Power equipment status monitoring method and related equipment based on high-precision time service of Beidou

Abstract

The present application discloses a power equipment status monitoring method and related devices based on high-precision Beidou time service, which relates to the technical field of Beidou satellites. The power equipment status monitoring method based on high-precision Beidou time service includes: acquiring Beidou satellite signals and collecting real-time ionospheric data; based on the Beidou satellite signals and the real-time ionospheric data, performing ionospheric delay compensation according to a preset dynamic compensation model to determine a high-precision Beidou time service signal, and realizing precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal; extracting characteristic information of real-time operation parameters of power equipment, obtaining global model knowledge of preset edge nodes in combination with a federated learning mechanism, and analyzing and judging the status of power equipment in real time according to a pre-trained lightweight neural network model to obtain real-time monitoring information on the health of power equipment, wherein the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training.

Description

Technical Field

[0001] This application relates to the field of Beidou satellite technology, and particularly to a method for monitoring the status of power equipment based on high-precision Beidou time service and related equipment. Background Art

[0002] In recent years, with the increase in the load of the power grid and power equipment, the real-time monitoring and maintenance of the status of power equipment have become increasingly important. Traditional methods for monitoring the status of power equipment often rely on ground monitoring stations or local sensors, with low data acquisition and transmission efficiency, making it difficult to achieve real-time status tracking of large-scale power equipment. In addition, due to the operation of power equipment in complex environments (such as ionospheric delay, multipath effect, etc.), traditional time service methods have problems with insufficient accuracy, resulting in limited accuracy of monitoring results.

[0003] Therefore, how to accurately obtain the real-time operation status information of power equipment while achieving real-time synchronization, transmission, and analysis of data has become a key technical problem in the current operation and maintenance and intelligent scheduling of power systems. Summary of the Invention

[0004] The main purpose of this application is to provide a method for monitoring the status of power equipment based on high-precision Beidou time service and related equipment, aiming to solve the technical problem of difficultly accurately obtaining the real-time operation status information of power equipment.

[0005] To achieve the above object, this application proposes a method for monitoring the status of power equipment based on high-precision Beidou time service, and the method includes:

[0006] Obtain Beidou satellite signals and collect real-time ionospheric data;

[0007] Based on the Beidou satellite signals and the real-time ionospheric data, perform ionospheric delay compensation according to a preset dynamic compensation model to determine a high-precision Beidou time service signal, and achieve precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal;

[0008] Extract the characteristic information of the real-time operation parameters of the power equipment, combine the federated learning mechanism to obtain the global model knowledge of preset edge nodes, and analyze and judge the status of the power equipment in real time according to a pre-trained lightweight neural network model to obtain real-time monitoring information on the health of the power equipment, where the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training.

[0009] In one embodiment, the step of performing ionospheric delay compensation according to a preset dynamic compensation model based on the Beidou satellite signals and the real-time ionospheric data to determine a high-precision Beidou time service signal includes:

[0010] Parse the Beidou satellite signal to determine the elevation angle of the Beidou satellite;

[0011] Parse the real-time ionosphere data to determine the ionospheric electron density profile;

[0012] Divide the ionospheric height range into multiple discrete height layers, and input the ionospheric electron density profile, the elevation angle of the Beidou satellite, the preset receiver geographical coordinates, and the radius of the Earth into a preset receiver vertical ionospheric delay field model to discretely calculate the delay compensation amount corresponding to each height layer;

[0013] Accumulate the delay compensation amounts of all height layers to obtain the real-time ionospheric delay compensation amount;

[0014] Based on the real-time ionospheric delay compensation amount, perform ionospheric delay compensation on the Beidou satellite signal to determine a high-precision Beidou timing signal.

[0015] In one embodiment, before the step of dividing the ionospheric height range into multiple discrete height layers, and inputting the ionospheric electron density profile, the elevation angle of the Beidou satellite, the preset receiver geographical coordinates, and the radius of the Earth into a preset receiver vertical ionospheric delay field model to discretely calculate the delay compensation amount corresponding to each height layer, it includes:

[0016] Obtain historical ionosphere data, corresponding historical satellite elevation angles, and corresponding timing error data to construct a training data set;

[0017] Input the training data set into a timing feature extraction network to be trained, and based on the non-linear mapping relationship between ionospheric spatio-temporal changes and timing errors, extract key timing features;

[0018] According to the key timing features, determine a correction coefficient through the network weights obtained by training;

[0019] Based on the correction coefficient, adaptively calibrate the receiver vertical ionospheric delay field model.

[0020] In one embodiment, before the step of extracting the characteristic information of the real-time operating parameters of the power equipment, combining the federated learning mechanism to obtain the global model knowledge of the preset edge nodes, and analyzing and judging the power equipment status in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the equipment health degree, it includes:

[0021] Obtain the historical state data of the power equipment and the corresponding fault records;

[0022] Input the historical status data of the power equipment into a neural network model to be trained for equipment status analysis and judgment, and obtain equipment health prediction information. Among them, during equipment status analysis and judgment, high-precision floating-point weights are converted into low-precision fixed-point numbers through quantization-aware training;

[0023] Calculate the contribution degree of each channel of the neural network model according to the activation value and gradient during the equipment status analysis and judgment process, and prune the channels with contribution degrees lower than the preset warning threshold;

[0024] Compare the equipment health prediction information with the fault record to determine the prediction difference value;

[0025] If the prediction difference value does not meet the preset prediction allowable error range, return to the step of inputting the historical status data of the power equipment into the neural network model to be trained for equipment status analysis and judgment. If the prediction difference value meets the preset prediction allowable error range, output the trained lightweight neural network model.

[0026] In one embodiment, the steps of extracting the characteristic information of the real-time operation parameters of the power equipment, combining the federated learning mechanism to obtain the global model knowledge of the preset edge nodes, and analyzing and judging the power equipment status in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the equipment health include:

[0027] Extract the characteristic information of the real-time operation parameters of the power equipment and construct a real-time feature vector;

[0028] Encrypt and upload the parameters of the local lightweight neural network model to the aggregation server, and obtain the global model parameters returned by the aggregation server;

[0029] Input the real-time feature vector into the lightweight neural network model using the global model parameters, analyze and judge the power equipment status in real time, and determine the real-time monitoring information of the equipment health.

[0030] In one embodiment, after the step of obtaining the real-time monitoring information of the equipment health includes:

[0031] Extract the key warning data in the real-time monitoring information and compress it into a short message data packet;

[0032] Send the short message data packet to the preset operation and maintenance warning device in a priority preemption mode through the preset Beidou channel;

[0033] If the sending fails, automatically re-transmit the short message data packet within the preset time interval based on the exponential backoff algorithm.

[0034] In addition, to achieve the above object, the present application further provides a power equipment status monitoring device based on Beidou high-precision timing, and the power equipment status monitoring device based on Beidou high-precision timing includes:

[0035] An acquisition module, configured to acquire Beidou satellite signals and collect real-time ionospheric data;

[0036] A synchronization module, configured to perform ionospheric delay compensation based on the Beidou satellite signals and the real-time ionospheric data according to a preset dynamic compensation model, determine a high-precision Beidou timing signal, and achieve precise synchronization of multi-source data of power equipment based on the high-precision Beidou timing signal;

[0037] A monitoring module, configured to extract characteristic information of real-time operation parameters of the power equipment, obtain global model knowledge of preset edge nodes in combination with a federated learning mechanism, and analyze and judge the status of the power equipment in real time according to a pre-trained lightweight neural network model to obtain real-time monitoring information on the health of the power equipment, wherein the lightweight neural network model is obtained by parameter compression training through channel pruning and quantization-aware training.

[0038] In addition, to achieve the above object, the present application further provides a power equipment status monitoring device based on Beidou high-precision timing, and the device includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the power equipment status monitoring method based on Beidou high-precision timing as described above.

