An outdoor installation GIS gas leakage fault diagnosis method and system

Abstract

This invention discloses a method and system for diagnosing gas leaks in outdoor GIS equipment, relating to the field of power equipment monitoring technology. The method includes acquiring time-series data synchronously collected by a mobile inspection platform moving along the periphery of the GIS equipment, including the original concentration of sulfur hexafluoride gas, ambient wind speed, wind direction angle, and platform spatial coordinate sequence; denoising the original concentration sequence and compensating for environmental wind field interference by combining the wind speed and wind direction angle sequences to generate a corrected concentration sequence; inputting this into a preset sensor dynamic response inverse model to obtain an instantaneous true concentration estimation sequence compensated for physical response lag; smoothing and interpolating the platform spatial coordinate sequence trajectory to generate a continuous motion trajectory function; spatiotemporally fusing the instantaneous true concentration estimation sequence with the motion trajectory function to generate a spatial concentration distribution function, and determining the spatial coordinates of the leak source by searching for its global or local maxima. This invention can eliminate the influence of wind field on gas diffusion and improve the accuracy of leak concentration measurement.

Description

Technical Field

[0001] This invention relates to the field of power equipment monitoring technology, and in particular to a method and system for diagnosing air leakage faults in outdoor-installed GIS. Background Technology

[0002] Gas-insulated switchgear (GIS) is widely used in power system transmission and transformation due to its advantages such as small size, excellent insulation performance, and long maintenance cycle, especially in substations in complex outdoor environments. Sulfur hexafluoride (SF6), the core insulating and arc-quenching medium of GIS, can cause its leakage, directly leading to a decrease in insulation performance and failure of arc-quenching capability, causing equipment failure and even grid outages, resulting in significant economic losses. Therefore, rapid and accurate diagnosis of SF6 leakage faults in outdoor GIS equipment has become a critical requirement for the power industry to ensure the safe operation of equipment.

[0003] In practical applications of outdoor GIS gas leak fault diagnosis, mobile inspection mode is widely used due to its ability to cover the entire equipment range and its high flexibility. However, the complex and ever-changing wind field in the outdoor environment has become a core bottleneck restricting the accuracy of diagnosis. Existing mobile inspection and diagnostic technologies fail to effectively handle the interference of wind field on the diffusion of leaked sulfur hexafluoride gas. Relying solely on raw concentration measurement data for leak source location leads to distortion of concentration distribution characteristics and large measurement deviations, ultimately resulting in low leak source location accuracy and large errors. This fails to meet the actual needs of the power industry for accurate handling of leak faults in outdoor GIS equipment. Summary of the Invention

[0004] To address the problem that existing technologies cannot eliminate the interference of wind fields on the diffusion of leaked sulfur hexafluoride gas, resulting in low accuracy and large errors in leak source location, this invention provides a method and system for diagnosing leaks in outdoor-installed GIS systems. This system effectively eliminates the influence of wind fields on the diffusion of leaked gas through environmental wind field interference compensation, thereby improving the accuracy of leak concentration measurement. The specific technical solution is as follows: This invention provides a method for diagnosing air leakage faults in outdoor-installed GIS systems, comprising: S1. Acquire the time-series data collected synchronously by the mobile inspection platform as it moves along the periphery of the GIS equipment. The time-series data includes the original concentration measurement sequence of sulfur hexafluoride gas, the environmental wind speed sequence, the environmental wind direction angle sequence, and the platform spatial coordinate sequence. S2. Denoise the original concentration measurement sequence to obtain a denoised concentration sequence; S3. Based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence, environmental wind field interference compensation is performed to generate an environmentally corrected concentration sequence. S4. Input the environmental correction concentration sequence into the preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. S5. Perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function; S6. The instantaneous true concentration estimation sequence is spatiotemporally fused with the continuous motion trajectory function to generate a spatial concentration distribution function, and the spatial coordinates of the leakage source are determined by searching for the global or local maxima of the spatial concentration distribution function.

