Safety distance detection method for high-voltage electrical equipment combined with Beidou positioning technology

Abstract

The present invention discloses a method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology, and relates to data processing related fields. The method includes: constructing a data sensing device, the data sensing device integrating a Beidou positioning module and an NB-Iot communication module; collecting multi-source observation data of the substation area according to the data sensing device, and sending the multi-source observation data to the edge computing device through the NB-Iot communication module; performing position calculation on the multi-source observation data according to the auxiliary positioning algorithm model embedded in the edge computing device, and obtaining positioning calculation data; collecting high-voltage electrical equipment distance detection samples in the substation area, and training to obtain a safe distance detection model; inputting the positioning calculation data into the safe distance detection model to obtain a safe distance detection result. The technical problem of insufficient detection accuracy in the existing safety distance detection of high-voltage electrical equipment is solved, and the technical effect of improving the accuracy of the detection result is achieved.

Description

Technical Field

[0001] The present application relates to data processing related fields, and in particular to a method for detecting safe distances of high-voltage electrical equipment in combination with Beidou positioning technology. Background Art

[0002] In the power industry, the safe operation of high-voltage electrical equipment is of vital importance. In order to ensure that these devices operate within the specified safety distance and prevent safety accidents caused by electrical discharge, short circuit, etc., accurate detection of the safety distance of high-voltage electrical equipment is an indispensable link. The existing conventional practice is to use GPS positioning technology to obtain the location of high-voltage electrical equipment and calculate the distance between them. However, in complex electromagnetic environments such as substations, GPS signals are often easily interfered, resulting in a decrease in positioning accuracy, and cannot meet the accuracy requirements of high-voltage electrical equipment safety distance detection.

[0003] In the current related technologies, the safety distance detection of high-voltage electrical equipment has the technical problem of insufficient detection accuracy. Summary of the invention

[0004] The present application provides a method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology. By constructing a data sensing device integrating a Beidou positioning module and an NB-IoT communication module, the method collects and transmits multi-source observation data in the substation area, and uses the auxiliary positioning algorithm model embedded in the edge computing device to solve the position of the multi-source observation data, obtain the positioning solution data, collect distance detection samples of high-voltage electrical equipment in the substation area, train a safe distance detection model, input the positioning solution data into the safe distance detection model, obtain the safe distance detection results of the high-voltage electrical equipment, and other technical means, the method realizes the accurate measurement and calculation of the position of the high-voltage electrical equipment, and achieves the technical effect of improving the accuracy of the detection results.

[0005] The present application provides a method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology, including: constructing a data perception device, the data perception device integrating a Beidou positioning module and an NB-Iot communication module; collecting multi-source observation data of a substation area according to the data perception device, and sending the multi-source observation data to an edge computing device through the NB-Iot communication module; performing position calculation on the multi-source observation data according to an auxiliary positioning algorithm model embedded in the edge computing device to obtain positioning calculation data; collecting distance detection samples of high-voltage electrical equipment in the substation area, and obtaining a safe distance detection model based on the training of the distance detection samples of the high-voltage electrical equipment; inputting the positioning calculation data into the safe distance detection model to obtain a safe distance detection result.

[0006] In a possible implementation, the multi-source observation data is sent to the edge computing device through the NB-Iot communication module, and the following processing is performed: the multi-source observation data is divided according to a preset data volume, and k groups of multi-source observation data are output, where k is a positive integer greater than or equal to 2; an edge computing network is constructed, wherein the edge computing network includes multiple edge nodes, and each edge node corresponds to an edge computing device; a status detection is performed on the edge computing network, and k edge computing devices are screened; the NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices accordingly.

[0007] In a possible implementation, the auxiliary positioning algorithm model includes a first auxiliary positioning algorithm channel and a second auxiliary positioning algorithm channel, and performs the following processing: identifying the number of observable Beidou satellites of the data sensing device; when the number of Beidou satellites is greater than or equal to a preset sensing number, performing position solving on the multi-source observation data based on the first auxiliary positioning algorithm channel to obtain positioning solution data, wherein the preset sensing number is 4; when the number of Beidou satellites is less than the preset sensing number, performing position solving on the multi-source observation data based on the second auxiliary positioning algorithm channel to obtain positioning solution data.