[0039] In addition, to achieve the above object, the present application further provides a storage medium, and the storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the power equipment status monitoring method based on Beidou high-precision timing as described above are implemented.

[0040] In addition, to achieve the above object, the present application further provides a computer program product, and the computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the power equipment status monitoring method based on Beidou high-precision timing as described above are implemented.

[0041] One or more technical solutions proposed by the present application have at least the following technical effects:

[0042] In related technologies, traditional power equipment status monitoring methods often rely on ground monitoring stations or local sensors, with low data acquisition and transmission efficiency, making it difficult to achieve real-time status tracking of large-scale power equipment. In addition, due to the operation of power equipment in complex environments (such as ionospheric delay, multipath effect, etc.), traditional timing methods have problems with insufficient accuracy, resulting in limited accuracy of monitoring results. In contrast, in this application, Beidou satellite signals are acquired and real-time ionospheric data is collected; based on the Beidou satellite signals and the real-time ionospheric data, ionospheric delay compensation is performed according to a preset dynamic compensation model to determine a high-precision Beidou timing signal, and precise synchronization of multi-source data of power equipment is achieved based on the high-precision Beidou timing signal; the characteristic information of the real-time operation parameters of the power equipment is extracted, the global model knowledge of preset edge nodes is obtained in combination with the federated learning mechanism, and the status of the power equipment is analyzed and judged in real time according to a pre-trained lightweight neural network model to obtain real-time monitoring information on the health of the power equipment. Among them, the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training. It can be understood that this application solves the problem of insufficient timing accuracy in traditional power equipment status monitoring methods, ensuring precise data synchronization and high reliability. Beidou timing synchronization can efficiently integrate multi-source data from different devices, achieve real-time transmission and analysis, and help the power system quickly discover and respond to problems. The lightweight neural network model can perform real-time analysis based on remote data, and in combination with the mechanism of federated learning, quickly extract key characteristic information, providing intelligent decision-making support for power maintenance and scheduling. Real-time monitoring and analysis of equipment status helps optimize energy scheduling, improve the efficiency and reliability of the power system. By predicting equipment failures and performing maintenance in advance, the costs of power equipment inspection and replacement can be reduced, and the asset life can be extended. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0044] To more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic flowchart provided for Embodiment 1 of the power equipment status monitoring method based on Beidou high-precision timing of the present application;

[0046] Figure 2 It is a schematic flowchart provided for Embodiment 2 of the power equipment status monitoring method based on Beidou high-precision timing of the present application;

[0047] Figure 3 Schematic diagram of the brief process of the power equipment status monitoring method based on Beidou high-precision time service provided by this application;

[0048] Figure 4 Schematic diagram of the module structure of the power equipment status monitoring device based on Beidou high-precision time service in the embodiment of this application;

[0049] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the power equipment status monitoring method based on Beidou high-precision time service in the embodiment of this application.

[0050] The realization of the purpose, functional characteristics and advantages of this application will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0051] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of this application and are not used to limit this application.

[0052] In order to better understand the technical solutions of this application, the following will be described in detail with reference to the accompanying drawings of the specification and the specific implementation manners.

[0053] The main solution of the embodiment of this application is:

[0054] Obtain Beidou satellite signals and collect real-time ionospheric data;

[0055] Based on the Beidou satellite signals and the real-time ionospheric data, perform ionospheric delay compensation according to a preset dynamic compensation model, determine a high-precision Beidou time service signal, and realize the precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal;

[0056] Extract the characteristic information of the real-time operation parameters of the power equipment, obtain the global model knowledge of the preset edge nodes in combination with the federated learning mechanism, and analyze and judge the power equipment status in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the power equipment health, where the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training.

[0057] In this embodiment, this application takes the power equipment status monitoring device based on Beidou high-precision time service as the execution subject. For the convenience of description, it is hereinafter referred to as the "device" for specific description.

[0058] Since existing technologies often rely on ground monitoring stations or local sensors, the data acquisition efficiency and transmission efficiency are relatively low, making it difficult to achieve real-time status tracking of large-scale power equipment. In addition, due to the operation of power equipment in complex environments (such as ionospheric delay, multipath effect, etc.), traditional time synchronization methods have problems with insufficient accuracy, resulting in limitations in the accuracy of monitoring results.

[0059] This application provides a solution, which solves the problem of insufficient time synchronization accuracy in traditional power equipment status monitoring methods, ensuring accurate data synchronization and high reliability. Beidou time synchronization can efficiently integrate multi-source data from different devices, achieve real-time transmission and analysis, and help the power system quickly discover and address problems. The lightweight neural network model can perform real-time analysis based on remote data, and combined with the mechanism of federated learning, quickly extract key feature information to provide intelligent decision-making support for power maintenance and scheduling. Real-time monitoring and analysis of equipment status help optimize energy scheduling, improve the efficiency and reliability of the power system. By predicting equipment failures and performing maintenance in advance, the costs of power equipment inspection and replacement can be reduced, and the asset lifespan can be extended.

[0060] Based on this, the embodiments of this application provide a method for monitoring the status of power equipment based on Beidou high-precision time synchronization, referring to Figure 1 , Figure 1 which is a schematic flowchart of the first embodiment of the method for monitoring the status of power equipment based on Beidou high-precision time synchronization in this application.

[0061] In this embodiment, the method for monitoring the status of power equipment based on Beidou high-precision time synchronization includes steps S10 to S30:

[0062] Step S10: Obtain Beidou satellite signals and collect real-time ionospheric data;

[0063] It should be noted that the Beidou satellite signals refer to the signals transmitted by the Beidou satellite navigation system (BDS) for positioning, navigation, and time synchronization. The Beidou satellite navigation system is a global satellite navigation system independently developed by China, and its signals include but are not limited to civilian signals in the B1 and B2 frequency bands, as well as possible military or special frequency band signals. In the present invention, the Beidou satellite signals are the basic data sources for achieving high-precision time synchronization and ionospheric delay compensation. Its protection scope should cover all Beidou satellite signals that can be parsed by the receiver and used for time synchronization, including but not limited to existing frequency bands and future possible extended frequency bands.

[0064] The real-time ionospheric data refers to the data related to the ionospheric state collected in real time during the monitoring process. The ionosphere is a part of the Earth's atmosphere, and its characteristics (such as electron density) can affect the propagation time of satellite signals, thereby affecting the timing accuracy. In the present invention, the real-time ionospheric data includes, but is not limited to, information such as ionospheric electron density profiles, total electron content (TEC), and satellite elevation angles. These data can be obtained through sensors built into the Beidou receiver or external sensors and are used in the dynamic compensation model to improve the timing accuracy. The scope of protection should include all data types related to the ionospheric state and capable of being used for timing compensation.

[0065] Exemplarily, this embodiment adopts an integrated Beidou receiver system for acquiring Beidou satellite signals and collecting real-time ionospheric data. The system mainly includes the following components:

[0066] Beidou receiver: A high-performance Beidou-3 compatible receiver is selected, supporting signal reception in B1I and B2I frequency bands. The receiver is built with a domestic chip and has a high-precision timing function and an ionospheric data acquisition module.

[0067] Ionospheric data acquisition module: This module receives the navigation message and pseudorange measurement data in the Beidou satellite signal, and resolves the change information of the total electron content (TEC) in the ionosphere in real time. At the same time, combining the geographical location of the receiver and the satellite elevation angle information, it calculates the influence of ionospheric delay on the timing signal.

[0068] Data processing unit: The data processing unit inside the receiver uses a real-time operating system, which can quickly process Beidou satellite signals and ionospheric data, and performs ionospheric delay compensation through the built-in dynamic compensation model, and finally outputs a high-precision timing signal.

