementioned power system monitoring method, electrical quantity data, environmental data, and video image data of the power equipment in the power system to be modeled are first acquired, all of which are used as equipment data of the power equipment in the power system to be modeled. The electrical quantity data, environmental data, and video image data are then preprocessed to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data, respectively. Feature extraction processing is then performed on the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data. The first target weight corresponding to the first feature vector, the second target weight, and the third target weight are then determined. The first feature vector corresponds to the second target weight, and the third feature vector corresponds to the third target weight. Then, based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment. The target feature vector is then input into the trained equipment state prediction model to obtain the target state information of the power equipment. Then, based on the target state information, the visual feature information of the power equipment is determined, and an initial three-dimensional model of the power system is constructed. Based on the visual feature information of the power equipment, the initial three-dimensional model is adjusted to obtain the target three-dimensional model of the power system. Finally, the power system is monitored using the target three-dimensional model. In this way, during the monitoring of the power system, through a series of processes such as preprocessing, feature extraction, and model processing of various equipment data of the power equipment in the power system to be modeled, the target state information corresponding to the power equipment can be accurately obtained. This allows for a more accurate determination of the visual feature information of the power equipment. Combined with the initial 3D model of the power system, the target 3D model of the power system can be obtained more accurately, which is beneficial to improving the monitoring accuracy of the power system. Moreover, by using a 3D model to monitor the power system, this method avoids the shortcomings of using a 2D interface monitoring method, which makes it difficult to intuitively display the spatial relationships and real-time changes between power equipment in the power system, resulting in low monitoring accuracy. This further improves the monitoring accuracy of the power system.

[0130] In an exemplary embodiment, step S101 above, obtaining equipment data of power equipment in the power system to be modeled, specifically includes the following: obtaining the current application scenario corresponding to the power equipment in the power system to be modeled; querying the correspondence between the application scenario and the data acquisition frequency based on the current application scenario to obtain the data acquisition frequency corresponding to the current application scenario, which is used as the target data acquisition frequency corresponding to the power equipment; and obtaining equipment data based on the target data acquisition frequency.

[0131] The current application scenario refers to the application scenario of the power equipment in the power system to be modeled at the current time. For example, wind turbine generators have application scenarios of stable power generation and strong wind warning.

[0132] The correspondence between application scenarios and data acquisition frequencies indicates the association between them. For example, in a stable power generation scenario, the data acquisition frequency for a wind turbine is once every 3 seconds; in a strong wind warning scenario, the data acquisition frequency is once per second.

[0133] The target data acquisition frequency refers to the data acquisition frequency corresponding to the power equipment.

[0134] For example, the server obtains the current application scenario corresponding to the power equipment in the power system to be modeled through the meteorological monitoring equipment installed in the power equipment in the power system to be modeled; then, the server queries the correspondence between the application scenario and the data acquisition frequency according to the current application scenario to obtain the data acquisition frequency corresponding to the current application scenario, and uses the data acquisition frequency as the target data acquisition frequency corresponding to the power equipment; according to the target data acquisition frequency, the server obtains the electrical quantity data, environmental data and video image data of the power equipment as the equipment data of the power equipment.

[0135] In this embodiment, by determining the current application scenario of the power equipment and then accurately querying the corresponding ideal data acquisition frequency, it is possible to ensure that the acquired data matches the actual business needs, thereby reducing unnecessary data acquisition and transmission, avoiding interference from redundant data, and improving data quality.

[0136] In an exemplary embodiment, step S104, which determines the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector, specifically includes the following: inputting electrical quantity data, environmental data, and video image data into the trained importance prediction model to obtain the first importance corresponding to the electrical quantity data, the second importance corresponding to the environmental data, and the third importance corresponding to the video image data; determining the first initial weight corresponding to the first feature vector, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector based on the first importance, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector; and normalizing the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

[0137] Among them, importance prediction models refer to network models used to determine the importance of data, such as random forest models.

[0138] Importance is used to indicate the degree of influence of the data.

[0139] The first importance level refers to the importance of the electrical quantity data.

[0140] The second importance refers to the importance of the environmental data.

[0141] The third importance refers to the importance of the video image data.

[0142] Here, the first initial weight refers to the weight initially assigned to the first feature vector.

[0143] The second initial weight refers to the weight initially assigned to the second feature vector.

[0144] The third initial weight refers to the weight initially assigned to the third feature vector.

[0145] For example, the server inputs electrical quantity data, environmental data, and video image data into the trained importance prediction model, respectively. Through the trained importance prediction model, the server obtains the first importance of the electrical quantity data, the second importance of the environmental data, and the third importance of the video image data. Next, the server queries the correspondence between importance and weight based on the first, second, and third importance, respectively, to obtain the first initial weight corresponding to the first feature vector, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector. Then, the server normalizes the first, second, and third initial weights to obtain the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector. For example, if the first, second, and third initial weights are 0.8, 0.6, and 0.6 respectively, after normalization, the obtained first target weight, second target weight, and third target weight are 0.4, 0.3, and 0.3 respectively.

[0146] In this embodiment, the importance prediction model, once trained, can accurately measure the criticality of electrical quantities, environmental data, and video image data, thereby accurately determining the corresponding initial weights. Combined with normalization processing, the corresponding target weights can be determined more accurately, providing an accurate data foundation for subsequent analysis.

