Methods, devices, equipment and media for gas leakage monitoring of power grid equipment

Abstract

This application discloses a method, apparatus, equipment, and medium for monitoring gas leaks in power grid equipment, belonging to the field of gas leak monitoring for power grid equipment. The method involves: acquiring real-time data of the leak area and the concentration distribution map, diffusion parameters, and heavy vapor parameters of the previous moment; updating the diffusion parameters, heavy vapor parameters, and local diffusion model based on meteorological data, population dynamic data, and sensor data, respectively; determining the gas concentration distribution and target risk based on the updated results, and updating the concentration distribution map. Therefore, by implementing this application, the problem of insufficient accuracy in gas leak monitoring for power grid equipment in existing technologies can be solved.

Description

Technical Field

[0001] This application relates to the field of gas leak monitoring, and in particular to a method, apparatus, equipment and medium for gas leak monitoring of power grid equipment. Background Technology

[0002] Gas leaks are characterized by their suddenness, rapid spread, and wide-ranging impact. Once they occur, they can spread rapidly within a very short time through airflow, human transport, or topographical diffusion, posing a serious threat to surrounding personnel, critical infrastructure, and the ecological environment. Especially in gas leaks affecting power grid equipment, the leak event can be coupled with the activities of power workers, multi-source meteorological changes, and complex terrain, forming a rapidly evolving chain of secondary disasters. Therefore, achieving real-time and accurate monitoring of gas leak processes and timely understanding of the diffusion trend of pollutants and their impact on key targets is a crucial prerequisite for ensuring public safety, improving emergency response efficiency, and minimizing accident losses.

[0003] Current methods for monitoring gas leaks in power grid equipment largely rely on fixed sensor networks, conventional meteorological data, and pre-set diffusion models for single-dimensional information collection and analysis. These systems typically refresh monitoring data through timed updates or manual triggering, making it difficult to respond in real-time to dynamic changes in environmental parameters, human behavior, and sensor data. Especially during the rapid evolution of leak events, existing technologies lack mechanisms for joint sensing and collaborative updating of multi-source heterogeneous information, resulting in adjustments to pollutant diffusion parameters, heavy vapor concentration estimation parameters, and local diffusion models lagging behind actual situational changes. Furthermore, existing methods often employ a globally uniform reset strategy during model updates, failing to differentiate responses to changes in different data types. This leads to untimely or excessive updates of key information, causing model oscillations and ultimately affecting the accuracy of leak impact range estimation. Summary of the Invention

[0004] This application provides a gas leakage monitoring method for power grid equipment, which can solve the problem of insufficient accuracy in gas leakage monitoring in the prior art.

[0005] In a first aspect, embodiments of the present invention provide a gas leakage monitoring method for power grid equipment, comprising: Real-time data of the gas leak area is acquired, and the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters of the leak area at the previous moment are acquired; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leak area includes several preset power grid devices; The first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter. The first heavy vapor concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter. The first environmental sensor data is input into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. Based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid equipment are determined. Based on the gas concentration distribution and the risk status of each of the preset power grid devices, the first gas concentration distribution map is updated to obtain a second gas concentration distribution map that displays the current gas leakage status of each of the preset power grid devices.

[0006] This application embodiment obtains the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters from the previous moment, providing a historical state benchmark for subsequent iterative updates. This avoids the blindness of starting from zero for each estimation and ensures the continuity and consistency of monitoring results over time. Secondly, by correcting the first pollutant diffusion parameters based on first meteorological data, the accuracy of diffusion range estimation is improved. Thirdly, by correcting the first heavy vapor concentration estimation parameters based on first population dynamic behavior data, the shortcomings of traditional methods that rely solely on macroscopic wind fields while ignoring the impact of population activities on near-surface airflow are overcome, significantly improving the accuracy of heavy vapor concentration distribution estimation in complex urban environments or densely populated areas. Furthermore, by inputting first environmental sensor data into a first preset local diffusion model for adjustment, and using the sensor's measured concentration values ​​as a calibration benchmark, deviation correction is applied to the output of the local diffusion model. This dynamically reduces the error between the model's predicted values ​​and the actual monitored values, further enhancing the reliability of local area concentration estimation. Finally, based on the corrected second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid device are comprehensively determined, and the second gas concentration distribution map is updated accordingly. This allows the monitoring results to not only reflect the overall macroscopic situation of leakage diffusion but also to more accurately present the specific impact on each preset power grid device. Therefore, the embodiments of this application can solve the problem of insufficient accuracy in gas leakage monitoring in the prior art.

[0007] As a preferred example of the first aspect, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: If the change in the first meteorological data relative to the second meteorological data at the previous moment is greater than a first preset threshold, then the first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter; otherwise, the first pollutant diffusion parameter is used as the second pollutant diffusion parameter.

[0008] In this preferred example, by setting a first preset threshold, the correction of pollutant diffusion parameters is triggered only when the change in meteorological data exceeds the threshold; otherwise, the parameters from the previous moment are used. This avoids frequent invalid updates caused by minor meteorological fluctuations, reduces computational redundancy and model oscillation risks, and ensures timely adjustment of diffusion parameters when significant meteorological changes occur. This keeps the pollutant diffusion projection synchronized with the actual environment, thereby improving the system's response efficiency while ensuring monitoring accuracy.

