Beidou positioning device operation state intelligent diagnosis method considering power tower monitoring

Abstract

The embodiment of the application provides a Beidou positioning device operation state intelligent diagnosis method considering power tower monitoring, and belongs to the technical field of power tower monitoring. The method comprises the following steps: obtaining operation state sample data of a Beidou positioning device of a power tower, wherein the operation state sample data comprises Beidou positioning quality data, combined positioning quality data and data link state data; the method constructs a Beidou positioning device operation state diagnosis model of the power tower, corrects the operation state diagnosis model according to the operation state sample data, inputs real-time data of the Beidou positioning device of the power tower into the Beidou positioning device operation state diagnosis model of the power tower for real-time analysis, so as to realize diagnosis on the operation state of the positioning device of the power tower, can accurately judge whether the current Beidou positioning device is abnormal, and further effectively improves the positioning precision and reliability of the Beidou positioning device.

Description

Technical Field

[0001] This invention relates to the field of power pole monitoring technology, and more specifically to an intelligent diagnostic method for the operating status of a Beidou positioning device that includes power pole monitoring. Background Technology

[0002] Transmission towers are critical infrastructure for power transmission, accounting for a significant proportion of the total power grid investment. Their safe and stable operation is essential for reliable and secure power supply. Transmission towers are widely constructed, traversing various terrains such as mountains, plains, lakeshores, and roadsides. Furthermore, the towers bear the weight of the transmission lines and are constantly exposed to wind and sun, making their steel structures susceptible to corrosion and aging. In the event of natural disasters such as icing, strong winds, or earthquakes, they may sway, shift, or overturn, leading to power outages.

[0003] Given the importance of transmission towers, power grid companies need to invest significant manpower and resources annually in their routine inspections and maintenance. In the event of a tower malfunction, large emergency repair teams must be dispatched for rapid repairs. With the development of IoT, BeiDou, and AI technologies, positioning devices are installed on transmission / power towers using the BeiDou Continuously Operating Reference System (CORS) to provide reference positioning services. These CORS platforms are connected to the power grid security access platform via a 4G communication link. However, during operation, factors affecting positioning accuracy exist, making it impossible to determine the accuracy of the current positioning information, i.e., whether the power tower positioning device is operating reliably. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent diagnostic method for the operating status of a BeiDou positioning device that includes power pole monitoring. This method has the function of diagnosing the operating status of the power pole positioning device.

[0005] To achieve the above objectives, one embodiment of the present invention provides an intelligent diagnostic method for the operational status of a BeiDou positioning device that considers power pole tower monitoring, comprising:

[0006] Obtain operational status sample data of the BeiDou positioning device on power poles, wherein the operational status sample data includes BeiDou positioning quality data, combined positioning quality data, and data link status data;

[0007] Construct a diagnostic model for the operational status of BeiDou positioning devices on power poles;

[0008] Preprocessing is performed on the BeiDou positioning quality data, the combined positioning quality data, and the data link status data;

[0009] The preprocessed data is input into the operation status diagnosis model of the Beidou positioning device for power poles to obtain the optimal solution of the parameters of the operation status diagnosis model of the Beidou positioning device for power poles, so as to train the operation status diagnosis model of the Beidou positioning device for power poles.

[0010] Acquire real-time BeiDou positioning quality data, combined positioning quality data, and data link status data of the BeiDou positioning device for the power pole tower;

[0011] The fault diagnosis and monitoring of the BeiDou positioning device for power poles is performed based on the real-time BeiDou positioning quality data, combined positioning quality data, and data link status data of the BeiDou positioning device for power poles.

[0012] Optionally, preprocessing the BeiDou positioning quality data includes:

[0013] Obtain the number of observable satellites from the BeiDou positioning quality data;

[0014] The number of observable satellites is preprocessed according to formula (1).

[0015]

[0016] Wherein, sigmoid(d) is the preprocessed value of the number of observable satellites, and d is the number of observable satellites;

[0017] Obtain the strength of the precision value from the BeiDou positioning quality data;

[0018] The strength of the precision value is preprocessed according to formula (2).

[0019]

[0020] Wherein, sigmoid(dop) is the value of the precision strength after preprocessing, and dop is the numerical value of the precision strength.

[0021] Obtain the carrier-to-noise ratio from the BeiDou positioning quality data;

[0022] The carrier-to-noise ratio is preprocessed according to formula (3).

[0023]

[0024] Among them, sigmoid(SINR) d SINR is the preprocessed value of the carrier-to-noise ratio. d The carrier-to-noise ratio is denoted as .

[0025] Optionally, preprocessing the combined positioning quality data includes:

[0026] Obtain the tower attitude measurement vector in inertial navigation positioning and BeiDou satellite positioning;

[0027] The error quality value of the combined positioning information of Beidou satellite positioning and inertial navigation positioning is calculated according to formula (4).