[0147] In an exemplary embodiment, step S108, which constructs an initial three-dimensional model of the power system, specifically includes the following: obtaining a wiring diagram of the power system; determining the topology information of the power system based on the wiring diagram; obtaining the shape and location information of the power equipment, and constructing an initial three-dimensional model of the power system based on the shape and location information of the power equipment and the topology information of the power system.

[0148] Wiring diagrams are used to represent the connection relationships, electrical paths, and mutual coordination methods of various electrical devices in a power system.

[0149] Topology information is used to represent the connection relationships and network structure of various power devices in a power system.

[0150] Among them, shape information is used to represent the external outline of each power device in the power system.

[0151] Location information is used to represent the geographical location of each power device in the power system.

[0152] For example, the server obtains the identification information of the power system and retrieves the wiring diagram of the power system from the database based on the identification information. Then, the server parses the wiring diagram of the power system to obtain parsed information and extracts the topology information of the power system from the parsed information. Next, the server obtains the image information of the power equipment and extracts the shape information of the power equipment from the image information. Then, the server uses a global positioning system to determine the location information of the power equipment. Finally, the server constructs an initial three-dimensional model of the power system based on the shape information and location information of the power equipment and the topology information of the power system.

[0153] In this embodiment, topology information is derived from the actual wiring diagram of the power system, and then a three-dimensional model is constructed by combining the shape and location information of the equipment. This can highly restore the actual physical layout of the power system and thus present a virtual scene that is almost identical to the site, avoiding the situation where traditional two-dimensional drawings cannot intuitively show spatial relationships.

[0154] In an exemplary embodiment, step S103 above, which involves performing feature extraction processing on the preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data to obtain a first feature vector corresponding to the preprocessed electrical quantity data, a second feature vector corresponding to the preprocessed environmental data, and a third feature vector corresponding to the preprocessed video image data, specifically includes the following: using the preprocessed electrical quantity data as the primary data and the preprocessed environmental data and preprocessed video image data as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a first feature vector; using the preprocessed environmental data as the primary data and the preprocessed electrical quantity data and preprocessed video image data as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a second feature vector; and using the preprocessed video image data as the primary data and the preprocessed electrical quantity data and preprocessed environmental data as auxiliary data, inputting them into a feature extraction model for feature extraction processing to obtain a third feature vector.

[0155] Among them, the main data can refer to the data with a large weight.

[0156] Auxiliary data can refer to data with smaller weights.

[0157] Among them, feature extraction model refers to network model that can perform feature extraction processing, such as transformer model.

[0158] For example, the server uses preprocessed electrical quantity data as the primary data and preprocessed environmental data and preprocessed video image data as auxiliary data, and inputs them into a feature extraction model for feature extraction processing to obtain a feature vector corresponding to the preprocessed electrical quantity data, which is used as the first feature vector. Next, the server uses preprocessed environmental data as the primary data and preprocessed electrical quantity data and preprocessed video image data as auxiliary data, and inputs them into a feature extraction model for feature extraction processing to obtain a feature vector corresponding to the preprocessed environmental data, which is used as the second feature vector. Then, the server uses preprocessed video image data as the primary data and preprocessed electrical quantity data and preprocessed environmental data as auxiliary data, and inputs them into a feature extraction model for feature extraction processing to obtain a feature vector corresponding to the preprocessed video image data, which is used as the third feature vector.

[0159] In this embodiment, by using different types of data as the main data and the remaining data as auxiliary data, corresponding feature extraction processing is performed, thereby deeply mining key features from various dimensions, making the first feature vector, second feature vector, and third feature vector more accurate, and providing a foundation for subsequent data processing.

[0160] In an exemplary embodiment, the power system monitoring method provided in this application further includes a training step for a trained equipment state prediction model, specifically including the following: acquiring sample equipment data of sample power equipment in a sample power system; the sample equipment data includes at least sample electrical quantity data, sample environmental data, and sample video image data of the sample power equipment; preprocessing the sample electrical quantity data, sample environmental data, and sample video image data respectively to obtain preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data; performing feature extraction processing on the preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data respectively to obtain a first sample feature vector corresponding to the preprocessed sample electrical quantity data, a second sample feature vector corresponding to the preprocessed sample environmental data, and... The third sample feature vector corresponding to the preprocessed sample video image data is obtained; the first target sample weight, the second target sample weight, and the third target sample weight corresponding to the first and second sample feature vectors are determined; based on the first, second, and third target sample weights, the first, second, and third sample feature vectors are summed to obtain the target sample feature vector of the sample power equipment; the target sample feature vector is input into the equipment state prediction model to be trained to obtain the predicted state information corresponding to the sample power equipment; the actual state information corresponding to the sample power equipment is obtained, and based on the difference between the predicted state information and the actual state information, the equipment state prediction model to be trained is iteratively trained to obtain the trained equipment state prediction model.

[0161] The sample power system refers to the power system used to train the equipment state prediction model to be trained.

[0162] Among them, sample power equipment refers to the power equipment in the sample power system.

[0163] The sample equipment data includes at least sample electrical quantity data, sample environmental data, and sample video image data of the sample power equipment.

