Operation and maintenance data visualization method and system based on smart power grid

Abstract

The invention relates to the technical field of data visualization, and provides an operation and maintenance data visualization method and system based on a smart power grid, which are used for improving the efficiency and the intelligent degree of power grid operation and maintenance visualization so as to improve the timeliness of power grid operation and maintenance decision management, and the method comprises the following steps: collecting a multi-source heterogeneous operation and maintenance data set in the smart power grid in real time; performing cross-modal cleaning and time alignment processing on the operation and maintenance data set to generate a preprocessed data set; executing dynamic feature fusion and correlation analysis on the preprocessed data set to generate an equipment state feature set and an equipment-environment interaction feature set; based on the equipment state feature set and the equipment-environment interaction feature set, generating an interactive visualization element set through a multi-dimensional visualization strategy; performing dynamic rendering and layout optimization on the interactive visual element set, and outputting a power grid operation and maintenance visual interface updated in real time; the power grid operation and maintenance visual interface is configured with a user operation priority response mechanism used for processing interaction conflicts.

Description

Technical Field

[0001] The present invention belongs to the field of data visualization technology, and specifically relates to a method and system for visualizing operation and maintenance data based on a smart grid. Background Art

[0002] With the rapid development of smart grids, grid data is becoming increasingly heterogeneous and multi-source. Grid data visualization technology has emerged to facilitate this transformation. Its goal is to present complex data in an intuitive graphical format, helping operations and maintenance personnel better understand grid operations. This visualization approach can improve operation and maintenance efficiency and identify potential problems promptly.

[0003] However, existing power grid data visualization technology has many flaws: in terms of data processing, there is a lack of effective cleaning and time alignment mechanisms for multi-source heterogeneous operation and maintenance data, resulting in uneven data quality and affecting the accuracy of subsequent analysis; in feature extraction, it fails to fully explore the deep relationship between equipment status and environmental interaction, making it difficult to fully reflect the actual situation of the power grid; the existing visualization process interaction method is single, and the visualization elements lack dynamicity and real-time update capabilities, which cannot meet the complex and changing operational needs of operation and maintenance personnel.

[0004] In view of this, how to improve the efficiency and intelligence of grid operation and maintenance visualization to enhance the timeliness of grid operation and maintenance decision-making management is a technical problem that needs to be overcome at present. Summary of the Invention

[0005] The present invention provides a method and system for visualizing operation and maintenance data based on a smart grid, which is used to improve the efficiency and intelligence of grid operation and maintenance visualization, thereby improving the timeliness of grid operation and maintenance decision-making management.

[0006] In a first aspect, an embodiment of the present invention provides an operation and maintenance data visualization method based on a smart grid, which is applied to an operation and maintenance data visualization system, and the method includes: real-time collection of multi-source heterogeneous operation and maintenance data sets in the smart grid; cross-modal cleaning and time alignment processing of the operation and maintenance data sets to generate a preprocessed data set; dynamic feature fusion and correlation analysis are performed on the preprocessed data set to generate a device status feature set and a device-environment interaction feature set; based on the device status feature set and the device-environment interaction feature set, an interactive visualization element set is generated through a multidimensional visualization strategy; dynamic rendering and layout optimization are performed on the interactive visualization element set to output a real-time updated power grid operation and maintenance visualization interface; wherein, the power grid operation and maintenance visualization interface is configured with a user operation priority response mechanism for handling interaction conflicts.

[0007] In a second aspect, an embodiment of the present invention provides an operation and maintenance data visualization system, which includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above method.

[0008] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, which includes a computer program. When the computer program runs on an operation and maintenance data visualization system, the computer program is used to enable the operation and maintenance data visualization system to execute the steps of the above method.

[0009] In the implementation of the present invention, by collecting the multi-source heterogeneous operation and maintenance data set of the smart grid in real time, all kinds of relevant information can be fully obtained; cross-modal cleaning and time alignment processing can effectively improve the data quality and consistency, making the pre-processed data set more usable; dynamic feature fusion and association analysis can be used to deeply explore the potential relationship of the data, thereby generating a feature set that accurately reflects the device status and device-environment interaction; further based on the multi-dimensional visualization strategy, an interactive visualization element set is generated, which can provide users with a variety of interaction methods; the final dynamic rendering and layout optimization can ensure the real-time update of the visualization interface and a reasonable layout. In addition, configuring the user operation priority response mechanism can ensure that user operations can be responded to in a complex interactive scenario in an orderly manner. In this way, the efficiency and intelligence of the grid operation and maintenance visualization can be improved, thereby improving the timeliness of the grid operation and maintenance decision-making management. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A flowchart of a method for visualizing operation and maintenance data based on a smart grid provided by an embodiment of the present invention.

[0011] Figure 2 A schematic diagram of the structure of an operation and maintenance data visualization system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the technical solutions of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments described in the present invention document without making any creative efforts shall fall within the scope of protection of the technical solutions of the present invention.

[0013] See also Figure 1 , which is a method for visualizing operation and maintenance data based on a smart grid provided in an embodiment of the present invention. The method can be applied to an operation and maintenance data visualization system, and the specific process is as S110-S150.

[0014] S110: Real-time collection of multi-source heterogeneous operation and maintenance data sets in smart grids.

[0015] In the embodiment of the present invention, the smart grid includes many different types of power equipment. To fully understand the operation status of the grid, it is necessary to collect multi-source heterogeneous operation and maintenance data sets in real time. For example, data can be collected from multiple power equipment distributed in various areas.

[0016] In terms of current time series data, taking a large substation as an example, it has multiple transmission lines, each of which has corresponding current data. These current data exist in the form of time series. For example, within one minute, the recorded current values ​​are 50A, 52A, 51A, etc., forming the initial current time series data.

[0017] Optionally, the voltage data segment is obtained from voltage monitoring devices connected to different nodes. These devices record voltage values ​​at regular intervals. For example, the voltage values ​​recorded at a certain moment are 220V, 218V, etc., which constitute the voltage data segment.

[0018] In addition, temperature gradient data is collected through temperature sensors installed in key parts of the equipment. The sensors monitor temperature changes in real time and calculate the temperature gradient based on the positional relationship. For example, sensors are arranged at different positions on the casing of a transformer, and the temperature gradient data is calculated after collecting the temperatures at different positions.

[0019] Optionally, the meteorological related data comes from surrounding meteorological monitoring stations, including information such as temperature, humidity, and wind speed. This information also has a timestamp, for example, at a certain moment, the temperature is recorded as 25°C, the humidity is 60%, and the wind speed is 3m / s.

[0020] The above-mentioned current time series data, voltage data segments, temperature gradient data and meteorological correlation data together constitute a multi-source heterogeneous operation and maintenance data set.

[0021] S120: Perform cross-modal cleaning and time alignment processing on the operation and maintenance data set to generate a pre-processed data set.

[0022] In an embodiment of the present invention, to ensure the accuracy and availability of data, the collected operation and maintenance data set needs to be cross-modal cleansing and time alignment processing. Optionally, the cross-modal cleansing and time alignment processing of the operation and maintenance data set to generate a pre-processed data set includes:

[0023] S121: Divide the current time series data of the operation and maintenance data set into initial data segments according to a preset time granularity, and perform linear interpolation based on adjacent data trends on missing initial data segments to generate interpolated current data segments.

[0024] Taking the aforementioned large substation as an example, the preset time granularity is set to every minute. The collected current time series data is divided into every minute to form initial data segments. If the current data within a certain minute is missing, such as the data at the 10th minute is missing, linear interpolation is required based on the trend of adjacent data. For example, the current value at the 9th minute is 50A, and the current value at the 11th minute is 52A. Since the current change usually has a certain continuity, it can be considered that the current changes linearly within these two minutes. Then, through linear interpolation calculation, the current value at the 10th minute can be calculated as (50+52)÷2=51A, thereby generating the interpolated current data segment, which ensures the integrity of the current data.

[0025] S122: Detecting abnormal voltage points exceeding a preset safety threshold in the voltage data segment of the operation and maintenance data set, and replacing the abnormal voltage points with historical voltage averages of corresponding devices to generate corrected voltage data segments.

[0026] For the substation's voltage data segment, the preset safety threshold is set between 210V and 230V. If, at a certain moment in the collected voltage data, the voltage value detected is 240V, exceeding the preset safety threshold and representing an abnormal voltage point, the system queries the voltage data for the device over the past month and calculates its historical voltage average. For example, if the historical voltage average is 225V, the abnormal voltage point of 240V is replaced with 225V, generating a corrected voltage data segment that better reflects the normal operation of the device.

[0027] S123: performing sliding window mean filtering on the temperature gradient data of the operation and maintenance data set, identifying abnormal fluctuation intervals in which the temperature change rate exceeds a threshold within the window, and performing Gaussian filtering to reduce noise to generate reduced-noise temperature data segments.