[0008] In a possible implementation, the first auxiliary positioning algorithm channel is a differential information routing auxiliary positioning algorithm, and performs the following processing: initialize the approximate position of the data sensing device; send the approximate position of the data sensing device and the multi-source observation data to the electric power Beidou positioning service platform through a remote communication module, and generate differential error parameters according to the electric power Beidou positioning service platform; send the differential error parameters to the edge computing device as input information of the first auxiliary positioning algorithm channel for position solution.

[0009] In a possible implementation, if the remote communication module is disconnected, the following processing is performed: the multi-source observation data is identified based on the first auxiliary positioning algorithm channel to generate differential error parameters, wherein the differential error parameters include a pseudorange correction number, a clock correction number and an ionospheric delay correction number; differential error correction is performed on the multi-source observation data according to the differential error parameters to obtain positioning solution data, and the first auxiliary positioning algorithm channel outputs the positioning solution data.

[0010] In a possible implementation, the second auxiliary positioning algorithm channel is a phase estimation auxiliary positioning algorithm, and performs the following processing: the second auxiliary positioning algorithm channel receives the real-time signal strength of the current edge computing device; the second auxiliary positioning algorithm channel identifies the signal strength of the observation data from the current source, and outputs the observed signal strength; positioning fitting is performed based on the real-time signal strength and the observed signal strength to determine the positioning solution data, and the second auxiliary positioning algorithm channel outputs the positioning solution data.

[0011] In a possible implementation, positioning fitting is performed according to the real-time signal strength and the observed signal strength to determine the positioning solution data, and the following processing is performed: a first key point is determined according to a comparison between the real-time signal strength and the observed signal strength; a neighborhood set based on the first key point is constructed; a feature vector of each neighborhood point in the neighborhood set is obtained, including the signal reception strength of each neighborhood point, the distance distribution weight of each neighborhood point from the first key point, and the reliability factor of each neighborhood point; fitting is performed according to the feature vector of each neighborhood point in the neighborhood set, and the positioning solution data is output.

[0012] In a possible implementation, the NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices, and performs the following processing: obtaining k local positioning solution data corresponding to the k edge computing devices; collaboratively processing the k local positioning solution data, and outputting the k local positioning solution data after collaborative processing; performing global error correction on the k local positioning solution data after collaborative processing, and outputting the collaborative positioning solution data.

[0013] The method for detecting the safe distance of high-voltage electrical equipment combined with Beidou positioning technology proposed in this application first constructs a data sensing device, which integrates a Beidou positioning module and an NB-Iot communication module. Then, multi-source observation data of the substation area is collected according to the data sensing device, and the multi-source observation data is sent to the edge computing device through the NB-Iot communication module. The multi-source observation data is solved according to the auxiliary positioning algorithm model embedded in the edge computing device to obtain the positioning solution data. Then, high-voltage electrical equipment distance detection samples are collected in the substation area, and a safe distance detection model is obtained by training the high-voltage electrical equipment distance detection samples. Finally, the positioning solution data is input into the safe distance detection model to obtain the safe distance detection result, thereby achieving the technical effect of improving the accuracy of the detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the method according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A flow chart of a method for detecting safe distances of high-voltage electrical equipment in combination with Beidou positioning technology provided in an embodiment of the present application.

[0016] Figure 2 A schematic diagram of the process of obtaining positioning solution data in a method for detecting safe distances of high-voltage electrical equipment in combination with Beidou positioning technology provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] 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 in accordance with the contents of the specification. 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 listed below.

[0018] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0019] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0020] The present application embodiment provides a method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology, such as Figure 1 As shown, the method includes: step S100, constructing a data sensing device, wherein the data sensing device integrates a Beidou positioning module and an NB-Iot communication module. Specifically, this step is a preparation stage, which is used to integrate the Beidou positioning module and the NB-Iot communication module into one device to form a data sensing device, which is used to collect multi-source observation data in the substation area. Among them, the Beidou positioning module is a technical module that uses China's Beidou Satellite Navigation System (BDS) for positioning and can receive signals sent by Beidou satellites. The NB-Iot communication module is a narrowband Internet of Things (NarrowBand Internet of Things) communication module, which is a low-power wide area network communication technology used to realize data communication between data sensing devices and edge computing devices.