[0005] Preferably, the denoising process for the original concentration measurement sequence includes: The original concentration measurement sequence was decomposed into multiple scales using discrete wavelet transform. Based on online estimation of the current environmental noise characteristics, the wavelet basis function and decomposition scale are adaptively selected; Among them, the wavelet basis function is selected by calculating the matching degree between the baseline noise signal collected under the leakage-free steady state and each basis function in the candidate wavelet basis function set, and selecting the basis function with the highest matching degree as the current denoising basis function; The energy percentage that satisfies the approximation coefficient of the J-th layer at the selected decomposition scale first exceeds the preset energy percentage threshold γ; the energy percentage The calculation formula is: in, These are the approximation coefficients for the Jth layer; For the first Layer detail factor; The scale for wavelet decomposition; The index is the ordinal number of the coefficient.

[0006] Preferably, a method for diagnosing air leakage faults in outdoor-installed GIS systems further includes: During the acquisition of time-series data, the instantaneous concentration change rate or concentration estimate is calculated in real time; When the instantaneous concentration change rate is detected to be greater than a preset change threshold or the estimated concentration value is greater than a preset concentration threshold, the mobile inspection platform is determined to have entered a suspected leak area, and a scanning mode is triggered. The mobile inspection platform is then controlled to perform at least one of the following operations in the suspected leak area: Change movement speed from cruising speed Adjust to scan speed ,satisfy ; Change the data sampling frequency from Upgraded to ,satisfy ; The mobile inspection platform is controlled to perform a reciprocating path scan within a designated area centered on the trigger location coordinates of the suspected leak area and with a preset length as the side length; Based on the higher spatiotemporal resolution time series data acquired in scanning mode, steps S2 to S6 are executed.

[0007] Preferably, the discrete-time expression of the inverse model of the sensor's dynamic response is: in, For the first The instantaneous concentration estimate at time [time]. For the first Environmental correction concentration value at any time, The time constant of the sensor, This represents the static sensitivity coefficient of the sensor. The sampling period.

[0008] Preferably, the time constant Calibrated in the following manner: Under standard experimental conditions, a force is applied to the sensor from... arrive The step concentration excitation was recorded, and the time required for the sensor output to reach the preset steady-state value was recorded. Calculate the time constant using the following formula. : in, The time required for the sensor output to reach the preset steady-state value.

[0009] Preferably, the environmental wind field interference compensation is achieved through the following calculations: Calculate the correction factor for surface concentration measurement based on wind field. : in, and The first Wind speed and wind direction at any given time. For measurement points The normal direction angle of the surface of the GIS equipment. An empirical attenuation coefficient related to the equipment geometry and environment; Calculate the environmental correction concentration value: in, This is the minimum correction factor protection threshold.

[0010] Preferably, in determining the coordinates of the leakage source After that, it also includes: Based on spatial concentration distribution The leakage rate is estimated by integrating the data within a certain range downwind of the leakage source. : in, For the selected integration region, For the area of ​​the spatial grid, and The average wind speed and direction within the integration area. The principal axis direction of the integration region. The diffusion coefficient is related to the properties of the gas.

[0011] Preferably, the step of spatiotemporally fusing the instantaneous true concentration estimation sequence with the continuous motion trajectory function to generate a spatial concentration distribution function, and determining the spatial coordinates of the leakage source by searching for the global or local maxima of the spatial concentration distribution function, includes: Based on the synchronization timestamp, each concentration value in the instantaneous true concentration estimation sequence is mapped to the corresponding spatial location described by the continuous motion trajectory function; The discrete location and concentration point pairs are transformed into a continuous spatial concentration distribution function through spatial interpolation algorithms. The peak search algorithm is used to search the spatial concentration distribution function and identify the extreme points of concentration anomalies; The spatial coordinates corresponding to the extreme points are determined as the location of the gas leak source in the GIS equipment, thus completing the location diagnosis.

[0012] Preferably, a method for diagnosing air leakage faults in outdoor-installed GIS systems further includes: Collect environmentally corrected concentration sequences during leak-free alarm periods Based on the corresponding environmental parameters, a concentration baseline model for each monitoring point was constructed. ,in An environmental vector containing temperature, humidity, wind speed, and wind direction; The baseline model is updated using data within the sliding time window, and the deviation between the current concentration reading and the baseline prediction is calculated. ; When the deviation Continuously exceeding the dynamic threshold When the preset number of occurrences is reached, an early leak warning will be triggered.