[0164] Among them, the sample electrical quantity data refers to the electrical quantity data of the sample power equipment.

[0165] Among them, the sample environmental data refers to the environmental data of the sample power equipment.

[0166] Among them, sample video image data refers to video image data of sample power equipment.

[0167] Among them, the preprocessed sample electrical quantity data refers to the sample electrical quantity data after preprocessing.

[0168] Among them, preprocessed sample environment data refers to sample environment data after preprocessing.

[0169] Among them, preprocessed sample video image data refers to sample video image data after preprocessing.

[0170] The first sample feature vector refers to the feature vector corresponding to the preprocessed sample electrical quantity data.

[0171] The second sample feature vector refers to the feature vector corresponding to the preprocessed sample environment data.

[0172] The third sample feature vector refers to the feature vector corresponding to the preprocessed sample video image data.

[0173] The first target sample weight refers to the final weight assigned to the feature vector of the first sample.

[0174] The second target sample weight refers to the final weight assigned to the feature vector of the second sample.

[0175] The third target sample weight refers to the final weight assigned to the feature vector of the third sample.

[0176] The target sample feature vector refers to the feature vector obtained by summing the first sample feature vector, the second sample feature vector, and the third sample feature vector based on the first target sample weight, the second target sample weight, and the third target sample weight.

[0177] The predicted state information corresponding to the sample power equipment refers to the predicted value of the state information corresponding to the sample power equipment.

[0178] The actual state information corresponding to the sample power equipment refers to the actual value of the state information corresponding to the sample power equipment.

[0179] For example, in response to a model training instruction for a device state prediction model to be trained, the server retrieves sample electrical quantity data, sample environmental data, and sample video image data of sample power equipment in a sample power system from a database. Next, the server preprocesses the sample electrical quantity data, sample environmental data, and sample video image data to obtain preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data, respectively. Then, the server performs feature extraction processing on the preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data to obtain a first sample feature vector corresponding to the preprocessed sample electrical quantity data, a second sample feature vector corresponding to the preprocessed sample environmental data, and a third sample feature vector corresponding to the preprocessed sample video image data. Finally, the server determines the first target sample weight corresponding to the first sample feature vector, the second target sample weight corresponding to the second sample feature vector, and the third sample feature vector. The server calculates the corresponding third target sample weights. Then, based on the first, second, and third target sample weights, it sums the first, second, and third sample feature vectors to obtain the target sample feature vector of the sample power equipment. Next, the server inputs the target sample feature vector into the equipment state prediction model to be trained to obtain the predicted state information corresponding to the sample power equipment. Then, the server retrieves the actual state information corresponding to the sample power equipment from the database and obtains the loss value based on the difference between the predicted state information and the actual state information. Next, the server adjusts the model parameters of the equipment state prediction model to be trained based on the loss value. Then, the server retrains the equipment state prediction model with adjusted model parameters until the loss value obtained by the trained equipment state prediction model is less than the loss value threshold. At this point, training stops, and the trained equipment state prediction model is taken as the completed equipment state prediction model.

[0180] In this embodiment, by pre-training the equipment state prediction model, it is convenient to predict the target state information of the power equipment after obtaining the target feature vector of the power equipment in practical applications. Moreover, the equipment state prediction model receives new data in each iteration, and performs internal model improvement and optimization, which makes it easier to make predictions more effectively and improves the prediction accuracy of the equipment state prediction model.

[0181] In one exemplary embodiment, such as Figure 2 As shown, another power system monitoring method is provided. Taking the application of this method on the server side as an example, the method includes the following steps:

[0182] Step S201: Obtain the current application scenario corresponding to the power equipment in the power system to be modeled; based on the current application scenario, query the correspondence between the application scenario and the data acquisition frequency to obtain the data acquisition frequency corresponding to the current application scenario, which is used as the target data acquisition frequency corresponding to the power equipment.

[0183] Step S202: Obtain equipment data according to the target data acquisition frequency: the equipment data includes at least electrical quantity data of the power equipment, environmental data and video image data.

[0184] Step S203: Preprocess the electrical quantity data, environmental data, and video image data respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data.

[0185] Step S204: The preprocessed electrical quantity data is used as the main data, and the preprocessed environmental data and preprocessed video image data are used as auxiliary data. The data are input into the feature extraction model for feature extraction processing to obtain the first feature vector.

[0186] Step S205: The preprocessed environmental data is used as the main data, and the preprocessed electrical quantity data and preprocessed video image data are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the second feature vector.

[0187] Step S206: The preprocessed video image data is used as the main data, and the preprocessed electrical quantity data and preprocessed environmental data are used as auxiliary data. These are input into the feature extraction model for feature extraction processing to obtain the third feature vector.

[0188] Step S207: Input the electrical quantity data, environmental data, and video image data into the trained importance prediction model to obtain the first importance of the electrical quantity data, the second importance of the environmental data, and the third importance of the video image data.

[0189] Step S208: Determine the first initial weight corresponding to the first feature vector, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector based on the first importance, the second importance, and the third importance, respectively.