[0021] Step S200, according to the multi-source observation data of the substation area collected by the data sensing device, the multi-source observation data is sent to the edge computing device through the NB-Iot communication module. Specifically, the data sensing device collects multi-source observation data in the substation area (such as Beidou satellite ephemeris parameters and pseudorange, carrier phase, carrier-to-noise ratio and other data to each satellite), and then sends these data to the edge computing device through the NB-Iot communication module. Among them, the multi-source observation data refers to the satellite signal data provided by the Beidou positioning module. The edge computing device is a computing device located at the edge of the network, which can process and analyze data from the data sensing device. Among them, the edge computing device is installed in a better position, the Beidou satellite observation quality is high, and the positioning accuracy is high; the surrounding environment of the data sensing device changes a lot, the satellite signal may be blocked, the received signal strength is weak, and the number of observable satellites changes greatly.

[0022] In a possible implementation, the multi-source observation data is sent to the edge computing device through the NB-Iot communication module, and step S200 further includes step S210, dividing the multi-source observation data according to a preset data volume, and outputting k groups of multi-source observation data, wherein k is a positive integer greater than or equal to 2. Specifically, the multi-source observation data collected by the data sensing device is divided according to a preset data volume, and the preset data volume is the amount of information that each group of data should contain, which can be set according to multiple factors such as system requirements, data processing capabilities, and communication bandwidth. By dividing, the original multi-source observation data is split into k groups, each group of data contains enough information for subsequent position solution and safety distance detection, and k is a positive integer greater than or equal to 2, indicating the number of groups into which the data is divided. Step S220, constructing an edge computing network, wherein the edge computing network includes multiple edge nodes, each edge node corresponds to an edge computing device. Specifically, an edge computing network is constructed, which is composed of multiple edge nodes, each edge node corresponds to an edge computing device. These edge computing devices are distributed throughout the substation area to provide distributed computing capabilities and data processing capabilities. Step S230, perform status detection on the edge computing network and select k edge computing devices. Specifically, after the edge computing network is built, perform status detection on it to ensure that each edge computing device is in normal working condition. Status detection includes checking the network connection, computing resources, storage resources, etc. of the device. Through status detection, k edge computing devices in good condition are selected for receiving and processing multi-source observation data. Step S240, the NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices respectively. Specifically, the NB-Iot communication module of the data perception device sends the divided k groups of multi-source observation data to the selected k edge computing devices respectively. In this way, each edge computing device will receive a set of data for subsequent position solution and safety distance detection. This implementation method avoids excessive computing pressure on single-point devices, resulting in data processing delays or failures, by dividing the multi-source observation data into multiple groups and sending them to multiple edge computing devices for processing. At the same time, the distributed computing capabilities of multiple edge computing devices improve the positioning capabilities of the entire system over a large range and the accuracy of safe distance detection.

[0023] In a possible implementation, after the NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices, step S200 further includes step S250, obtaining k local positioning solution data corresponding to the k edge computing devices. Specifically, on each screened edge computing device, the embedded auxiliary positioning algorithm model is run. The auxiliary positioning algorithm model processes the received multi-source observation data, and each edge computing device independently calculates the local positioning solution data based on the received observation data and its own computing power. Step S260, the k local positioning solution data are collaboratively processed, and the k local positioning solution data after collaborative processing are output. Specifically, a central control node is established or an existing edge computing device is used as a coordinator to collect the local positioning solution data of all edge computing devices. The collected local positioning solution data are processed using a collaborative algorithm (such as weighted average, Kalman filter, particle filter, etc.) to reduce the solution differences between different devices, and the k local positioning solution data after collaborative processing are output, which are improved in accuracy and consistency. Step S270, perform global error correction on the k local positioning solution data after the collaborative processing, and output the collaborative positioning solution data. Specifically, on the basis of collaborative processing, use known high-precision reference points (such as fixed marking points in the substation) or external high-precision positioning services (such as the CORS network) to perform global error correction on the collaboratively processed data. The corrected data is the final collaborative positioning solution data, which has reached a high level in accuracy and consistency. The collaborative positioning solution data is output for use by the subsequent safety distance detection model. This implementation method improves the accuracy and consistency of positioning data through multi-device collaborative processing and global error correction, providing a reliable foundation for subsequent safety distance detection.