[0069] It can be understood that after the receiver is started, it automatically searches for and locks the Beidou satellite signal, and obtains the pseudorange, Doppler frequency shift, and navigation message information of the satellite. By parsing the navigation message, the ionospheric delay correction parameters (such as ionospheric delay model coefficients) are extracted. At the same time, combining the high-precision clock built into the receiver, the change of ionospheric TEC is measured in real time. The collected ionospheric data is input into a preset dynamic compensation model to calculate the ionospheric delay compensation amount at the current moment, and the Beidou timing signal is corrected. The accuracy of the timing signal after compensation reaches the sub-nanosecond level, which can meet the requirements of the high-precision power equipment monitoring system.

[0070] It is understandable that by collecting ionospheric data in real time and performing dynamic compensation, the data synchronization accuracy of the power equipment monitoring system has been significantly improved. By using the anti-spoofing technology and high-precision time service characteristics of Beidou satellite signals, the risk of time service signals being tampered with is effectively avoided, and the reliability of the system is improved. This system can operate stably in a complex electromagnetic environment. Especially in areas with frequent ionospheric disturbances, it can still maintain high-precision time service, providing a reliable time sequence reference for the real-time monitoring of power equipment. Through the integrated receiver design and the application of domestic chips, the hardware cost of the system is reduced, while the dependence on external high-precision time service equipment is reduced, and the economy of the system is improved.

[0071] In summary, in this embodiment, by acquiring Beidou satellite signals and collecting real-time ionospheric data, high-precision time service and data synchronization are achieved, significantly improving the performance and reliability of the power equipment monitoring system.

[0072] Step S20: Based on the Beidou satellite signal and the real-time ionospheric data, perform ionospheric delay compensation according to a preset dynamic compensation model to determine a high-precision Beidou time service signal, and achieve precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal;

[0073] It should be noted that the dynamic compensation model refers to a mathematical model or algorithm for real-time correction of the influence of ionospheric delay. This model is based on the characteristics of Beidou satellite signals and the spatio-temporal variation law of the ionosphere. By analyzing parameters such as the ionospheric electron density profile and satellite elevation angle, the ionospheric delay compensation amount is calculated, thereby improving the accuracy of the time service signal.

[0074] The ionospheric delay compensation refers to the process of correcting the signal propagation delay caused by the ionosphere through a dynamic compensation model. Ionospheric delay is one of the main factors affecting satellite time service accuracy. By collecting ionospheric data (such as TEC values) in real time and combining with the compensation model, the influence of delay on time service accuracy can be significantly reduced. The high-precision Beidou time service signal refers to the Beidou satellite time service signal after ionospheric delay compensation, and its accuracy is usually better than traditional time service methods (such as GPS time service), and can reach the sub-nanosecond level or even higher. The precise synchronization of multi-source data of power equipment refers to the process of precisely aligning multi-source data from different sensors and monitoring devices in time by using a high-precision Beidou time service signal. Multi-source data usually includes different types of data such as current, voltage, temperature, and vibration. Precise synchronization can ensure the consistency of these data in the time dimension, thereby providing a reliable data basis for the condition monitoring and fault diagnosis of power equipment.

[0075] Exemplarily, based on the signal characteristics of Beidou-3 satellites, a vertical ionospheric delay field model for the receiver is designed, and the delay compensation amount formula is as follows:

[0076] Among them, Ne(h) is the ionospheric electron density profile, θ is the satellite elevation angle, R is the radius of the Earth, and k is a correction coefficient.

[0077] Exemplarily, referring to Figure 2 , the Beidou receiver receives Beidou satellite signals in real time, analyzes the satellite elevation angle and navigation message, and collects ionospheric TEC data. The sensor network collects multi-source data such as current, voltage, temperature, and vibration of power equipment. The ionospheric TEC data, satellite elevation angle, and receiver geographical location are input into the dynamic compensation model to calculate the ionospheric delay compensation amount. The Beidou satellite signal is compensated for delay to generate a high-precision timing signal. Based on the high-precision Beidou timing signal, the multi-source data collected by the sensor is timestamped to achieve precise synchronization.

[0078] In this embodiment, by calculating the ionospheric delay compensation amount, the Beidou satellite signal is compensated for delay to generate a high-precision timing signal. It is realized that based on the high-precision Beidou timing signal, the multi-source data collected by the sensor is timestamped.

[0079] Step S30: Extract the characteristic information of the real-time operation parameters of the power equipment, combine the federated learning mechanism to obtain the global model knowledge of the preset edge nodes, and analyze and judge the state of the power equipment in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the power equipment health. Among them, the lightweight neural network model is obtained by parameter compression training through channel pruning and quantization-aware training.

[0080] It should be noted that the characteristic information of the real-time operation parameters refers to the key characteristics that can reflect the equipment state extracted from the real-time operation data of the power equipment. These characteristic information includes but is not limited to statistical values, change rates, spectral characteristics, etc. of parameters such as current, voltage, temperature, vibration, and partial discharge intensity. The federated learning mechanism is a distributed machine learning method that allows multiple edge nodes (devices) to cooperate in training the global model by sharing model parameters without sharing the original data. The lightweight neural network model refers to a neural network model optimized by specific technologies, which significantly reduces the number of model parameters and computational complexity while maintaining a high accuracy rate to adapt to the resource-constrained edge computing environment.

[0081] Additionally, it should be noted that the channel pruning is a model compression technique that removes channels with low contribution degrees by analyzing the contribution degrees of each channel in the neural network, thereby reducing the number of model parameters and computational complexity. The quantization-aware training is a model optimization technique that converts high-precision floating-point weights into low-precision fixed-point numbers during the training phase, while adjusting the model structure and parameters to reduce the storage space and computational complexity of the model, and at the same time, tries to maintain the accuracy of the model as much as possible. The real-time monitoring information of the power equipment health refers to the information reflecting the current health state of the equipment obtained by analyzing the real-time operation data of the power equipment, combining the lightweight neural network model and the federated learning mechanism. These information include the health score of the equipment, the failure probability, the remaining life prediction, etc.

[0082] Exemplarily, the sensor network collects the operation parameters of the power equipment in real time, including current, voltage, temperature, vibration, and partial discharge signals. The feature extraction module preprocesses the collected data, extracts key feature information, and forms a feature vector. Each edge node uses the locally collected data to train the lightweight neural network model, extracts the model parameters, and encrypts and uploads them to the aggregation server. The aggregation server updates the global model parameters according to the federated learning algorithm, combining the parameters of each edge node, and broadcasts the updated parameters back to each edge node. The edge node uses the updated global model parameters to analyze and judge the real-time feature vector, and evaluate the health state of the power equipment. According to the health score and failure probability output by the model, the real-time monitoring information of the power equipment health is generated. If the health score is lower than the preset threshold or the failure probability exceeds the warning value, the system will extract the key alarm data and compress it into a short message data packet. Through the Beidou short message communication or 4G / 5G network, the alarm information is transmitted to the operation and maintenance center in real time.

[0083] In summary, this embodiment realizes the efficient and accurate real-time monitoring of the power equipment health by extracting the real-time operation parameter feature information of the power equipment, combining the federated learning mechanism and the lightweight neural network model, and significantly improves the operation and maintenance efficiency and reliability of the power system.

[0084] This embodiment provides a method for monitoring the status of power equipment based on high-precision Beidou time service, which solves the problem of insufficient time service accuracy in traditional power equipment status monitoring methods, ensuring accurate data synchronization and high reliability. Beidou time service synchronization can efficiently integrate multi-source data from different devices, realize real-time transmission and analysis, and help the power system quickly discover and respond to problems. The lightweight neural network model can perform real-time analysis based on remote data, and combined with the mechanism of federated learning, quickly extract key feature information to provide intelligent decision-making support for power maintenance and scheduling. Real-time monitoring and analysis of equipment status help optimize energy scheduling, improve the efficiency and reliability of the power system. By predicting equipment failures and performing maintenance in advance, the costs of power equipment inspection and replacement can be reduced, and the asset life can be extended.