[0190] Step S209: Normalize the first initial weight, the second initial weight, and the third initial weight to obtain the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

[0191] Step S210: Based on the first target weight, the second target weight, and the third target weight, sum the first feature vector, the second feature vector, and the third feature vector to obtain the target feature vector of the power equipment.

[0192] Step S211: Input the target feature vector into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0193] Step S212: Determine the visual feature information corresponding to the power equipment based on the target status information.

[0194] Step S213: Obtain the wiring diagram of the power system; determine the topology information of the power system based on the wiring diagram; obtain the shape and location information of the power equipment, and construct the initial three-dimensional model of the power system based on the shape and location information of the power equipment and the topology information of the power system.

[0195] Step S214: Adjust the initial 3D model according to the visual feature information of the power equipment to obtain the target 3D model of the power system.

[0196] Step S215: Monitor the power system using the target 3D model.

[0197] In the aforementioned power system monitoring method, during the monitoring process, a series of processes, including preprocessing, feature extraction, and model processing of various equipment data of the power equipment in the power system to be modeled, can accurately obtain the target state information corresponding to the power equipment. This allows for a more accurate determination of the visual feature information corresponding to the power equipment. Combined with the initial 3D model of the power system, a more accurate target 3D model of the power system can be obtained, which is beneficial to improving the monitoring accuracy of the power system. Moreover, by using a 3D model to monitor the power system, this method avoids the shortcomings of using a 2D interface monitoring method, which makes it difficult to intuitively display the spatial relationships and real-time changes between power equipment in the power system, resulting in low monitoring accuracy. This further improves the monitoring accuracy of the power system.

[0198] In an exemplary embodiment, to more clearly illustrate the power system monitoring method provided in this application, the following detailed description uses a specific embodiment. In one embodiment, as... Figure 3As shown, this application also provides a power system visualization monitoring method based on a time series mapping model. In the process of monitoring the power system, real-time operational data, including electrical quantity data, environmental data, and video images, is first collected from monitoring equipment deployed in the power system. Then, the collected multi-source data undergoes preprocessing, including data cleaning, data calibration, and data synchronization, to ensure data accuracy and consistency. Next, a three-dimensional model of the power system is constructed based on the geographical wiring diagram and equipment layout diagram. Finally, a time series mapping model is used to map the fused comprehensive dataset onto the three-dimensional model, thereby achieving a three-dimensional visualization of dynamic data. Specifically, it includes the following:

[0199] Step 1: Data Acquisition. Real-time operational data, including electrical quantity data, environmental data, and video images, is collected from monitoring equipment deployed within the power system.

[0200] Step two, data preprocessing. Preprocessing is performed on the collected multi-source data, including data cleaning, data calibration, and data synchronization, to ensure data accuracy and consistency.

[0201] Step 3: 3D Modeling. Based on the geographical wiring diagram and equipment layout diagram of the power system, a 3D model of the power system is constructed. The 3D model contains information such as the spatial location, connection relationship, size and shape of the power equipment, and can realistically reflect the physical structure of the power system.

[0202] Step four, data mapping and visualization. A time series mapping model is used to map the fused integrated dataset onto a 3D model, thereby achieving a 3D visualization of the dynamic data.

[0203] Furthermore, step one specifically includes:

[0204] Real-time operational data is collected from various monitoring devices deployed in the power system (such as SCADA systems, PMU devices, infrared thermometers, video surveillance cameras, etc.). The data that can be collected includes, but is not limited to, the following categories:

[0205] (1) Electrical quantity data:

[0206] Voltage: Reflects the voltage level at different nodes in a power system.

[0207] Current: Monitors the load status of power transmission lines or equipment.

[0208] Power: Includes active power and reactive power, used to analyze the energy efficiency of equipment and the operational stability of the power grid.

[0209] (2) Environmental data:

[0210] Temperature and humidity: These reflect the operating environment of the equipment and help identify potential failures caused by deteriorating environmental conditions.

[0211] Smoke concentration: An early sign of overheating or fire in auxiliary identification equipment.

[0212] (3) Video image data:

[0213] Real-time images are captured from monitoring cameras of critical equipment (such as transformers and circuit breakers) to assist in assessing equipment status and troubleshooting.

[0214] It should be noted that the data acquisition frequency of each monitoring device can be optimized according to the application scenario (e.g., PMU devices sample 50 times per second, SCADA devices sample once per second).

[0215] Furthermore, step two specifically includes:

[0216] The collected data often contains noise, missing values, or out-of-sync timestamps, requiring preprocessing to ensure the accuracy of subsequent analysis. Specific preprocessing steps include:

[0217] (1) Data cleaning:

[0218] Abnormal data is removed or marked based on threshold rules or anomaly detection algorithms, and duplicate data and data that are outside the reasonable range (such as abnormally high or negative voltage values) are deleted.

[0219] Use interpolation or fitting methods to fill in missing data.

[0220] (2) Data calibration and standardization:

[0221] Calibration: Standardize the units of measurement for multi-source data (e.g., standardize temperature units to degrees Celsius and voltage units to kilovolts).

[0222] Standardization: Normalizing data of different units and magnitudes to give them a consistent dimension.

[0223] (3) Data feature extraction:

[0224] Extract features from raw data to improve its expressive power:

[0225] Among them, electrical quantity characteristics:

[0226] First-order difference: reflects the rate of change of electrical quantities.