[0024] Step S300, performing position calculation on the multi-source observation data according to the auxiliary positioning algorithm model embedded in the edge computing device, and obtaining positioning solution data. Specifically, after receiving the multi-source observation data, the edge computing device uses its embedded auxiliary positioning algorithm model to perform position calculation on these data and obtain positioning solution data. Among them, the auxiliary positioning algorithm model is an algorithm used to calculate the location information of the device based on the multi-source observation data, and can include multiple algorithms to adapt to different observation conditions and data quality. The positioning solution data is the device location information calculated by the auxiliary positioning algorithm model.

[0025] like Figure 2As shown, in a possible implementation, step S300 further includes step S310, and the auxiliary positioning algorithm model includes a first auxiliary positioning algorithm channel and a second auxiliary positioning algorithm channel. Specifically, in the edge computing device, an auxiliary positioning algorithm model is embedded. This model is not a single algorithm channel, but includes two independent algorithm channels: a first auxiliary positioning algorithm channel and a second auxiliary positioning algorithm channel. These two channels are optimized for different observation conditions and data quality to provide more accurate position solution results. Among them, the first auxiliary positioning algorithm channel is an algorithm channel used when the observation conditions are good (such as a sufficient number of Beidou satellites), which is used to provide higher positioning accuracy. The second auxiliary positioning algorithm channel is an algorithm channel used when the observation conditions are poor (such as an insufficient number of Beidou satellites), which is used to improve positioning accuracy through other auxiliary information.

[0026] Step S320, identifying the number of observable Beidou satellites of the data sensing device. Specifically, after receiving the multi-source observation data sent by the data sensing device, the edge computing device first identifies the number of observable Beidou satellites contained in these data, that is, the number of Beidou satellite signals that the data sensing device can receive at the current position, which is an important basis for determining which auxiliary positioning algorithm channel to use. Step S330, when the number of Beidou satellites is greater than or equal to the preset sensing number, the multi-source observation data is positionally solved based on the first auxiliary positioning algorithm channel to obtain positioning solution data, wherein the preset sensing number is 4. Specifically, if the number of observable Beidou satellites identified is greater than or equal to the preset sensing number (4 in this example), the edge computing device selects to use the first auxiliary positioning algorithm channel to position solve the multi-source observation data, because when the number of Beidou satellites is sufficient, the first auxiliary positioning algorithm channel can provide higher positioning accuracy. Step S340, when the number of Beidou satellites is less than the preset sensing number, the multi-source observation data is positionally solved based on the second auxiliary positioning algorithm channel to obtain positioning solution data. Specifically, if the number of observable Beidou satellites identified is less than the preset number of perceptions, the edge computing device chooses to use the second auxiliary positioning algorithm channel to solve the position of the multi-source observation data, because when the observation conditions are poor, the second auxiliary positioning algorithm channel can use other auxiliary information to improve the positioning accuracy, thereby ensuring the reliability of positioning. This implementation method introduces two independent auxiliary positioning algorithm channels and selects the appropriate algorithm channel for position solution according to the different number of observable Beidou satellites, ensuring that accurate and reliable position information can be obtained under different observation conditions.

[0027] In a possible implementation, step S330 further includes step S331, wherein the first auxiliary positioning algorithm channel is a differential information routing auxiliary positioning algorithm. Specifically, the first auxiliary positioning algorithm channel is concretized as a differential information routing auxiliary positioning algorithm, which is an algorithm that uses differential information (i.e., error parameters in the process of satellite signal propagation) to improve positioning accuracy, and reduces positioning errors by receiving and processing differential information. Step S332, initializing the approximate position of the data sensing device. Specifically, before using the differential information routing auxiliary positioning algorithm, the approximate position of the data sensing device is first initialized, and this approximate position is an initial estimate obtained by other means (such as GPS coarse positioning, map matching, etc.). Step S333, sending the approximate position of the data sensing device and the multi-source observation data to the electric power Beidou positioning service platform through a remote communication module, and generating differential error parameters according to the electric power Beidou positioning service platform. Specifically, after initializing the approximate position, the edge computing device sends the approximate position of the data sensing device and the collected multi-source observation data to the electric power Beidou positioning service platform through a remote communication module (such as 4G / 5G, etc.). This platform is a server specifically used to process Beidou positioning data and can generate differential error parameters. Step S334, send the differential error parameters to the edge computing device as input information of the first auxiliary positioning algorithm channel for position solution. Specifically, after receiving the approximate position and multi-source observation data of the data sensing device, the electric power Beidou positioning service platform generates differential error parameters, which are then sent back to the edge computing device as input information of the first auxiliary positioning algorithm channel (differential information routing auxiliary positioning algorithm) for position solution.