[0013] This invention also provides an outdoor-installed GIS air leakage fault diagnosis system, which applies the aforementioned method and includes: The data acquisition unit is used to acquire time-series data synchronously collected by the mobile inspection platform as it moves along the periphery of the GIS equipment. The time-series data includes the original concentration measurement sequence of sulfur hexafluoride gas, the environmental wind speed sequence, the environmental wind direction angle sequence, and the platform spatial coordinate sequence. The first data processing unit is used to perform noise reduction processing on the original concentration measurement value sequence to obtain a noise-reduced concentration sequence. An environmental compensation unit is used to perform environmental wind field interference compensation based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence to generate an environmentally corrected concentration sequence. The true concentration calculation unit is used to input the environmentally corrected concentration sequence into a preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. The second data processing unit is used to perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function. The fault location analysis unit is used to perform spatiotemporal fusion of the instantaneous true concentration estimation sequence and the continuous motion trajectory function to generate a spatial concentration distribution function, and to determine the spatial coordinates of the leakage source by searching for the global or local maxima of the spatial concentration distribution function.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides a method for diagnosing gas leaks in outdoor-installed GIS systems. By simultaneously collecting multi-dimensional time-series data including concentration, wind speed, wind direction, and spatial coordinates, and compensating for environmental wind field interference, the method effectively eliminates the influence of wind on the diffusion of leaked gas, improving the accuracy of leak concentration measurement. Simultaneously, by combining noise reduction processing and sensor dynamic response inverse model compensation, measurement deviations are further corrected to obtain a precise instantaneous real concentration sequence. Spatiotemporal data fusion is achieved through trajectory smoothing interpolation to generate a spatial concentration distribution function. Extreme point search is used to locate the spatial coordinates of the leak source, significantly improving the accuracy of leak source location. This solution is suitable for outdoor mobile inspection scenarios, eliminating the need for additional fixed monitoring points. It provides maintenance personnel with a basis for rapid fault handling, ensuring the safe and stable operation of GIS equipment, while reducing the environmental risks associated with sulfur hexafluoride gas leaks. Attached Figure Description

[0015] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0016] Figure 1 This is a flowchart of a method for diagnosing air leakage faults in outdoor-installed GIS according to the present invention.

[0017] Figure 2 This is a schematic diagram of an outdoor-installed GIS air leakage fault diagnosis system according to the present invention.

[0018] Figure 3This is a schematic diagram of the GIS structure of the present invention.

[0019] Figure 4 This is a simplified schematic diagram of the guide rail of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that, when used in this specification, the terms “comprising” and “including” indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0022] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] It should also be further understood that the term "and / or" as used in this specification refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes such combinations.

[0024] See Figure 3 and Figure 4 This invention provides a simplified structural principle for diagnosing gas leakage faults in outdoor-installed gas-insulated switchgear (GIS). The structure includes a sulfur hexafluoride (SF6) gas sensor module 1, a wind direction and speed module 2, a positioning module 3, a track inspection robot module 4, a track module 5, a signal transmission module 7, and a test and calculation module 6. The SF6 gas sensor module 1, wind direction and speed module 2, and positioning module 3 are fixedly mounted on the track inspection robot module 4, which is movable on the track module 5. The track module 5 is a circular track coaxial with the gas chamber connection flange. The detection terminals of the SF6 gas sensor module 1 are located close to the GIS flange, and the SF6 gas sensor module 1 and wind direction and speed module 2 are installed close together. The signal transmission module 7 transmits the information collected by the SF6 gas sensor module 1 and wind direction and speed module 2 to the test and calculation module 6.

[0025] Please see Figure 1Based on the simplified structural principle of outdoor-installed gas-insulated switchgear (GIS) leakage fault diagnosis, this invention provides a method for diagnosing leakage faults in outdoor-installed GIS, including: S1. Acquire time-series data synchronously collected by the mobile inspection platform as it moves along the perimeter of the GIS equipment. The time-series data includes a sequence of original concentration measurements of sulfur hexafluoride gas. Environmental wind speed value sequence Environmental wind direction sequence and platform space coordinate sequence ,in This represents the total number of sampling points; In practice, mobile inspection platforms, such as track robots and drones, are controlled to perform inspections along pre-set or real-time planned paths, close to the periphery of GIS equipment. During the movement, the integrated sensing unit on the platform synchronously collects time-series data streams using a unified clock source.

