Operation status monitoring method of power Beidou positioning platform combined with edge computing

Abstract

The present application provides a method for monitoring the operation status of an electric power Beidou positioning platform combined with edge computing, which relates to the field of edge computing technology, including: the edge computing terminal obtains the remote communication link status parameters from the remote communication module, and obtains the local communication link status parameters from the local communication module; obtains the observable satellite data quality of the edge computing device and the local power sensing device; predicts the communication network link quality and positioning quality through a pre-trained long short-term memory network; uses the communication link quality degradation trend and the satellite data quality degradation trend as inputs to the fault classification model to obtain the status fault analysis results. This application can solve the technical problems in the prior art that the real-time and positioning accuracy of the power equipment status monitoring are affected by the poor stability and quality of the local communication network, and achieve the technical effect of improving the real-time, positioning accuracy and overall system reliability of the power equipment status monitoring.

Description

Technical Field

[0001] The present application relates to the field of edge computing technology, and in particular to a method for monitoring the operating status of an electric power Beidou positioning platform combined with edge computing. Background Art

[0002] With the popularization and application of Beidou satellite navigation system, satellite-based positioning technology has gradually become an important part of power equipment monitoring and management. However, existing positioning technology and communication networks still face some challenges in practical applications.

[0003] At present, existing power sensing devices usually do not have remote communication access capabilities, which makes them have obvious limitations in real-time data transmission, remote monitoring and positioning accuracy improvement. In order to make up for this shortcoming, many power sensing devices are connected to edge computing devices through local communication networks to achieve data transmission and processing. However, although this access method through the local communication network makes it possible for remote monitoring and positioning of power equipment, there are still some problems. The stability and quality of the local communication network itself directly affect the transmission efficiency and accuracy of the data. If there are problems such as interference, packet loss or delay in the local communication link, it may cause unstable data transmission, which in turn affects the accuracy of power equipment status monitoring and positioning accuracy.

[0004] To sum up, the existing technology has technical problems such as interference, packet loss or delay in data transmission due to the poor stability and quality of the local communication network, which further affects the real-time status monitoring of power equipment and the accuracy of positioning, resulting in the reliability and accuracy of power sensing equipment in complex environments being greatly reduced, affecting the operating efficiency and safety of the power system. Summary of the invention

[0005] The purpose of this application is to provide a method for monitoring the operating status of an electric power Beidou positioning platform combined with edge computing, so as to solve the problems existing in the prior art such as interference, packet loss or delay in the data transmission process due to the poor stability and quality of the local communication network, which further affects the real-time status monitoring of power equipment and the accuracy of positioning, resulting in greatly reduced reliability and accuracy of power sensing equipment in complex environments, affecting the technical problems of the operating efficiency and safety of the power system.

[0006] In view of the above problems, the present application provides an operating status monitoring method for an electric power Beidou positioning platform combined with edge computing, including: according to a set acquisition cycle, the edge computing terminal obtains remote communication link status parameters from a remote communication module, and obtains local communication link status parameters from a local communication module, wherein the remote communication module is used for the edge computing device to communicate with the electric power Beidou positioning platform, and the local communication module is used for the edge computing device to communicate with the local power sensing device; according to the set acquisition cycle, the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device are obtained; the remote communication link status parameters, the local communication link status parameters, the observable satellite data quality of the edge computing device, and the observable satellite data quality of the local power sensing device are used as input data, and the communication network link quality and positioning quality are predicted through a pre-trained long short-term memory network, and the communication link quality degradation trend and the satellite data quality degradation trend are output; the communication link quality degradation trend and the satellite data quality degradation trend are used as inputs of a fault classification model, and the fault classification model is a neural network model that converges through training to obtain a state fault analysis result.

[0007] In a possible implementation, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing includes: the remote communication link status parameters and local communication link status parameters include: link signal-to-interference-noise ratio and received signal strength.

[0008] In a possible implementation, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing includes: obtaining the double difference of carrier phase measurement noise of the sensing device and the reference station observing satellites according to the number of observable satellites and satellite index variables; obtaining the approximate position coordinate value of the sensing device and the first-order derivative difference of the pseudorange of the approximate position of the edge computing device pointing to the observing satellite; establishing a positioning correction equation for the differential calibration information of the edge computing device and the reference station based on the double difference of carrier phase measurement noise, the approximate position coordinate value of the sensing device, and the first-order derivative difference of the pseudorange of the approximate position of the edge computing device pointing to the observing satellite; solving the positioning correction equation according to the least squares method, which includes a design matrix; calculating the variance matrix of the positioning result based on the design matrix, and transforming the variance matrix in the geodetic coordinate system using the transformation matrix to obtain the variance matrix in the geodetic coordinate system; calculating the precision attenuation factor of the sensing device observing the satellite according to the variance matrix and the variance matrix in the geodetic coordinate system as the observable satellite data quality of the edge computing device.