[0028] Among them, the differential information routing assisted positioning algorithm can perform position calculation according to the following method.

[0029] Let the number of observable satellites be , and the number is , the positioning solution equation can be written as: (1), where is the carrier phase measurement noise, From data sensing devices to observable satellites Pseudorange expressions in approximate coordinates After linearization, the difference of the first-order Taylor expansion coefficients corresponding to the three-dimensional coordinates is, Data-aware devices and BeiDou base station To observable satellites The difference in integer ambiguity, , Data-aware devices With BeiDou base station Observing satellites simultaneously The double difference of the carrier phase, , Data-aware devices The received Beidou signal frequency corresponds to the carrier wavelength. For data-aware devices at approximate coordinates BeiDou Satellite The pseudorange of The BeiDou satellites observed by the base station The pseudorange of are the three-dimensional coordinate correction numbers respectively. The least square solution of the position correction can be obtained by minimizing the carrier phase measurement noise variance: (2), where (3), (4), the above expression has been locked by the integer ambiguity resolution algorithm This implementation method uses the differential information routing assisted positioning algorithm and the differential information provided by the Beidou satellite system to correct the positioning error, significantly improving the positioning accuracy.

[0030] In a possible implementation, step S330 further includes step S335, if the remote communication module is disconnected, the multi-source observation data is identified based on the first auxiliary positioning algorithm channel to generate differential error parameters, wherein the differential error parameters include pseudorange corrections, clock corrections and ionospheric delay corrections. Specifically, in step S333, the edge computing device originally sends the approximate position and multi-source observation data to the electric power Beidou positioning service platform through the remote communication module to generate differential error parameters. However, if the remote communication module is disconnected for some reason (such as network failure, insufficient signal coverage, etc.), this step cannot be performed. In this case, step S335 provides an alternative solution, which uses the Beidou satellite parameters observed by the internal Beidou positioning module of the edge computing device itself for solution, including identifying the characteristics of the satellite signal strength, frequency offset, phase delay, etc., and using the model information such as satellite orbit and clock error pre-embedded in the algorithm. Through these analyses and calculations, the first auxiliary positioning algorithm channel generates a set of differential error parameters. These parameters are used to reflect the various errors in the satellite signal propagation process under the current observation conditions as accurately as possible, including pseudorange corrections (used to correct the distance error caused by atmospheric refraction, multipath effect and other factors in the satellite signal propagation process), clock corrections (used to correct the time synchronization error between the satellite clock and the ground receiver clock) and ionospheric delay corrections (used to correct the influence of the ionosphere on the satellite signal propagation speed).

[0031] Step S336, performing differential error correction on the multi-source observation data according to the differential error parameters, obtaining positioning solution data, and the first auxiliary positioning algorithm channel outputs the positioning solution data. Specifically, after generating the differential error parameters, these parameters are applied to the multi-source observation data to correct the errors therein, and finally the positioning solution data is output. One solution method is: replace the positioning solution equation (1) with Expression Replace it with the double difference between the carrier phase observed by the edge computing device and the carrier phase observed by the data sensing device, and Replaced with the BeiDou satellite data observed by edge computing devices This implementation makes up for this defect to a certain extent by enabling the first auxiliary positioning algorithm channel to autonomously generate differential error parameters when the remote communication module is disconnected. Although this autonomously generated differential error parameter is not as accurate as the parameter obtained from the electric power Beidou positioning service platform, it can still provide a relatively reliable positioning result in the case of communication interruption, improving the reliability and robustness of the positioning system.