[0026] S2. Denoise the original concentration measurement sequence to obtain a denoised concentration sequence; Using Discrete Wavelet Transform (DWT) Perform multi-scale decomposition; Based on online estimation of the current environmental noise characteristics, wavelet basis functions are adaptively selected. Decomposition Scale ; The adaptive selection is achieved through the following steps: Calculate the baseline noise signal acquired under leak-free steady-state conditions. With candidate wavelet basis function set The degree of matching of each basis function : , Select the wavelet basis function with the highest matching degree. As the current denoising basis function; The decomposition scale The conditions for determining whether the following conditions are met are: No. Layer approximation coefficient Energy percentage First time exceeding the preset threshold (generally ): in, These are the approximation coefficients for the Jth layer; For the first Layer detail factor; The scale for wavelet decomposition; The index is the ordinal number of the coefficient.

[0027] S3. Based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence, environmental wind field interference compensation is performed to generate an environmentally corrected concentration sequence. The environmental wind field interference compensation is achieved through the following model: Calculate the correction factor for surface concentration measurement based on wind field. : in, and The first Wind speed and wind direction at any given time. For measurement points The normal direction angle of the surface of the GIS equipment. Empirical attenuation coefficients related to equipment geometry and environment ( ); Calculate the environmental correction concentration value: in, This is the minimum correction factor protection threshold.

[0028] One of the biggest challenges in leak detection for outdoor GIS equipment is the interference of natural wind. Wind disperses and dilutes leaked gas, causing significant deviations between sensor readings and the actual leak intensity and location. This paper quantifies the amplifying effect of wind on apparent concentration (e.g., concentration accumulation on the windward side) or the weakening effect (e.g., concentration dilution on the leeward side) by combining wind speed, wind direction, and the geometric orientation of the equipment surface through a cosine relationship including an empirical coefficient β. This model enables the system to maintain stable detection sensitivity and positioning accuracy under different wind speeds and directions.

[0029] S4. Input the environmental correction concentration sequence into the preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. The discrete-time expression of the inverse model of the sensor's dynamic response is: in, For the first The instantaneous concentration estimate at time [time]. For the first Environmental correction concentration value at any time, The time constant of the sensor, This represents the static sensitivity coefficient of the sensor. The sampling period is This is a discrete-time index.

[0030] Compared to using complex black-box models, such as neural networks for hysteresis compensation, this model requires very little computation and is suitable for efficient operation in embedded devices with limited computing power or edge computing units that require real-time processing, ensuring the real-time response of the system.

[0031] Specifically, the time constant Calibrated in the following manner: Under standard experimental conditions, a force is applied to the sensor from... arrive A step concentration excitation was applied, and the sensor output was recorded until a steady-state value was reached. 90% of the time required Calculate the time constant using the following formula. : S5. Perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function; To ensure spatial positioning accuracy, the platform's original positioning coordinates are processed: The Kalman filter or extended Kalman filter (EKF) is used to perform optimal estimation and smoothing of the platform spatial coordinate sequence containing measurement noise; For periods of data loss due to signal obstruction or other reasons, spline interpolation and other algorithms are used to perform trajectory interpolation, generating a high-precision platform continuous motion trajectory function that is continuous in time and smooth in space, which serves as the benchmark for spatial mapping of concentration data.

[0032] S6. The instantaneous true concentration estimation sequence and the continuous motion trajectory function are spatiotemporally fused at a unified timestamp to generate a spatial concentration distribution function. The spatial coordinates of the leakage source are determined by searching for the global or local maxima of the spatial concentration distribution function.

[0033] Based on the synchronization timestamp, each concentration value in the instantaneous true concentration estimation sequence is mapped to the corresponding spatial location described by the continuous motion trajectory function; The discrete location and concentration point pairs are transformed into a continuous spatial concentration distribution function through spatial interpolation algorithms. The peak search algorithm is used to search the spatial concentration distribution function and identify the extreme points of concentration anomalies; The spatial coordinates corresponding to the extreme points are determined as the location of the gas leak source in the GIS equipment, thus completing the location diagnosis.

[0034] This invention provides a method for diagnosing gas leaks in outdoor-installed GIS systems. By simultaneously collecting multi-dimensional time-series data including concentration, wind speed, wind direction, and spatial coordinates, and compensating for environmental wind field interference, the method effectively eliminates the influence of wind on the diffusion of leaked gas, improving the accuracy of leak concentration measurement. Simultaneously, by combining noise reduction processing and sensor dynamic response inverse model compensation, measurement deviations are further corrected to obtain a precise instantaneous real concentration sequence. Spatiotemporal data fusion is achieved through trajectory smoothing interpolation to generate a spatial concentration distribution function. Extreme point search is used to locate the spatial coordinates of the leak source, significantly improving the accuracy of leak source location. This solution is suitable for outdoor mobile inspection scenarios, eliminating the need for additional fixed monitoring points. It provides maintenance personnel with a basis for rapid fault handling, ensuring the safe and stable operation of GIS equipment, while reducing the environmental risks associated with sulfur hexafluoride gas leaks.

