A global subsidence monitoring method for a power substation, an electronic device, and a medium

Abstract

The application relates to a kind of global settlement monitoring methods of electric power substation, electronic equipment and medium, the method comprises: obtaining the time series settlement data of electric power substation based on PS-InSAR technology, the grid division of electric power substation area is carried out based on time series settlement data, and permanent scatterer at the intersection of grid is selected as key settlement monitoring point;Beidou settlement monitoring machine base station is set in the periphery of electric power substation, and a Beidou settlement monitoring machine station is set in the middle area of electric power substation to obtain the settlement data of the position;The settlement data of Beidou settlement monitoring machine is input into the dynamic fitting function constructed, and the settlement value of key settlement monitoring point in electric power substation is calculated in real time, wherein the dynamic fitting function represents the dynamic relationship between the settlement data of Beidou settlement monitoring machine and the settlement data of key settlement monitoring point.Compared with prior art, the application has the advantages of realizing global, real-time settlement monitoring of electric power substation at low cost and the like.

Description

Technical Field

[0001] This invention relates to the field of substation settlement monitoring technology, and in particular to a method, electronic equipment and medium for full-area settlement monitoring of power substations based on PS-InSAR technology. Background Technology

[0002] As the core hub of the power system, power substations undertake critical functions such as voltage transformation, power distribution, and transmission. Their safe and stable operation directly affects the reliability of the entire power grid. With the continuous growth of electricity demand and the expansion of power grid construction in my country, the facilities of early-built substations are gradually entering the aging stage, and problems such as declining equipment performance and reduced structural stability are becoming increasingly prominent. At the same time, to adapt to the development needs of the new power system, the number of substation renovation and expansion projects has increased significantly. However, the foundation disturbance during the renovation and expansion process, the changes in the load of new equipment, and the cumulative effect of the aging of existing facilities can easily cause uneven settlement in the substation area, leading to safety hazards such as equipment tilting, stress concentration in busbar connections, and insulator breakage. In severe cases, it can even cause equipment damage or power outages, resulting in significant economic losses and social impact.

[0003] The existing technology has the following drawbacks: 1. Although PS-InSAR (Permanent Scatterer Synthetic Aperture Radar Interferometry) technology has a wide monitoring area and low monitoring cost, it cannot achieve real-time settlement monitoring of power substations due to the limitation of SAR satellite revisit cycle. 2. Currently, settlement monitoring in power substations mostly relies on settlement monitoring robots for inspection or manual testing. Settlement monitoring robots have complex and costly equipment; while manual testing has low intelligence and high labor costs. Therefore, there is an urgent need for a settlement monitoring method for power substations that is low-cost and has a wide monitoring range.

[0004] A search revealed that Chinese invention patent application publication number CN111522006A discloses a method for monitoring land subsidence by fusing BeiDou and InSAR data. The method includes: acquiring BeiDou observation data of monitoring points within a monitoring area and synthetic aperture radar (SAR) image data of permanent scattering point (PS) points within the monitoring area; performing subsidence time-series calculations on the BeiDou observation data and the SAR image data respectively to obtain the BeiDou subsidence time-series of the monitoring points and the SAR subsidence time-series of the PS points; fusing the BeiDou subsidence time-series and the SAR subsidence time-series of common points among the PS points that overlap with the monitoring point to obtain a fused subsidence time-series of the common points; constructing a subsidence field surface equation for the monitoring area based on the fused subsidence time-series of the common points and the subsidence field surface equation; and performing spatiotemporal interpolation calculations on other PS points that do not overlap with the monitoring point to obtain fused subsidence time-series of the other PS points, thereby achieving monitoring of the monitoring area based on the fused subsidence time-series of the common points and the fused subsidence time-series of the other PS points. The existing patent application suffers from limitations due to satellite reentry cycles (resulting in time delays) and high software and hardware costs.

[0005] How to achieve real-time, full-area settlement monitoring of power substations at low cost has become a technical problem that needs to be solved. Summary of the Invention

[0006] The purpose of this invention is to overcome the defects of the prior art by providing a method, electronic equipment and medium for monitoring the settlement of the entire power substation.