[0032] In a possible implementation, step S340 further includes step S341, wherein the second auxiliary positioning algorithm channel is a phase estimation auxiliary positioning algorithm. Specifically, when the number of Beidou satellites observable by the data perception device is less than the preset perception number (4), the second auxiliary positioning algorithm channel is used for position solution. In this implementation, the second auxiliary positioning algorithm channel is designated as a phase estimation auxiliary positioning algorithm. The phase estimation auxiliary positioning algorithm is an algorithm that uses satellite signal phase information to assist positioning. Step S342, the second auxiliary positioning algorithm channel receives the real-time signal strength of the current edge computing device. Specifically, the real-time signal strength refers to the strength of the signal sent by the edge computing device when it reaches the data perception device. Step S343, the second auxiliary positioning algorithm channel identifies the signal strength of the observation data of the current source and outputs the observation signal strength. Specifically, the second auxiliary positioning algorithm channel identifies the signal strength of multi-source observation data, distinguishes signals from different sources, and extracts the observation signal strength related to the satellite signal, that is, the observation signal strength refers to the strength of the satellite signal when it reaches the data perception device. Step S344, positioning fitting is performed according to the real-time signal strength and the observed signal strength, and the positioning solution data is determined. The second auxiliary positioning algorithm channel outputs the positioning solution data. Specifically, the real-time signal strength and the observed signal strength information are combined with the known satellite orbit and clock parameters to perform positioning fitting. Positioning fitting is an iterative process, which continuously adjusts the positioning parameters (such as position coordinates and time) to minimize the difference between the observed data and the predicted data. After positioning fitting, the device position data is obtained, including longitude, latitude, altitude and other information. This implementation method uses the phase estimation auxiliary positioning algorithm as the second auxiliary positioning algorithm channel, because when the number of satellites is insufficient, the traditional pseudo-range positioning method may be affected by large errors, and phase estimation can provide higher positioning accuracy, especially in complex environments such as multipath effects and atmospheric delays. By introducing the recognition and fitting process of real-time signal strength and observed signal strength, additional information about the signal propagation path is provided, the uncertainty in the positioning process is reduced, and the accuracy and reliability of positioning are further improved.

[0033] In a possible implementation, positioning fitting is performed according to the real-time signal strength and the observed signal strength to determine the positioning solution data, and step S344 further includes step S3441, comparing the real-time signal strength and the observed signal strength to determine the first key point. Specifically, the real-time signal strength (signal from the edge computing device) and the observed signal strength (signal from the satellite) are compared to find the position points with obvious signal strength characteristics and high reliability, and these position points are used as "key points". Step S3442, construct a neighborhood set based on the first key point. Specifically, after the first key point is determined, a "neighborhood set" is constructed around this point, and this set includes other position points that are close to the first key point in space, and these position points have similar signal strength characteristics. Step S3443, obtain the feature vector of each neighborhood point in the neighborhood set, including the signal reception strength of each neighborhood point, the distance distribution weight of each neighborhood point and the first key point, and the reliability factor of each neighborhood point. Specifically, for each position point (neighborhood point) in the neighborhood set, its feature vector is calculated. This feature vector includes the signal reception strength of the point, the weight assigned to its distance from the first key point (the weight assigned according to the distance between the neighborhood point and the first key point, the closer the distance, the higher the weight) and its reliability factor (based on the stability and consistency of the signal strength). Step S3444, fitting is performed according to the feature vector of each neighborhood point in the neighborhood set, and the positioning solution data is output. Specifically, the feature vector of the neighborhood point is used for fitting to find the position coordinate that best represents the entire neighborhood set. This position coordinate is the final positioning result of the data perception device. This implementation method constructs a neighborhood set based on the first key point and obtains the feature vector of each neighborhood point, making full use of the signal strength information for fitting, which not only improves the accuracy of positioning, but also enhances the robustness of positioning, and can obtain reliable results even in complex signal environments or insufficient satellites.

[0034] Among them, the phase estimation assisted positioning algorithm can perform position calculation according to the following method.