[0009] In a possible implementation, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing includes: obtaining the distance from the edge computing device to the sensing device through local communication ranging; calculating the carrier phase correction value of the sensing device based on the distance from the edge computing device to the sensing device; calculating the variance matrix and the variance matrix in the geodetic coordinate system based on the carrier phase correction value in combination with the satellite data of the edge computing device; calculating the observation satellite precision attenuation factor of the local communication network-assisted sensing device positioning based on the variance matrix and the variance matrix in the geodetic coordinate system, and obtaining the observable satellite data quality of the local electric power sensing device.

[0010] In a possible implementation, the method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing includes: the positioning correction equation expression of the differential calibration information of the edge computing device and the reference station is: , where N is the number of observable satellites, a and b are satellite index variables, ; is the double difference of the carrier phase measurement noise of the sensing device L and the reference station r observing satellites a and b, λ is the wavelength of the carrier signal, is the difference of the first-order derivative of the pseudorange from the approximate position of the edge computing device to satellites a and b, The pseudo-range observations of satellites a and b by sensing device L, is the integer ambiguity difference between the sensing device L and the reference station r, are the three-dimensional coordinate correction numbers respectively; the positioning correction number settlement result obtained by the least squares method is: , where the design matrices A and P are: , ; The variance matrix is: ; The variance matrix in the geodetic coordinate system is: ,in, is the coordinate transformation matrix from the earth coordinate system to the earth protocol coordinate system at the sensing device; The precision dilution factors GDOP, PDOP, HDOP, and VDOP of the satellite observed by the sensing device are: , , calculate and obtain the precision reduction factor of the satellite observed by the sensing device.

[0011] In a possible implementation, the method for monitoring the operation status of the power Beidou positioning platform combined with edge computing includes: according to the formula: , calculate the carrier phase correction value of the sensing device, where, is the carrier phase correction value of the sensing device for satellite a, is the carrier phase observation value of satellite a by the edge computing device, , They represent the pseudoranges of the edge computing device and the sensing device respectively, and λ is the wavelength of the carrier signal.

[0012] In a possible implementation, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing includes: the long short-term memory network includes: an input layer, a hidden layer, and an output layer, and a weight coefficient is set for each layer, wherein the input layer contains time series data, the hidden layer processes and converts the data, and the output layer is used to output prediction results; wherein the weight coefficient is continuously optimized during training, the hidden layer contains neurons, and each neuron outputs a related bias, and the bias is used to adjust the output of the model.

[0013] In a possible implementation, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing includes: establishing an atmospheric delay model by modeling the ionosphere and troposphere delay impact data; obtaining real-time weather data; based on the real-time weather data, performing delay analysis on the real-time weather data through the atmospheric delay model to determine delay correction parameters; and using the delay correction parameters to correct the communication link quality degradation trend and the satellite data quality degradation trend.

[0014] The technical solution provided in the present application has at least the following technical effects or advantages: by following the set acquisition cycle, the edge computing terminal obtains the remote communication link status parameters from the remote communication module and obtains the local communication link status parameters from the local communication module, wherein the remote communication module is used for the edge computing device to communicate with the electric power Beidou positioning platform, and the local communication module is used for the edge computing device to communicate with the local power sensing device; according to the set acquisition cycle, the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device are obtained; the remote communication link status parameters, the local communication link status parameters and the edge computing are combined into a single data acquisition module; the local communication link status parameters and the local power sensing device are combined into a single data acquisition module; the local communication link status parameters and the remote communication link status parameters ... The observable satellite data quality of the equipment and the observable satellite data quality of the local power sensing device are used as input data, and the communication network link quality and positioning quality are predicted through a pre-trained long short-term memory network, and the communication link quality degradation trend and the satellite data quality degradation trend are output; the communication link quality degradation trend and the satellite data quality degradation trend are used as inputs of a fault classification model, and the fault classification model is a neural network model that converges through training to obtain a state fault analysis result. That is to say, by achieving the technical goal of improving the stability of the local communication network and the reliability of data transmission, the technical effect of improving the real-time performance of power equipment status monitoring, positioning accuracy and overall system reliability is achieved.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0017] Figure 1 A flow chart of a method for monitoring the operation status of an electric power Beidou positioning platform combined with edge computing in this application; Figure 2 This is the architecture diagram of the Beidou positioning device operation status monitoring and fault classification model for this application; Figure 3 A schematic diagram of a process for obtaining the quality of observable satellite data of the edge computing device in the method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing in this application; Figure 4 This is a diagram of the internal structure of the long short-term memory model in this application. DETAILED DESCRIPTION

[0018] This application provides a method for monitoring the operation status of the power Beidou positioning platform combined with edge computing, which solves the existing technical problems that the stability and quality of the local communication network are poor, resulting in interference, packet loss or delay in the data transmission process, further affecting the real-time status monitoring of power equipment and the accuracy of positioning accuracy, resulting in the reliability and accuracy of power sensing equipment in complex environments. The reliability and accuracy of the power sensing equipment are greatly reduced, affecting the operating efficiency and safety of the power system. The technical goal of improving the stability of the local communication network and the reliability of data transmission is achieved, and the technical effect of improving the real-time status monitoring of power equipment, positioning accuracy and overall system reliability is achieved.