[0007] The objective of this invention can be achieved through the following technical solutions: According to one aspect of the present invention, a method for monitoring the settlement of a power substation across its entire area is provided, the method comprising: The time-series settlement data of power substations are obtained based on PS-InSAR technology. The power substation area is divided into grids based on the time-series settlement data, and permanent scatterers at the grid intersections are selected as key settlement monitoring points. Beidou settlement monitoring base stations are set up around the power substation, and a Beidou settlement monitoring station is set up in the middle area of ​​the power substation to obtain settlement data at the location. The settlement data from the Beidou settlement monitoring machine is input into a constructed dynamic fitting function to calculate the settlement value of key settlement monitoring points in the power substation in real time. The dynamic fitting function represents the dynamic relationship between the settlement data of the Beidou settlement monitoring machine and the settlement data of key settlement monitoring points.

[0008] As a preferred technical solution, the dynamic fitting function is constructed using curve regression and its order is dynamically adjusted according to the settlement status of key settlement monitoring points.

[0009] As a preferred technical solution, the dynamic adjustment of the order based on the settlement state of key settlement monitoring points specifically means: if the settlement state is uniform settlement, the original cubic polynomial fitting function is maintained; if the settlement state is accelerated settlement, it is automatically upgraded to a quartic polynomial fitting function; if the settlement state is stable with no settlement, it is automatically downgraded to a quadratic polynomial fitting function.

[0010] As a preferred technical solution, if the order of the dynamic fitting function is three, then the fitting function corresponding to the cubic polynomial is specifically as follows: , In the formula, For the first i Fitted settlement data from key settlement monitoring points For settlement data from the Beidou settlement monitoring machine, , , , For the first i The fitting function coefficients for the key settlement monitoring points are yet to be determined.

[0011] As a preferred technical solution, let the unknown vector be... ; constant term vector , , , , , To and Measured settlement data at key settlement monitoring points at the same time, with the subscript n indicating the nth set of settlement data; The nth set of Beidou settlement monitoring data; coefficient matrix ,in , For the first i The number of settlement data points at key settlement monitoring points This refers to the settlement data from the Beidou settlement monitoring machine in the nth data set; The element in the i-th row and j-th column of the coefficient matrix of the corresponding system of equations; Solve the system of equations simultaneously Find the unknown vector B, which is the undetermined coefficient of the fitting function; After obtaining the undetermined coefficients of the fitting function, settlement data from the Beidou settlement monitoring machine will be used. x By inputting the fitting function, the settlement value of the key settlement monitoring points can be calculated.

[0012] As a preferred technical solution, the fitting function is periodically retrained based on real-time collected BeiDou data and subsidence data, and the undetermined coefficients of the fitting function are dynamically updated.

[0013] As a preferred technical solution, the iteration period of the fitting function is adaptively adjusted according to the settling rate.

[0014] As a preferred technical solution, the acquisition of time-series settlement data of power substations based on PS-InSAR technology includes: Acquire satellite imagery of the monitoring area of ​​the power substation; Calculate the overall coherence coefficient of each satellite image, select the satellite image with the largest overall coherence coefficient as the master image, and register all satellite images with the selected master image to establish a master-slave relationship; All satellite imagery was interferometrically processed to obtain interferometric subsets, and DEM data was incorporated for terrain phase correction. Permanent scatterers are selected by calculating the phase standard deviation; By using singular value decomposition to jointly solve each interference subset, the deformation phase, terrain phase, atmospheric phase, and noise phase are separated from the interference phase; A model is established to show the relationship between the phase difference between adjacent points and the surface deformation rate function. The atmospheric phase component is removed, and the phase difference component caused by surface deformation is separated to obtain the time-series settlement data of the power substation.

[0015] According to another aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement the method described thereon.

[0016] According to a third aspect of the present invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described thereon.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1) This invention uses PS-InSAR to acquire full-domain time-series settlement data and then determines key settlement monitoring points. Beidou settlement monitoring stations collect local data, and a dynamic fitting function is used to associate key settlement monitoring points and local data. This not only enables large-scale settlement monitoring of power substations with the help of PS-InSAR, but also uses Beidou monitoring stations to make up for the deficiency of PS-InSAR in real-time monitoring. At the same time, by selecting key monitoring points through grid division, the invention balances the full coverage and accuracy of monitoring, and can more comprehensively and timely grasp the settlement status of substations.