[0227] Δx(t)=x(t)-x(t-Δt), formula (2)

[0228] Fluctuation characteristics: Calculate the variance within a short time window.

[0229] Among them, environmental quantity characteristics:

[0230] Sliding window average: Represents short-term trends.

[0231] Extreme value detection: Record the maximum and minimum values ​​of temperature and humidity.

[0232] Among them, video features:

[0233] Image processing algorithms are used to extract features such as brightness and edge density from video frames.

[0234] (4) Data synchronization:

[0235] Data from different devices is aligned based on timestamps to ensure that all data sources are merged on the same time base.

[0236] Since different data sources may have different sampling frequencies and timestamps, synchronization in both time and space is required.

[0237] Time synchronization involves using interpolation or alignment methods to align the data with a unified time reference. For high-frequency data such as PMU data, direct sampling can be used; for low-frequency data such as environmental data, linear interpolation can be used.

[0238] Spatial synchronization refers to the ability of data acquisition devices distributed in different locations to map their spatial information onto a unified power system topology using coordinate mapping methods.

[0239] Furthermore, step (4) specifically includes:

[0240] The collected data from multiple data sources are processed and used as the time series data source for the time series data mapping model:

[0241] X(t) = [X1(t), X2(t), ..., X n (t)],Equation (3)

[0242] Where X i (t) is the i-th eigenvalue at time t.

[0243] The real-time data provided by each sensor or monitoring device can form a time series. For example:

[0244] X1(t): Voltage time series, representing the voltage value at time t.

[0245] X2(t): Current time series, representing the current value at time t.

[0246] X3(t): Temperature time series, representing the temperature value at time t.

[0247] These data will be determined based on the actual monitoring data collected.

[0248] Furthermore, step three specifically includes:

[0249] Based on the equipment layout and wiring diagram of the power system, a 3D model is constructed to show the physical structure and connection relationships of the system:

[0250] (1) Model elements:

[0251] Simulate the actual shape of the equipment (such as transformers and high-voltage circuit breakers) and its spatial location.

[0252] Construct the route and topology of the power grid.

[0253] (2) Dynamic updates:

[0254] Use real-time data to dynamically adjust the state in the model, such as the color, brightness, and transparency of the device.

[0255] (3) Model optimization:

[0256] Lightweight modeling technology is used to reduce computational load and improve display performance.

[0257] Adding background maps and geographic information makes the 3D model more realistic.

[0258] Introducing a layered display function (such as displaying only specific areas or types of devices) improves the operability of the system.

[0259] Furthermore, step four specifically includes:

[0260] (1) Multidimensional data mapping:

[0261] Multidimensional data mapping is performed in a 3D model to achieve dynamic visualization.

[0262] By performing time series analysis on electrical quantity data (such as voltage, current, power, etc.) and environmental data (such as temperature, humidity, smoke concentration, etc.), a time series mapping function is established:

[0263]

[0264] Among them, a i X is the weighting coefficient. i (t) represents the time series of the i-th data source, where t is the time variable and n is the number of data sources.

[0265] This mapping function converts time-series information from various data sources into a unified integrated time series, thereby dynamically adjusting the device status in the 3D model.

[0266] The composite data f(t) is the result obtained through weighted summation, reflecting the overall situation of all input data sources. In 3D visualization, this value will be used to control the state of the device.

[0267] Electrical quantity data: A comprehensive value calculated based on parameters such as voltage and current to determine whether the equipment is in a normal, overloaded, or faulty state.

[0268] Environmental data: Environmental parameters such as temperature and humidity affect the operating status of the equipment and may require adjustments to the appearance of the equipment (such as color change or transparency).

[0269] Among them, a i The weighting coefficients determine the degree of influence of each data source on the overall mapping result f(t). If voltage and current are the main monitoring factors, higher values ​​can be set for the weighting coefficients a1 and a2 for voltage and current; if environmental data (such as temperature and humidity) have a relatively small impact on the status of power equipment, lower values ​​can be set for the weighting coefficient a3 for temperature and humidity.

[0270] Weighting coefficient a i This can be determined using the following methods:

[0271] Empirical value: Based on the analysis of historical data, the importance of different data sources to the system's operating status is estimated.

[0272] Data analysis: Statistical methods (such as correlation analysis, regression analysis, etc.) are used to calculate the degree of influence of each data source on the target variable (such as equipment status, system security) and obtain the weight coefficients.

[0273] Expert knowledge: The weighting coefficients are adjusted by power system experts or engineers based on practical experience.

[0274] Here, n refers to the number of data sources, which is the total number of data sources in the model. The specific number depends on the number of devices deployed in the power system. For example, there may be multiple sensor data such as voltage, current, temperature, and humidity, with each sensor serving as a data source i.

[0275] For example, suppose there are three data sources: voltage, current, and temperature.

[0276] X1(t): Voltage time series, representing the voltage value at time t.

[0277] X2(t): Current time series, representing the current value at time t.

[0278] X3(t): Temperature time series, representing the temperature value at time t.

[0279] To construct a comprehensive mapping model, we can assume:

[0280] Voltage (X1(t)) and current (X2(t)) are more important to the equipment state, so they are given higher weighting coefficients, such as a1 = 0.4 and a2 = 0.4.