[0028]

[0029] Where S is the error quality value of the combined positioning information of BeiDou satellite positioning and inertial navigation positioning, and Q is... INS For measuring the noise error cross-correlation matrix of an inertial navigation positioning sensor, R BD For the double-difference phase observation noise of the differential positioning algorithm between the BeiDou reference station and the positioning device, p INS p is the tower attitude measurement vector obtained for inertial navigation and positioning. BD Tower attitude measurement obtained for BeiDou satellite positioning;

[0030] The error quality value is preprocessed according to formula (5).

[0031]

[0032] Wherein, sigmoid(S) is the preprocessed value of the error quality value, and A is the value of S when CDF = 0.8 obtained from the Monte Carlo simulation of S.

[0033] Optionally, preprocessing the data link status data includes:

[0034] The data link status data is preprocessed according to formula (6).

[0035]

[0036] Among them, TCP alive The value after preprocessing for the data link status.

[0037] Optionally, obtaining the optimal solution for the operational status diagnostic model parameters of the BeiDou positioning device for power poles includes:

[0038] The preprocessed data is input into the operational status diagnostic model of the Beidou positioning device for power poles;

[0039] The hidden layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (7).

[0040]

[0041] Among them, z n w is the output value of the hidden layer of the operational status diagnosis model for the Beidou positioning device on the power pole. nm The weights of the hidden layer, The data is preprocessed, M is the number of input layers, m is an integer number (where m ≤ M), and n is an integer number.

[0042] Optionally, obtaining the optimal solution for the parameters of the power pole Beidou positioning device operation status diagnosis model further includes:

[0043] The output layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (8).

[0044]

[0045] Where, η k The output value of the output layer of the power pole Beidou positioning device operation status diagnosis model is given, where ELU() is the activation function, and... w kn b represents the weights of the output layer. k The output layer is the bias, N is the number of hidden layers, and n≤N, k is an integer number.

[0046] Optionally, obtaining the optimal solution for the parameters of the power pole Beidou positioning device operation status diagnosis model further includes:

[0047] The softmax value of the output value of each output layer is calculated according to formula (9).

[0048]

[0049] Where, φ l η is the softmax value of the output value of the output layer. l The output value of the output layer of the power pole Beidou positioning device operation status diagnosis model is given, where l is an integer number, c is an intermediate variable, and c = max(η). k )+ε, where ε is a very small positive number, K is the number of output layers, and k≤K, K=5.

[0050] Optionally, obtaining the optimal solution for the operational status diagnostic model parameters of the Beidou positioning device for power poles also includes:

[0051] The loss function is calculated according to formula (10).

[0052]

[0053] Where MSE is the value of the loss function, L is the number of softmax layers (where l ≤ L), i is the fault sample index variable, and I is the total number of fault samples. When the input sample is i, the softmax layer is the softmax value of the l-th layer;

[0054] The loss function is minimized using the stochastic gradient descent algorithm to obtain the model parameters of the power pole Beidou positioning device operation status diagnosis model;

[0055] The operational status diagnosis model of the BeiDou positioning device for power poles is corrected based on the model parameters of the model model.

[0056] On the other hand, the present invention also provides a computer-readable storage medium storing instructions for being read by a machine to cause the machine to execute the intelligent diagnostic method for the operating status of the BeiDou positioning device as described above.

[0057] Through the above technical solution, the intelligent diagnostic method for the operation status of Beidou positioning devices considering power pole monitoring provided by the present invention constructs a diagnostic model for the operation status of Beidou positioning devices on power poles, corrects the diagnostic model based on operational status sample data, and then inputs real-time data of the Beidou positioning devices on power poles into the diagnostic model for real-time analysis, so as to realize the diagnosis of the operation status of the positioning devices on power poles. It can accurately determine whether the current Beidou positioning device is abnormal, that is, it can determine whether the quality of the positioning information obtained by the current Beidou positioning device meets the requirements, thereby effectively improving the positioning accuracy and reliability of the Beidou positioning device.

[0058] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description section. Attached Figure Description

[0059] The accompanying drawings are provided to further illustrate embodiments of the present invention and form part of the specification. They are used together with the following detailed description to explain the embodiments of the present invention, but do not constitute a limitation thereof. In the drawings:

[0060] Figure 1 This is a flowchart of an intelligent diagnostic method for the operating status of a Beidou positioning device considering power pole monitoring, according to an embodiment of the present invention.

[0061] Figure 2 This is a flowchart of data preprocessing in a Beidou positioning device operation status intelligent diagnosis method considering power pole monitoring according to an embodiment of the present invention.

[0062] Figure 3 This is a flowchart of model training in a Beidou positioning device operation status intelligent diagnosis method considering power pole monitoring according to an embodiment of the present invention.