[0028] Taking the temperature gradient data of the transformer in the substation as an example, the sliding window size is set to 10 time points, that is, every 10 consecutive temperature gradient data are a window. The mean is calculated in each window. For example, if the temperature gradient data in a certain window is 0.5℃ / m, 0.6℃ / m, 0.4℃ / m, etc., the mean is calculated to be (0.5+0.6+0.4)÷3=0.5℃ / m. Then the temperature change rate in the window is calculated. If the temperature change rate in a certain window exceeds the preset threshold of 0.2℃ / m / min, the window is identified as an abnormal fluctuation interval. For these abnormal fluctuation intervals, Gaussian filtering is used for noise reduction. Gaussian filtering is a weighted average processing of the data based on the distribution characteristics of the Gaussian function, so that the abnormal fluctuation data is closer to the normal fluctuation range, thereby generating a noise-reduced temperature data segment.

[0029] S124: Extract the timestamp information of the meteorological-related data of the operation and maintenance data set, and synchronize the timestamp information of the meteorological-related data with the timestamps of the interpolated current data segment, the corrected voltage data segment, and the noise-reduced temperature data segment to generate a synchronized environmental impact factor sequence.

[0030] It is understood that meteorological data is timestamped. For example, if a certain meteorological monitoring data is recorded at 10:00:00, the current, voltage, and temperature data also have corresponding timestamps. The timestamp of the meteorological data is compared with the timestamps of the interpolated current data segment, the corrected voltage data segment, and the noise-reduced temperature data segment. If the current data is recorded at 10:00:05, the voltage data is recorded at 10:00:03, and the temperature data is recorded at 10:00:07, the timestamps of these data are synchronized by adjusting or selecting the closest time point. For example, all are aligned to the time point of 10:00:05, and the synchronized meteorological data (temperature, humidity, wind speed, etc.) is combined with the current, voltage, and temperature data to form a synchronized sequence of environmental impact factors, ensuring the temporal consistency of different types of data.

[0031] S125: performing unified time coding on the interpolated current data segment, the corrected voltage data segment, the noise-reduced temperature data segment, and the synchronized environmental impact factor sequence to generate the preprocessed data set.

[0032] In this step, a unified time coding method is used for the interpolated current data segment, the corrected voltage data segment, the denoised temperature data segment, and the synchronized environmental impact factor sequence. For example, in seconds, the time corresponding to each data point is converted into the number of seconds calculated from a fixed starting time (such as 0:00:00 on the same day). For example, if a data point is recorded at 10:01:00, the number of seconds converted is 10×3600+1×60+0=36060 seconds. All data are time-coded as described above, and all the encoded data are integrated to generate a preprocessed data set, providing a unified and standardized data foundation for subsequent analysis and processing.

[0033] S130: Performing dynamic feature fusion and association analysis on the pre-processed data set to generate a device state feature set and a device-environment interaction feature set.

[0034] In an embodiment of the present invention, in order to gain a deeper understanding of the device state and the interaction between the device and the environment, it is necessary to perform dynamic feature fusion and correlation analysis on the preprocessed data set. Optionally, performing dynamic feature fusion and correlation analysis on the preprocessed data set to generate a device state feature set and a device-environment interaction feature set includes:

[0035] S131: performing multi-scale wavelet decomposition on the interpolated current data segment to generate a fluctuation component and a trend component, and calculating the energy density ratio of each component.

[0036] For the current data segment after interpolation, taking the current data segment generated above as an example, a multi-scale wavelet decomposition method is used for processing. Wavelet decomposition can decompose the signal into components of different frequencies. The embodiment of the present invention decomposes the current data into a fluctuation component and a trend component. For example, after the current data is decomposed, the fluctuation component reflects the short-term rapid change of the current, and the trend component reflects the long-term change trend of the current. Subsequently, the energy density of the fluctuation component is calculated. For example, the value of the fluctuation component in a time period is 5A, 6A, 4A, etc. The energy density is calculated by adding the squares of each value and dividing it by the length of the time period, such as (52+62+4 2 ) ÷ 3. Similarly, the energy density of the trend component is calculated, and then the ratio of the energy density of the fluctuation component to the energy density of the trend component is calculated. This ratio serves as a characteristic value that reflects the relative relationship between the fluctuation and trend in the current data.

[0037] S132: performing density clustering on the corrected voltage data segment to generate abnormal voltage point distribution density, and calculating a regional cumulative abnormality index based on the clustering result.

[0038] For example, clustering parameters can be set to classify voltage data according to its distribution density. If the voltage data in one area is concentrated around 220V, while in another area, it is concentrated around 215V, density clustering can be used to separate the voltage data from these different areas. The number of abnormal voltage points (voltage points outside the normal range) in each cluster area is calculated and then divided by the total number of voltage data points in the area to obtain the abnormal voltage point distribution density. For example, if a cluster area has 100 voltage data points and 10 of them are abnormal, the abnormal voltage point distribution density is 10 ÷ 100 = 0.1. Based on the abnormal voltage point distribution density of each cluster area, the regional cumulative anomaly index is calculated. For example, if the substation has three cluster areas with abnormal voltage point distribution densities of 0.1, 0.05, and 0.15, respectively, the regional cumulative anomaly index is calculated as (0.1 + 0.05 + 0.15) ÷ 3 = 0.1, which reflects the overall degree of voltage anomaly within the entire area.

[0039] S133: performing slope analysis on the temperature data segment after noise reduction to extract the temperature rising rate, and counting the number of times the temperature fluctuation exceeds a threshold within a unit time to generate the abnormal fluctuation frequency.

[0040] Optionally, the denoised temperature data segment is analyzed. Taking the temperature data of the transformer as an example, the temperature difference between adjacent time points is calculated and then divided by the time interval to obtain the temperature rise rate. For example, within 10 minutes, the temperature rises from 30°C to 35°C, and the time interval is 10 minutes, that is, 600 seconds. The temperature rise rate is (35-30) ÷ 600 = 0.0083°C / s. The temperature fluctuation threshold is set to 1°C, and the number of times the temperature fluctuates by more than 1°C per unit time (such as one hour) is counted. For another example, within one hour, if the temperature fluctuates by more than 1°C five times, the frequency of abnormal fluctuations is 5 times / hour. These two characteristic values ​​reflect the rising trend and fluctuation of the temperature, respectively.

[0041] S134: Inputting the synchronized environmental impact factor sequence into a pre-trained environmental weight prediction model, and outputting a combination vector of temperature impact weight, humidity impact weight, and wind speed impact weight.

[0042] Optionally, the synchronized sequence of environmental impact factors (including information such as temperature, humidity, and wind speed) is input into a pre-trained environmental weight prediction model. This model is trained using a large amount of historical data and can predict the impact weights of temperature, humidity, and wind speed on device operation based on the input environmental data. For example, based on the current input environmental data, the model outputs a temperature impact weight of 0.6, a humidity impact weight of 0.2, and a wind speed impact weight of 0.2. These three weights form a combined vector [0.6, 0.2, 0.2], which is used to represent the degree of impact of environmental factors on device status.

[0043] S135: Feature stitching is performed on the energy density ratio, the abnormal voltage point distribution density, the regional cumulative abnormality index, the temperature rise rate and the combination vector to generate a device state feature set and a device-environment interaction feature set; wherein, the energy density ratio, the regional cumulative abnormality index and the temperature rise rate have been subjected to maximum and minimum normalization processing before feature stitching.

[0044] First, the energy density ratio, regional cumulative anomaly index, and temperature rise rate are normalized to their maximum and minimum values. Taking the energy density ratio as an example, its value range is between 0.1 and 0.9. Using the normalization formula (x-min) ÷ (max-min), it is mapped to the range between 0 and 1. For example, if the energy density ratio is 0.5, the normalization result is (0.5-0.1) ÷ (0.9-0.1) = 0.5. The same process is performed for the regional cumulative anomaly index and temperature rise rate. The normalized energy density ratio, abnormal voltage point distribution density, regional cumulative anomaly index, temperature rise rate, and combined vector are then concatenated. For example, these features are arranged in a certain order to form a multidimensional feature vector, such as [0.5, 0.1, 0.1, 0.0083, 0.6, 0.2, 0.2]. This feature vector forms part of the device status feature set and the device-environment interaction feature set. This integration of different types of features provides more comprehensive data support for subsequent visualization and analysis.

[0045] S140: Based on the device state feature set and the device-environment interaction feature set, generate an interactive visualization element set through a multi-dimensional visualization strategy.

[0046] In an embodiment of the present invention, in order to more intuitively display the device status and the interactive relationship between the device and the environment, a multi-dimensional visualization strategy is used to generate a set of interactive visualization elements based on the feature set generated above. Optionally, the multi-dimensional visualization strategy is used to generate a set of interactive visualization elements based on the device status feature set and the device-environment interaction feature set, including:

[0047] S141: Mapping the energy density ratio and the regional cumulative anomaly index to a three-dimensional visualization space using a multi-view projection strategy, wherein node size parameters of a dynamic topology graph are generated based on the energy density ratio, and node color ring gradient parameters are generated based on the regional cumulative anomaly index.

[0048] In a three-dimensional visualization space, for energy density ratios, for example, areas with higher energy density ratios have larger node sizes in the corresponding dynamic topology graphs; areas with lower energy density ratios have smaller node sizes. For example, the energy density ratio ranges from 0 to 1. When the energy density ratio is 0.8, it is mapped to a larger node size, such as a radius of 5 units; when the energy density ratio is 0.2, it is mapped to a smaller node size, such as a radius of 1 unit. For the regional cumulative anomaly index, a node color ring gradient parameter is generated based on its numerical value. If the regional cumulative anomaly index is high, the color ring color tends to be red; if it is low, the color ring color tends to be green. For example, when the regional cumulative anomaly index is 0.8, the color ring color is dark red; when the regional cumulative anomaly index is 0.2, the color ring color is light green. In this way, the energy density ratio and regional cumulative anomaly index are displayed in an intuitive graphical manner in a three-dimensional visualization space.