[0281] Temperature (X3(t)) has a relatively small impact on the equipment status, so it is assigned a low weighting coefficient, such as a3 = 0.2.

[0282] Therefore, the comprehensive mapping function f(t) can be expressed as:

[0283] f(t) = 0.4·X1(t) + 0.4·X 2 (t)+0.2·X3(t), Equation (4)

[0284] In this formula:

[0285] X1(t), X2(t), and X3(t) are data collected from the sensors in real time.

[0286] The comprehensive value f(t) at each time point can be used to adjust the status of electrical equipment in the 3D model (e.g., to display the health status of the equipment through color or brightness changes). For example, if the value deviates little from the standard value, the equipment is displayed in green, indicating that the equipment is operating normally; if the value deviates significantly from the standard value, the equipment is displayed in red, indicating overload or failure.

[0287] (2) Dynamic mapping of 3D models:

[0288] Based on the output of the aforementioned time-series mapping function, the visual characteristics of each electrical device in the 3D model, such as color, brightness, and transparency, are dynamically adjusted. The color or brightness of the device corresponds to its electrical quantity data, for example:

[0289] Normal operating status: Green;

[0290] Overload status: Red;

[0291] Fault status: Gray.

[0292] At the same time, environmental data (such as temperature and humidity) are overlaid onto the 3D model through color layers, allowing monitoring personnel to observe both the operating status of the power system and the surrounding environmental conditions simultaneously.

[0293] In the above embodiments, during the monitoring of the power system, a series of processes, including preprocessing, feature extraction, and model processing of various equipment data of the power equipment in the power system to be modeled, can accurately obtain the target state information corresponding to the power equipment. This allows for a more accurate determination of the visual feature information corresponding to the power equipment. Combined with the initial three-dimensional model of the power system, a more accurate target three-dimensional model of the power system can be obtained, which is beneficial to improving the monitoring accuracy of the power system. Moreover, by using a three-dimensional model to monitor the power system, this method avoids the shortcomings of using a two-dimensional interface monitoring method, which makes it difficult to intuitively display the spatial relationships and real-time changes between power equipment in the power system, resulting in low monitoring accuracy. This, in turn, improves the monitoring accuracy of the power system. Simultaneously, a time-series mapping model is introduced to perform spatiotemporal correlation analysis on real-time data from multiple data sources (electrical quantities, environmental data, etc.), mapping them into a comprehensive dynamic dataset. This model enables dynamic and accurate 3D visualization of the operating status of power equipment, environmental changes, and video surveillance, providing more precise monitoring information. Based on real-time collected multi-dimensional data such as electrical quantities and environmental data, and through methods such as dynamic weight adjustment and time-series analysis, the time-series mapping model not only reflects the health status of equipment in real time but also automatically adapts and adjusts the display effect according to changes in system status. This allows the system to react quickly to changes in the operating status of power equipment and dynamically adjust the display parameters in the 3D model, such as... The system monitors equipment color, brightness, and other parameters to provide more accurate and timely feedback to monitoring personnel. By introducing a time-series mapping model, it performs time-series analysis on various types of power system data, integrating electrical quantity data with environmental data, video surveillance data, and other multi-source information to form a dynamic, real-time comprehensive mapping result, providing more accurate dynamic updates for 3D visualization. Through 3D visualization and multi-dimensional data integration, it not only displays the status of power equipment but also the equipment's operating environment and video surveillance information, providing comprehensive system status awareness. Through real-time data feedback and anomaly detection, using the time-series mapping model combined with anomaly detection rules and early warning mechanisms, it ensures that the system can respond to changes in the status of power equipment in real time, promptly detecting and warning of potential faults.

[0294] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0295] Based on the same inventive concept, this application also provides a power system monitoring device for implementing the power system monitoring method described above. The solution provided by this device is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more power system monitoring device embodiments provided below can be found in the limitations of the power system monitoring method described above, and will not be repeated here.

[0296] In one exemplary embodiment, such as Figure 4 As shown, a power system monitoring device is provided, comprising: a data acquisition module 401, a data processing module 402, a feature extraction module 403, a weight determination module 404, a vector summation module 405, a state prediction module 406, an information determination module 407, a model processing module 408, and a system monitoring module 409, wherein:

[0297] The data acquisition module 401 is used to acquire equipment data of the power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment.

[0298] The data processing module 402 is used to preprocess electrical quantity data, environmental data and video image data respectively to obtain preprocessed electrical quantity data, preprocessed environmental data and preprocessed video image data.

[0299] The feature extraction module 403 is used to perform feature extraction processing on the preprocessed electrical quantity data, preprocessed environmental data and preprocessed video image data respectively, to obtain the first feature vector corresponding to the preprocessed electrical quantity data, the second feature vector corresponding to the preprocessed environmental data and the third feature vector corresponding to the preprocessed video image data.

[0300] The weight determination module 404 is used to determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

[0301] The vector summation module 405 is used to sum the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain the target feature vector of the power equipment.

[0302] The state prediction module 406 is used to input the target feature vector into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment.

[0303] The information determination module 407 is used to determine the visual feature information corresponding to the power equipment based on the target status information.