[0019] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0020] Please see attached Figure 1 ,This application provides an operating status monitoring method of an electric power Beidou positioning platform combined with edge computing, which specifically includes the following steps.

[0021] Step 1: According to the set collection cycle, the edge computing terminal obtains the remote communication link status parameters from the remote communication module and obtains the local communication link status parameters from the local communication module, wherein the remote communication module is used for the communication connection between the edge computing device and the electric power Beidou positioning platform, and the local communication module is used for the communication connection between the edge computing device and the local electric power sensing device.

[0022] Specifically, the collection period refers to the time interval for data collection, which is used to periodically obtain the status information of the communication link. The collection period is preset, such as the collection period is set by a person skilled in the art according to actual conditions.

[0023] The edge computing terminal is a device used to process and analyze data. It is used to obtain the status parameters of the remote communication link through the remote communication module and the status parameters of the local communication link through the local communication module.

[0024] The state parameters of the remote communication link are obtained from the remote communication module. The state parameters of the remote communication link refer to the quality, stability, speed and other information of the network connection when communicating between the device and the external system, which are used to evaluate the reliability of remote communication. The weaker the signal strength of the remote communication link, the greater the possibility of data transmission delay or packet loss, and vice versa.

[0025] The edge computing terminal also obtains local communication link status parameters from the local communication module. The local communication link refers to the connection status between the edge computing device and the local power sensing device, including factors such as data transmission speed, bandwidth, and delay, which can affect the transmission efficiency and accuracy of local data.

[0026] The difference between the remote communication module and the local communication module is that the remote communication module is mainly used for communication between edge computing devices and the electric power Beidou positioning platform, while the local communication module is responsible for connecting with local power sensing devices. For example, the electric power Beidou positioning platform may be responsible for accurately locating and tracking the location of the equipment, while the local power sensing device monitors the status of the power equipment in real time. The cooperation of the two communication modules can ensure the communication stability and accuracy of information exchange of the equipment in different environments.

[0027] Step 2: According to the set collection cycle, obtain the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device.

[0028] Specifically, according to the set collection cycle, data is collected regularly within a predetermined time interval to ensure the timeliness and continuity of the data, and then the observable satellite data quality of the edge computing device is obtained, that is, the edge computing device evaluates its availability and quality through the received satellite signal. Satellite data quality includes signal strength, clarity, delay and error. Among them, if the signal strength is stronger, the data quality is higher and the positioning accuracy is better; conversely, if the signal is weaker, it may lead to worse data quality and lower positioning accuracy.

[0029] According to the set collection cycle, the observable satellite data quality of the local power sensing device is obtained, that is, the ability of the local power sensing device to locate and monitor through satellite signals is obtained, which in turn affects the working effect of the sensing device and the accuracy of the data.

[0030] By collecting the observable satellite data quality of edge computing devices and local power sensing devices, it is possible to compare the performance under different conditions, and then optimize the performance of the equipment to ensure high-quality and stable services in different environments.

[0031] Step 3: Use the remote communication link state parameters, local communication link state parameters, observable satellite data quality of the edge computing device, and observable satellite data quality of the local power sensing device as input data, predict the communication network link quality and positioning quality through a pre-trained long short-term memory network, and output the communication link quality degradation trend and satellite data quality degradation trend.

[0032] Specifically, the long-distance communication link state parameters, the local communication link state parameters, the observable satellite data quality of the edge computing device, and the observable satellite data quality of the local power sensing device are used as input data, and the long short-term memory network (LSTM) neural network model is used to predict the communication network link quality and positioning quality. The long short-term memory network can process time series data and identify long-term dependencies in the data, so as to accurately predict future trends. Among them, the input data is divided into training data and verification data according to a preset division ratio, and the preset division ratio is obtained by a technician in the field according to the actual situation. For example, the division ratio of training data to verification data is 7:3. The long short-term memory network is trained by the training data. When the output of the long short-term memory network tends to converge, the output result of the long short-term memory network is verified by the verification data. If the verification accuracy of the long short-term memory network meets the preset verification accuracy, the training of the long short-term memory network is completed. Among them, the preset verification accuracy is obtained by a technician in the field according to the actual situation. The output result of the long short-term memory network includes the degradation trend of the communication link quality and the degradation trend of the satellite data quality. The deterioration trend of communication link quality may be manifested as decreased signal strength, increased transmission delay, etc., while the deterioration trend of satellite data quality may be manifested as reduced positioning accuracy, poor satellite signal quality, etc. The output results help to foresee possible problems in the future, make corrections or optimizations in advance, and ensure the stability and efficiency of the system.