[0009] As a preferred example of the first aspect, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: Obtain the wind speed change, wind direction change, temperature change, and humidity change from the first meteorological data; Based on the changes in wind speed and wind direction, the advection transport parameters are determined, and based on the changes in temperature and humidity, the turbulence diffusion coefficient and settling parameters are determined. The second pollutant diffusion parameters are determined based on the advection transport parameters, the turbulent diffusion coefficient, and the sedimentation parameters.

[0010] In this preferred example, by extracting wind speed and direction changes to determine advection transport parameters, the dominant migration direction and rate of pollutants can be accurately reflected. Simultaneously, by determining turbulent diffusion coefficients and sedimentation parameters based on temperature and humidity changes, the dispersion intensity and gravitational sedimentation behavior of pollutants can be precisely characterized. The comprehensive updating of pollutant diffusion parameters using these three methods enables the diffusion model to match real-time weather conditions from multiple physical dimensions, significantly improving the accuracy of estimating the diffusion range and concentration distribution of gas leaks.

[0011] As a preferred example of the first aspect, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: If the change in the dynamic behavior data of the first population relative to the dynamic behavior data of the second population at the previous moment is greater than the second preset threshold, then the first heavy steam concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy steam concentration estimation parameter; otherwise, the first heavy steam concentration estimation parameter is used as the second heavy steam concentration estimation parameter.

[0012] In this preferred example, by setting a second preset threshold, the correction of the heavy vapor concentration estimation parameters is triggered only when the change in the dynamic behavior data of the population exceeds the threshold; otherwise, the parameters from the previous moment are used. This effectively filters out small random fluctuations in the population, avoiding computational redundancy and model instability caused by frequent invalid corrections. At the same time, it ensures that the parameters are adjusted in a timely manner when there are significant changes in the population, making the heavy vapor diffusion estimation more consistent with the actual dynamic environment, thereby improving the accuracy of gas leakage monitoring for power grid equipment.

[0013] As a preferred example of the first aspect, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: Based on the dynamic behavior data of the first crowd, the average movement vector corresponding to the crowd in each grid unit is calculated; wherein, each grid unit is determined by dividing several preset areas in the leakage area; The wind field data of each preset area is obtained, and the local airflow disturbance vector of each grid cell is obtained based on the average movement vector of the crowd corresponding to each grid cell and the wind field data of each preset area. The first heavy vapor concentration estimation parameters are corrected based on the local airflow disturbance vector of each grid cell to obtain the second heavy vapor concentration estimation parameters.

[0014] In this preferred example, by gridding the leakage area and calculating the average movement vector of the crowd in each grid cell, the driving effect of crowd movement on local airflow can be accurately captured. Combined with the wind field data of the preset area, the local airflow disturbance vector is obtained, thereby quantifying and integrating the complex influence of crowd behavior on heavy vapor diffusion into the model. Finally, the heavy vapor concentration estimation parameters are corrected based on the disturbance vector, making the diffusion direction and concentration distribution of heavy vapor closer to reality, which significantly improves the accuracy of gas leakage monitoring for power grid equipment.

[0015] As a preferred example of the first aspect, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: If the change in the first environmental sensor data relative to the second environmental sensor data at the previous moment is greater than a third preset threshold, then the first environmental sensor data is input into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model; otherwise, the first preset local diffusion model is used as the second preset local diffusion model.

[0016] In this preferred example, by setting a third preset threshold, the local diffusion model is only adjusted when the change in environmental sensor data exceeds the threshold; otherwise, the model from the previous moment is used. This avoids frequent invalid adjustments caused by sensor noise or minor fluctuations, reducing computational overhead and the risk of model oscillation. Simultaneously, it ensures timely model calibration when measured data changes significantly, keeping the local diffusion prediction synchronized with the actual concentration distribution, thereby effectively improving the accuracy and stability of gas leak monitoring for power grid equipment.

[0017] As a preferred example of the first aspect, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: Based on the preset environmental sensor prediction data and the first environmental sensor data, a deviation amount is determined to measure the deviation between the predicted value and the actual value. Based on the deviation, determine the correction coefficient of the first preset local diffusion model; Based on the correction coefficient, the local diffusion coefficient in the first preset local diffusion model is adjusted to obtain the second preset local diffusion model.

[0018] In this preferred example, the deviation is determined by comparing the predicted and measured values ​​from the environmental sensor, quantifying the difference between the model output and the actual concentration. A correction coefficient is then calculated based on the deviation, achieving adaptive quantification of model error. Finally, the correction coefficient is used to adjust the local diffusion coefficient, dynamically calibrating the diffusion model to the measured data. The synergistic effect of these three elements integrates real-time sensor feedback into the model update, effectively suppressing prediction drift and significantly improving the accuracy of gas leak monitoring for power grid equipment.