[0035] The data sensing device feeds back the time series value of the signal strength sent by the edge computing device monitored in the downlink , is the number of all edge computing devices in the local area, The data sensing device receives the first beacon frame in the kth beacon frame sending cycle. The received signal strength of the local communication network beacon frame of the edge computing device, and the sending period of the local communication network beacon frame is ,In one positioning cycle, the data sensing device can receive K beacon frames to maintain frame synchronization, The index variable of the received beacon frame signal strength vector. They are the number of satellites observable by data sensing devices and the number of auxiliary positioning satellites observable by edge computing devices. , for data-aware devices The observed phase of each auxiliary positioning satellite can be corrected by the edge computing device observed phase and the local communication network ranging result to obtain the phase estimate. The reference location received signal strength data set collected in advance, are the known coordinates of the reference point, The signal strength received by the corresponding data sensing device, is the reference point index variable, is the number of reference points. The smaller the position change when selecting the reference point, the higher the positioning accuracy, but the greater the impact of the received signal strength measurement error, so the position change of adjacent reference points along a single coordinate axis is Just be equivalent.

[0036] against Find the index of the reference point with the smallest received signal strength distance from all reference points: (5) and remember , is the estimated location of the k-th beacon transmission period data sensing device. is the minimum number of estimated values ​​of location points contained in the neighborhood of the key point, is the neighborhood radius. For all location point estimates, Perform the following processing.

[0037] Step A: Select any location point coordinates , the calculation meets The number of location points, if greater than Then Enter key point location set , and all other location points in the neighborhood are included in the set .

[0038] Step B: Set All locations in Calculate the number of location points in the neighborhood. If it is greater than Then Enter key point location set , and combine all other The location point is drawn into the collection In, until It is an empty set. Output key point position set .

[0039] Step C: Repeat steps AB for the remaining points in the , until all points have been traversed once, and output multiple sets .

[0040] Select the final key point set with the most elements , the estimated position of the sensing device e can be obtained: (6) The precise location coordinates of the known edge computing device, the estimated location of the data sensing device, and The coordinate value of the auxiliary positioning satellite position can be calculated as follows to obtain the carrier phase of the auxiliary positioning satellite positioning signal to the data sensing device e: (7), where is the carrier phase measurement value of the observed satellite u calculated based on the estimated position value of the data sensing device, They are the pseudoranges from the data sensing device and edge computing device to the satellite u respectively.

[0041] According to the above method, we can obtain all data sensing devices e for The carrier phase observation values ​​of the auxiliary positioning satellites can be used to solve the position coordinates of the data sensing device using equations (1)-(4) to obtain the position coordinates .

[0042] The local communication signal strength measurement and the edge computing device observation satellite assisted positioning results follow Gaussian distribution respectively. , , , are variance matrices respectively. The final coordinate information of the data sensing device can be expressed as: (8).

[0043] Step S400, collect distance detection samples of high-voltage electrical equipment in the substation area, and train a safe distance detection model based on the distance detection samples of high-voltage electrical equipment. Specifically, collect distance detection samples of high-voltage electrical equipment (such as transformers, circuit breakers, disconnectors, etc.) in the substation area, and these samples include information such as the location and distance of the equipment. Then use these sample data to train a safe distance detection model, which can predict or determine whether the distance between devices is safe.

[0044] Step S500, input the positioning solution data into the safety distance detection model to obtain the safety distance detection result. Specifically, the obtained positioning solution data is input into the trained safety distance detection model, and the model calculates the safety distance detection result based on the input data. The safety distance detection result indicates whether the distance between the high-voltage electrical equipment is safe. This result can be a binary classification (safe / unsafe), or a specific distance value or distance range. The embodiment of the present application constructs a data sensing device integrating a Beidou positioning module and an NB-IoT communication module, collects and transmits multi-source observation data in the substation area, uses the auxiliary positioning algorithm model embedded in the edge computing device to solve the position of the multi-source observation data, obtains positioning solution data, collects high-voltage electrical equipment distance detection samples in the substation area, trains to obtain a safety distance detection model, inputs the positioning solution data into the safety distance detection model, obtains the safety distance detection result of the high-voltage electrical equipment, and other technical means, so as to realize the accurate measurement and calculation of the position of the high-voltage electrical equipment, and achieve the technical effect of improving the accuracy of the detection results.