[0035] It should be noted that the method also includes visual tracing of the leak event: Based on the spatial concentration distribution function and current wind field data, a time-reversed diffusion cloud map is generated, starting from the coordinates of the leakage source and reflecting the gas diffusion path and concentration decay over a historical period, through particle reverse trajectory simulation or diffusion equation inversion. The time-reversed diffusion cloud map is overlaid with the 3D model of the GIS equipment and the historical trajectory of the inspection robot to generate a comprehensive source tracing visualization interface that includes leakage source, diffusion path, concentration gradient and time information.

[0036] The comprehensive source tracing visualization interface visually recreates the entire story of the leak, providing in-depth information support for operation and maintenance decisions. Managers can easily assess the leak's impact range, identify downwind at-risk equipment, and determine the leak's duration and severity through the visualization interface.

[0037] In a preferred embodiment of this application, it further includes: During the acquisition of time-series data, the instantaneous concentration change rate is calculated in real time. or concentration estimate ; When detected or At that time, it was determined that they had entered a suspected leak area, among which The rate of change threshold, The concentration threshold; Trigger the scanning mode and control the mobile inspection platform to perform at least one of the following operations in the suspected leak area: Change movement speed from cruising speed Reduce to fine scan speed ,satisfy ; Change the data sampling frequency from Upgraded to ,satisfy ; The control platform is based on trigger points Centered on, with side length as Perform a back-and-forth scanning path planning within the square area; Based on the higher spatiotemporal resolution time-series data acquired in scanning mode, steps S2 to S6 are performed to obtain a spatial concentration distribution with higher resolution and confidence. and the coordinates of the leak point .

[0038] This preferred embodiment proposes intelligent inspection control, upgrading the traditional uniform-speed, equal-interval sampling inspection mode to an adaptive dynamic inspection strategy. When the system initially identifies areas of abnormal concentration through real-time algorithms during normal patrols, it can automatically drive the mobile platform to perform deceleration, encrypted sampling, or reciprocating scanning in the suspected area. This avoids the drawbacks of operating at low speed throughout in pursuit of high accuracy. Furthermore, in terms of accuracy, by acquiring higher spatiotemporal resolution data near potential leak points, the positioning errors caused by motion blur and insufficient sampling are reduced. This achieves a shift from passive recording to active perception and response, reducing reliance on external manual intervention.

[0039] In a preferred embodiment of this application, when determining the coordinates of the leakage source... After that, it also includes: Based on spatial concentration distribution The leakage rate is estimated by integrating the data within a certain range downwind of the leakage source. : in, For the selected integration region, For the area of ​​the spatial grid, and The average wind speed and direction within the integration area. The principal axis direction of the integration region. The diffusion coefficient is related to the properties of the gas.

[0040] In actual operation and maintenance, simply locating the leak point is insufficient for maintenance personnel to determine the urgency of the leak, whether immediate power outage for repair is necessary, or to estimate maintenance resources. This preferred embodiment provides an estimated leakage rate Q by integrating regional data based on spatial concentration distribution and wind speed and direction, thus transforming discrete spatial concentration measurements into a continuous leakage flow estimate. At the safety operation and maintenance level, leakage risks can be categorized, triggering different levels of warnings to guide the development of differentiated maintenance strategies.

[0041] In a preferred embodiment of this application, it further includes: Collect environmentally corrected concentration sequences during leak-free alarm periods Based on the corresponding environmental parameters, a concentration baseline model for each monitoring point was constructed. ,in An environmental vector containing temperature, humidity, wind speed, and wind direction; The baseline model is updated using data within the sliding time window, and the deviation between the current concentration reading and the baseline prediction is calculated. ; When the deviation Continuously exceeding the dynamic threshold When the preset number of occurrences is reached, an early warning of minor leaks will be triggered even if the absolute value does not reach the global alarm threshold. The system will then automatically increase the sensitivity of the intelligent inspection control or initiate a preventative scan of the affected area.