[0019] In a second aspect, the present invention provides a gas leakage monitoring device for power grid equipment, comprising: a data acquisition module, a first monitoring module, a second monitoring module, and a third monitoring module; The data acquisition module is used to acquire real-time data of the gas leakage area, and to acquire the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters of the leakage area at the previous moment; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leakage area includes several preset power grid devices; The first monitoring module is used to correct the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter, and to correct the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter, and to input the first environmental sensor data into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. The second monitoring module is used to determine the gas concentration distribution and the risk status of each preset power grid device based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model. The third monitoring module is used to update the first gas concentration distribution map based on the gas concentration distribution and the risk status of each of the preset power grid devices, so as to obtain a second gas concentration distribution map that displays the current gas leakage status of each of the preset power grid devices.

[0020] As a preferred example of the second aspect, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: If the change in the first meteorological data relative to the second meteorological data at the previous moment is greater than a first preset threshold, then the first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter; otherwise, the first pollutant diffusion parameter is used as the second pollutant diffusion parameter.

[0021] As a preferred example of the second aspect, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: Obtain the wind speed change, wind direction change, temperature change, and humidity change from the first meteorological data; Based on the changes in wind speed and wind direction, the advection transport parameters are determined, and based on the changes in temperature and humidity, the turbulence diffusion coefficient and settling parameters are determined. The second pollutant diffusion parameters are determined based on the advection transport parameters, the turbulent diffusion coefficient, and the sedimentation parameters.

[0022] As a preferred example of the second aspect, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: If the change in the dynamic behavior data of the first population relative to the dynamic behavior data of the second population at the previous moment is greater than the second preset threshold, then the first heavy steam concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy steam concentration estimation parameter; otherwise, the first heavy steam concentration estimation parameter is used as the second heavy steam concentration estimation parameter.

[0023] As a preferred example of the second aspect, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: Based on the dynamic behavior data of the first crowd, the average movement vector corresponding to the crowd in each grid unit is calculated; wherein, each grid unit is determined by dividing several preset areas in the leakage area; The wind field data of each preset area is obtained, and the local airflow disturbance vector of each grid cell is obtained based on the average movement vector of the crowd corresponding to each grid cell and the wind field data of each preset area. The first heavy vapor concentration estimation parameters are corrected based on the local airflow disturbance vector of each grid cell to obtain the second heavy vapor concentration estimation parameters.

[0024] As a preferred example of the second aspect, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: If the change in the first environmental sensor data relative to the second environmental sensor data at the previous moment is greater than a third preset threshold, then the first environmental sensor data is input into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model; otherwise, the first preset local diffusion model is used as the second preset local diffusion model.

[0025] As a preferred example of the second aspect, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: Based on the preset environmental sensor prediction data and the first environmental sensor data, a deviation amount is determined to measure the deviation between the predicted value and the actual value. Based on the deviation, determine the correction coefficient of the first preset local diffusion model; Based on the correction coefficient, the local diffusion coefficient in the first preset local diffusion model is adjusted to obtain the second preset local diffusion model.

[0026] In summary, this application's embodiments, by acquiring the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters from the previous moment, provide a historical state benchmark for subsequent iterative updates, avoiding the blindness of starting from zero for each estimation and ensuring the continuity and consistency of monitoring results over time. Secondly, by correcting the first pollutant diffusion parameters based on first meteorological data, the accuracy of diffusion range estimation is improved. Thirdly, by correcting the first heavy vapor concentration estimation parameters based on first population dynamic behavior data, the shortcomings of traditional methods that rely solely on macroscopic wind fields while ignoring the impact of population activity on near-surface airflow are overcome, significantly improving the accuracy of heavy vapor concentration distribution estimation in complex urban environments or densely populated areas. Furthermore, by inputting first environmental sensor data into a first preset local diffusion model for adjustment, and using the sensor's measured concentration values ​​as a calibration benchmark, deviation correction is applied to the local diffusion model's output, dynamically reducing the error between the model's predicted values ​​and the actual monitored values, further enhancing the reliability of local area concentration estimation. Finally, based on the corrected second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid device are comprehensively determined, and the second gas concentration distribution map is updated accordingly. This allows the monitoring results to not only reflect the overall macroscopic situation of leakage diffusion but also to more accurately present the specific impact on each preset power grid device. Therefore, the embodiments of this application can solve the problem of insufficient accuracy in gas leakage monitoring in the prior art.

[0027] Another embodiment of this application also provides a terminal device, including: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps of the gas leak monitoring method for power grid equipment as described in this application.