[0085] In a feasible implementation manner, the steps of compensating for the ionospheric delay based on the Beidou satellite signal and the real-time ionospheric data according to a preset dynamic compensation model to determine a high-precision Beidou time service signal include:

[0086] Parse the Beidou satellite signal to determine the elevation angle of the Beidou satellite;

[0087] Parse the real-time ionospheric data to determine the ionospheric electron density profile;

[0088] Divide the ionospheric height range into multiple discrete height layers, input the ionospheric electron density profile, the elevation angle of the Beidou satellite, the preset receiver geographical coordinates, and the Earth's radius into a preset receiver vertical ionospheric delay field model, and discretely calculate the delay compensation amount corresponding to each height layer;

[0089] Accumulate the delay compensation amounts of all height layers to obtain the real-time ionospheric delay compensation amount;

[0090] Based on the real-time ionospheric delay compensation amount, perform ionospheric delay compensation on the Beidou satellite signal to determine a high-precision Beidou time service signal.

[0091] It should be noted that the elevation angle of the Beidou satellite refers to the angle between the transmission direction of the Beidou satellite signal and the horizontal plane of the receiver. It is an important parameter used in satellite navigation systems to describe the position of the satellite relative to the receiver. The magnitude of the elevation angle affects the length of the signal propagation path and the delay amount of the signal in the ionosphere. The ionospheric electron density profile refers to the distribution curve of the electron density in the ionosphere varying with height. It reflects the degree of influence of the ionosphere on satellite signal propagation and is a key parameter for ionospheric delay compensation.

[0092] Additionally, it should be noted that dividing the ionospheric height range into multiple discrete height layers means that for the sake of simplifying calculations, the continuous height interval of the ionosphere is divided into several discrete height layers. The electron density of each height layer can be estimated through interpolation or fitting methods, and thus used to calculate the ionospheric delay. The receiver vertical ionospheric delay field model is a mathematical model for calculating the ionospheric delay. Based on parameters such as the ionospheric electron density profile, satellite elevation angle, receiver geographical coordinates, and the Earth's radius, it calculates the delay amount of the signal in the ionosphere through analytical methods or numerical methods. Discretized calculation means that after dividing the ionosphere into multiple discrete height layers, the contribution of each height layer to the satellite signal delay is calculated separately, and the total delay amount is obtained by accumulation. This method can effectively simplify the calculation complexity and improve the accuracy of delay compensation at the same time. The real-time ionospheric delay compensation amount refers to the real-time correction value of the ionospheric delay obtained through the above models and calculation methods. This compensation amount is used to correct the delay error of the Beidou satellite signal during its propagation in the ionosphere, thereby improving the timing accuracy.

[0093] Exemplarily, in high-precision timing applications, the ionospheric delay is one of the main factors affecting the timing accuracy of satellite signals. When the Beidou satellite signal passes through the ionosphere, it will be delayed due to the change in the ionospheric electron density. In order to improve the timing accuracy, it is necessary to accurately compensate for the ionospheric delay. This embodiment realizes the output of high-precision timing signals by analyzing the Beidou satellite signal and real-time ionospheric data and combining with the vertical ionospheric delay field model.

[0094] The Beidou receiver receives the Beidou satellite signal in real time and analyzes the satellite elevation angle and the ionospheric delay correction parameters in the navigation message.

[0095] The ionospheric monitoring module collects the ionospheric TEC data, combines it with the receiver geographical coordinates (and the Earth's radius) to estimate the ionospheric electron density profile. The ionospheric height range is divided into multiple discrete height layers.

[0096] For each height layer, according to the ionospheric electron density profile, satellite elevation angle, receiver geographical coordinates, and the Earth's radius, it is input into the receiver vertical ionospheric delay field model. For each discrete height layer, the corresponding delay compensation amount is calculated. The delay compensation amounts of all discrete height layers are accumulated to obtain the real-time ionospheric delay compensation amount. According to the real-time ionospheric delay compensation amount, the Beidou satellite signal is corrected to obtain a high-precision Beidou timing signal, and the corrected timing signal that meets the high-precision timing requirements is output.

[0097] It is understandable that through ionospheric delay compensation, the timing accuracy is improved from the microsecond level of traditional methods to the sub-nanosecond level, meeting the requirements of high-precision applications such as power system synchronization and financial transaction timestamps. By adopting a discretized calculation method, it can adapt to ionospheric changes under different geographical locations and atmospheric conditions, improving the stability of the system in complex environments. By dividing the ionosphere into discrete height layers for calculation, the calculation process of delay compensation is simplified, the consumption of hardware resources is reduced, and it is suitable for running on resource-constrained edge devices. Combining the anti-jamming ability and high-precision timing characteristics of the Beidou system, the system can still maintain high-precision timing in areas with complex electromagnetic environments and frequent ionospheric disturbances, and the reliability is significantly improved. By updating the ionospheric delay compensation amount in real time, the timing error caused by ionospheric changes is reduced, the dependence on redundant devices is decreased, and the system resource utilization is optimized.

[0098] In summary, in this embodiment, by parsing Beidou satellite signals and real-time ionospheric data and combining with the vertical ionospheric delay field model, high-precision timing signal output is achieved, significantly improving the timing accuracy and system reliability, and it is applicable to various high-precision timing application scenarios.

[0099] In a feasible implementation manner, before the step of dividing the ionospheric height range into multiple discrete height layers and inputting the ionospheric electron density profile, the Beidou satellite elevation angle, the preset receiver geographical coordinates, and the earth radius into the preset receiver vertical ionospheric delay field model to discretely calculate the delay compensation amount corresponding to each height layer, it includes:

[0100] Obtain historical ionospheric data, the corresponding historical satellite elevation angle, and the corresponding timing error data, and construct a training dataset;

[0101] Input the training dataset into the timing feature extraction network to be trained, and based on the non-linear mapping relationship between ionospheric spatio-temporal changes and timing errors, extract key timing features;

[0102] According to the key timing features, determine the correction coefficient through the network weights obtained by training;

[0103] Based on the correction coefficient, adaptively calibrate the receiver vertical ionospheric delay field model.

[0104] It should be noted that the historical ionospheric data refers to the ionospheric characteristic data recorded over a past period of time, including information such as ionospheric electron density, total electron content, and ionospheric height distribution. These data usually come from satellite observations, ground monitoring stations, or other atmospheric sounding means. The historical satellite elevation angle refers to the elevation angle data of the satellite signal relative to the receiver over a past period of time. These data record the elevation angle changes of the satellite at different times and positions, reflecting the geometric characteristics of the signal propagation path. The timing error data refers to the deviation data between the satellite timing signal and the true time in practical applications. These errors are caused by various factors such as ionospheric delay, tropospheric delay, satellite clock error, and receiver noise. The timing feature extraction network is a neural network architecture for processing time series data, capable of extracting time-related feature information from historical data. The key timing features refer to the core features extracted from historical data that can reflect the relationship between ionospheric spatio-temporal changes and timing errors. These features can include statistical features of the time series (such as mean, variance), spectral features, rate of change, etc. The correction coefficient refers to the parameter calculated based on the extracted key timing features and network weights for calibrating the model. It reflects the actual influence degree of ionospheric spatio-temporal changes on timing errors and is used to adjust the accuracy of the ionospheric delay model.

[0105] Exemplarily, in a satellite timing system, ionospheric delay is one of the main factors affecting timing accuracy. Traditional ionospheric delay models are usually based on empirical formulas and are difficult to adapt to complex ionospheric spatio-temporal changes, especially in regions with intense ionospheric activity. To improve timing accuracy, in this embodiment, historical data is acquired and machine learning methods are used to dynamically calibrate the ionospheric delay model, thereby achieving high-precision timing signal output.

[0106] It can be understood that historical ionospheric TEC data, satellite elevation angle data are obtained from a Beidou receiver, and timing error data is obtained by comparing with a high-precision time reference (such as an atomic clock).