[0033] Step 4: Use the communication link quality degradation trend and satellite data quality degradation trend as inputs of a fault classification model, wherein the fault classification model is a neural network model that converges through training to obtain a state fault analysis result.

[0034] Specifically, if Figure 2 As shown in the figure, the degradation trend of the communication link quality and the degradation trend of the satellite data quality are used as the input of the fault classification model, and the state fault judgment result is obtained through the prediction of the fault classification model. The fault classification model is a trained and converged neural network model. During the training process, the neural network will learn the relationship between input and output based on historical data, so that it can accurately classify and predict the fault type. Training convergence means that the fault classification model adjusts the weights and parameters through multiple iterations during the continuous optimization process, and finally reaches the optimal state, so that the fault classification model can accurately predict different fault types. For example, the degradation trend of the communication link quality may indicate increased link packet loss or delay, while the degradation trend of the satellite data quality may indicate weak satellite signals and reduced positioning accuracy. The fault classification model can analyze and give the state fault judgment result, so that repair or optimization measures can be taken in advance.

[0035] The method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing can achieve the technical goal of improving the stability of the local communication network and the reliability of data transmission, and achieve the technical effect of improving the real-time performance, positioning accuracy and overall system reliability of electric power equipment status monitoring.

[0036] Furthermore, the present application also includes: the remote communication link status parameters and local communication link status parameters include: link signal-to-interference-and-noise ratio, received signal strength.

[0037] Specifically, the communication quality is measured through the remote communication link status parameters and the local communication link status parameters, and the communication stability and transmission effect are evaluated to determine whether the communication is normal or needs to be optimized.

[0038] Next, the remote communication link status parameters and the local communication link status parameters include the link signal-to-interference-noise ratio and the received signal strength, respectively. The link signal-to-interference-noise ratio refers to the ratio of the signal to the interference in the communication link, which is used to measure the clarity and quality of the signal. Among them, the higher the signal-to-interference ratio, the clearer the signal and the better the communication quality; conversely, when the signal-to-interference ratio is low, noise or data loss may occur. The received signal strength refers to the signal strength received by the receiving end, which is used to reflect the strength of the signal. Among them, the stronger the signal strength, the better the communication quality, the less likely data loss and delay, and vice versa, the worse it is, and delays or packet loss may occur.

[0039] The link signal-to-interference-noise ratio and received signal strength help monitor the health of the communication link in real time, promptly discover and solve communication problems, and thus improve the reliability and efficiency of the system.

[0040] Further, if Figure 3 As shown, the present application also includes: obtaining the double difference of carrier phase measurement noise of the sensing device and the reference station observing satellites according to the number of observable satellites and the satellite index variable; obtaining the approximate position coordinate value of the sensing device and the pseudo-range first-order derivative difference of the approximate position of the edge computing device pointing to the observed satellite; establishing a positioning correction equation of the differential calibration information of the edge computing device and the reference station based on the double difference of carrier phase measurement noise, the approximate position coordinate value of the sensing device and the pseudo-range first-order derivative difference of the approximate position of the edge computing device pointing to the observed satellite; solving the positioning correction equation according to the least squares method, which includes a design matrix; calculating the variance matrix of the positioning result based on the design matrix, and transforming the variance matrix in the geodetic coordinate system using the transformation matrix to obtain the variance matrix in the geodetic coordinate system; calculating the precision attenuation factor of the sensing device observing the satellite according to the variance matrix and the variance matrix in the geodetic coordinate system as the observable satellite data quality of the edge computing device.

[0041] Specifically, by counting the number and index information of satellites that can be observed, the difference in noise generated by the carrier phase measurement between the sensing device and the base station observation satellite when observing the same satellite can be obtained, which is called the carrier phase measurement noise double difference. The carrier phase measurement noise double difference reflects the quality of the satellite signal and the accuracy of the measurement. For example, when the noise is small, the measurement accuracy is higher and the positioning is more accurate.

[0042] Next, starting from the preliminary positions of the sensing device and the edge computing device, the approximate position coordinates of the sensing device are obtained, and the difference of the first-order derivative of the pseudorange pointing from the edge computing device to the satellite is calculated. Pseudorange is a measurement method from the satellite to the receiving device, and the position is determined by calculating the propagation time of the signal. The difference of the first-order derivative of the pseudorange indicates the rate of change of the satellite signal in time, reflecting the change of the signal.

[0043] Then, based on the double difference of carrier phase measurement noise, the approximate position coordinate value of the sensing device, and the first-order derivative difference of the pseudorange of the approximate position of the edge computing device pointing to the observation satellite, a positioning correction equation of the differential calibration information of the edge computing device and the base station is established to correct the positioning error between the edge computing device and the base station, which can correct the errors in the measurement and improve the positioning accuracy.