[0028] Another embodiment of this application also provides a computer-readable storage medium item, including: a stored computer program, which, when the computer program is running, controls the device where the computer-readable storage medium is located to perform the steps of the gas leak monitoring method for power grid equipment of this application. Attached Figure Description

[0029] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0030] Figure 1 This is a flowchart illustrating an embodiment of a gas leakage monitoring method for power grid equipment provided by the present invention. Figure 2 This is a module structure diagram of one embodiment of a gas leakage monitoring device for power grid equipment provided by the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0033] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0034] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0035] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0036] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0037] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0038] Example 1 Please refer to Figure 1 To address the insufficient accuracy of gas leak monitoring in existing technologies, this application provides a gas leak monitoring method for power grid equipment, comprising: S1. Obtain real-time data of the gas leakage area, and obtain the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters of the leakage area at the previous moment; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leakage area includes several preset power grid devices; As a preferred implementation, real-time data is acquired through various sensors and data interfaces deployed within the leak area. Meteorological data primarily comes from regional weather stations or miniature weather monitoring instruments, capable of collecting macro-meteorological information such as wind speed, wind direction, temperature, and humidity in real time. Dynamic crowd behavior data is acquired through video surveillance systems, WiFi probes, or UWB positioning devices, providing precise real-time location, direction of movement, and local density for each pedestrian. Environmental sensor data is typically provided by fixed or mobile gas concentration detectors, such as electrochemical sensors or photoionization detectors, distributed around the leak source and in key protection areas, continuously transmitting measured pollutant concentration values. The first gas concentration distribution map from the previous moment refers to the leak impact range map generated in the previous iteration, usually stored in the system database as contour lines or heat maps, with the concentration levels of each preset power grid device marked on the map. The first pollutant diffusion parameters include advection transport parameters, turbulent diffusion coefficients, and sedimentation parameters. These parameters are calculated from the initial meteorological conditions and leak source strength and stored in the model configuration file. The first set of vapor concentration estimation parameters is specifically designed to simulate the diffusion behavior of gases denser than air near the ground. This includes local airflow disturbance correction factors and diffusion coefficient weighting factors. The system automatically reads this historical data as an iterative benchmark upon startup or each update, ensuring continuity and comparability between subsequent corrections and estimations.

[0039] Specifically, the pre-installed power grid equipment can be any object of user concern, such as densely populated areas, important infrastructure, sensitive ecological areas, and evacuation routes.

[0040] It should be noted that the first gas concentration distribution map is a contour map overlaid on a map showing the extent of pollutant diffusion, and different colors or icons are used to indicate the degree to which preset power grid equipment is affected.

[0041] S2. Correct the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter, and correct the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter, and input the first environmental sensor data into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. In some embodiments, after obtaining the first pollutant diffusion parameters, the first heavy vapor concentration estimation parameters, and the first preset local diffusion model at the previous moment, this embodiment will execute three sets of update operations in parallel.

[0042] Specifically, the first group involves corrections to meteorological data: In this embodiment, the currently collected first meteorological data is compared with the second meteorological data from the previous moment, and the changes in wind speed, wind direction, temperature, and humidity are calculated. If any of these changes exceeds a pre-defined first threshold (e.g., a wind speed change exceeding 1 m / s or a wind direction deflection exceeding 15 degrees), a parameter correction process is triggered—the advection transport parameters are recalculated using the changes in wind speed and wind direction, the turbulent diffusion coefficient and sedimentation parameters are recalculated using the changes in temperature and humidity, and finally, these three are combined into the second pollutant diffusion parameter; if the change does not exceed the threshold, the first pollutant diffusion parameter is directly used as the second pollutant diffusion parameter, avoiding frequent invalid calculations due to small fluctuations.

[0043] Specifically, the second set of updates targets the dynamic behavior data of the crowd. In this embodiment, the leak area is divided into several grid cells (e.g., 5m × 5m squares). Based on the first set of dynamic behavior data (real-time coordinates, direction of movement, and speed of each pedestrian), the average movement vector of the crowd within each grid cell is calculated. Then, combined with the wind field data of the area where the grid cell is located, the local airflow disturbance vector of each grid cell is obtained through iterative calculation—this process considers the mutual influence of airflow between adjacent grid cells and crowd behavior patterns (e.g., unidirectional movement, opposing movement, local stagnation, or circling). If the change in the current dynamic behavior data of the crowd compared to the previous moment exceeds a second preset threshold (e.g., a sudden 50% increase in crowd density within a grid cell or a change in movement direction from unidirectional to opposing), these local airflow disturbance vectors are used to adjust the diffusion coefficient and concentration correction factor in the first heavy vapor concentration estimation parameters to generate the second heavy vapor concentration estimation parameters; otherwise, the parameters from the previous moment are directly used.

[0044] Specifically, the third set of updates is based on environmental sensor data. This embodiment compares the current first environmental sensor data with the second environmental sensor data from the previous moment. If the change exceeds a third preset threshold (e.g., a sensor reading suddenly increases by more than 30%), the first environmental sensor data is input into a first preset local diffusion model. A second preset local diffusion model is obtained through the following steps: first, the deviation between the concentration prediction value and the actual sensor measurement value at each sensor location is calculated using the first preset local diffusion model; then, a correction coefficient is determined based on the magnitude and direction of the deviation; finally, the local diffusion coefficient in the first preset local diffusion model is adjusted using this correction coefficient, making the corrected model output closer to the actual monitored value. If the sensor data change does not exceed the threshold, the first preset local diffusion model is directly used as the second preset local diffusion model. Through these three sets of parallel differentiated updates, the system can keep pollutant diffusion parameters, heavy vapor concentration estimation parameters, and local diffusion models synchronized with the real environment while ensuring computational efficiency.