[0107] These data are organized into a time series format to construct a training dataset. The dataset includes the following:

[0108] Input features: ionospheric TEC value, satellite elevation angle, receiver geographical location, timestamp.

[0109] Output label: timing error.

[0110] The training dataset is input into an LSTM neural network for training. The LSTM network can capture long-term dependencies in time series data and is suitable for processing complex non-linear relationships between ionospheric spatio-temporal changes and timing errors.

[0111] During the training process, the network learns the mapping relationship between the ionospheric TEC changes, satellite elevation angle changes, and timing errors, and extracts key timing features, such as the TEC change rate, error volatility, etc. According to the key timing features extracted by the LSTM network and the network weights obtained through training, the correction coefficient is calculated. The correction coefficient reflects the adjustment amplitude of the ionospheric delay model under different conditions. The calculated correction coefficient is applied to the vertical ionospheric delay field model of the receiver to dynamically adjust the model parameters. The calibrated model can more accurately reflect the current ionospheric state, thereby improving the accuracy of the timing signal.

[0112] It can be understood that in this embodiment, by obtaining historical data and using machine learning methods to dynamically calibrate the ionospheric delay model, the timing accuracy and system reliability are significantly improved, which is applicable to various high-precision timing application scenarios.

[0113] In a feasible implementation manner, before the steps of extracting the characteristic information of the real-time operation parameters of the power equipment, combining the federated learning mechanism to obtain the global model knowledge of the preset edge nodes, and analyzing and judging the power equipment state in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the equipment health degree, the following steps are included:

[0114] Obtain the historical state data of the power equipment and the corresponding fault records;

[0115] Input the historical state data of the power equipment into the neural network model to be trained for equipment state analysis and judgment to obtain the equipment health degree prediction information. Among them, during the equipment state analysis and judgment, the high-precision floating-point weights are converted into low-precision fixed-point numbers through quantization-aware training;

[0116] According to the activation values and gradients during the equipment state analysis and judgment process, calculate the contribution degree of each channel of the neural network model, and prune the channels with the contribution degree lower than the preset warning threshold;

[0117] Compare the equipment health degree prediction information with the fault records to determine the prediction difference value;

[0118] If the prediction difference value does not meet the preset prediction allowable error range, return to the step of inputting the historical state data of the power equipment into the neural network model to be trained for equipment state analysis and judgment. If the prediction difference value meets the preset prediction allowable error range, output the trained lightweight neural network model.

[0119] It should be noted that the historical state data of the power equipment refers to various data generated during the operation of the power equipment, including but not limited to operation parameters such as current, voltage, temperature, vibration, partial discharge intensity, as well as information such as equipment maintenance records and operation duration. These data reflect the operation state of the equipment at different time points and are the basis for equipment health analysis. Quantization-aware training is a neural network training technique that converts high-precision floating-point weights into low-precision fixed-point numbers during the training phase, while adjusting the network structure and parameters to reduce the storage space and computational complexity of the model, while trying to maintain the accuracy of the model. Channel contribution refers to the degree of contribution of each channel (or feature map) in the neural network to the model output. By analyzing the activation values and gradients, the importance of each channel can be quantified. Channels with lower contribution have less impact on the model output and can be pruned to optimize the model structure. Pruning is a model optimization technique that reduces the number of model parameters and computational complexity by removing channels or weights with lower contribution in the neural network, while trying to maintain the accuracy of the model. Pruning can be divided into structured pruning (removing entire channels) and unstructured pruning (removing individual weights). The prediction difference value refers to the difference between the output of the neural network model (equipment health prediction information) and the true value (fault record). By calculating the prediction difference value, the accuracy and reliability of the model can be evaluated. The prediction allowable error range refers to a pre-set error threshold range used to determine whether the prediction result of the model meets the requirements of practical applications. If the prediction difference value is within the allowable error range, the prediction of the model is considered reliable; otherwise, the model needs to be further optimized. A lightweight neural network model refers to a neural network model optimized by techniques such as quantization-aware training and channel pruning, which can significantly reduce the number of model parameters and computational complexity while maintaining a high accuracy, and is suitable for running in resource-constrained edge computing environments.

[0120] Exemplarily, the health status monitoring of power equipment is crucial for ensuring the stable operation of the power system. Traditional methods rely on manual inspections and empirical judgments, which are inefficient and difficult to monitor in real time. In this embodiment, by obtaining the historical state data and fault records of the power equipment, using a neural network model for equipment state analysis and health prediction, and optimizing the model through quantization-aware training and channel pruning techniques, a lightweight neural network model is finally obtained to achieve efficient and accurate health monitoring of power equipment.

[0121] It can be understood that the historical state data of the power equipment is obtained from the sensor network, including parameters such as current, voltage, temperature, and vibration. The historical state data is associated with the corresponding fault records to construct a training dataset. The historical state data is input into the neural network model for equipment state analysis and health prediction.

[0122] During the training process, the quantization-aware training technique is adopted to gradually convert high-precision floating-point weights into low-precision fixed-point numbers, reducing the storage space and computational complexity of the model. During the model training process, the activation values and gradient information of each channel are recorded. The contribution degree of each channel is calculated based on the activation values and gradients, and the channels with contribution degrees lower than the preset warning threshold are removed to optimize the model structure. The predicted device health information is compared with the fault records, and the prediction difference value is calculated. If the prediction difference value does not meet the preset allowable prediction error range, retraining is returned to continue optimizing the model.

[0123] If the prediction difference value meets the preset error range, the lightweight neural network model with training completed is output.

[0124] It can be understood that by analyzing the power equipment status and predicting the health degree through the neural network model, the monitoring accuracy is significantly improved, potential faults can be detected in advance, and the equipment downtime is reduced. By adopting the quantization-aware training and channel pruning techniques, the number of model parameters is reduced, the inference speed is improved, and the computational power consumption is reduced, which is suitable for running in resource-constrained edge computing environments. Through training with historical data and iterative optimization, the model can adapt to different types of power equipment and operating environments and has good generalization ability.

[0125] In summary, in this embodiment, by obtaining the historical status data and fault records of power equipment and optimizing the neural network model using the quantization-aware training and channel pruning techniques, efficient and accurate monitoring of the health degree of power equipment is achieved, significantly improving the operation and maintenance efficiency and reliability of the power system.

[0126] In a feasible implementation manner, the steps of extracting the feature information of the real-time operation parameters of the power equipment, obtaining the global model knowledge of the preset edge nodes in combination with the federated learning mechanism, and analyzing and judging the power equipment status in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the equipment health degree include:

[0127] Extract the feature information of the real-time operation parameters of the power equipment to construct a real-time feature vector;

[0128] Encrypt and upload the parameters of the local lightweight neural network model to the aggregation server to obtain the global model parameters returned by the aggregation server;

[0129] Input the real-time feature vector into the lightweight neural network model using the global model parameters to analyze and judge the power equipment status in real time and determine the real-time monitoring information of the equipment health degree.

[0130] It should be noted that the real-time feature vector refers to a vector composed of feature information extracted from the real-time operation parameters of power equipment, which is used to characterize the state of the equipment at the current moment. These feature information can include statistical values, change rates, or spectral features of parameters such as current, voltage, temperature, vibration, and partial discharge intensity. The aggregation server refers to a central server in the network that is used to collect and process data from multiple edge nodes. In federated learning, the aggregation server is responsible for receiving the model parameters uploaded by each edge node, updating the global model parameters through a specific algorithm (such as weighted average), and broadcasting the updated parameters back to each edge node. The global model parameters refer to the neural network model parameters updated through the federated learning mechanism, which integrates the local model knowledge of multiple edge nodes and can better adapt to the characteristics of different devices and environments. The real-time monitoring information of the device health refers to the information reflecting the current health state of the power equipment obtained through model analysis and judgment. These information can include health scores, failure probabilities, remaining service life predictions, etc., which are used to help operation and maintenance personnel understand the device state in a timely manner and take corresponding measures.