[0018] 2) This invention uses curve regression to construct a dynamic fitting function and combines it with settlement state adjustment order to make the fitting function adaptable to the settlement change characteristics of different areas of the substation. This avoids the limitations of fixed models, improves the accuracy of the correlation between Beidou monitoring data and key settlement point data, and makes the fitting results of settlement data more consistent with the actual settlement situation. This ensures both fitting effect and computational efficiency.

[0019] 3) This invention transforms the solution of undetermined coefficients of the fitting function into a simultaneous calculation of a system of linear equations by constructing an unknown vector, a constant vector, and a coefficient matrix. This makes the process of solving the fitting coefficients of key settlement monitoring points more standardized and quantifiable, which not only improves the accuracy of coefficient solution but also allows technicians to quickly obtain fitting parameters through a clear matrix operation process, thereby enhancing the operability, real-time performance, and economic benefits of monitoring.

[0020] 4. This invention retrains the fitting function periodically using real-time BeiDou data and settlement data, enabling dynamic updates of the undetermined coefficients. This allows the fitting function to continuously adapt to changes in the substation's settlement state, avoiding the accumulation of errors caused by fixed coefficients and improving the long-term accuracy and timeliness of settlement data calculation. Furthermore, the iteration cycle of the fitting function is adaptively adjusted with the settlement rate. When the settlement rate is high, the cycle can be shortened to accurately track changes; when the settlement is stable, the cycle can be extended to save computational resources. This balances the accuracy of settlement monitoring with resource utilization efficiency, making the solution more closely aligned with the dynamic characteristics of actual substation settlement. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating the whole-area settlement monitoring method of the present invention; Figure 2 This is a schematic diagram of the process for obtaining time-series settlement data of power substations based on PS-InSAR in this invention. Figure 3 This is a schematic diagram illustrating the process of achieving full-area settlement monitoring of power substations through dynamic fitting functions in this invention. Detailed Implementation

[0022] 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 should fall within the scope of protection of the present invention.

[0023] The purpose of this invention is to provide a method for monitoring the settlement of power substations across the entire area based on PS-InSAR technology. This method can utilize the wide monitoring area and low monitoring cost of PS-InSAR technology to achieve full-area settlement monitoring of power substations. Furthermore, by combining BeiDou settlement monitoring data and using curve regression, real-time settlement monitoring of power substations can be achieved.

[0024] Example 1 This embodiment relates to a method for monitoring the settlement of a power substation across the entire area based on PS-InSAR technology, such as... Figure 1 It includes the following steps: Step 1, PS-InSAR Settlement Data Acquisition: Acquire Sentinel-1A SAR satellite imagery within the power substation area, perform interferometric processing on the satellite imagery, select permanent scatterers, and combine with DEM data to remove topographic phase, atmospheric phase, and noise phase to obtain time-series settlement data of the power substation. For example... Figure 2 ,include; (1) Acquire Sentinel-1A SAR satellite images (hereinafter referred to as satellite images) covering power substations and crop them to the monitoring area; (2) Calculate the overall coherence coefficient of each satellite image, select the satellite image with the highest overall coherence coefficient as the master image, and register all satellite images with the selected master image to establish a master-slave relationship. The formula for calculating the overall coherence coefficient is as follows: , (1) In the formula, The overall coherence coefficient is the primary basis for selecting the main image; The time baseline coherence coefficient; The spatial baseline coherence coefficient; The Doppler coherence coefficient; The system's thermal noise figure is given.

[0025] (3) Interferometry was applied to all satellite images, and high-precision DEM data from SRTM3 V4 was introduced for terrain phase correction to improve the measurement accuracy of land subsidence. (4) Select a permanent scatterer by calculating the phase standard deviation. The formula for calculating the phase standard deviation is as follows: , (2) In the formula: The phase standard deviation; The standard deviation of amplitude. The average difference in amplitude; This is the amplitude deviation index.

[0026] By using singular value decomposition to jointly solve each interference subset, the deformation phase, terrain phase, atmospheric phase, and noise phase are separated from the interference phase. The calculation formula is as follows: = + + , (3) In the formula: Interference phase; For deformation phase; For terrain phase; Atmospheric phase; This is the noise phase.