[0045] In a preferred embodiment, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: If the change in the first meteorological data relative to the second meteorological data at the previous moment is greater than a first preset threshold, then the first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter; otherwise, the first pollutant diffusion parameter is used as the second pollutant diffusion parameter.

[0046] In a preferred embodiment, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: Obtain the wind speed change, wind direction change, temperature change, and humidity change from the first meteorological data; Based on the changes in wind speed and wind direction, the advection transport parameters are determined, and based on the changes in temperature and humidity, the turbulence diffusion coefficient and settling parameters are determined. The second pollutant diffusion parameters are determined based on the advection transport parameters, the turbulent diffusion coefficient, and the sedimentation parameters.

[0047] In a preferred embodiment, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: If the change in the dynamic behavior data of the first population relative to the dynamic behavior data of the second population at the previous moment is greater than the second preset threshold, then the first heavy steam concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy steam concentration estimation parameter; otherwise, the first heavy steam concentration estimation parameter is used as the second heavy steam concentration estimation parameter.

[0048] In a preferred embodiment, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: Based on the dynamic behavior data of the first crowd, the average movement vector corresponding to the crowd in each grid unit is calculated; wherein, each grid unit is determined by dividing several preset areas in the leakage area; The wind field data of each preset area is obtained, and the local airflow disturbance vector of each grid cell is obtained based on the average movement vector of the crowd corresponding to each grid cell and the wind field data of each preset area. The first heavy vapor concentration estimation parameters are corrected based on the local airflow disturbance vector of each grid cell to obtain the second heavy vapor concentration estimation parameters.

[0049] Specifically, this embodiment first divides the leak area into multiple small grids (e.g., 5 meters square). Then, based on crowd dynamic data, it calculates the average movement vector of all people in each grid, i.e., the overall direction and speed of movement of the crowd within that grid. Next, this embodiment obtains wind field data for each grid location—this wind field is not simply the wind speed predicted in weather forecasts, but rather a local airflow that takes into account factors such as buildings and street orientation. The average movement vector of the crowd and the wind field data are combined, and the local airflow disturbance vector for each grid is obtained through iterative calculation. During iteration, the mutual influence of airflow between adjacent grids and crowd behavior patterns are considered. Finally, these local airflow disturbance vectors are used to adjust the diffusion coefficient in the heavy vapor diffusion model; for example, increasing the diffusion coefficient where the crowd's movement direction is consistent and decreasing it where the crowd is stationary, thereby obtaining the corrected heavy vapor concentration estimation parameters.

[0050] In a preferred embodiment, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: If the change in the first environmental sensor data relative to the second environmental sensor data at the previous moment is greater than a third preset threshold, then the first environmental sensor data is input into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model; otherwise, the first preset local diffusion model is used as the second preset local diffusion model.

[0051] In a preferred embodiment, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: Based on the preset environmental sensor prediction data and the first environmental sensor data, a deviation amount is determined to measure the deviation between the predicted value and the actual value. Based on the deviation, determine the correction coefficient of the first preset local diffusion model; Based on the correction coefficient, the local diffusion coefficient in the first preset local diffusion model is adjusted to obtain the second preset local diffusion model.

[0052] Specifically, this embodiment reads the concentration prediction values ​​of the first preset local diffusion model at the locations of each environmental sensor. These prediction values ​​are calculated based on the model parameters from the previous moment. Simultaneously, this embodiment collects real-time data from the first environmental sensor using gas concentration sensors deployed within the leak area; this data represents the measured concentration values ​​at each sensor location at the current moment. The deviation is obtained by subtracting the predicted value from the measured value at each sensor location. This deviation can be positive (predicted value too high) or negative (predicted value too low). This embodiment determines the correction coefficient based on the absolute value and direction of the deviation. For example, if the measured concentration at a sensor location is 30% higher than the predicted value, it indicates that the model underestimated the diffusion intensity in that local area, and the correction coefficient will be greater than 1; conversely, if the measured value is lower than the predicted value, the correction coefficient will be less than 1. The specific value of the correction coefficient can be calculated using a proportional-integral-derivative (PID) algorithm or empirical formulas; the larger the deviation, the greater the deviation of the correction coefficient from 1. Finally, this correction coefficient is multiplied by the local diffusion coefficient in the first preset local diffusion model to obtain the second preset local diffusion model. In this way, when faced with similar weather and population conditions, the updated model's output concentration predictions will converge towards the actual monitored values, thereby reducing the prediction error at the next moment. If the correction directions given by multiple sensors are inconsistent, the system will also take the weighted average as the final correction coefficient to avoid misadjustment caused by noise from a single sensor.