[0131] Exemplarily, in the power system, real-time monitoring of the health state of power equipment is crucial for preventing faults and ensuring the safe operation of the power grid. However, traditional centralized monitoring methods have problems such as high data transmission delay and large consumption of computing resources, and it is difficult to adapt to large-scale distributed monitoring scenarios. In this embodiment, by extracting the real-time operation parameter feature information of power equipment and combining the federated learning mechanism and lightweight neural network model, efficient and accurate real-time monitoring of the health of power equipment is achieved, while protecting data privacy and reducing the consumption of computing resources.

[0132] It can be understood that the sensor network collects the operation parameters of power equipment in real time, including current, voltage, temperature, vibration, and partial discharge signals.

[0133] The feature extraction module preprocesses the collected data, extracts key feature information, and forms a real-time feature vector. Each edge computing node uses the locally collected data to train a lightweight neural network model, extracts the model parameters, and encrypts and uploads them to the aggregation server.

[0134] The aggregation server receives the model parameters from multiple edge nodes, updates the global model parameters through a federated learning algorithm (such as FedAvg), and broadcasts the updated parameters back to each edge node. The edge node inputs the real-time feature vector into the lightweight neural network model using the global model parameters for real-time analysis and judgment.

[0135] The model outputs the real-time monitoring information of the device health. If the health score is lower than the preset threshold or the failure probability exceeds the warning value, the system will trigger an alarm and transmit the key information to the operation and maintenance center through Beidou short message communication or 4G / 5G network.

[0136] In this embodiment, through the lightweight neural network model and the federated learning mechanism, the system can analyze the status of power equipment in real time at the edge node, significantly improving the monitoring efficiency and response speed. The real-time output of the health score and the failure probability provides accurate decision-making support for the operation and maintenance personnel.

[0137] In summary, in this embodiment, by extracting the real-time operation parameter characteristic information of power equipment, combining the federated learning mechanism and the lightweight neural network model, the efficient and accurate real-time monitoring of the health of power equipment is realized, significantly improving the operation and maintenance efficiency and reliability of the power system, while protecting data privacy and reducing the consumption of computing resources.

[0138] In a feasible implementation manner, after the step of obtaining the real-time monitoring information of the equipment health, the following steps are included:

[0139] Extract the key alarm data in the real-time monitoring information and compress it into a short message data packet;

[0140] Send the short message data packet to the preset operation and maintenance warning device in a priority preemption mode through the preset Beidou channel;

[0141] If the sending fails, automatically re-transmit the short message data packet within the preset time interval based on the exponential backoff algorithm.

[0142] It should be noted that the key alarm data refers to the data extracted from the real-time monitoring information related to equipment failures, abnormal states or other emergencies. These data usually have high priority and need to be transmitted in time to notify the operation and maintenance personnel to take measures. The short message data packet refers to the data format in which the key alarm data is compressed and encapsulated to be suitable for short-distance and low-bandwidth transmission. In the Beidou system, the short message communication is a function that supports text message transmission and is usually used in emergency situations or scenarios with small data volumes. The preset Beidou channel refers to the Beidou communication channel pre-configured for specific applications (such as power equipment monitoring). The Beidou system supports multiple communication modes, including short message communication, satellite communication, etc. The preset channel is usually optimized according to the requirements of the application scenario to ensure the reliability and priority of data transmission. The priority preemption mode refers to the mode of allocating transmission priorities according to the importance and urgency of data during the communication process. In case of an emergency, the key alarm data can preempt the channel resources and be transmitted preferentially to ensure timely delivery. The exponential backoff algorithm is an algorithm that delays and retries according to the exponential law after the communication transmission fails. By increasing the delay time for each retry, this algorithm avoids channel congestion caused by frequent retries, thereby improving the success rate of data transmission. The preset time interval refers to the time range set for each retry in the exponential backoff algorithm. This interval can be adjusted according to the requirements of the application scenario to balance the retry frequency and the transmission success rate.

[0143] Exemplarily, in the operation and maintenance of power systems, timely transmission of critical alarm information is crucial for quickly responding to equipment failures. However, traditional communication methods may cause delays or failures in alarm information transmission due to network congestion or signal interruption. In this embodiment, by extracting critical alarm data from real-time monitoring information and using the priority preemption mode and exponential backoff algorithm of Beidou short message communication, it is ensured that alarm information can be transmitted to operation and maintenance warning devices efficiently and reliably.

[0144] It can be understood that the monitoring device collects the operation status data of power equipment in real time and transmits it to the data processing unit. The data processing unit analyzes the equipment status through a preset health model, extracts critical alarm data, compresses and encapsulates the alarm data into a short message data packet. The data processing unit sends the short message data packet to the Beidou communication module. The Beidou communication module preferentially sends the alarm data packet to the operation and maintenance warning device according to the preset priority preemption mode. For example, if there is other non-alarm data transmission at the same moment, the alarm data packet will preferentially preempt the channel resources. If the operation and maintenance warning device does not receive the alarm data packet within the preset time (for example, due to signal interruption or network congestion resulting in transmission failure), the Beidou communication module will start the exponential backoff algorithm.

[0145] According to the exponential backoff algorithm, the first retransmission delay time is 2 seconds, the second retransmission delay time is 4 seconds, the third retransmission delay time is 8 seconds, and so on. The preset time interval is to complete retransmission within 60 seconds.

[0146] After successful retransmission, the operation and maintenance warning device receives and analyzes the alarm data packet, triggering the corresponding alarm prompt.

[0147] It can be understood that through the priority preemption mode, it is ensured that critical alarm data can be preferentially transmitted in a complex network environment, significantly improving the transmission reliability of alarm information.

[0148] The exponential backoff algorithm automatically retransmits in case of transmission failure, further improving the transmission success rate of alarm information and ensuring that operation and maintenance personnel can receive alarm information in a timely manner.

[0149] In summary, in this embodiment, by extracting critical alarm data and using the priority preemption mode and exponential backoff algorithm of Beidou short message communication, efficient and reliable transmission of alarm information is achieved, significantly improving the operation and maintenance efficiency and reliability of power systems.

[0150] Exemplarily, to help understand the implementation process of the power equipment status monitoring method based on Beidou high-precision timing obtained by combining this embodiment with the above-mentioned Embodiment 1, please refer to Figure 3 , Figure 3A brief process schematic diagram of a power equipment status monitoring method based on Beidou high-precision time service is provided. Specifically:

[0151] In this embodiment, Beidou high-precision time service, ionospheric delay compensation, federated learning, lightweight neural network model, and reliable alarm transmission mechanism are comprehensively applied to achieve high-precision monitoring and real-time alarm of power equipment status.

[0152] The Beidou receiver obtains Beidou satellite signals in real time and analyzes the satellite elevation angle and ionospheric TEC data.

[0153] The ionospheric height range is divided into multiple discrete height layers. Combining the ionospheric electron density profile, receiver geographical coordinates, and the Earth's radius, it is input into a preset vertical ionospheric delay field model to discretely calculate the delay compensation amount of each height layer.

[0154] The delay compensation amounts of all height layers are accumulated to obtain the real-time ionospheric delay compensation amount, and the Beidou satellite signal is compensated to output a high-precision time service signal.

[0155] The sensor network collects the operation parameters of power equipment in real time, extracts feature information, and constructs a real-time feature vector.

[0156] The parameters of the local lightweight neural network model are encrypted and uploaded to the aggregation server to obtain global model parameters.

[0157] The real-time feature vector is input into the global model to analyze the power equipment status in real time and output real-time monitoring information on the equipment health.

[0158] The key alarm data in the real-time monitoring information is extracted and compressed into a short message data packet.

[0159] Through a preset Beidou channel, the short message data packet is sent to the operation and maintenance warning device in a priority preemption mode.