[0027] A model was established to show the relationship between the phase difference between adjacent points and the surface deformation rate. By inverting the model, the atmospheric phase component was removed, and the phase difference component caused by surface deformation was separated. The specific formula is as follows: , (4) In the formula, v For linear deformation rate, This represents the time baseline of the k-th interferometric pair. For radar wavelength, Let be the vertical spatial baseline of the k-th interference pair. R represents the terrain error, and R is the radar slant range. The radar incident angle, These are the interference phase difference between adjacent points, the atmospheric phase difference, and the noise phase difference, respectively.

[0028] (1) to (5) are existing technologies and will not be described in detail in this embodiment.

[0029] Step 2, Identify key settlement monitoring points in the power substation: After obtaining the time-series settlement data of the power substation, divide the power substation area into zones using... The area is divided into grids, and permanent scatterers at the grid intersections are selected as key settlement monitoring points.

[0030] Step 3: Installation and data acquisition of the Beidou settlement monitoring device Within a 2-kilometer radius of the power substation, at least one BeiDou settlement monitoring base station should be installed on a relatively stable rooftop or rock formation. Another BeiDou settlement monitoring station should be installed at a suitable location in the central area of ​​the substation. Both BeiDou settlement monitoring devices will acquire stable local settlement data through their built-in high-precision positioning chips and transmit the monitoring results to the backend via the Internet of Things (IoT). The BeiDou settlement monitoring base station serves as a reference station; its own settlement is negligible. It provides a stable reference coordinate benchmark, providing calibration for the settlement data from the BeiDou settlement monitoring station and ensuring the accuracy of the monitoring data. The BeiDou settlement monitoring station is deployed within the substation area. As a monitoring station, it directly collects displacement information (including vertical settlement data) at its location. Combined with the reference data from the BeiDou settlement monitoring base station, the final settlement amount of the power substation area is calculated.

[0031] Step 4: A curve regression method is used to construct a functional relationship between the settlement data from the BeiDou settlement monitoring machine and the settlement data from key settlement monitoring points, thereby achieving real-time, full-area settlement monitoring of the power substation. Figure 3 This includes the following steps: (1) Construct the dynamic fitting function, the specific formula is as follows: , In the formula, For the first i Fitted settlement data from key settlement monitoring points For settlement data from the Beidou settlement monitoring machine, , , , For the first i The fitting function coefficients for the key settlement monitoring points are yet to be determined.

[0032] (2) Construct the coefficient matrix for solving the system of equations ,in , This refers to the amount of settlement data at this key settlement monitoring point. Let n be the settlement value of the Beidou settlement monitoring machine in the nth data set; The element in the i-th row and j-th column of the coefficient matrix of the corresponding system of equations; (3) Construct the vector of unknowns for solving the system of equations ; (4) Construct the constant term vector for solving the system of equations ,in, , , , , To and Measured settlement data at key settlement monitoring points at the same time; (5) Solve the system of equations simultaneously to find the unknown vector B, which is the undetermined coefficient of the fitting function. The specific formula is as follows: , After obtaining the undetermined coefficients of the fitting function, the fitting function is completed, and subsequent settlement data from the Beidou settlement monitoring machine are used. x The settlement value of the key settlement monitoring points can then be calculated.

[0033] (6) Dynamically solve and update the unknown vector B, and add a trend weighting factor. Based on real-time collected BeiDou data and subsidence data, the fitting function is periodically (e.g., weekly) retrained, and the undetermined coefficients of the fitting function are automatically updated, including: Assign higher weights to recent data (within the iteration cycle) (e.g., weight coefficient = 1.2), and lower weights to historical data (the first 3 cycles) (weight coefficient = 0.8) to balance the timeliness and stability of the data; reconstruct the weighted coefficient matrix A and the constant term vector C, and solve for the undetermined coefficients Bnew of the new fitting function; calculate the deviation between the undetermined coefficients of the new fitting function and the undetermined coefficients of the original fitting function: if the deviation is <5%, retain the undetermined coefficients of the original fitting function; if the deviation is ≥5%, update to Bnew to avoid frequent fluctuations in the fitting function.

[0034] Adaptive cycle setting: The iteration cycle is 7 days (which can be adjusted according to the substation settlement rate; if the settlement is accelerated, the cycle is shortened to 3 days). The fitting function is automatically updated once in each cycle.