[0053] S3. Determine the gas concentration distribution and the risk status of each preset power grid device based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model. In a preferred implementation, after updating the pollutant diffusion parameters, heavy vapor concentration estimation parameters, and local diffusion model, this embodiment uses these three sets of parameters to jointly extrapolate the current gas concentration distribution. Specifically, the system inputs the second pollutant diffusion parameter into the macroscopic diffusion model to simulate the migration path and concentration decay of pollutants in a large-scale atmospheric environment. Simultaneously, for densely populated or topographically complex micro-segments, this embodiment calls the second preset local diffusion model and, combined with the second heavy vapor concentration estimation parameter, performs fine-tuning of the concentration distribution within the micro-segment, thereby obtaining a high-resolution concentration distribution map of the entire leak area. The map uses contour lines or color gradients to indicate the real-time concentration values ​​at different locations. Based on this, this embodiment compares the concentration values ​​at the locations of preset power grid equipment within the leak area one by one, assessing the current risk level of each target according to a pre-set risk threshold—for example, a concentration below the warning threshold is marked as "low risk," between the warning and evacuation thresholds is marked as "medium risk," and exceeding the evacuation threshold is marked as "high risk." If a preset power grid device happens to be located on the main diffusion path of the pollutant, even if the current concentration has not exceeded the standard, the system will still provide a "potential risk" prediction based on the diffusion trend. Ultimately, the risk status of all pre-set power grid equipment will be presented on the concentration distribution map in the form of a list or icon annotation, allowing emergency command personnel to quickly locate key areas that require priority handling.

[0054] S4. Based on the gas concentration distribution and the risk status of each of the preset power grid devices, update the first gas concentration distribution map to obtain a second gas concentration distribution map for displaying the current gas leakage status of each of the preset power grid devices.

[0055] In a preferred embodiment, after obtaining the current gas concentration distribution and the risk status of each preset power grid device, this embodiment begins to update the first gas concentration distribution map from the previous moment. First, this embodiment retains the geographical base map information from the original map, and then overlays the newly calculated concentration distribution data onto the base map in the form of contour lines or heat maps. The concentration contour lines are regenerated based on the measured and calculated results; for example, the boundary lines corresponding to thresholds such as 0.1ppm, 0.5ppm, and 1ppm are smoothly drawn, and different concentration areas are filled with color gradations from light yellow to dark red. For each preset power grid device, the system differentiates its risk status on the map: low-risk targets are marked with green dots or "Safe" labels, medium-risk targets with yellow triangles and the word "Caution," and high-risk targets with flashing red icons and an accompanying "Evacuation" prompt. If the risk status of a target changes compared to the previous moment, this embodiment will use a continuous visual transition method. For example, the color of the target's icon will gradually change from green to yellow within 0.5 seconds, while the concentration contour line will smoothly move from the old position to the new position, instead of abruptly changing. This way, users can intuitively feel the dynamic evolution of the leakage range.

[0056] Furthermore, based on the gas concentration distribution maps, this embodiment presents the integrated event impact using a continuous visual transition. This means that when the event impact changes, the visual elements on the interface do not suddenly change, but rather update smoothly and gradually, such as gradually expanding or shrinking the diffusion range, or gradually changing the color depth, thereby helping users better understand the dynamic evolution of the event. In addition, this embodiment also provides a time navigation function, allowing users to review or preview the evolution of the event impact. Users can use controls such as the timeline and play button to view the event impact at a specific point in the past, or simulate the possible development trend of the event over a future period. This is of great significance for event review and analysis and the formulation of emergency plans.

[0057] In summary, this application's embodiments, by acquiring the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters from the previous moment, provide a historical state benchmark for subsequent iterative updates, avoiding the blindness of starting from zero for each estimation and ensuring the continuity and consistency of monitoring results over time. Secondly, by correcting the first pollutant diffusion parameters based on first meteorological data, the accuracy of diffusion range estimation is improved. Thirdly, by correcting the first heavy vapor concentration estimation parameters based on first population dynamic behavior data, the shortcomings of traditional methods that rely solely on macroscopic wind fields while ignoring the impact of population activity on near-surface airflow are overcome, significantly improving the accuracy of heavy vapor concentration distribution estimation in complex urban environments or densely populated areas. Furthermore, by inputting first environmental sensor data into a first preset local diffusion model for adjustment, and using the sensor's measured concentration values ​​as a calibration benchmark, deviation correction is applied to the local diffusion model's output, dynamically reducing the error between the model's predicted values ​​and the actual monitored values, further enhancing the reliability of local area concentration estimation. Finally, based on the corrected second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid device are comprehensively determined, and the second gas concentration distribution map is updated accordingly. This allows the monitoring results to not only reflect the overall macroscopic situation of leakage diffusion but also to more accurately present the specific impact on each preset power grid device. Therefore, the embodiments of this application can solve the problem of insufficient accuracy in gas leakage monitoring in the prior art.