[0044] Next, the least squares method can minimize the sum of squares of the errors, making the solution closer to the true value. According to the least squares method, the positioning correction equation is solved, including the design matrix. The design matrix can help organize and process the parameters and variables in the equation, making the solution process more efficient and accurate.

[0045] Then, after obtaining the positioning result by solving the design matrix, the variance matrix of the positioning result is calculated to measure the size of the positioning error. The variance matrix is ​​a statistic that reflects the accuracy and reliability of the data. And in the geodetic coordinate system, the variance matrix is ​​transformed using the transformation matrix to obtain the variance matrix in the geodetic coordinate system, so as to more accurately represent the accuracy of the positioning result, which is convenient for further analysis and use.

[0046] Finally, based on the variance matrix and the variance matrix in the geodetic coordinate system, the precision attenuation factor of the satellite observed by the perception device is calculated. The precision attenuation factor reflects the accuracy loss caused by noise, interference and other factors during the transmission of satellite observation data. As the quality of observable satellite data of the edge computing device, the quality of the satellite data received by the edge computing device is quantified, thereby judging the credibility and accuracy of the data.

[0047] Furthermore, the present application also includes: obtaining the distance from the edge computing device to the sensing device through local communication ranging; calculating the carrier phase correction value of the sensing device based on the distance from the edge computing device to the sensing device; calculating the variance matrix and the variance matrix in the geodetic coordinate system based on the carrier phase correction value in combination with the satellite data of the edge computing device; calculating the observation satellite precision attenuation factor of the local communication network assisted sensing device positioning based on the variance matrix and the variance matrix in the geodetic coordinate system, and obtaining the observable satellite data quality of the local power sensing device.

[0048] Specifically, the physical distance between the edge computing device and the sensing device is calculated by measuring the signal propagation time in the local communication module. For example, radar or ultrasonic technology is used to determine the direct distance between the two devices.

[0049] Next, the carrier phase correction value of the sensing device is calculated based on the distance from the edge computing device to the sensing device. The carrier phase correction value is used to compensate for the difference in signal propagation time caused by the distance to ensure the accuracy of the position calculation. For example, when the distance between the edge computing device and the sensing device is far, the carrier phase will change due to the signal propagation delay, so it is necessary to correct the phase according to this distance to reduce the positioning error caused by it.

[0050] Then, according to the carrier phase correction value, combined with the satellite data of the edge computing device, the variance matrix and the variance matrix in the geodetic coordinate system are calculated. The variance matrix reflects the uncertainty and accuracy of the positioning result and is used to evaluate the error size of the position calculation. Then, in order to convert the result into a more standard geographic coordinate form, the geodetic coordinate system conversion method is used to convert the variance matrix into a geodetic coordinate system, so as to make a more accurate assessment of the positioning accuracy on a global scale.

[0051] Next, based on the variance matrix and the variance matrix in the geodetic coordinate system, the observed satellite precision reduction factor of the local communication network-assisted sensing device positioning is calculated, which reflects the degree of attenuation of the sensing device positioning accuracy with the assistance of the local communication network, and obtains the observable satellite data quality of the local power sensing device. Among them, the smaller the precision reduction factor, the higher the data quality, the more accurately the sensing device can observe the satellite, and the more reliable the positioning result, and vice versa.

[0052] By correcting the carrier phase and calculating the variance matrix in combination with satellite data, the accuracy information in the geodetic coordinate system is obtained. By calculating the precision reduction factor, it helps to evaluate the quality of observable satellite data of local power sensing devices and ensure positioning accuracy and data reliability.

[0053] Furthermore, the present application also includes: the positioning correction equation expression of the differential calibration information of the edge computing device and the reference station is: , where N is the number of observable satellites, a and b are satellite index variables, ; is the double difference of the carrier phase measurement noise of the sensing device L and the reference station r observing satellites a and b, λ is the wavelength of the carrier signal, is the difference of the first-order derivative of the pseudorange from the approximate position of the edge computing device to satellites a and b, The pseudo-range observations of satellites a and b by sensing device L, is the integer ambiguity difference between the sensing device L and the reference station r, are the three-dimensional coordinate correction numbers respectively; the positioning correction number settlement result obtained by the least squares method is: , where the design matrices A and P are: , ; The variance matrix is: ; The variance matrix in the geodetic coordinate system is: ,in, is the coordinate transformation matrix from the earth coordinate system to the earth protocol coordinate system at the sensing device; The precision dilution factors GDOP, PDOP, HDOP, and VDOP of the satellite observed by the sensing device are: , , calculate and obtain the precision reduction factor of the satellite observed by the sensing device.

[0054] Specifically, the positioning correction equation of the differential calibration information of the edge computing device and the base station is used to correct the positioning error and improve the accuracy. Where N is the number of observable satellites, and a and b are satellite index variables used to identify different satellites. The values ​​of satellite index variables a and b are less than or equal to the number of observable satellites.