[0160] If the transmission fails, the data packet is automatically retransmitted within a preset time interval based on the exponential backoff algorithm.

[0161] In this embodiment, through the comprehensive application of Beidou high-precision time service, ionospheric delay compensation, federated learning, lightweight neural network model, and reliable alarm transmission mechanism, high-precision monitoring and real-time alarm of power equipment status are achieved, significantly improving the operation and maintenance efficiency and reliability of the power system.

[0162] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the power equipment status monitoring method based on Beidou high-precision time service in this application. Any more forms of simple transformation based on this technical concept are within the protection scope of this application.

[0163] The present application also provides a power equipment status monitoring device based on Beidou high-precision time service. Please refer to Figure 4 , the power equipment status monitoring device based on Beidou high-precision time service includes:

[0164] An acquisition module 10, configured to acquire Beidou satellite signals and collect real-time ionospheric data;

[0165] A synchronization module 20, configured to perform ionospheric delay compensation based on the Beidou satellite signals and the real-time ionospheric data according to a preset dynamic compensation model, determine a high-precision Beidou time service signal, and achieve precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal;

[0166] A monitoring module 30, configured to extract feature information of real-time operation parameters of the power equipment, obtain global model knowledge of preset edge nodes in combination with a federated learning mechanism, and analyze and judge the status of the power equipment in real time according to a pre-trained lightweight neural network model to obtain real-time monitoring information on the health of the power equipment, where the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training.

[0167] And / or, the synchronization module 20 includes:

[0168] A first parsing module, configured to parse the Beidou satellite signals to determine the elevation angle of Beidou satellites;

[0169] A second parsing module, configured to parse the real-time ionospheric data to determine the ionospheric electron density profile;

[0170] A first discretization module, configured to divide the ionospheric height range into multiple discrete height layers, input the ionospheric electron density profile, the elevation angle of Beidou satellites, a preset receiver geographical coordinate, and the earth radius into a preset receiver vertical ionospheric delay field model, and discretely calculate the delay compensation amount corresponding to each height layer;

[0171] A first accumulation module, configured to accumulate the delay compensation amounts of all height layers to obtain the real-time ionospheric delay compensation amount;

[0172] A first compensation module, configured to perform ionospheric delay compensation on the Beidou satellite signals based on the real-time ionospheric delay compensation amount to determine a high-precision Beidou time service signal.

[0173] And / or, the first discretization module includes:

[0174] A first acquisition module, configured to acquire historical ionospheric data, corresponding historical satellite elevation angles, and corresponding timing error data, and construct a training dataset;

[0175] The first extraction module is used to input the training data set into the time series feature extraction network to be trained, and based on the non-linear mapping relationship between the spatio-temporal variation of the ionosphere and the timing error, extract key time series features;

[0176] The first determination module is used to determine the correction coefficient according to the key time series features and the network weights obtained through training;

[0177] The first calibration module is used to adaptively calibrate the vertical ionospheric delay field model of the receiver based on the correction coefficient.

[0178] And / or, the power equipment status monitoring device based on Beidou high-precision timing includes:

[0179] The second acquisition module is used to acquire the historical status data of the power equipment and the corresponding fault records;

[0180] The first judgment module is used to input the historical status data of the power equipment into the neural network model to be trained for equipment status analysis and judgment, and obtain equipment health prediction information. Among them, during equipment status analysis and judgment, high-precision floating-point weights are converted into low-precision fixed-point numbers through quantization-aware training;

[0181] The first calculation module is used to calculate the contribution degree of each channel of the neural network model according to the activation value and gradient during the equipment status analysis and judgment process, and prune the channels with contribution degrees lower than the preset warning threshold;

[0182] The first comparison module is used to compare the equipment health prediction information with the fault records to determine the prediction difference value;

[0183] The first loop module is used to, if the prediction difference value does not meet the preset prediction allowable error range, return to the step of inputting the historical status data of the power equipment into the neural network model to be trained for equipment status analysis and judgment. If the prediction difference value meets the preset prediction allowable error range, output the trained lightweight neural network model.

[0184] And / or, the monitoring module 30 includes:

[0185] The second extraction module is used to extract the feature information of the real-time operation parameters of the power equipment and construct a real-time feature vector;

[0186] The first upload module is used to encrypt and upload the parameters of the local lightweight neural network model to the aggregation server and obtain the global model parameters returned by the aggregation server;

[0187] A first analysis module, configured to input the real-time feature vector into a lightweight neural network model using the global model parameters, analyze and judge the state of the power equipment in real time, and determine the real-time monitoring information of the equipment health.

[0188] And / or, the monitoring module 30 includes:

[0189] A third extraction module, configured to extract key alarm data from the real-time monitoring information and compress it into a short message data packet;

[0190] A first sending module, configured to send the short message data packet to a preset operation and maintenance warning device in a priority preemption mode through a preset Beidou channel;

[0191] A first transmission module, configured to automatically re-transmit the short message data packet within a preset time interval based on an exponential backoff algorithm if the sending fails.

[0192] The power equipment status monitoring device based on Beidou high-precision time service provided by this application adopts the power equipment status monitoring method based on Beidou high-precision time service in the above embodiment, and can solve the technical problem of difficultly accurately obtaining the real-time operation status information of power equipment. Compared with the prior art, the beneficial effects of the power equipment status monitoring device based on Beidou high-precision time service provided by this application are the same as those of the power equipment status monitoring method based on Beidou high-precision time service provided by the above embodiment, and other technical features in the power equipment status monitoring device based on Beidou high-precision time service are the same as the features disclosed in the method of the above embodiment, and will not be elaborated here.

[0193] This application provides a power equipment status monitoring device based on Beidou high-precision time service. The power equipment status monitoring device based on Beidou high-precision time service includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the power equipment status monitoring method based on Beidou high-precision time service in the first embodiment above.

[0194] Next, refer to Figure 5, which shows a schematic structural diagram of a power equipment status monitoring device suitable for implementing the embodiments of the present application based on Beidou high-precision time service. The power equipment status monitoring device based on Beidou high-precision time service in the embodiments of the present application may include, but is not limited to, mobile terminals such as mobile phones, tablet computers, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown power equipment status monitoring device based on Beidou high-precision time service is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0195] As Figure 5 shown, the power equipment status monitoring device based on Beidou high-precision time service may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which may perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 into the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the power equipment status monitoring device based on Beidou high-precision time service are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the power equipment status monitoring device based on Beidou high-precision time service to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a power equipment status monitoring device with various systems based on Beidou high-precision time service, it should be understood that it is not required to implement or have all the shown systems. More or fewer systems may be alternatively implemented or had.

[0196] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by a processing device 1001, the above-mentioned functions defined in the methods of the embodiments disclosed in the present application are executed.

[0197] The power equipment status monitoring device based on Beidou high-precision time service provided by the present application adopts the power equipment status monitoring method based on Beidou high-precision time service in the above-mentioned embodiments, and can solve the technical problem of difficultly accurately obtaining the real-time operation status information of power equipment. Compared with the prior art, the beneficial effects of the power equipment status monitoring device based on Beidou high-precision time service provided by the present application are the same as those of the power equipment status monitoring method based on Beidou high-precision time service provided by the above-mentioned embodiments, and other technical features in the power equipment status monitoring device based on Beidou high-precision time service are the same as the features disclosed in the method of the previous embodiment, and will not be elaborated here.

[0198] It should be understood that each part disclosed in the present application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0199] As mentioned above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, and all should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0200] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the power equipment status monitoring method based on Beidou high-precision time service in the above-mentioned embodiments.

[0201] The computer-readable storage medium provided by the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0202] The above computer-readable storage medium may be included in the power equipment status monitoring device based on Beidou high-precision time service; or it may exist alone without being assembled into the power equipment status monitoring device based on Beidou high-precision time service.