[0304] The model processing module 408 is used to construct an initial three-dimensional model of the power system and adjust the initial three-dimensional model according to the visual feature information of the power equipment to obtain the target three-dimensional model of the power system.

[0305] The system monitoring module 409 is used to monitor and process the power system through the target three-dimensional model.

[0306] In an exemplary embodiment, the data acquisition module 401 is further configured to acquire the current application scenario corresponding to the power equipment in the power system to be modeled; query the correspondence between the application scenario and the data acquisition frequency according to the current application scenario to obtain the data acquisition frequency corresponding to the current application scenario as the target data acquisition frequency corresponding to the power equipment; and acquire equipment data according to the target data acquisition frequency.

[0307] In an exemplary embodiment, the weight determination module 404 is further configured to input electrical quantity data, environmental data, and video image data into the trained importance prediction model to obtain a first importance corresponding to the electrical quantity data, a second importance corresponding to the environmental data, and a third importance corresponding to the video image data; determine a first initial weight corresponding to a first feature vector, a second initial weight corresponding to a second feature vector, and a third initial weight corresponding to a third feature vector based on the first importance, the second importance, and the third importance, respectively; and normalize the first initial weight, the second initial weight, and the third initial weight to obtain a first target weight corresponding to a first feature vector, a second target weight corresponding to a second feature vector, and a third target weight corresponding to a third feature vector.

[0308] In an exemplary embodiment, the model processing module 408 is further configured to acquire a wiring diagram of the power system; determine the topology information of the power system based on the wiring diagram; acquire the shape information and location information of the power equipment; and construct an initial three-dimensional model of the power system based on the shape information and location information of the power equipment and the topology information of the power system.

[0309] In an exemplary embodiment, the feature extraction module 403 is further configured to input preprocessed electrical quantity data as primary data, and preprocessed environmental data and preprocessed video image data as auxiliary data into the feature extraction model for feature extraction processing to obtain a first feature vector; input preprocessed environmental data as primary data, and preprocessed electrical quantity data and preprocessed video image data as auxiliary data into the feature extraction model for feature extraction processing to obtain a second feature vector; and input preprocessed video image data as primary data, and preprocessed electrical quantity data and preprocessed environmental data as auxiliary data into the feature extraction model for feature extraction processing to obtain a third feature vector.

[0310] In an exemplary embodiment, the power system monitoring device further includes a model training module for acquiring sample equipment data of sample power equipment in a sample power system. The sample equipment data includes at least sample electrical quantity data, sample environmental data, and sample video image data of the sample power equipment. The sample electrical quantity data, sample environmental data, and sample video image data are preprocessed to obtain preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data. Feature extraction processing is then performed on the preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data to obtain a first sample feature vector corresponding to the preprocessed sample electrical quantity data, a second sample feature vector corresponding to the preprocessed sample environmental data, and preprocessed sample video image data. The corresponding third sample feature vector; determine the first target sample weight corresponding to the first sample feature vector, the second target sample weight corresponding to the second sample feature vector, and the third target sample weight corresponding to the third sample feature vector; based on the first target sample weight, the second target sample weight, and the third target sample weight, sum the first sample feature vector, the second sample feature vector, and the third sample feature vector to obtain the target sample feature vector of the sample power equipment; input the target sample feature vector into the equipment state prediction model to be trained to obtain the predicted state information corresponding to the sample power equipment; obtain the actual state information corresponding to the sample power equipment, and based on the difference between the predicted state information and the actual state information, iteratively train the equipment state prediction model to be trained to obtain the trained equipment state prediction model.

[0311] Each module in the aforementioned power system monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0312] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores electrical quantity data, environmental data, and video image data, etc. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a power system monitoring method.

[0313] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0314] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0315] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0316] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0317] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0318] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0319] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A power system monitoring method, characterized in that, The method includes: Obtain equipment data of power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment; The electrical quantity data, the environmental data, and the video image data are preprocessed respectively to obtain preprocessed electrical quantity data, preprocessed environmental data, and preprocessed video image data. Using the preprocessed electrical quantity data as the primary data and the preprocessed environmental data and preprocessed video image data as auxiliary data, the data are input into a feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the preprocessed electrical quantity data. Using the preprocessed environmental data as the primary data and the preprocessed electrical quantity data and preprocessed video image data as auxiliary data, the data are input into the feature extraction model for feature extraction processing to obtain a second feature vector corresponding to the preprocessed environmental data. Using the preprocessed video image data as the primary data and the preprocessed electrical quantity data and preprocessed environmental data as auxiliary data, the data are input into the feature extraction model for feature extraction processing to obtain a third feature vector corresponding to the preprocessed video image data. Determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector; Based on the first target weight, the second target weight, and the third target weight, the first feature vector, the second feature vector, and the third feature vector are summed to obtain the target feature vector of the power equipment. The target feature vector is input into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment. Based on the target state information, the correspondence between the state information and the visual feature information is queried to obtain the visual feature information corresponding to the target state information, which is used as the visual feature information corresponding to the power equipment. An initial three-dimensional model of the power system is constructed, and the initial three-dimensional model is adjusted according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system. The power system is monitored and processed using the target 3D model.