[0055] Next, the sensing device L and the reference station r observe the double difference of the carrier phase measurement noise of satellites a and b It is the phase difference caused by signal noise when the sensing device and the base station observe the same satellite, reflecting the quality problem of the signal during the propagation process. The smaller the value, the more accurate the positioning. Otherwise, the greater the error. In addition, λ represents the wavelength of the carrier signal. The longer the wavelength of the carrier signal, the smaller the displacement change per unit time, which affects the accuracy of the carrier measurement. Otherwise, the accuracy is lower. It represents the rate of change of signal propagation speed. The smaller the difference of the first-order derivative of the pseudorange, the smoother the change of signal propagation speed and the higher the measurement accuracy, and vice versa.

[0056] Then, is the integer ambiguity difference between the sensing device L and the reference station r, that is, the error difference between the sensing device and the reference station when observing satellite signals due to the difference in integer ambiguity. The larger the integer ambiguity difference, the larger the positioning error, and vice versa.

[0057] Next, the positioning error is adjusted by calculating the correction amount, including the correction in the longitude, latitude and altitude directions, to obtain the three-dimensional coordinate correction number. , which can improve the initial positioning accuracy of the sensing device and thus enable more accurate positioning.

[0058] Then, the least squares method is used to find the optimal solution to minimize the error. The positioning correction number settlement result is obtained according to the least squares method. The design matrices A and P represent the coefficient matrix and covariance matrix related to the positioning error, respectively, and work together to help obtain the optimal solution.

[0059] Next, the error range of the positioning result is obtained through the variance matrix. Each element in the variance matrix reflects the error size in different dimensions (such as longitude, latitude, and altitude).

[0060] Then, since the conversion between different coordinate systems will affect the error, the error matrix is ​​transformed from the local coordinate system to the geodetic coordinate system by using a transformation matrix so as to be compatible with the global positioning system.

[0061] Finally, the positioning quality of the sensing device is evaluated by calculating the precision dilution factor of the sensing device observing the satellite. GDOP, PDOP, HDOP, and VDOP represent the overall precision dilution, position precision dilution, horizontal precision dilution, and vertical precision dilution factors, respectively. By calculating the precision dilution factor, the quality of satellite data and the reliability of the positioning system can be measured.

[0062] Through the differential positioning equation, least squares method and related variance matrix calculation, the positioning error of the sensing device can be corrected and its positioning accuracy can be improved. Finally, through the calculation of the precision reduction factor, a more accurate satellite data quality assessment can be obtained, thereby optimizing the performance of the entire positioning system.

[0063] Furthermore, the present application also includes: according to the formula: , calculate the carrier phase correction value of the sensing device, where, is the carrier phase correction value of the sensing device for satellite a, is the carrier phase observation value of satellite a by the edge computing device, , They represent the pseudoranges of the edge computing device and the sensing device respectively, and λ is the wavelength of the carrier signal.

[0064] Specifically, the correction value of the signal phase between the sensing device and the satellite is calculated. The carrier phase correction value is used to reduce the phase measurement error caused by differences in signal propagation paths and environmental factors, thereby improving positioning accuracy.

[0065] Next, in order to compensate for the measurement error caused by the instability of the signal propagation path or other factors (such as the influence of the atmosphere), the phase correction value of satellite A is made based on the observed signal through the sensing device. , the sensing device can obtain more accurate phase measurement results. Among them, the carrier phase observation value is to calculate the distance by measuring the phase change of the satellite signal, and the edge computing device obtains the relative position with the satellite by capturing the satellite signal and measuring its phase.

[0066] Next, the pseudorange is calculated by measuring the signal propagation time to obtain the distance between the edge computing device and the sensing device and the satellite. However, since there may be errors in signal propagation, the pseudorange measurement contains errors. The more accurate the pseudorange, the higher the accuracy of the positioning result, and vice versa.

[0067] Finally, the wavelength λ of the carrier signal is calculated based on the frequency of the carrier. The shorter the wavelength, the finer the periodic change of the signal, the smaller the measurement error, and the higher the accuracy of the carrier signal, and vice versa.

[0068] By calculating the carrier phase correction value of the sensing device and combining the carrier phase observation value and pseudo-range information of the sensing device and edge computing device, the influence of the error in signal propagation on the positioning accuracy can be reduced by correcting the observation value, and finally a higher-precision positioning result can be achieved.

[0069] Further, if Figure 4 As shown, the present application also includes: the long short-term memory network includes: an input layer, a hidden layer, and an output layer, and a weight coefficient is set for each layer, wherein the input layer contains time series data, the hidden layer processes and converts the data, and the output layer is used to output the prediction result; wherein the weight coefficient is continuously optimized during training, the hidden layer contains neurons, and each neuron outputs a related bias, and the bias is used to adjust the output of the model.

[0070] Specifically, the LSTM network includes: input layer, hidden layer, and output layer. Each layer sets a weight coefficient to adjust and optimize the data transmission and conversion process. The input layer is responsible for receiving raw data or time series data, the hidden layer is used to process and learn the characteristics of the data, and the output layer converts the processed information into the final prediction result.