[0042] In this preferred embodiment, a baseline model is constructed by continuously learning the normal concentration pattern under leak-free conditions, and the deviation between the current reading and the baseline prediction is calculated in real time to identify weak, early abnormal signals. It can detect slow-growing weak leakage trends far below the fixed global alarm threshold, or abnormal concentration drifts caused by environmental changes. The baseline model and dynamic thresholds can be updated over time to adapt to slow changes caused by equipment aging and seasonal changes, maintaining long-term effectiveness.

[0043] Please see Figure 2 This invention also provides an outdoor-installed GIS air leakage fault diagnosis system, which applies the aforementioned method and includes: The data acquisition unit is used to acquire time-series data synchronously collected by the mobile inspection platform as it moves along the periphery of the GIS equipment. The time-series data includes the original concentration measurement sequence of sulfur hexafluoride gas, the environmental wind speed sequence, the environmental wind direction angle sequence, and the platform spatial coordinate sequence. The first data processing unit is used to perform noise reduction processing on the original concentration measurement value sequence to obtain a noise-reduced concentration sequence. An environmental compensation unit is used to perform environmental wind field interference compensation based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence to generate an environmentally corrected concentration sequence. The true concentration calculation unit is used to input the environmentally corrected concentration sequence into a preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. The second data processing unit is used to perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function. The fault location analysis unit is used to perform spatiotemporal fusion of the instantaneous true concentration estimation sequence and the continuous motion trajectory function at a unified timestamp to generate a spatial concentration distribution function, and to determine the spatial coordinates of the leakage source by searching for the global or local maxima of the spatial concentration distribution function.

[0044] The functional explanations of each unit in this embodiment are the same as those in an outdoor GIS air leakage fault diagnosis method, and the technical effects are the same, so they will not be repeated here.

[0045] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0046] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0047] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0048] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the specification of the present invention.

Claims

1. A method for diagnosing air leakage faults in outdoor-installed GIS systems, characterized in that, include: S1. Acquire the time-series data collected synchronously by the mobile inspection platform as it moves along the periphery of the GIS equipment. The time-series data includes the original concentration measurement sequence of sulfur hexafluoride gas, the environmental wind speed sequence, the environmental wind direction angle sequence, and the platform spatial coordinate sequence. S2. Denoise the original concentration measurement sequence to obtain a denoised concentration sequence; S3. Based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence, environmental wind field interference compensation is performed to generate an environmentally corrected concentration sequence. S4. Input the environmental correction concentration sequence into the preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. S5. Perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function; S6. The instantaneous true concentration estimation sequence is spatiotemporally fused with the continuous motion trajectory function to generate a spatial concentration distribution function, and the spatial coordinates of the leakage source are determined by searching for the global or local maxima of the spatial concentration distribution function.

2. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1, characterized in that, The denoising process for the original concentration measurement sequence includes: The original concentration measurement sequence was decomposed into multiple scales using discrete wavelet transform. Based on online estimation of the current environmental noise characteristics, the wavelet basis function and decomposition scale are adaptively selected; Among them, the wavelet basis function is selected by calculating the matching degree between the baseline noise signal collected under the leakage-free steady state and each basis function in the candidate wavelet basis function set, and selecting the basis function with the highest matching degree as the current denoising basis function; The energy percentage that satisfies the approximation coefficient of the J-th layer at the selected decomposition scale first exceeds the preset energy percentage threshold γ; the energy percentage The calculation formula is: in, These are the approximation coefficients for the Jth layer; For the first Layer detail factor; The scale for wavelet decomposition; The index is the ordinal number of the coefficient.

3. A method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1 or 2, characterized in that, Also includes: During the acquisition of time-series data, the instantaneous concentration change rate or concentration estimate is calculated in real time; When the instantaneous concentration change rate is detected to be greater than a preset change threshold or the estimated concentration value is greater than a preset concentration threshold, the mobile inspection platform is determined to have entered a suspected leak area, and a scanning mode is triggered. The mobile inspection platform is then controlled to perform at least one of the following operations in the suspected leak area: Change movement speed from cruising speed Adjust to scan speed ,satisfy ; Change the data sampling frequency from Upgraded to ,satisfy ; The mobile inspection platform is controlled to perform a reciprocating path scan within a designated area centered on the trigger location coordinates of the suspected leak area and with a preset length as the side length. Based on the higher spatiotemporal resolution time series data acquired in scanning mode, steps S2 to S6 are executed.

4. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1, characterized in that, The discrete-time expression of the inverse model of the sensor's dynamic response is: in, For the first The instantaneous concentration estimate at time [time]. For the first Environmental correction concentration values ​​at any given time The time constant of the sensor, This represents the static sensitivity coefficient of the sensor. The sampling period.

5. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 4, characterized in that, The time constant Calibrated in the following manner: Under standard experimental conditions, a force is applied to the sensor from... arrive The step concentration excitation was recorded, and the time required for the sensor output to reach the preset steady-state value was recorded. ; Calculate the time constant using the following formula : in, The time required for the sensor output to reach the preset steady-state value.

6. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 4, characterized in that, The environmental wind field interference compensation is achieved through the following calculations: Calculate the correction factor for surface concentration measurement based on wind field. : in, and The first Wind speed and wind direction at any given time. For measurement points The normal direction angle of the surface of the GIS equipment. An empirical attenuation coefficient related to the equipment geometry and environment; Calculate the environmental correction concentration value: in, This is the minimum correction factor protection threshold.

7. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1, characterized in that, Determining the coordinates of the leak source After that, it also includes: Based on spatial concentration distribution The leakage rate is estimated by integrating the data within a certain range downwind of the leakage source. : in, For the selected integration region, For the area of ​​the spatial grid, and The average wind speed and direction within the integration area. The principal axis direction of the integration region. The diffusion coefficient is related to the properties of the gas.

8. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1, characterized in that, The step of spatiotemporally fusing the instantaneous true concentration estimation sequence with the continuous motion trajectory function to generate a spatial concentration distribution function, and determining the spatial coordinates of the leakage source by searching for the global or local maxima of the spatial concentration distribution function, includes: Based on the synchronization timestamp, each concentration value in the instantaneous true concentration estimation sequence is mapped to the corresponding spatial location described by the continuous motion trajectory function; The discrete location and concentration point pairs are transformed into a continuous spatial concentration distribution function through spatial interpolation algorithms. The peak search algorithm is used to search the spatial concentration distribution function and identify the extreme points of concentration anomalies; The spatial coordinates corresponding to the extreme points are determined as the location of the gas leak source in the GIS equipment, thus completing the location diagnosis.

9. The method for diagnosing air leakage faults in outdoor-installed GIS according to claim 1, characterized in that, Also includes: Collect environmentally corrected concentration sequences during leak-free alarm periods Based on the corresponding environmental parameters, a concentration baseline model for each monitoring point was constructed. ,in An environmental vector containing temperature, humidity, wind speed, and wind direction; The baseline model is updated using data within the sliding time window, and the deviation between the current concentration reading and the baseline prediction is calculated. ; When the deviation Continuously exceeding the dynamic threshold When the preset number of occurrences is reached, an early leak warning will be triggered.

10. An outdoor-installed GIS air leakage fault diagnosis system, characterized in that, The method described by any one of claims 1 to 9 includes: The data acquisition unit is used to acquire time-series data synchronously collected by the mobile inspection platform as it moves along the periphery of the GIS equipment. The time-series data includes the original concentration measurement sequence of sulfur hexafluoride gas, the environmental wind speed sequence, the environmental wind direction angle sequence, and the platform spatial coordinate sequence. The first data processing unit is used to perform noise reduction processing on the original concentration measurement value sequence to obtain a noise-reduced concentration sequence. An environmental compensation unit is used to perform environmental wind field interference compensation based on the denoised concentration sequence, wind speed sequence, and wind direction angle sequence to generate an environmentally corrected concentration sequence. The true concentration calculation unit is used to input the environmentally corrected concentration sequence into a preset sensor dynamic response inverse model to calculate the instantaneous true concentration estimation sequence with physical response hysteresis compensated. The second data processing unit is used to perform trajectory smoothing and interpolation on the platform spatial coordinate sequence to generate a continuous motion trajectory function. The fault location analysis unit is used to perform spatiotemporal fusion of the instantaneous true concentration estimation sequence and the continuous motion trajectory function at a unified timestamp to generate a spatial concentration distribution function, and to determine the spatial coordinates of the leakage source by searching for the global or local maxima of the spatial concentration distribution function.

Images