[0049] S142: Based on a layered mapping strategy, the temperature rise rate is mapped through a height field to generate a color block altitude parameter of a three-dimensional thermal map, and based on the abnormal fluctuation frequency, a color block pulsation parameter is generated through a transparency attenuation function.

[0050] For the temperature rise rate, taking a 3D heat map of a specific area as an example, the higher the temperature rise rate, the higher the corresponding color block altitude. For example, when the temperature rise rate is 0.01°C / s, the color block altitude is set to 10 units; when the temperature rise rate is 0.005°C / s, the color block altitude is set to 5 units. For the frequency of abnormal fluctuations, a transparency attenuation function is used to generate the color block pulsation parameters. For example, when the frequency of abnormal fluctuations is high, the color block transparency is low and the pulsation speed is fast; when the frequency of abnormal fluctuations is low, the color block transparency is high and the pulsation speed is slow. For example, if the frequency of abnormal fluctuations is 10 times / hour, the transparency attenuation function calculates the color block transparency to be 0.3 and the pulsation speed to be 3 beats per second; if the frequency of abnormal fluctuations is 2 times / hour, the transparency is 0.8 and the pulsation speed is 1 beat per second. In this way, through height field mapping and transparency attenuation function, the temperature rise rate and abnormal fluctuation frequency are displayed in the 3D heat map with different visual characteristics.

[0051] S143: Using a multi-dimensional vector fusion algorithm, the temperature influence weight, humidity influence weight, and wind speed influence weight in the combined vector are mapped to arrow length parameters, feather parameters, and inclination parameters of the meteorological vector, respectively.

[0052] Optionally, a multidimensional vector fusion algorithm is used to map the temperature, humidity, and wind speed influence weights in the combined vector. For example, the higher the temperature influence weight, the longer the arrow length of the meteorological vector. For example, when the temperature influence weight is 0.8, the arrow length is 10 units; when the temperature influence weight is 0.2, the arrow length is 2 units. The humidity influence weight corresponds to the feathering parameter. The higher the humidity influence weight, the more obvious the feathering effect. For example, when the humidity influence weight is 0.6, the feathering parameter is set to give the arrow edge a wider blurred effect; when the humidity influence weight is 0.2, the feathering effect is weaker. The wind speed influence weight corresponds to the inclination parameter. The higher the wind speed influence weight, the greater the arrow inclination angle. For example, when the wind speed influence weight is 0.7, the arrow inclination angle is 60°; when the wind speed influence weight is 0.3, the arrow inclination angle is 30°. In this way, the influence weight of environmental factors is intuitively displayed in the form of a meteorological vector.

[0053] S144: Establish a cross-view association mechanism to synchronize the spatial coordinates of the node size parameters and node color ring gradient parameters of the dynamic topology map, the color block altitude parameters and color block pulsation parameters of the three-dimensional heat map, and the arrow length parameters, feathering parameters and inclination parameters of the meteorological vector, to generate a set of interactive visualization elements with coordinate linkage.

[0054] Optionally, a cross-view association mechanism is established to ensure that elements between different views can be associated and interact with each other. For example, when the node size or color ring gradient parameters of a node in a dynamic topology map change due to a change in the energy density ratio or the regional cumulative anomaly index, the color block altitude parameters and color block pulsation parameters of the corresponding area in the three-dimensional thermal map will be adjusted accordingly through the synchronous alignment of spatial coordinates, and the parameters of the meteorological vector will also change synchronously according to the combined influence of environmental factors. For example, if the energy density ratio of a node in a dynamic topology map increases and the node size increases, the color block altitude parameters of the corresponding area in the associated three-dimensional thermal map will also increase, and the arrow length of the meteorological vector may become longer due to the change in the temperature influence weight, forming an interactive visualization element set with coordinate linkage. Users can gain a deeper understanding of the interaction between device status and environmental factors by operating and observing the linkage relationship between these elements.

[0055] S150: Dynamically rendering and optimizing the layout of the interactive visualization element set to output a real-time updated power grid operation and maintenance visualization interface; wherein the power grid operation and maintenance visualization interface is configured with a user operation priority response mechanism for handling interaction conflicts.

[0056] In an embodiment of the present invention, in order to provide users with a clear, smooth, and interactively friendly visualization interface, it is necessary to dynamically render and optimize the layout of the interactive visualization element set, and configure a user operation priority response mechanism. Optionally, the dynamic rendering and layout optimization of the interactive visualization element set to output a real-time updated power grid operation and maintenance visualization interface includes:

[0057] S151: Creating a topology view in a three-dimensional space projection coordinate system based on the node size parameters and node color ring gradient parameters of the dynamic topology graph in the interactive visualization element set.

[0058] In an embodiment of the present invention, a topological view that displays the connection relationship of power grid equipment is constructed as an example, and a power grid area containing multiple substations and transmission lines is used as an example. Each substation is represented by a node in the dynamic topology diagram. According to the previously determined node size parameters, for example, a certain important substation has a high energy density ratio, and the corresponding node size parameter is set to a radius of 10 units, while the node radius of some small substations may be 3 units. For the node color ring gradient parameter, if the cumulative anomaly index of a substation area is high, the color ring is displayed as dark red, such as the RGB value of the color ring is (255, 0, 0); if the anomaly index is low, the color ring is light green, and the RGB value is (0, 255, 0). In a three-dimensional projected coordinate system, these nodes are arranged according to their actual connection relationship in the power grid, and the transmission lines are connected to each node with lines. The thickness of the line can be set according to factors such as the current carrying capacity of the transmission line. For example, the line with high current carrying capacity is thicker, with a width of 5 units, and the line with low current carrying capacity is 2 units wide. This creates a topological view in a three-dimensional projection coordinate system that can intuitively display the connection relationship between power grid equipment and the relevant characteristics of each device.

[0059] S152: Generate a thermal map with a height field gradient by superimposing the color block altitude parameters and the color block pulsation parameters of the three-dimensional thermal map in the three-dimensional space projection coordinate system.

[0060] Taking the three-dimensional heat map of the transformer area as an example, a thermal map is generated by overlaying the previously determined color block altitude and pulsation parameters. For transformers at different locations, if a transformer has a faster temperature rise rate, its corresponding color block altitude parameter is higher, for example, 15 units, while a transformer with a slower temperature rise rate has an altitude of 5 units. Regarding the pulsation parameter, if a transformer has a high frequency of abnormal fluctuations, it will pulsate four times per second and have a transparency of 0.4; if a transformer has a low frequency of abnormal fluctuations, it will pulsate once per second and have a transparency of 0.8. In a three-dimensional projected coordinate system, these color blocks with different altitude and pulsation characteristics are overlaid and displayed according to the actual location of the transformer, forming a thermal map with an altitude field gradient. This map allows users to intuitively visualize the temperature changes of transformers at different locations. Areas with higher altitudes indicate faster temperature rises, while areas with more pronounced pulsation indicate larger temperature fluctuations, making it easier for operators to quickly locate areas of equipment with potential problems.

[0061] S153: Mapping the arrow length parameter, feather parameter, and inclination parameter of the meteorological vector to the three-dimensional space projection coordinate system to generate a dynamic vector field meteorological view.

[0062] Taking the meteorological conditions in the power grid region as an example, meteorological vector parameters are mapped into a 3D projected coordinate system to generate a meteorological view. For areas with a high temperature influence weight, such as a temperature influence weight of 0.7, the corresponding meteorological vector arrow length is set to 12 units. When the humidity influence weight is 0.5, the feathering parameter creates a moderate blurring effect on the arrow edge. When the wind speed influence weight is 0.6, the arrow inclination is 50°. In the 3D projected coordinate system, meteorological vectors with different lengths, feathering, and inclination characteristics are plotted based on meteorological data at different locations. Each meteorological vector represents the comprehensive meteorological impact at a specific location. Multiple meteorological vectors form a dynamic vector field meteorological view. This view allows users to understand the direction and extent of the impact of meteorological factors in different regions on power grid equipment. For example, a longer arrow indicates a greater temperature influence, while a larger inclination indicates a greater wind speed influence.

[0063] S154: constructing an adaptive layout matrix according to the size of the user terminal window, spatially arranging the topology view, thermal view, and meteorological view according to a preset division ratio, and establishing a coordinate mapping relationship among the three views.

[0064] In an embodiment of the present invention, the user terminal window size is 1920×1080 pixels. First, an adaptive layout matrix is ​​constructed, based on a preset partitioning ratio. For example, the topology view occupies 40% of the window width and 50% of the height; the thermal view occupies 30% of the window width and 40% of the height; and the meteorological view occupies 30% of the window width and 40% of the height. In this layout, the topology view is placed in the majority of the left side of the window, the thermal view in the upper right corner, and the meteorological view in the lower right corner. A coordinate mapping relationship is then established between the three views. For example, if the coordinates of a node in the topology view are (x1, y1, z1), the corresponding relative position coordinates (x2, y2, z2) and (x3, y3, z3) in the thermal and meteorological views can be determined through this coordinate mapping relationship. This allows users to easily view information from different aspects.