[0035] When the settlement value at critical points approaches 80% of the equipment's safety threshold, the following adaptive operation will be performed: 1) Automatically shorten the iteration cycle for this location to 1 day, increasing the model update frequency; 2) Add a threshold proximity correction term to the fitting function, such as ( x - x threshold ) 2 , x threshold (using the BeiDou data corresponding to the threshold) to amplify the fitting accuracy of this region; 3) Synchronously trigger early warning signals and associate them with the station's operation and maintenance system.

[0036] This scheme enables intelligent iteration with dynamic updates of the fitting function, which not only solves the problem of accuracy decay of static models, but also enhances the accurate response to substation settlement risks.

[0037] Adaptive adjustment of the fitting function: The settlement rate (settlement rate = settlement amount / time) of key settlement monitoring points is calculated using a sliding window (window size = 2 iteration cycles). It automatically identifies settlement states such as uniform settlement, accelerated settlement, and stable no settlement, and dynamically adjusts the order of the fitting function based on the settlement state: for uniform settlement, the original cubic polynomial fitting function is maintained; for accelerated settlement, it is automatically upgraded to a fourth-order polynomial fitting function (increasing the order of the fitting function). x 4 (Item), to improve the fitting accuracy for nonlinear trends; if it is stable and without settlement, it is downgraded to a quadratic polynomial fitting function to reduce redundant calculations.

[0038] This invention uses adaptive polynomial curve regression to construct a functional relationship between BeiDou data and the settlement of key points, solving the problem that BeiDou data cannot be directly correlated with the settlement of key points within the station, and realizing the conversion of wide-area BeiDou data into precise settlement within the station.

[0039] In summary, this invention first divides the power substation into zones to determine the locations of key settlement monitoring points and acquires time-series settlement monitoring data for each key point using PS-InSAR technology. Second, a BeiDou settlement monitoring device is installed at a suitable location within the power substation, and the settlement data from the BeiDou device is curve-fitted with the time-series settlement data from each key monitoring point to establish a functional relationship between the settlement data. Finally, the settlement prediction for each key monitoring point is performed using the functional relationship between the settlement data and the real-time settlement data from the BeiDou device, achieving full-area settlement monitoring of the power substation. This monitoring method can achieve real-time settlement monitoring of the entire power substation area under relatively economical conditions, overcoming the problems of long monitoring intervals and untimely monitoring associated with single PS-InSAR technology. Furthermore, this method only requires the installation of one BeiDou settlement monitoring device, making the equipment simple and inexpensive, thus solving the problem of high costs associated with traditional power substation settlement monitoring.

[0040] Example 2 This embodiment relates to a power substation full-area settlement monitoring device based on PS-InSAR technology. The device includes: The PS-InSAR settlement data acquisition module acquires Sentinel-1A SAR satellite images within the power substation area, performs interferometric processing on the satellite images, selects permanent scatterers, and combines DEM data to remove terrain phase, atmospheric phase, and noise phase to obtain time-series settlement data of the power substation. The key settlement monitoring point selection module acquires the time-series settlement data of the power substation, divides the power substation area into regions using a 5m×5m grid, and selects the permanent scattering bodies at the grid intersections as key settlement monitoring points. For BeiDou settlement monitoring, at least one BeiDou settlement monitoring base station should be installed on a relatively stable rooftop or rock within a 2-kilometer radius of the power substation, and another BeiDou settlement monitoring station should be installed at an appropriate location in the central area of ​​the power substation. The BeiDou settlement monitoring device acquires stable local settlement data through its built-in high-precision positioning chip and transmits the monitoring results to the backend via the Internet of Things.

[0041] The real-time global settlement monitoring module employs curve regression to construct a dynamic fitting function between settlement data from the BeiDou settlement monitoring system and settlement data from key monitoring points. Based on real-time acquired BeiDou and settlement data, the fitting function is periodically (e.g., weekly) retrained, and its undetermined coefficients are automatically updated. The real-time settlement data from the BeiDou settlement monitoring system is input into the constructed dynamic fitting function to calculate the settlement values ​​at key monitoring points in the power substation in real time, achieving real-time global settlement monitoring of the power substation.