[0203] The above computer-readable storage medium carries one or more programs. When the one or more programs are executed by the power equipment status monitoring device based on Beidou high-precision time service, the power equipment status monitoring device based on Beidou high-precision time service is enabled to: obtain Beidou satellite signals and collect real-time ionospheric data;

[0204] Based on the Beidou satellite signals and the real-time ionospheric data, perform ionospheric delay compensation according to a preset dynamic compensation model, determine a high-precision Beidou time service signal, and achieve precise synchronization of multi-source data of power equipment based on the high-precision Beidou time service signal;

[0205] Extract the characteristic information of the real-time operation parameters of the power equipment, combine the federated learning mechanism to obtain the global model knowledge of the preset edge nodes, and analyze and judge the power equipment status in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the power equipment health, where the lightweight neural network model is obtained through parameter compression training by channel pruning and quantization-aware training.

[0206] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN: Local Area Network) or a wide area network (WAN: Wide Area Network), or it can be connected to an external computer (for example, by connecting through an Internet service provider via the Internet).

[0207] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of the code, and this module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0208] The modules described in the embodiments of this application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0209] The readable storage medium provided by this application is a computer-readable storage medium. The computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for performing the above-mentioned power equipment status monitoring method based on Beidou high-precision time service, and can solve the technical problem of difficult to accurately obtain the real-time operation status information of power equipment. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by this application are the same as those of the power equipment status monitoring method based on Beidou high-precision time service provided by the above embodiments, and will not be elaborated here.

[0210] The present application also provides a computer program product, including a computer program, which implements the steps of the power equipment status monitoring method based on Beidou high-precision time service as described above when executed by a processor.

[0211] The computer program product provided by the present application can solve the technical problem of difficult to accurately obtain the real-time operation status information of power equipment. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as those of the power equipment status monitoring method based on Beidou high-precision time service provided in the above embodiments, and will not be elaborated here.

[0212] The above are only partial embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structural transformation made under the technical concept of the present application by using the content of the specification and drawings of the present application, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present application.

Claims

1. A method for monitoring the state of power equipment based on Beidou high-precision timing, characterized in that: The method includes: Obtain Beidou satellite signals and collect real-time ionosphere data; Based on the Beidou satellite signal and the real-time ionospheric data, ionospheric delay compensation is performed according to a preset dynamic compensation model, a high-precision Beidou timing signal is determined, and accurate synchronization of multi-source data of power equipment is achieved based on the high-precision Beidou timing signal; The characteristic information of the real-time operating parameters of the power equipment is extracted, and the global model knowledge of the preset edge nodes is obtained in combination with the federated learning mechanism. The state of the power equipment is analyzed and judged in real time according to the pre-trained lightweight neural network model to obtain real-time monitoring information on the health of the power equipment, wherein the lightweight neural network model is obtained by parameter compression training through channel pruning and quantization-aware training.

2. The method according to claim 1, characterized in that The step of performing ionospheric delay compensation based on the Beidou satellite signal and the ionospheric real-time data according to a preset dynamic compensation model to determine a high-precision Beidou timing signal comprises: Analyze the Beidou satellite signal to determine the Beidou satellite elevation angle; Analyzing the real-time ionospheric data to determine the ionospheric electron density profile; The ionospheric height range is divided into a plurality of discrete height layers, the ionospheric electron density profile, the Beidou satellite elevation angle, the preset receiver geographic coordinates and the earth radius are input into a preset receiver vertical ionospheric delay field model, and the delay compensation amount corresponding to each height layer is discretized and calculated; Accumulate the delay compensation values ​​of all altitude layers to obtain the real-time delay compensation value of the ionosphere; Based on the real-time ionospheric delay compensation amount, ionospheric delay compensation is performed on the Beidou satellite signal to determine a high-precision Beidou timing signal.

3. The method according to claim 2, characterized in that The step of dividing the ionospheric height range into a plurality of discrete height layers, inputting the ionospheric electron density profile, the Beidou satellite elevation angle, the preset receiver geographic coordinates and the earth radius into a preset receiver vertical ionospheric delay field model, and discretizing and calculating the delay compensation amount corresponding to each height layer comprises: Obtain historical ionospheric data, corresponding historical satellite elevation angles, and corresponding timing error data to construct a training data set; Inputting the training data set into the time series feature extraction network to be trained for training, and extracting key time series features based on the nonlinear mapping relationship between the spatiotemporal variation of the ionosphere and the timing error; According to the key timing characteristics, a correction coefficient is determined by the network weight obtained through training; Based on the correction coefficient, the vertical ionospheric delay field model of the receiver is adaptively calibrated.

4. The method according to claim 1, characterized in that The step of extracting the characteristic information of the real-time operating parameters of the power equipment, acquiring the global model knowledge of the preset edge node in combination with the federated learning mechanism, and analyzing and judging the state of the power equipment in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the health of the power equipment includes: Obtain historical status data of power equipment and corresponding fault records; The historical status data of the power equipment is input into the neural network model to be trained to analyze and judge the equipment status, and obtain equipment health prediction information, wherein the high-precision floating-point weights are converted into low-precision fixed-point numbers through quantization perception training during the equipment status analysis and judgment; Calculate the contribution of each channel of the neural network model according to the activation value and gradient in the process of analyzing and judging the status of the device, and prune the channels whose contribution is lower than the preset warning threshold; Comparing the equipment health prediction information with the fault record to determine a prediction difference value; If the predicted difference value does not meet the preset prediction allowable error range, then return to the step of inputting the historical status data of the power equipment into the neural network model to be trained for equipment status analysis and judgment; if the predicted difference value meets the preset prediction allowable error range, then output the trained lightweight neural network model.

5. The method according to claim 1, characterized in that The steps of extracting the characteristic information of the real-time operating parameters of the power equipment, acquiring the global model knowledge of the preset edge nodes in combination with the federated learning mechanism, and analyzing and judging the state of the power equipment in real time according to the pre-trained lightweight neural network model to obtain the real-time monitoring information of the health of the power equipment include: Extracting characteristic information of real-time operating parameters of the electric power equipment and constructing a real-time characteristic vector; Encrypt the parameters of the local lightweight neural network model and upload them to the aggregation server, and obtain the global model parameters returned by the aggregation server; The real-time feature vector is input into a lightweight neural network model using the global model parameters to analyze and judge the state of the power equipment in real time and determine the real-time monitoring information of the health of the equipment.

6. The method according to claim 1, characterized in that The step of obtaining real-time monitoring information of the health of the power equipment includes: Extract key alarm data from real-time monitoring information and compress it into short message data packets; Send short message data packets to the preset operation and maintenance warning equipment in priority preemptive mode through the preset Beidou channel; If the transmission fails, the short message data packet is automatically retransmitted within a preset time interval based on an exponential backoff algorithm.

7. A power equipment status monitoring device based on Beidou high-precision timing, characterized in that: The device comprises: Acquisition module, used to acquire Beidou satellite signals and collect real-time ionospheric data; A synchronization module, for performing ionospheric delay compensation based on the Beidou satellite signal and the ionospheric real-time data according to a preset dynamic compensation model, determining a high-precision Beidou timing signal, and realizing accurate synchronization of multi-source data of power equipment according to the high-precision Beidou timing signal; The monitoring module is used to extract the characteristic information of the real-time operating parameters of the power equipment, obtain the global model knowledge of the preset edge nodes in combination with the federated learning mechanism, analyze and judge the status of the power equipment in real time according to the pre-trained lightweight neural network model, and obtain real-time monitoring information on the health of the power equipment, wherein the lightweight neural network model is obtained by parameter compression training through channel pruning and quantization-aware training.

8. A power equipment status monitoring device based on Beidou high-precision timing, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for monitoring the state of electric power equipment based on Beidou high-precision timing as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the power equipment status monitoring method based on Beidou high-precision timing are implemented as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the method for monitoring the state of electric power equipment based on Beidou high-precision timing are implemented as described in any one of claims 1 to 6.

Images