[0065] S155: When a focus operation of a node area in the topology view is detected, the color block altitude parameters of the corresponding spatial coordinates in the thermal view are synchronously adjusted based on the coordinate mapping relationship, and the feathering parameter transparency of the associated area vector in the meteorological view is increased.

[0066] For example, when the user clicks on a substation node in the topology view to focus, the system detects the operation. According to the coordinate mapping relationship established previously, the color block corresponding to the spatial coordinates in the thermal view is found. For example, the altitude parameter of the color block corresponding to the substation in the thermal view was originally 8 units, but it is now increased to 12 units to highlight the temperature changes in the area. At the same time, the vector of the associated area is found in the meteorological view, and the transparency of its feathering parameter is increased from 0.5 to 0.8. In this way, when the user focuses on a device in the topology view, he can intuitively see the enhanced display of temperature changes in the area where the device is located in the thermal view and a clearer display of the influence of related meteorological factors in the meteorological view, providing a more comprehensive information association display.

[0067] S156: Performing spatiotemporal interpolation calculation on the motion trajectory of the meteorological vector, generating trajectory smoothing parameters based on the real-time change rate of the wind speed influence weight, and performing dynamic rendering using a Bezier curve fitting algorithm.

[0068] It is understandable that the position and parameters of the meteorological vector change over time. First, a spatiotemporal interpolation calculation is performed on the trajectory of the meteorological vector. For example, within a certain time period, the meteorological vector moves from position A to position B. The spatiotemporal interpolation calculation can be used to obtain the approximate position of the vector at the intermediate moments. Based on the real-time rate of change of the wind speed influence weight, such as the wind speed influence weight changes from 0.4 to 0.6 within a certain time period, with a rate of change of 0.2 / unit time, a trajectory smoothing parameter is generated based on this rate of change. The motion trajectory of the meteorological vector is then dynamically rendered using a Bezier curve fitting algorithm. Bezier curves can make the motion trajectory of the vector smoother and more natural. For example, by fitting the starting point, control point, and end point of the meteorological vector using a Bezier curve, the vector presents a smooth curved trajectory during motion, rather than a rigid straight line, improving the visualization effect and user experience.

[0069] S157: Constructing an abnormal fluctuation propagation path in the thermal view, calculating a path confidence interval based on the temperature rise rate and the historical propagation pattern, and generating a gradient color band through transparency gradient mapping.

[0070] In the thermal visualization, the propagation path of abnormal temperature fluctuations in a transformer is constructed as an example. Based on the transformer's temperature rise rate (for example, a rate of 0.015°C / s), and combined with historical propagation patterns of abnormal fluctuations at similar temperature rise rates, data analysis and models are used to calculate the likely propagation path of the abnormal fluctuation. For example, according to historical data, when the temperature rise rate is between 0.01-0.02°C / s, the abnormal fluctuation typically propagates along a specific path to surrounding equipment. A confidence interval for this propagation path is calculated, for example, 80%. Then, a gradient color band is generated using transparency gradient mapping. High-confidence areas have lower transparency and darker colors, such as red at a transparency of 0.3. Low-confidence areas have higher transparency and lighter colors, such as light red at a transparency of 0.8. This allows the thermal visualization to visually identify the likely propagation direction and confidence level of the abnormal fluctuation.

[0071] S158: Detect the geometric collision relationship of each element in the dynamic topology map, three-dimensional heat map and meteorological view in real time. When the ratio of the intersection volume of the node bounding box of the dynamic topology map and the color block bounding box of the three-dimensional heat map to the volume of the smaller bounding box exceeds a preset percentage threshold, activate the spherical expansion algorithm to perform azimuth decoupling and spatial reorganization of the collision view.

[0072] For example, during real-time detection, the bounding box of a node in the dynamic topology map is set to a sphere with a radius of 8 units, and the bounding box of a color block in the three-dimensional heat map is set to a cuboid with a length, width, and height of 10, 8, and 6 units, respectively. Calculate their intersecting volume. For example, if the intersecting volume is 200 cubic units, and the volume of the smaller bounding box (cuboid) is 480 cubic units, the intersecting volume accounts for 200÷480≈41.7%. When the ratio exceeds a preset percentage threshold, such as 30%, the spherical expansion algorithm is activated. The algorithm first decouples the azimuth and displays the nodes and color blocks separately at different angles. Then, the space is reorganized, such as rearranging the nodes and color blocks in space to avoid visual overlap and confusion, so that users can clearly see each element without affecting the viewing and analysis of information.

[0073] In an optional embodiment, the method further includes:

[0074] S210: Monitoring a user's touch operation trajectory on the power grid operation and maintenance visualization interface, and extracting acceleration characteristics and a contact area change rate of the touch operation trajectory.

[0075] When a user interacts with the power grid operation and maintenance visualization interface using a touchscreen, the system begins monitoring the user's touch operation trajectory. For example, when a user slides their finger across the screen to view information in different areas, the system records the finger's position coordinates at each moment, forming a touch operation trajectory. For this trajectory, the system calculates its acceleration characteristics. For example, if a finger moves from position (x1, y1) to (x2, y2) over a period of time, with a time interval of t, the acceleration is calculated by calculating the ratio of the change in velocity to the time. For example, if the initial velocity is v1 and the velocity changes to v2 after time t, the acceleration a = (v2 - v1) / t. The contact area change rate is also calculated. When the finger first touches the screen, the contact area is S1. As the finger slides, the contact area changes, reaching S2 at a certain moment, with a time interval of Δt. The contact area change rate = (S2 - S1) / Δt. These characteristics are used for subsequent operation judgment and processing.

[0076] S220: Matching a preset view zoom instruction set according to the acceleration feature, and generating a hot zone focus weight parameter according to the contact area change rate.

[0077] The preset view scaling instruction set includes scaling operations corresponding to different acceleration ranges. For example, when the acceleration a is greater than a certain threshold a1, it corresponds to a view magnification operation; when the acceleration a is less than a certain threshold a2 (a2 < a1), it corresponds to a view reduction operation. For example, when the acceleration a = 0.5 (the unit is set according to the actual situation), by matching with the preset instruction set, it is determined as a view magnification operation. For the contact area change rate, when the contact area change rate is positive and large, it indicates that the user may be more concerned about the current contact area, and a higher hot zone focus weight parameter is generated. For example, when the contact area change rate is 0.2 (the unit is set according to the actual situation), according to the preset rules, the hot zone focus weight parameter is generated as 0.8, indicating that this area has a higher focus weight, and subsequent operations will pay more attention to this area.

[0078] S230: Based on the hot zone focus weight parameter, adjust the scaling ratio of the node size parameter of the dynamic topology map, and simultaneously increase the blinking frequency of the associated color block pulsation parameter in the three-dimensional thermal map.

[0079] According to the generated hot zone focus weight parameter, the hot zone focus weight parameter is 0.8. For the node size parameter of the dynamic topology map located in this hot zone, increase its scaling ratio. For example, the original node radius is 5 units, and now it is scaled to 7 units to make it more prominent in the topology map. At the same time, for the color block pulsation parameter associated with this hot zone in the three-dimensional thermal map, increase its blinking frequency. For example, the original color block pulsates 2 times per second, and now it is increased to 4 times per second. This can highlight the hot zone that the user is concerned about in different views, facilitating the user to more clearly view the device status information in this area.

[0080] S240: Input the adjusted node size parameter and color block pulsation parameter into the particle rendering module to generate a touch feedback particle flow, and superimpose it on the edge area of the power grid operation and maintenance visualization interface; among them, the scaling instruction of single-point touch is preferentially responded to, and when multi-point touch is detected, an operation type conflict arbitration mechanism is enabled.

[0081] The adjusted node size parameters and color block pulsation parameters are input into the particle rendering module. The particle rendering module generates a touch feedback particle stream based on these parameters. For example, as the node size increases and the color block pulsation frequency increases, more particles with denser density and more obvious flickering effects are generated. These particle streams are superimposed on the edge areas of the power grid operation and maintenance visualization interface, creating a visual feedback effect, letting users know that their operations are being responded to by the system. In terms of touch operation processing, single-point touch zoom commands are prioritized. When multi-touch is detected, such as when a user performs different operations with two fingers at the same time, an operation type conflict arbitration mechanism is activated. This mechanism uses preset rules, such as first determining the priority of the operation or merging operations based on similarity, to ensure that the system can correctly handle complex multi-touch operations and avoid display anomalies or functional confusion caused by operation conflicts.

[0082] In an optional embodiment, the method further includes:

[0083] S310: Analyze the regional cumulative anomaly index in the device status feature set in real time, and activate the anomaly tracing mode when the index exceeds a preset risk threshold.

[0084] The system continuously analyzes the regional cumulative anomaly index within the device status feature set in real time. For example, if the preset risk threshold is set at 0.6, and the regional cumulative anomaly index for a region is calculated to be 0.7, exceeding the preset risk threshold, the system automatically activates anomaly tracing mode. In this mode, the system conducts in-depth analysis of the cause of the regional equipment anomaly and the possible path of its spread, allowing operations and maintenance personnel to take timely action to prevent further escalation.