[0058] Example 2 like Figure 2 As shown, based on the above method embodiments, corresponding device embodiments are provided; An embodiment of the present invention provides a gas leakage monitoring device for power grid equipment, comprising: a data acquisition module 21, a first monitoring module 22, a second monitoring module 23, and a third monitoring module 24; The data acquisition module 21 is used to acquire real-time data of the gas leakage area, and to acquire the first gas concentration distribution map, the first pollutant diffusion parameter, and the first heavy vapor concentration estimation parameter of the leakage area at the previous moment; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leakage area includes several preset power grid devices; The first monitoring module 22 is used to correct the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter, and to correct the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter, and to input the first environmental sensor data into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. The second monitoring module 23 is used to determine the gas concentration distribution and the risk status of each preset power grid device based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters and the second preset local diffusion model. The third monitoring module 24 is used to update the first gas concentration distribution map according to the gas concentration distribution and the risk status of each of the preset power grid devices, so as to obtain a second gas concentration distribution map for displaying the current gas leakage status of each of the preset power grid devices.

[0059] In a preferred embodiment, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: If the change in the first meteorological data relative to the second meteorological data at the previous moment is greater than a first preset threshold, then the first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter; otherwise, the first pollutant diffusion parameter is used as the second pollutant diffusion parameter.

[0060] In a preferred embodiment, the step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: Obtain the wind speed change, wind direction change, temperature change, and humidity change from the first meteorological data; Based on the changes in wind speed and wind direction, the advection transport parameters are determined, and based on the changes in temperature and humidity, the turbulence diffusion coefficient and settling parameters are determined. The second pollutant diffusion parameters are determined based on the advection transport parameters, the turbulent diffusion coefficient, and the sedimentation parameters.

[0061] In a preferred embodiment, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: If the change in the dynamic behavior data of the first population relative to the dynamic behavior data of the second population at the previous moment is greater than the second preset threshold, then the first heavy steam concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy steam concentration estimation parameter; otherwise, the first heavy steam concentration estimation parameter is used as the second heavy steam concentration estimation parameter.

[0062] In a preferred embodiment, the step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: Based on the dynamic behavior data of the first crowd, the average movement vector corresponding to the crowd in each grid unit is calculated; wherein, each grid unit is determined by dividing several preset areas in the leakage area; The wind field data of each preset area is obtained, and the local airflow disturbance vector of each grid cell is obtained based on the average movement vector of the crowd corresponding to each grid cell and the wind field data of each preset area. The first heavy vapor concentration estimation parameters are corrected based on the local airflow disturbance vector of each grid cell to obtain the second heavy vapor concentration estimation parameters.

[0063] In a preferred embodiment, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: If the change in the first environmental sensor data relative to the second environmental sensor data at the previous moment is greater than a third preset threshold, then the first environmental sensor data is input into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model; otherwise, the first preset local diffusion model is used as the second preset local diffusion model.

[0064] In a preferred embodiment, the step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: Based on the preset environmental sensor prediction data and the first environmental sensor data, a deviation amount is determined to measure the deviation between the predicted value and the actual value. Based on the deviation, determine the correction coefficient of the first preset local diffusion model; Based on the correction coefficient, the local diffusion coefficient in the first preset local diffusion model is adjusted to obtain the second preset local diffusion model.

[0065] For more detailed steps and working principles of this embodiment, please refer to the relevant description in Embodiment 1, but not limited to these descriptions.

[0066] In summary, this application's embodiments, by acquiring the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters from the previous moment, provide a historical state benchmark for subsequent iterative updates, avoiding the blindness of starting from zero for each estimation and ensuring the continuity and consistency of monitoring results over time. Secondly, by correcting the first pollutant diffusion parameters based on first meteorological data, the accuracy of diffusion range estimation is improved. Thirdly, by correcting the first heavy vapor concentration estimation parameters based on first population dynamic behavior data, the shortcomings of traditional methods that rely solely on macroscopic wind fields while ignoring the impact of population activity on near-surface airflow are overcome, significantly improving the accuracy of heavy vapor concentration distribution estimation in complex urban environments or densely populated areas. Furthermore, by inputting first environmental sensor data into a first preset local diffusion model for adjustment, and using the sensor's measured concentration values ​​as a calibration benchmark, deviation correction is applied to the local diffusion model's output, dynamically reducing the error between the model's predicted values ​​and the actual monitored values, further enhancing the reliability of local area concentration estimation. Finally, based on the corrected second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid device are comprehensively determined, and the second gas concentration distribution map is updated accordingly. This allows the monitoring results to not only reflect the overall macroscopic situation of leakage diffusion but also to more accurately present the specific impact on each preset power grid device. Therefore, the embodiments of this application can solve the problem of insufficient accuracy in gas leakage monitoring in the prior art.

[0067] It is understood that the above-described device embodiments correspond to the method embodiments of this application, and can implement the gas leakage monitoring method for power grid equipment provided by any of the above-described method embodiments of this application.

[0068] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided in this application, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0069] Example 3 Based on the above embodiments of the gas leak monitoring method for power grid equipment, another embodiment of this application provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the gas leak monitoring method for power grid equipment according to any embodiment of this application.

[0070] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more module units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0071] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0072] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0073] Example 4 Based on the above-described method embodiments, another embodiment of this application provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute the gas leakage monitoring method for power grid equipment described in any of the above-described method embodiments of this application.