[0071] Then, during the training process, the weight coefficients of the LSTM network will be continuously adjusted through the back-propagation algorithm to minimize the error between the predicted value and the true value, ensuring that the LSTM network can better learn the data pattern and make the LSTM network's prediction more accurate.

[0072] Then, the neurons in the hidden layer are responsible for processing the input data that has a greater impact on the prediction results and obtaining the output results through calculation. Each neuron has a bias to adjust its output to make it more consistent with the laws of the data, thereby improving the prediction accuracy.

[0073] The input layer receives data, and after being processed by the hidden layer, the output layer gives the prediction result. During the training process, the weight coefficients are continuously optimized to improve the prediction ability of the model. The neurons in the hidden layer use the bias to adjust the output to adapt to the characteristics and rules of the data, thereby improving the learning ability and accuracy of the network, which helps the network achieve efficient and accurate results in tasks such as time series prediction.

[0074] Furthermore, the present application also includes: establishing an atmospheric delay model by modeling the ionosphere and troposphere delay impact data; obtaining real-time weather data; based on the real-time weather data, performing delay analysis on the real-time weather data through the atmospheric delay model to determine delay correction parameters; and using the delay correction parameters to correct the communication link quality degradation trend and the satellite data quality degradation trend.

[0075] Specifically, the ionosphere and troposphere will cause different degrees of delay in the propagation of signals. The ionosphere mainly affects the propagation of high-frequency signals, while the troposphere affects the propagation of low-frequency signals. In order to more accurately predict the propagation delay of signals in the atmosphere, the atmospheric delay model is established through the ionosphere and troposphere delay impact data, and then the delay of the signal in the transmission process is more accurately calculated, providing a basis for subsequent corrections.

[0076] Next, weather data that affects atmospheric delays, such as temperature, humidity, and air pressure, are collected in real time through sensors or meteorological service platforms, or through equipment such as meteorological satellites, ground meteorological stations, or meteorological radars. These data will affect the state of the ionosphere and troposphere, thereby affecting signal propagation.

[0077] Then, the real-time weather data is input into the atmospheric delay model for analysis, the delay in signal propagation is calculated, and the corresponding delay correction parameters are determined. If the atmospheric humidity is high, the signal propagation delay may increase, and the correction parameters need to be adjusted according to the atmospheric delay model to improve the prediction accuracy of signal quality.

[0078] Next, the delay correction parameters are used to correct the degradation trends of the communication link quality and the satellite data quality, that is, the quality of the communication link and satellite data is evaluated, and the quality degradation trend is corrected, thereby optimizing the performance of the communication and positioning systems to ensure that data transmission and positioning are more accurate and stable. Among them, the degradation of the communication link quality is manifested as signal loss, increased delay, etc., while the degradation of the satellite data quality is manifested as increased positioning error or reduced data accuracy.

[0079] By establishing an atmospheric delay model and modeling the impact of the ionosphere and troposphere, the delay in signal propagation can be predicted and corrected, helping to accurately calculate delay correction parameters, improve the quality of communication links and satellite data, reduce errors and fluctuations in signal transmission, and thus improve the reliability and accuracy of the system.

[0080] To sum up, the method for monitoring the operating status of the electric power Beidou positioning platform combined with edge computing provided in the present application has the following technical effects: by following the set acquisition cycle, the edge computing terminal obtains the remote communication link status parameters from the remote communication module and obtains the local communication link status parameters from the local communication module, wherein the remote communication module is used for the communication connection between the edge computing device and the electric power Beidou positioning platform, and the local communication module is used for the communication connection between the edge computing device and the local power sensing device; according to the set acquisition cycle, the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device are obtained; the remote communication link status parameters and the local communication link status parameters are used as the parameters of the local power sensing device; The data and the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device are used as input data, and the communication network link quality and positioning quality are predicted through a pre-trained long short-term memory network, and the communication link quality degradation trend and the satellite data quality degradation trend are output; the communication link quality degradation trend and the satellite data quality degradation trend are used as inputs of a fault classification model, and the fault classification model is a neural network model that converges through training to obtain a state fault analysis result. That is to say, by achieving the technical goal of improving the stability of the local communication network and the reliability of data transmission, the technical effect of improving the real-time performance of power equipment status monitoring, positioning accuracy and overall system reliability is achieved.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. The method for monitoring the operation status of the power Beidou positioning platform combined with edge computing is characterized in that: include: According to the set collection cycle, the edge computing terminal obtains the remote communication link status parameters from the remote communication module and obtains the local communication link status parameters from the local communication module, wherein the remote communication module is used for the edge computing device to communicate with the electric power Beidou positioning platform, and the local communication module is used for the edge computing device to communicate with the local electric power sensing device; According to the set collection period, obtaining the observable satellite data quality of the edge computing device and the observable satellite data quality of the local power sensing device; The remote communication link state parameters, the local communication link state parameters, the observable satellite data quality of the edge computing device, and the observable satellite data quality of the local power sensing device are used as input data, and the communication network link quality and positioning quality are predicted through a pre-trained long short-term memory network, and the communication link quality degradation trend and the satellite data quality degradation trend are output; The communication link quality degradation trend and the satellite data quality degradation trend are used as inputs of a fault classification model. The fault classification model is a neural network model that converges through training to obtain a state fault analysis result.

2. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 1 is characterized in that: The remote communication link status parameters and local communication link status parameters include: link signal to interference and noise ratio, and received signal strength.

3. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 1 is characterized in that: Obtaining the quality of observable satellite data of the edge computing device, including: According to the number of observable satellites and satellite index variables, the double difference of the carrier phase measurement noise of the sensing device and the base station observing the satellite is obtained; Obtain the approximate position coordinate value of the sensing device and the first-order derivative difference of the pseudo-range pointing to the observation satellite of the edge computing device; Based on the carrier phase measurement noise double difference, the approximate position coordinate value of the sensing device, and the pseudo-range first-order derivative difference of the approximate position of the edge computing device pointing to the observation satellite, a positioning correction equation for the differential calibration information of the edge computing device and the reference station is established; Solving the positioning correction equation, including the design matrix, according to the least squares method; Based on the design matrix, a variance matrix of the positioning result is calculated, and the variance matrix is ​​transformed in the geodetic coordinate system using a transformation matrix to obtain a variance matrix in the geodetic coordinate system; According to the variance matrix and the variance matrix in the geodetic coordinate system, the precision attenuation factor of the satellite observed by the sensing device is calculated as the observable satellite data quality of the edge computing device.

4. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 3 is characterized in that: Obtaining the observable satellite data quality of the local power sensing device, including: Obtain the distance from the edge computing device to the sensing device through local communication ranging; Calculate a carrier phase correction value of the sensing device according to the distance between the edge computing device and the sensing device; According to the carrier phase correction value, combined with the satellite data of the edge computing device, the variance matrix and the variance matrix in the geodetic coordinate system are calculated; According to the variance matrix and the variance matrix in the geodetic coordinate system, the observation satellite precision attenuation factor of the local communication network-assisted sensing device positioning is calculated to obtain the observable satellite data quality of the local power sensing device.

5. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 3 is characterized in that: Calculate the dilution of precision factor of the satellite observed by the sensing device, including: The positioning correction equation expression of the differential calibration information of the edge computing device and the reference station is: ， Where N is the number of observable satellites, a and b are satellite index variables, ; is the double difference of the carrier phase measurement noise of the sensing device L and the reference station r observing satellites a and b, λ is the wavelength of the carrier signal, is the difference of the first-order derivative of the pseudorange from the approximate position of the edge computing device to satellites a and b, The double difference of the pseudo-range observation difference of satellites a and b by the sensing device L and the reference station r at the same time, is the integer ambiguity difference between the sensing device L and the reference station r, are the three-dimensional coordinate correction numbers respectively; The settlement result of the positioning correction number obtained by the least squares method is: , where the design matrices A and P are: , ; The variance matrix is: ; The variance matrix in the geodetic coordinate system is: ,in, The coordinate conversion matrix from the earth coordinate system to the earth protocol coordinate system at the sensing device; make The precision dilution factors GDOP, PDOP, HDOP, and VDOP of the satellite observed by the sensing device are: , , calculate and obtain the precision reduction factor of the satellite observed by the sensing device.

6. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 4 is characterized in that: Calculating a carrier phase correction value of the sensing device according to the distance between the edge computing device and the sensing device, including: According to the formula: , calculate the carrier phase correction value of the sensing device, where, is the carrier phase correction value of the sensing device for satellite a, is the carrier phase observation value of satellite a by the edge computing device, , They represent the pseudoranges of the edge computing device and the sensing device respectively, and λ is the wavelength of the carrier signal.

7. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 1, characterized in that: The long short-term memory network includes: an input layer, a hidden layer, and an output layer, and a weight coefficient is set for each layer, wherein the input layer contains time series data, the hidden layer processes and converts the data, and the output layer is used to output the prediction results; The weight coefficient is continuously optimized during training, the hidden layer includes neurons, each neuron outputs a related bias, and the bias is used to adjust the output of the model.

8. The method for monitoring the operation status of the electric power Beidou positioning platform combined with edge computing as claimed in claim 1, characterized in that: Also includes: Establish an atmospheric delay model by modeling the ionospheric and tropospheric delay effects on the data; Get real-time weather data; According to the real-time weather data, performing delay analysis on the real-time weather data through the atmospheric delay model to determine a delay correction parameter; The delay correction parameter is used to correct the communication link quality degradation trend and the satellite data quality degradation trend.

Images