[0085] S320: extracting a correlation matrix between abnormal fluctuation frequency and temperature rise rate of the same equipment in the historical operation and maintenance data set in the abnormality tracing mode.

[0086] After activating the abnormality tracing mode, the system searches for data on the same equipment from the historical operation and maintenance data set. For example, for a transformer of a certain model, its operation and maintenance data for the past year is extracted to analyze the relationship between the frequency of abnormal fluctuations and the rate of temperature rise. By counting and analyzing these data, a correlation matrix is ​​constructed. For example, in different time periods, the frequency of abnormal fluctuations is 5 times / month, 3 times / month, etc., and the temperature rise rates are 0.005℃ / s, 0.01℃ / s, etc., and then these data are organized into a matrix form (also known as a correlation matrix). This correlation matrix can help analyze the potential connection between abnormal fluctuations and the rate of temperature rise, and provide a basis for subsequently determining the abnormal propagation path.

[0087] S330: Generate a probability density distribution map of the abnormal propagation path of the device according to the association matrix, and encode the probability density distribution map as a semi-transparent thermal overlay; wherein, if historical data is missing, use the average association matrix of similar devices as a default value.

[0088] Optionally, based on the constructed association matrix, a probability density distribution diagram of the abnormal propagation path of the equipment is generated through data analysis and modeling algorithms. For example, by analyzing the data in the association matrix, it is found that when the temperature rise rate reaches a certain value, abnormal fluctuations are more likely to propagate along certain specific lines. These propagation paths and corresponding probability densities are displayed in a graphical manner to form a probability density distribution diagram. The distribution diagram is then encoded as a semi-transparent thermal overlay so that it can be superimposed on a three-dimensional thermal map. If historical data is missing and the association matrix for the equipment cannot be constructed, the average association matrix of similar equipment is used as the default value. For example, for transformers of the same model produced by the same manufacturer, the average association matrix data of other similar transformers is used for subsequent analysis and processing to ensure that the abnormality tracing process can continue.

[0089] S340: Embed the semi-transparent thermal overlay layer into the area below the color block altitude parameter of the three-dimensional heat map through a depth buffer layered rendering strategy.

[0090] Optionally, the encoded semi-transparent thermal overlay is embedded in the three-dimensional thermal map using a depth buffer layered rendering strategy. The depth buffer can record the depth information of each pixel in three-dimensional space, and use this information to determine the display order of different layers. In an embodiment of the present invention, the semi-transparent thermal overlay is placed in the area below the color block altitude parameter of the three-dimensional thermal map. For example, when rendering a three-dimensional thermal map, the color block altitude information is rendered first, and then the semi-transparent thermal overlay is accurately drawn below the color block altitude based on the information in the depth buffer, so that when the user views the thermal map, he can see the temperature of the device and the probability distribution of the abnormal propagation path at the same time, providing a more intuitive information display for analyzing device anomalies.

[0091] In an optional embodiment, the method further includes:

[0092] S410: Continuously capture the time-series variation data of the arrow length parameter and the inclination parameter of the meteorological vector, and generate a dynamic attenuation curve of the wind speed influence weight.

[0093] The system continuously monitors the changes in the arrow length parameter and inclination parameter of the meteorological vector over time. For example, these two parameters of the meteorological vector are recorded every minute. For another example, within an hour, the arrow length parameter gradually decreases from 10 units to 8 units, and the inclination parameter changes from 45° to 30°. Based on these recorded data, with time as the horizontal axis and the wind speed impact weight (which can be calculated from the arrow length and inclination parameters through a certain algorithm, such as wind speed impact weight = arrow length × sin (inclination)) as the vertical axis, a dynamic attenuation curve of the wind speed impact weight is generated. This curve can intuitively show the changing trend of the wind speed impact weight over time, helping operation and maintenance personnel understand the dynamic process of the impact of meteorological factors on power grid equipment.

[0094] S420: Perform extreme point detection on the dynamic attenuation curve, extract abnormal time segments with sudden slope changes in the curve, and mark them as meteorological event trigger points.

[0095] The generated dynamic attenuation curve is analyzed to detect extreme points. For example, mathematical methods such as derivatives are used to find points where the slope of the curve is zero. These points may be maximum or minimum points. Attention is also paid to sections of the curve where the slope changes suddenly, that is, where the curve changes suddenly intensify or slow down. For example, at a certain moment, the slope of the curve suddenly changes from 0.2 to -0.5. This time segment is identified as an abnormal time segment and marked as a meteorological event trigger point. These trigger points may correspond to sudden changes in meteorological conditions, potentially affecting the operation of power grid equipment and requiring further attention and analysis.

[0096] S430: Reversely search the temperature impact weight of the corresponding moment in the synchronized environmental impact factor sequence according to the meteorological event trigger point.

[0097] After identifying the meteorological event trigger point, the temperature impact weight for that moment is searched in the synchronized environmental impact factor sequence based on the time corresponding to the trigger point. For example, if the meteorological event trigger point is 2:30 PM, the temperature impact weight recorded at that moment in the environmental impact factor sequence is 0.5. By obtaining this temperature impact weight, we can understand the extent to which temperature factors affect equipment operation when meteorological conditions change, providing data support for subsequent analysis of the comprehensive impact of meteorological events on equipment.

[0098] S440: performing normalized fusion calculation on the temperature influence weight and the wind speed influence weight, generating a meteorological event warning mark and inserting it into the end of the arrow of the dynamic vector field meteorological view; wherein, a time tolerance window is set to compensate for data delay.

[0099] In actual operation, the temperature influence weight and wind speed influence weight must first be normalized. The purpose of normalization is to adjust the two weight values ​​to a unified range to facilitate subsequent fusion calculations.

[0100] For the temperature impact weight, first determine its value range. For example, in a large amount of past data statistics, the minimum value of the temperature impact weight is 0.1 and the maximum is 0.9. For a specific temperature impact weight value currently obtained, such as 0.6, the normalization calculation process is: subtract the minimum value from this value, and then divide it by the difference between the maximum and minimum values. In other words, (0.6-0.1) ÷ (0.9-0.1) = 0.5 ÷ 0.8 = 0.625, thus obtaining the normalized temperature impact weight.

[0101] For the wind speed impact weight, we also need to first define its value range. Let's set the minimum wind speed impact weight to 0.2 and the maximum to 0.8. The current wind speed impact weight is 0.5. The normalized calculation is (0.5 - 0.2) ÷ (0.8 - 0.2) = 0.3 ÷ 0.6 = 0.5, which is the normalized wind speed impact weight.

[0102] Next, a fusion calculation is performed using a simple weighted average method. This embodiment of the present invention sets a fusion coefficient for the temperature impact weight, set to 0.6. The fusion coefficient for the wind speed impact weight is then 1-0.6=0.4. The fused weight is calculated by multiplying the normalized temperature impact weight by the fusion coefficient for the temperature impact weight, and then adding the normalized wind speed impact weight by the fusion coefficient for the wind speed impact weight. That is, the fused weight = normalized temperature impact weight × 0.6 + normalized wind speed impact weight × 0.4. Substituting the previously calculated normalized temperature impact weight of 0.625 and the normalized wind speed impact weight of 0.5, we obtain the fused weight = 0.625 × 0.6 + 0.5 × 0.4 = 0.375 + 0.2 = 0.575.

[0103] A weather event warning icon is generated based on the fused weight. Pre-set rules define that when the fused weight is greater than or equal to 0.7, a red warning icon is generated, indicating a high risk to the equipment. When the weight is between 0.4 and 0.7, a yellow warning icon is generated, indicating a certain risk requiring attention. When the weight is less than 0.4, a green normal icon is generated. Since the fused weight calculated above is 0.575, a yellow warning icon is generated.

[0104] During data processing, delays may occur in data collection and transmission, so a time tolerance window is set to compensate for data delays. For example, a time tolerance window of 5 minutes is set before and after. When a meteorological event trigger point is detected, the corresponding temperature impact weight is searched and the above fusion calculation is performed within a 5-minute period before and after the trigger point. This ensures that the generated alarm flag more accurately reflects the actual impact of the meteorological event on the equipment.

[0105] Finally, insert the generated meteorological event alarm identifier into the arrow end of the dynamic vector field meteorological view. This allows users to intuitively see the meteorological event alarm corresponding to each meteorological vector in the dynamic vector field meteorological view, allowing them to quickly understand the potential impact of meteorological factors on power grid equipment.

[0106] In an optional embodiment, the method further includes:

[0107] S510: Periodically read the color ring gradient parameters of the nodes in the interactive visualization element set, and count the occurrence frequency of the color ring gradient parameters of each node within a preset time window.

[0108] In an embodiment of the present invention, the system reads the node color ring gradient parameters in the interactive visualization element set according to a preset period. The period can be determined according to actual needs, for example, it is set to perform a reading operation every 15 minutes.

[0109] For example, consider a dynamic topology containing multiple nodes. Each node has different color ring gradient parameters, which reflect certain status characteristics of the device it represents. Set a preset time window, such as one hour. During this hour, the system will continuously record the occurrence of each node's color ring gradient parameters.