[0074] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

Claims

1. A method for monitoring gas leaks in power grid equipment, characterized in that, include: Real-time data of the gas leakage area is obtained, and a first gas concentration distribution map, a first pollutant diffusion parameter, and a first heavy vapor concentration estimation parameter of the leakage area at the previous moment are obtained; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leakage area includes several preset power grid devices; The first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter. The first heavy vapor concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter. The first environmental sensor data is input into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. Based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model, the gas concentration distribution and the risk status of each preset power grid equipment are determined. Based on the gas concentration distribution and the risk status of each of the preset power grid devices, the first gas concentration distribution map is updated to obtain a second gas concentration distribution map that displays the current gas leakage status of each of the preset power grid devices.

2. The gas leakage monitoring method for power grid equipment as described in claim 1, characterized in that, The step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: If the change in the first meteorological data relative to the second meteorological data at the previous moment is greater than a first preset threshold, then the first pollutant diffusion parameter is corrected based on the first meteorological data to obtain the second pollutant diffusion parameter; otherwise, the first pollutant diffusion parameter is used as the second pollutant diffusion parameter.

3. The gas leakage monitoring method for power grid equipment as described in claim 2, characterized in that, The step of correcting the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter includes: Obtain the wind speed change, wind direction change, temperature change, and humidity change from the first meteorological data; Based on the changes in wind speed and wind direction, the advection transport parameters are determined, and based on the changes in temperature and humidity, the turbulence diffusion coefficient and settling parameters are determined. The second pollutant diffusion parameters are determined based on the advection transport parameters, the turbulent diffusion coefficient, and the sedimentation parameters.

4. The gas leakage monitoring method for power grid equipment as described in claim 1, characterized in that, The step of correcting the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter includes: If the change in the dynamic behavior data of the first population relative to the dynamic behavior data of the second population at the previous moment is greater than the second preset threshold, then the first heavy steam concentration estimation parameter is corrected based on the first population dynamic behavior data to obtain the second heavy steam concentration estimation parameter; otherwise, the first heavy steam concentration estimation parameter is used as the second heavy steam concentration estimation parameter.

5. A gas leakage monitoring method for power grid equipment as described in claim 4, characterized in that, The step of correcting the first heavy vapor concentration estimation parameters based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameters includes: Based on the dynamic behavior data of the first crowd, the average movement vector corresponding to the crowd in each grid unit is calculated; wherein, each grid unit is determined by dividing several preset areas in the leakage area; The wind field data of each preset area is obtained, and the local airflow disturbance vector of each grid cell is obtained based on the average movement vector of the crowd corresponding to each grid cell and the wind field data of each preset area. The first heavy vapor concentration estimation parameters are corrected based on the local airflow disturbance vector of each grid cell to obtain the second heavy vapor concentration estimation parameters.

6. A gas leakage monitoring method for power grid equipment as described in claim 1, characterized in that, The step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: If the change in the first environmental sensor data relative to the second environmental sensor data at the previous moment is greater than a third preset threshold, then the first environmental sensor data is input into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model; otherwise, the first preset local diffusion model is used as the second preset local diffusion model.

7. A gas leakage monitoring method for power grid equipment as described in claim 6, characterized in that, The step of inputting the first environmental sensor data into a first preset local diffusion model for adjustment to obtain a second preset local diffusion model includes: Based on the preset environmental sensor prediction data and the first environmental sensor data, a deviation amount is determined to measure the deviation between the predicted value and the actual value. Based on the deviation, determine the correction coefficient of the first preset local diffusion model; Based on the correction coefficient, the local diffusion coefficient in the first preset local diffusion model is adjusted to obtain the second preset local diffusion model.

8. A gas leak monitoring device for power grid equipment, characterized in that, include: The system comprises a data acquisition module, a first monitoring module, a second monitoring module, and a third monitoring module. The data acquisition module is used to acquire real-time data of the gas leakage area, and to acquire the first gas concentration distribution map, first pollutant diffusion parameters, and first heavy vapor concentration estimation parameters of the leakage area at the previous moment; wherein, the real-time data includes first meteorological data, first population dynamic behavior data, and first environmental sensor data, and the leakage area includes several preset power grid devices; The first monitoring module is used to correct the first pollutant diffusion parameter based on the first meteorological data to obtain the second pollutant diffusion parameter, and to correct the first heavy vapor concentration estimation parameter based on the first population dynamic behavior data to obtain the second heavy vapor concentration estimation parameter, and to input the first environmental sensor data into the first preset local diffusion model for adjustment to obtain the second preset local diffusion model. The second monitoring module is used to determine the gas concentration distribution and the risk status of each preset power grid device based on the second pollutant diffusion parameters, the second heavy vapor concentration estimation parameters, and the second preset local diffusion model. The third monitoring module is used to update the first gas concentration distribution map based on the gas concentration distribution and the risk status of each of the preset power grid devices, so as to obtain a second gas concentration distribution map that displays the current gas leakage status of each of the preset power grid devices.

9. A terminal device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements a gas leak monitoring method for power grid equipment as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform a gas leak monitoring method for power grid equipment as described in any one of claims 1 to 7.

Images