2. The method according to claim 1, characterized in that, The acquisition of equipment data for power equipment in the power system to be modeled includes: Obtain the current application scenario corresponding to the power equipment in the power system to be modeled; Based on the current application scenario, the correspondence between the application scenario and the data acquisition frequency is queried to obtain the data acquisition frequency corresponding to the current application scenario, which is used as the target data acquisition frequency for the power equipment. The device data is acquired based on the target data acquisition frequency.

3. The method according to claim 1, characterized in that, Determining the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector includes: The electrical quantity data, the environmental data, and the video image data are respectively input into the trained importance prediction model to obtain the first importance corresponding to the electrical quantity data, the second importance corresponding to the environmental data, and the third importance corresponding to the video image data; Based on the first importance, the second importance, and the third importance, the first initial weight corresponding to the first feature vector, the second initial weight corresponding to the second feature vector, and the third initial weight corresponding to the third feature vector are determined respectively. The first initial weight, the second initial weight, and the third initial weight are normalized to obtain the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector.

4. The method according to claim 1, characterized in that, The construction of the initial three-dimensional model of the power system includes: Obtain the wiring diagram of the power system; Based on the wiring diagram, the topology information of the power system is determined; The shape and location information of the power equipment are obtained, and an initial three-dimensional model of the power system is constructed based on the shape and location information of the power equipment and the topology information of the power system.

5. The method according to any one of claims 1 to 4, characterized in that, The trained device state prediction model was obtained through the following method: Acquire sample equipment data of sample power equipment in the sample power system; the sample equipment data includes at least sample electrical quantity data, sample environmental data, and sample video image data of the sample power equipment. The sample electrical quantity data, the sample environmental data, and the sample video image data are preprocessed respectively to obtain preprocessed sample electrical quantity data, preprocessed sample environmental data, and preprocessed sample video image data. Feature extraction processing is performed on the preprocessed sample electrical quantity data, the preprocessed sample environmental data, and the preprocessed sample video image data respectively to obtain a first sample feature vector corresponding to the preprocessed sample electrical quantity data, a second sample feature vector corresponding to the preprocessed sample environmental data, and a third sample feature vector corresponding to the preprocessed sample video image data. Determine the first target sample weight corresponding to the first sample feature vector, the second target sample weight corresponding to the second sample feature vector, and the third target sample weight corresponding to the third sample feature vector; Based on the first target sample weight, the second target sample weight, and the third target sample weight, the first sample feature vector, the second sample feature vector, and the third sample feature vector are summed to obtain the target sample feature vector of the sample power equipment. The target sample feature vector is input into the equipment state prediction model to be trained to obtain the predicted state information corresponding to the sample power equipment. Obtain the actual state information corresponding to the sample power equipment, and iteratively train the equipment state prediction model to be trained based on the difference between the predicted state information and the actual state information to obtain the trained equipment state prediction model.

6. A power system monitoring device, characterized in that, The device includes: The data acquisition module is used to acquire equipment data of the power equipment in the power system to be modeled: the equipment data includes at least electrical quantity data, environmental data and video image data of the power equipment; The data processing module is used to preprocess the electrical quantity data, the environmental data and the video image data respectively to obtain preprocessed electrical quantity data, preprocessed environmental data and preprocessed video image data; The feature extraction module is used to input the preprocessed electrical quantity data as primary data, and the preprocessed environmental data and the preprocessed video image data as auxiliary data into the feature extraction model for feature extraction processing to obtain a first feature vector corresponding to the preprocessed electrical quantity data; to input the preprocessed environmental data as primary data, and the preprocessed electrical quantity data and the preprocessed video image data as auxiliary data into the feature extraction model for feature extraction processing to obtain a second feature vector corresponding to the preprocessed environmental data; and to input the preprocessed video image data as primary data, and the preprocessed electrical quantity data and the preprocessed environmental data as auxiliary data into the feature extraction model for feature extraction processing to obtain a third feature vector corresponding to the preprocessed video image data. The weight determination module is used to determine the first target weight corresponding to the first feature vector, the second target weight corresponding to the second feature vector, and the third target weight corresponding to the third feature vector; The vector summation module is used to sum the first feature vector, the second feature vector, and the third feature vector according to the first target weight, the second target weight, and the third target weight to obtain the target feature vector of the power equipment. The state prediction module is used to input the target feature vector into the trained equipment state prediction model to obtain the target state information corresponding to the power equipment. The information determination module is used to query the correspondence between the target state information and the visual feature information based on the target state information, and obtain the visual feature information corresponding to the target state information as the visual feature information corresponding to the power equipment. The model processing module is used to construct an initial three-dimensional model of the power system and adjust the initial three-dimensional model according to the visual feature information corresponding to the power equipment to obtain the target three-dimensional model of the power system. The system monitoring module is used to monitor and process the power system using the target 3D model.

7. The apparatus according to claim 6, characterized in that, The data acquisition module is also used to acquire the current application scenario corresponding to the power equipment in the power system to be modeled; based on the current application scenario, query the correspondence between the application scenario and the data acquisition frequency to obtain the data acquisition frequency corresponding to the current application scenario, which is used as the target data acquisition frequency corresponding to the power equipment. The device data is acquired based on the target data acquisition frequency.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images