[0110] For example, the color ring gradient parameters of node A exhibit a specific color and gradient effect. Within an hour, the system detected this color ring gradient parameter 10 times. Node B's color ring gradient parameters exhibited a different characteristic, appearing 8 times. Node C's color ring gradient parameters were still different, appearing 12 times, and so on. Using these statistical methods, we can understand the frequency of changes in each node's color ring gradient parameters during this period, providing important data for subsequent analysis of device status. This statistical data can reflect the stability and changing trends of device status. If the color ring gradient parameters of a node appear abnormally frequently, it may indicate a significant change in the device's status, requiring further attention and analysis.

[0111] S520: Processing the occurrence frequency using a preset device state degradation model, and outputting device health prediction values ​​corresponding to different color ring gradients.

[0112] The preset equipment state degradation model is established based on a large amount of historical operation and maintenance data and equipment operating characteristics. The function of this model is to predict the health of the equipment based on the frequency of occurrence of the node color ring gradient parameters.

[0113] The model performs a complex series of analyses and calculations on the frequency of occurrence of each node's color ring gradient parameter. For example, if the color ring gradient parameter for node A appears 10 times, the model will first compare this frequency with the normal range of occurrences for the color ring gradient parameter for that node in historical data. For example, if historical data shows that the normal range of occurrences for the color ring gradient parameter for that node is between 8 and 12 times, the model will then perform a comprehensive calculation based on this comparison, combined with other relevant factors such as device operating time and environmental factors.

[0114] The model may contain various calculation logic and rules. For example, the deviation of the frequency of occurrence from the normal range is multiplied by different weight coefficients, and the influence of other relevant factors is added to obtain a numerical value. This value is further converted and processed to obtain the predicted device health value corresponding to the color ring gradient. For example, after the model calculation, the predicted device health value for node A is 0.7.

[0115] For node B, the color ring gradient parameter appears 8 times, and the model is processed similarly to the above method. By comparing with historical data and considering various relevant factors, the predicted device health value for node B is calculated to be 0.8.

[0116] The color ring gradient parameter of node C appears 12 times. After a series of model processing, the corresponding equipment health prediction value is 0.6.

[0117] These device health prediction values ​​range from 0 to 1. Higher values ​​indicate better device health; lower values ​​indicate potential device issues requiring attention from maintenance personnel. By using a pre-set device state degradation model to process the frequency of occurrence of color ring gradient parameters, maintenance personnel can be provided with intuitive and valuable information about device health, helping to identify potential equipment failures in advance and implement appropriate maintenance measures in a timely manner.

[0118] S530: Mapping the device health prediction value to a filling ratio parameter of the circular progress bar, and generating a device health label according to the filling ratio parameter.

[0119] In this step, the predicted value of the device health is converted into a more intuitive visual representation, namely the filling ratio parameter of the circular progress bar, and the corresponding device health label is generated.

[0120] The mapping between the predicted device health value and the circular progress bar fill ratio parameter is set to simply multiply the predicted device health value by 100%, and the result is the circular progress bar fill ratio. For example, if the predicted device health value of node A is 0.7, the corresponding circular progress bar fill ratio parameter is 0.7 × 100% = 70%. This means that when the circular progress bar is displayed, it will be filled at a ratio of 70%.

[0121] The predicted value of the device health of node B is 0.8, and the corresponding filling ratio parameter of the circular progress bar is 0.8×100%=80%.

[0122] The predicted value of the device health of node C is 0.6, and the corresponding filling ratio parameter of the circular progress bar is 0.6×100%=60%.

[0123] Based on these fill ratio parameters, a device health label is generated. The label should contain both fill ratio information and a description of the health level represented by the fill ratio.

[0124] For node A, the filling ratio is 70%, and the generated device health label content is "Device health 70%, good status".

[0125] For node B, the filling ratio is 80%, and the generated device health label content is "Device health 80%, good status".

[0126] For node C, the filling ratio is 60%, and the generated device health label content is "Device health 60%, need attention".

[0127] By mapping the device health prediction value to the circular progress bar filling ratio parameter and generating corresponding labels, operation and maintenance personnel can understand the health status of the device represented by each node at a glance when viewing the dynamic topology map, making it easier to quickly locate devices with potential problems and improve operation and maintenance efficiency.

[0128] S540: Dynamically bind the device health label in the peripheral area of ​​the node of the dynamic topology map, and update the edge transition state of the node color ring gradient parameter through anti-aliasing rendering; wherein, the Z-axis hierarchical relationship between the label and the node is processed through an independent rendering channel.

[0129] In the dynamic topology map, the generated device health labels must be accurately bound to the corresponding node peripheral area. This operation allows users to directly obtain the health information of the device represented by each node when viewing the topology map.

[0130] For example, for node A, a label reading "Device health 70%, good condition" is placed appropriately around node A. This placement ensures that the node itself and other important information are not obscured, while also ensuring that the label is clearly visible to the user. Similarly, for nodes B and C, their corresponding device health labels are accurately bound to the surrounding areas of the corresponding nodes.

[0131] To enhance the user's visual experience and make the node color ring gradient display smoother and more natural, anti-aliasing rendering technology is used to update the edge transition state of the node color ring gradient parameters. Anti-aliasing rendering can effectively reduce the jagged edges of the color ring, making the color transition of the color ring more delicate and soft.

[0132] During the rendering process, the Z-axis hierarchical relationship between labels and nodes is processed through independent rendering channels. This is because labels and nodes have different positional relationships in three-dimensional space. Through independent rendering channels, the display order and effect of labels and nodes in the Z-axis direction can be controlled separately. For example, the label can be set slightly above the node so that the label will not be obscured by the node in the display, while forming an overall visual effect with the node. In this way, when rendering a dynamic topology map, labels and nodes can be presented to users in a clear and reasonable hierarchical relationship, further enhancing the readability and ease of use of the visual interface, and helping operation and maintenance personnel better understand and analyze the status information of power grid equipment.

[0133] In a non-limiting embodiment, after outputting the real-time updated grid operation and maintenance visualization interface, the method further includes: monitoring a user's multi-touch gestures on the grid operation and maintenance visualization interface, extracting the curvature radius and contact pressure average of the gesture trajectory; matching a preset view rotation sensitivity parameter according to the curvature radius, and generating a depth of field offset for the touch focus area according to the contact pressure average; adjusting the Z-axis scaling factor of the node size parameters of the topology view in the three-dimensional space projection coordinate system based on the depth of field offset, and simultaneously reducing the altitude parameters of the non-focus color blocks in the thermal view; inputting the adjusted Z-axis scaling factor and altitude parameters into a ray tracing engine to generate a visualization interface with a dynamic depth of field effect; and calculating the Euler angle change rate of the topology view in real time according to the view rotation sensitivity parameter, and smoothly rendering the perspective switching animation using a quaternion interpolation algorithm. In actual implementation, the X / Y axis ratio of the original node size parameters can be maintained unchanged.

[0134] By outputting a real-time, updated grid operation and maintenance visualization interface, the system further enhances the user interaction experience and visualization. When users perform multi-touch gestures on the grid operation and maintenance visualization interface, the system responds quickly. For example, when users use both hands to perform complex operations such as rotating and zooming on the screen, the system accurately extracts the curvature radius and average contact pressure of the gesture trajectory.

[0135] For example, a user's multi-touch gesture forms a trajectory, and a specific algorithm calculates the radius of curvature of that trajectory. A smaller radius indicates a more curved gesture, potentially indicating a more precise operation. Conversely, a larger radius indicates a gentler operation. The system also calculates the average contact pressure. A higher contact pressure may indicate a stronger user's operation and a higher level of focus.

[0136] Next, the system matches the preset view rotation sensitivity parameters based on the curvature radius. For example, a smaller curvature radius matches a higher view rotation sensitivity parameter, meaning the view will rotate more sensitively based on the user's gestures, allowing the user to view a specific area in detail. A depth of field offset is generated for the touch focus area based on the average contact pressure. Higher average contact pressure increases the generated depth of field offset, making the focus area more prominent.

[0137] Based on the depth of field offset, the system adjusts the Z-axis scaling factor of the topology view's node size parameters in the 3D projection coordinate system. For example, as the depth of field offset increases, the Z-axis scaling factor adjusts accordingly, making the topology view's nodes appear more three-dimensional along the Z axis. Simultaneously, the altitude parameters of non-focused color blocks in the thermal view are reduced, highlighting the focus area and preventing excessive non-critical information from cluttering the user's field of view.

[0138] The adjusted Z-axis scaling factor and altitude parameters are then fed into the ray tracing engine. Based on these parameters, the ray tracing engine simulates the propagation of light in a 3D scene, generating a visualization interface with a dynamic depth of field effect. This interface allows users to experience a more realistic, three-dimensional visual experience, as if they were observing the device in the actual scene.

[0139] Finally, the system calculates the Euler angle change rate of the topology view in real time based on the view rotation sensitivity parameter. Quaternion interpolation is used to smoothly render the topology view's perspective switching. For example, when the user quickly rotates the view, the quaternion interpolation algorithm makes the view's rotation transition more natural and smooth, avoiding any stuttering or jumping. Furthermore, in actual implementation, the X / Y axis ratio of the original node size parameters remains unchanged, ensuring that the shape and proportional relationships of the nodes remain consistent during scaling and rotation, thereby ensuring that users can accurately understand the connections and layout relationships between devices.