[0042] Example 3 The electronic device of this invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0043] Multiple components in the device are connected to the I / O interface, including: input units such as keyboards and mice; output units such as various types of displays and speakers; storage units such as disks and optical discs; and communication units such as network interface cards (NICs), modems, and wireless transceivers. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0044] The processing unit performs the various methods and processes described above. For example, in some embodiments, the methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute the methods by any other suitable means (e.g., by means of firmware).

[0045] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0046] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0047] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0048] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring the settlement of a power substation across its entire area, characterized in that, The method includes: The time-series settlement data of power substations are obtained based on PS-InSAR technology. The power substation area is divided into grids based on the time-series settlement data, and permanent scatterers at the grid intersections are selected as key settlement monitoring points. Beidou settlement monitoring base stations are set up around the power substation, and a Beidou settlement monitoring station is set up in the middle area of ​​the power substation to obtain settlement data at the location. The settlement data from the Beidou settlement monitoring machine is input into a constructed dynamic fitting function to calculate the settlement value of key settlement monitoring points in the power substation in real time. The dynamic fitting function represents the dynamic relationship between the settlement data of the Beidou settlement monitoring machine and the settlement data of key settlement monitoring points.

2. The method for monitoring the settlement of a power substation across its entire area according to claim 1, characterized in that, The dynamic fitting function is constructed using curve regression and its order is dynamically adjusted based on the settlement status of key settlement monitoring points.

3. The method for monitoring the settlement of a power substation across its entire area according to claim 2, characterized in that, The specific steps for dynamically adjusting the order based on the settlement status of key settlement monitoring points are as follows: if the settlement status is uniform settlement, the original cubic polynomial fitting function is maintained; if the settlement status is accelerated settlement, the fitting function is automatically upgraded to a quartic polynomial; if the settlement status is stable with no settlement, the fitting function is automatically downgraded to a quadratic polynomial.

4. The method for monitoring the settlement of a power substation across its entire area according to claim 2, characterized in that, If the order of the dynamic fitting function is three, then the fitting function for the cubic polynomial is as follows: ， In the formula, For the first i Fitted settlement data from key settlement monitoring points For settlement data from the Beidou settlement monitoring machine, , , , For the first i The fitting function coefficients for the key settlement monitoring points are yet to be determined.

5. The method for monitoring the settlement of a power substation across its entire area according to claim 4, characterized in that, Let the unknown vector ; constant term vector , , , , , To and Measured settlement data at key settlement monitoring points at the same time, with the subscript n indicating the nth set of settlement data; The nth set of Beidou settlement monitoring data; coefficient matrix ,in , For the first i The number of settlement data points at key settlement monitoring points This refers to the settlement data from the Beidou settlement monitoring machine in the nth data set; The element in the i-th row and j-th column of the coefficient matrix of the corresponding system of equations; Solve the system of equations simultaneously Find the unknown vector B, which is the undetermined coefficient of the fitting function; After obtaining the undetermined coefficients of the fitting function, settlement data from the Beidou settlement monitoring machine will be used. x By inputting the fitting function, the settlement value of the key settlement monitoring points can be calculated.

6. The method for monitoring the settlement of a power substation across its entire area according to claim 4, characterized in that, The fitting function is periodically retrained based on real-time collected BeiDou data and settlement data, and the undetermined coefficients of the fitting function are dynamically updated.

7. A method for monitoring the settlement of a power substation across its entire area according to claim 4 or 6, characterized in that, The iteration period of the fitting function is adaptively adjusted according to the settling rate.

8. The method for monitoring the settlement of a power substation across its entire area according to claim 1, characterized in that, The time-series settlement data of power substations acquired based on PS-InSAR technology includes: Acquire satellite imagery of the monitoring area of ​​the power substation; Calculate the overall coherence coefficient of each satellite image, select the satellite image with the largest overall coherence coefficient as the master image, and register all satellite images with the selected master image to establish a master-slave relationship; All satellite imagery was interferometrically processed to obtain interferometric subsets, and DEM data was incorporated for terrain phase correction. Permanent scatterers are selected by calculating the phase standard deviation; By using singular value decomposition to jointly solve each interference subset, the deformation phase, terrain phase, atmospheric phase, and noise phase are separated from the interference phase; A model is established to show the relationship between the phase difference between adjacent points and the surface deformation rate function. The atmospheric phase component is removed, and the phase difference component caused by surface deformation is separated to obtain the time-series settlement data of the power substation.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 8.

Images