[0045] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for detecting safe distance of high-voltage electrical equipment in combination with Beidou positioning technology, characterized in that: The method comprises: Construct a data sensing device, wherein the data sensing device integrates a Beidou positioning module and an NB-Iot communication module; Collect multi-source observation data of the substation area according to the data perception device, and send the multi-source observation data to the edge computing device through the NB-Iot communication module; Performing position calculation on the multi-source observation data according to the auxiliary positioning algorithm model embedded in the edge computing device to obtain positioning solution data; The auxiliary positioning algorithm model includes a first auxiliary positioning algorithm channel and a second auxiliary positioning algorithm channel, including: Identify the number of BeiDou satellites observable by the data sensing device; When the number of Beidou satellites is greater than or equal to a preset sensing number, performing position solution on the multi-source observation data based on the first auxiliary positioning algorithm channel to obtain positioning solution data, wherein the preset sensing number is 4; When the number of Beidou satellites is less than the preset sensing number, performing position calculation on the multi-source observation data based on the second auxiliary positioning algorithm channel to obtain positioning solution data; Collecting high-voltage electrical equipment distance detection samples in the substation area, and training a safe distance detection model based on the high-voltage electrical equipment distance detection samples; The positioning solution data is input into the safety distance detection model to obtain a safety distance detection result.

2. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 1, characterized in that: Sending the multi-source observation data to the edge computing device through the NB-Iot communication module includes: Dividing the multi-source observation data according to a preset data amount, and outputting k groups of multi-source observation data, where k is a positive integer greater than or equal to 2; Building an edge computing network, wherein the edge computing network includes a plurality of edge nodes, each edge node corresponding to an edge computing device; Performing status detection on the edge computing network and screening k edge computing devices; The NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices accordingly.

3. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 1, characterized in that: The first auxiliary positioning algorithm channel is a differential information routing auxiliary positioning algorithm, including: Initializing an approximate position of the data sensing device; The approximate position of the data sensing device and the multi-source observation data are sent to the electric power Beidou positioning service platform through a remote communication module, and a differential error parameter is generated according to the electric power Beidou positioning service platform; The differential error parameter is sent to the edge computing device as input information of the first auxiliary positioning algorithm channel for position solution.

4. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 3, characterized in that: If the remote communication module is disconnected, the method includes: Identifying the multi-source observation data based on the first auxiliary positioning algorithm channel to generate differential error parameters, wherein the differential error parameters include a pseudorange correction number, a clock correction number, and an ionospheric delay correction number; The differential error of the multi-source observation data is corrected according to the differential error parameter to obtain positioning solution data, and the first auxiliary positioning algorithm channel outputs the positioning solution data.

5. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 1, characterized in that: The second auxiliary positioning algorithm channel is a phase estimation auxiliary positioning algorithm, including: The second auxiliary positioning algorithm channel receives the real-time signal strength of the current edge computing device; The second auxiliary positioning algorithm channel performs signal strength identification on the observation data of the current source and outputs the observation signal strength; Positioning fitting is performed according to the real-time signal strength and the observed signal strength to determine positioning solution data, and the second auxiliary positioning algorithm channel outputs the positioning solution data.

6. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 5, characterized in that: Performing positioning fitting according to the real-time signal strength and the observed signal strength to determine positioning solution data includes: Determine a first key point by comparing the real-time signal strength with the observed signal strength; Constructing a neighborhood set based on the first key point; Obtaining a feature vector of each neighborhood point in the neighborhood set, including a signal reception strength of each neighborhood point, a distance distribution weight between each neighborhood point and the first key point, and a reliability factor of each neighborhood point; Fitting is performed according to the characteristic vector of each neighborhood point in the neighborhood set, and positioning solution data is output.

7. The method for detecting the safe distance of high-voltage electrical equipment in combination with Beidou positioning technology as claimed in claim 2, characterized in that: The NB-Iot communication module sends the k groups of multi-source observation data to the k edge computing devices respectively, including: Obtain k local positioning solution data corresponding to the k edge computing devices; Performing collaborative processing on the k local positioning solution data, and outputting the k local positioning solution data after the collaborative processing; Perform global error correction on the k local positioning solution data after the collaborative processing, and output collaborative positioning solution data.

Images