[0140] In a non-limiting embodiment, after the output of the real-time updated power grid operation and maintenance visualization interface, it also includes: real-time collection of the rendering frame rate of the interactive visualization element set, and activation of the rendering load balancing mode when the frame rate is lower than a preset threshold; in the rendering load balancing mode, statistics are made on the screen space share of each node size parameter in the dynamic topology diagram, and micro-nodes whose share is less than a preset percentage threshold are screened out; the node color ring gradient parameters of the micro-nodes are replaced with sub-resolution texture maps, and the geometric meshes of adjacent micro-nodes are merged into a target instantiation model; the collision volume of the color block bounding box in the thermal view is recalculated according to the target instantiation model to reduce the spatial segmentation granularity of the bounding box; a culling algorithm is used to remove invisible color blocks outside the collision volume, to generate an optimized visualization element set and trigger interface redrawing. In actual implementation, the micro-nodes that are focused by the user's touch can be excluded.

[0141] After outputting the real-time updated grid operation and maintenance visualization interface, the system introduces a rendering load balancing mechanism to ensure smoothness and efficiency. The system collects the rendering frame rate of the interactive visualization elements in real time, for example, once every second. For example, if the collected frame rate falls below a preset threshold of 60 frames per second, it indicates a heavy rendering load on the system, and rendering load balancing is activated.

[0142] In rendering load balancing mode, the system first calculates the screen space usage of each node's size parameters in the dynamic topology. For example, the system calculates the screen space usage of each node by calculating the pixel area it occupies on the screen. It then selects micro-nodes whose usage is below a preset percentage threshold. These micro-nodes are generally less visually important to the overall information presented.

[0143] For these micronodes, the system replaces their node color ring gradient parameters with a sub-resolution texture map. While sub-resolution texture maps lack the same level of detail as the original high-resolution map, they significantly reduce rendering resources. Furthermore, the system merges the geometric meshes of adjacent micronodes into a target instanced model. For example, several adjacent micronodes with similar functions can be merged into a larger model. This reduces the number of objects that need to be processed during rendering, improving rendering efficiency.

[0144] Next, the collision volume of the color block bounding boxes in the heat map is recalculated based on the target instantiation model. Due to the merging of micronodes and parameter adjustments, the color block bounding boxes in the heat map will also change. Recalculating the collision volume can more accurately determine which color blocks are visible and which are invisible in the current view. At the same time, reducing the spatial segmentation granularity of the bounding box means reducing the computational effort required for collision detection, further improving rendering efficiency.

[0145] Finally, the system uses a culling algorithm to remove invisible color blocks outside the collision volume. For example, by determining whether the color block is within the visible range of the user's current perspective, those color blocks that are not within the visible range are directly removed from the rendering queue. In this way, the generated optimized set of visual elements greatly reduces the resources required for rendering, and the system triggers the interface to redraw. In actual implementation, in order to avoid affecting the user's operating experience, the micro-nodes that are focused by the user's touch will be excluded. These focused micro-nodes are usually the focus of user attention. Preserving their original display effects can ensure that users can obtain detailed information. At the same time, by optimizing other non-focused micro-nodes, the rendering smoothness of the overall interface is guaranteed, allowing users to monitor and analyze power grid operations in an efficient and smooth visualization environment.

[0146] It is worth mentioning that in the specific implementation process, those skilled in the art can perform the following processing based on the existing technology to ensure the complete and clear implementation of the embodiment: by clearly defining the temperature gradient change rate as a composite dimension ℃ / (m·min) to improve the unit confusion problem; by citing the allowable voltage deviation range (±10%) of the low-voltage distribution system specified in the International Electrotechnical Commission standard IEC60038 to improve the lack of basis for setting the voltage safety threshold; by using the cubic spline interpolation algorithm to compensate for the millisecond timestamp deviation to improve the time alignment accuracy of multi-source data; by introducing cross-validation and grid search to adjust the parameters to optimize the environmental weight prediction model to improve the problem of insufficient model credibility; by using the dynamic sliding window extreme value method to adjust the normalization range in real time to improve the feature distortion risk caused by the fixed normalization interval; by defining a gesture type priority mapping table (such as pinch to zoom > slide to pan > long press to focus) Methods are used to improve the problem of disordered responses in user operation conflict scenarios; a regular online calibration mechanism is established between the predicted value of equipment health and the actual maintenance records to improve the problem of long-term deviation accumulation in the prediction model; a three-dimensional similarity matching algorithm is constructed based on equipment model, installation environment, and operating years to improve the applicability error of the matrix of similar equipment when historical data is missing; the subjectivity of setting meteorological event alarm thresholds is improved by balancing the false alarm rate and the missed alarm rate through ROC curve analysis; the rendering performance bottleneck problem in high-density node scenarios is improved by combining OpenGL multi-sampling anti-aliasing (MSAA) technology with instanced rendering; the problem of erroneous operation recognition caused by touch parameter fluctuations is improved by extracting the curvature characteristics of gesture trajectories through a Bezier curve fitting algorithm; the stereoscopic perspective distortion problem caused by linear calculation of depth of field offset is improved by establishing a nonlinear piecewise function mapping relationship between the Z-axis scaling factor and the mean contact pressure.

[0147] In summary, the embodiments of the present invention can comprehensively obtain various types of relevant information by collecting multi-source heterogeneous operation and maintenance data sets of smart grids in real time; cross-modal cleaning and time alignment processing can effectively improve data quality and consistency, making the pre-processed data set more usable; dynamic feature fusion and association analysis can be used to deeply explore the potential relationship of data, thereby generating a feature set that accurately reflects the device status and device-environment interaction; further based on the multi-dimensional visualization strategy, an interactive visualization element set is generated to provide users with a variety of interaction methods; the final dynamic rendering and layout optimization can ensure the real-time update of the visualization interface and a reasonable layout. In addition, configuring a user operation priority response mechanism can ensure that user operations can be responded to in an orderly manner in complex interactive scenarios. In this way, the efficiency and intelligence of grid operation and maintenance visualization can be improved, thereby improving the timeliness of grid operation and maintenance decision-making management.

[0148] Based on the same inventive concept, an embodiment of the present invention also provides an operation and maintenance data visualization system. Figure 2 As shown, it is a structural diagram of a possible operation and maintenance data visualization system provided in an embodiment of the present invention. Figure 2 In the embodiment, the operation and maintenance data visualization system 200 includes a processor 210 and a memory 220. The memory 220 stores a computer program executable by the processor 210. The processor 210 can perform the steps of the above-mentioned operation and maintenance data visualization method based on the smart grid by executing the instructions stored in the memory 220.

[0149] Based on the same inventive concept, an embodiment of the present invention provides a computer-readable storage medium, which includes a computer program. When the computer program is run on an operation and maintenance data visualization system, the computer program is used to enable the operation and maintenance data visualization system to execute the steps of the above-mentioned operation and maintenance data visualization method based on the smart grid. In some possible implementations, various aspects of the operation and maintenance data visualization method based on the smart grid provided by the present invention can also be implemented in the form of a program product, which includes a computer program. When the program product is run on the operation and maintenance data visualization system, the computer program is used to enable the operation and maintenance data visualization system to execute the steps of the above-mentioned operation and maintenance data visualization method based on the smart grid. For example, the operation and maintenance data visualization system can execute the following steps: Figure 1 Follow the steps shown in .

[0150] In the technical solutions involved in the above-mentioned embodiments of the present invention, whether it is performing comparison calculations of multi-dimensional features or constructing composite parameters, if there are problems caused by significant differences in the number of dimensions, dimensional units and semantic meanings of different features, technical personnel in this field, based on their professional knowledge and past practical experience, are fully able to understand that these differences need to be properly handled so that the calculation results are accurate and comparable, and avoid situations such as logical confusion and unclear mathematical meaning.

[0151] In detail, when faced with features with different numbers of dimensions, in order to accurately calculate the similarity, matching degree or feature distance between different features, technical personnel in this field can use a variety of strategies, such as feature selection, feature extraction, kernel function and other strategies for adaptive processing.

[0152] When processing the comparison of multi-dimensional features, in order to achieve comparable alignment of feature spaces, those skilled in the art may adopt a variety of existing general technical means, including but not limited to the following existing technologies: standardization preprocessing, mapping conversion, space projection, etc.

[0153] In the process of constructing composite parameters (such as loss function values), different parameter items often have different dimensions. Those skilled in the art can adopt existing normalization processing or adaptive weight allocation mechanism based on distribution characteristics.

[0154] The general technical approaches described above for solving the feature matching and loss balancing problems are common knowledge in the field. These techniques have been fully validated and widely used in numerous practical applications, and those skilled in the art can skillfully and flexibly apply these methods to address similar dimensional discrepancies.

[0155] The formulas and calculation processes involved in the embodiments of the present invention, whether used for multi-dimensional feature comparison or composite loss function construction, strictly follow the principle of dimensional correspondence. The variables in each formula have clear and definite physical meanings, and their operation logic is also fully consistent with basic mathematical and physical logic. The operation results must be the reasonable results expected by the present invention. Those skilled in the art have the ability to comprehensively apply the above-mentioned general technical means according to specific data conditions and business needs, and effectively solve the various problems caused by the number of dimensions, dimensional differences, etc. in the multi-dimensional feature comparison calculation and composite loss function construction in the embodiments, and ensure the accuracy, reliability and feasibility of the technical solution of the present invention.

Claims

1. A method for visualizing operation and maintenance data based on smart grid, characterized in that: include: Real-time collection of multi-source heterogeneous operation and maintenance data sets in smart grids; Performing cross-modal cleaning and time alignment processing on the operation and maintenance data set to generate a preprocessed data set; Performing dynamic feature fusion and association analysis on the preprocessed data set to generate a device state feature set and a device-environment interaction feature set; Based on the device state feature set and the device-environment interaction feature set, generating an interactive visualization element set through a multi-dimensional visualization strategy; The interactive visualization element set is dynamically rendered and layout optimized to output a real-time updated power grid operation and maintenance visualization interface; wherein the power grid operation and maintenance visualization interface is configured with a user operation priority response mechanism for handling interaction conflicts.

2. The method according to claim 1, wherein The cross-modal cleaning and time alignment processing of the operation and maintenance data set to generate a pre-processed data set includes: Dividing the current time series data of the operation and maintenance data set into initial data segments according to a preset time granularity, and performing linear interpolation based on adjacent data trends on missing initial data segments to generate interpolated current data segments; Detecting abnormal voltage points exceeding a preset safety threshold in the voltage data segment of the operation and maintenance data set, and replacing the abnormal voltage points with historical voltage averages of corresponding equipment to generate corrected voltage data segments; Performing a sliding window mean filter on the temperature gradient data of the operation and maintenance data set, identifying an abnormal fluctuation interval in which the temperature change rate exceeds a threshold within the window, and performing Gaussian filtering to reduce noise to generate a noise-reduced temperature data segment; Extracting timestamp information of the meteorological-related data of the operation and maintenance data set, and synchronously aligning the timestamp information of the meteorological-related data with the timestamps of the interpolated current data segment, the corrected voltage data segment, and the noise-reduced temperature data segment to generate a synchronized environmental impact factor sequence; The interpolated current data segment, the corrected voltage data segment, the noise-reduced temperature data segment, and the synchronized environmental impact factor sequence are uniformly time-coded to generate the pre-processed data set.

3. The method according to claim 2, wherein The performing dynamic feature fusion and association analysis on the pre-processed data set to generate a device state feature set and a device-environment interaction feature set includes: Performing multi-scale wavelet decomposition on the interpolated current data segment to generate a fluctuation component and a trend component, and calculating the energy density ratio of each component; Performing density clustering on the corrected voltage data segment to generate abnormal voltage point distribution density, and calculating a regional cumulative abnormality index based on the clustering result; Perform slope analysis on the noise-reduced temperature data segment to extract the temperature rise rate, and count the number of times the temperature fluctuation exceeds a threshold within a unit time to generate the abnormal fluctuation frequency; Inputting the synchronized environmental impact factor sequence into a pre-trained environmental weight prediction model, and outputting a combination vector of temperature impact weight, humidity impact weight, and wind speed impact weight; The energy density ratio, the abnormal voltage point distribution density, the regional cumulative abnormality index, the temperature rise rate and the combination vector are feature spliced ​​to generate a device state feature set and a device-environment interaction feature set.

4. The method according to claim 3, wherein The generating of the interactive visualization element set by a multi-dimensional visualization strategy based on the device state feature set and the device-environment interaction feature set includes: A multi-view projection strategy is used to map the energy density ratio and the regional cumulative anomaly index to a three-dimensional visualization space, wherein node size parameters of a dynamic topology graph are generated based on the energy density ratio, and node color ring gradient parameters are generated based on the regional cumulative anomaly index; Based on a layered mapping strategy, the temperature rise rate is mapped through a height field to generate a color block altitude parameter of a three-dimensional thermal map, and based on the abnormal fluctuation frequency, a color block pulsation parameter is generated through a transparency attenuation function; Using a multi-dimensional vector fusion algorithm, the temperature influence weight, humidity influence weight, and wind speed influence weight in the combined vector are respectively mapped to the arrow length parameter, feather parameter, and inclination parameter of the meteorological vector; A cross-view association mechanism is established to synchronize the spatial coordinates of the node size parameters and node color ring gradient parameters of the dynamic topology map, the color block altitude parameters and color block pulsation parameters of the three-dimensional heat map, and the arrow length parameters, feathering parameters and inclination parameters of the meteorological vector, thereby generating a set of interactive visualization elements with coordinate linkage.

5. The method according to claim 4, wherein The dynamically rendering and layout optimization of the interactive visualization element set to output a real-time updated power grid operation and maintenance visualization interface includes: Creating a topology view in a three-dimensional space projection coordinate system based on node size parameters and node color ring gradient parameters of the dynamic topology graph in the interactive visualization element set; Generate a thermal map with a height field gradient by superimposing the color block altitude parameters and the color block pulsation parameters of the three-dimensional thermal map in the three-dimensional space projection coordinate system; Mapping the arrow length parameter, feather parameter, and inclination parameter of the meteorological vector to the three-dimensional space projection coordinate system to generate a dynamic vector field meteorological view; Constructing an adaptive layout matrix according to the size of the user terminal window, spatially arranging the topological view, thermal view, and meteorological view according to a preset division ratio, and establishing a coordinate mapping relationship between the three views; When a focus operation on a node area in the topology view is detected, the altitude parameters of the color blocks corresponding to the spatial coordinates in the thermal view are synchronously adjusted based on the coordinate mapping relationship, and the transparency of the feather parameters of the associated area vector in the meteorological view is increased; Performing spatiotemporal interpolation calculation on the motion trajectory of the meteorological vector, generating trajectory smoothing parameters based on the real-time change rate of the wind speed influence weight, and performing dynamic rendering using a Bezier curve fitting algorithm; Constructing an abnormal fluctuation propagation path in the thermal map, calculating a path confidence interval based on the temperature rise rate and the historical propagation pattern, and generating a gradient color band through transparency gradient mapping; The geometric collision relationship of each element in the dynamic topology map, three-dimensional heat map and meteorological view is detected in real time. When the ratio of the intersection volume of the node bounding box of the dynamic topology map and the color block bounding box of the three-dimensional heat map to the volume of the smaller bounding box exceeds a preset percentage threshold, the spherical expansion algorithm is activated to perform azimuth decoupling and spatial reorganization of the collision view.

6. The method according to claim 5, wherein The method further comprises: monitoring a user's touch operation trajectory on the power grid operation and maintenance visualization interface, and extracting acceleration characteristics and contact area change rates of the touch operation trajectory; Matching a preset view zoom instruction set according to the acceleration feature, and generating a hot zone focus weight parameter according to the contact area change rate; Adjusting the scaling ratio of the node size parameters of the dynamic topology map based on the hot zone focus weight parameter, and simultaneously increasing the flashing frequency of the associated color block pulsation parameter in the three-dimensional heat map; The adjusted node size parameters and color block pulsation parameters are input into a particle rendering module to generate a touch feedback particle flow, and are superimposed on the edge area of ​​the power grid operation and maintenance visualization interface.

7. The method according to claim 5, wherein The method further comprises: Real-time analysis of the regional cumulative anomaly index in the device status feature set, and activation of the anomaly tracing mode when the index exceeds a preset risk threshold; Extracting a correlation matrix between abnormal fluctuation frequency and temperature rise rate of the same equipment in the historical operation and maintenance data set under the abnormal tracing mode; generating a probability density distribution map of the device anomaly propagation path according to the association matrix, and encoding the probability density distribution map as a semi-transparent thermal overlay; The semi-transparent thermal overlay layer is embedded in the area below the color block altitude parameter of the three-dimensional heat map through a depth buffer layered rendering strategy.

8. The method according to claim 5, wherein The method further comprises: Continuously capture the time-series change data of the arrow length parameter and inclination parameter of the meteorological vector to generate a dynamic attenuation curve of the wind speed influence weight; Perform extreme point detection on the dynamic attenuation curve, extract abnormal time segments with sudden slope changes in the curve and mark them as meteorological event trigger points; Reversely retrieve the temperature impact weight of the corresponding moment in the synchronized environmental impact factor sequence according to the meteorological event trigger point; The temperature influence weight and the wind speed influence weight are normalized and fused to generate a meteorological event warning mark and insert it into the end of the arrow of the dynamic vector field meteorological view.

9. The method according to claim 1, wherein The method further comprises: Periodically reading the node color ring gradient parameters in the interactive visualization element set, and counting the occurrence frequency of each node color ring gradient parameter within a preset time window; The occurrence frequency is processed by a preset equipment state degradation model, and equipment health prediction values ​​corresponding to different color ring gradients are output; Mapping the device health prediction value to a filling ratio parameter of a circular progress bar, and generating a device health label according to the filling ratio parameter; The device health label is dynamically bound to the peripheral area of ​​the node in the dynamic topology map, and the edge transition state of the node color ring gradient parameter is updated through anti-aliasing rendering.

10. An operation and maintenance data visualization system, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to perform the steps of any one of the methods of claims 1 to 9.

Images