[0063] Figure 4 This is an architecture diagram of a model in an intelligent diagnostic method for the operation status of a Beidou positioning device that considers power pole monitoring, according to an embodiment of the present invention. Detailed Implementation

[0064] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0065] Figure 1 This is a flowchart of an intelligent diagnostic method for the operational status of a BeiDou positioning device considering power pole monitoring, according to one embodiment of the present invention. Figure 1 The intelligent diagnostic method for the operational status of the BeiDou positioning device may include:

[0066] In step S10, operational status sample data of the BeiDou positioning device for power poles is acquired. This operational status sample data includes BeiDou positioning quality data, combined positioning quality data, and data link status data. The BeiDou positioning device for power poles integrates a BeiDou positioning module, an inertial navigation positioning module, and a combined positioning filtering algorithm module for both positioning methods. It also includes a remote communication link with the BeiDou positioning platform, enabling the transmission of network differential positioning information between the positioning platform and the BeiDou positioning module. The BeiDou positioning device for power poles obtains precise pole location information through BeiDou network differential positioning or BeiDou + inertial navigation combined positioning. Factors affecting the positioning accuracy of the BeiDou positioning device include BeiDou satellite positioning quality degradation, abnormal data link transmission of network differential positioning information, and combined navigation quality degradation. Specifically, the operational status sample data includes sample data corresponding to power pole faults, i.e., historical fault data.

[0067] In step S11, a diagnostic model for the operating status of the Beidou positioning device on the power pole is constructed.

[0068] In step S12, the BeiDou positioning quality data, combined positioning quality data, and data link status data are preprocessed. Since the different data types have different dimensions and value ranges, preprocessing is necessary.

[0069] In step S13, the preprocessed data is input into the power pole BeiDou positioning device operation status diagnosis model to obtain the optimal solution of the model parameters for training the model. Specifically, after obtaining the optimal solution of the power pole BeiDou positioning device operation status diagnosis model parameters, the constructed model is modified to complete the training of the model.

[0070] In step S14, real-time BeiDou positioning quality data, combined positioning quality data, and data link status data of the BeiDou positioning device on the power pole are acquired.

[0071] In step S15, fault diagnosis and monitoring of the BeiDou positioning device on the power pole is performed based on the real-time BeiDou positioning quality data, combined positioning quality data, and data link status data. Specifically, the real-time data of the BeiDou positioning device on the power pole is compared and analyzed with the operational status sample data to obtain the current operational status of the BeiDou positioning device, thus achieving fault diagnosis of the BeiDou positioning device on the power pole.

[0072] In steps S10 to S15, operational status sample data of the BeiDou positioning device on the power pole is first acquired. This preprocessed operational status sample data is then input into the operational status diagnostic model of the BeiDou positioning device on the power pole to correct the model. Real-time positioning data of the BeiDou positioning device on the power pole is then acquired and input into the corrected operational status diagnostic model of the BeiDou positioning device on the power pole. This real-time positioning data is compared with the operational status sample data to diagnose the operational status of the BeiDou positioning device on the power pole, thereby achieving real-time monitoring and diagnosis of the BeiDou positioning device on the power pole.

[0073] Traditional power pole positioning devices are susceptible to factors affecting positioning accuracy during operation, making it impossible to determine the accuracy of current positioning information, or the reliability of the device. In this embodiment of the invention, a diagnostic model for the operating status of the power pole BeiDou positioning device is trained using sample data of the device's operating status. This model is then used to diagnose the real-time data of the power pole BeiDou positioning device. This method accurately determines whether the BeiDou positioning device is malfunctioning, and whether the quality of the positioning information acquired by the device meets requirements. This provides a basis for selecting positioning information and troubleshooting, thereby effectively improving the positioning accuracy and reliability of the BeiDou positioning device.

[0074] In this embodiment of the invention, when training the operational status diagnostic model of the BeiDou positioning device for power poles using operational status sample data or diagnosing the real-time data of the power pole positioning device, data preprocessing is required. Specific preprocessing steps can be as follows: Figure 2 As shown. Specifically, in Figure 2 The intelligent diagnostic method for the operational status of the BeiDou positioning device may also include:

[0075] In step S20, the number of observable satellites in the BeiDou positioning quality data is obtained. The total number of observable satellites is D, i.e., d ≤ D. The more observable satellites that can monitor power poles, the higher the positioning accuracy; therefore, the number of observable satellites needs to be used as one of the parameters of positioning quality. Specifically, the BeiDou positioning quality data can be obtained from the BeiDou positioning module.

[0076] In step S21, the number of observable satellites is preprocessed according to formula (1).

[0077]

[0078] Here, sigmoid(d) is the preprocessed value representing the number of observable satellites, where d is the number of observable satellites. Specifically, to obtain positioning information, the receiver must observe at least four satellites. Therefore, when d ≤ 3, the preprocessed value is sufficiently small, and as the number of observable satellites increases, the preprocessed value approaches 1, indicating better positioning performance.

[0079] In step S22, the precision strength of the BeiDou positioning quality data is obtained. The specific classification of precision strength can include position precision factor (PDOP), horizontal precision factor (HDOP), and vertical precision factor (VDOP). Specifically, the DOP values ​​range from 0.5 to 99.9.

[0080] In step S23, the precision value strength is preprocessed according to formula (2).

[0081]

[0082] Wherein, sigmoid(dop) is the value after preprocessing for the precision strength factor, and dop is the numerical value of the precision strength factor. Specifically, the smaller the precision factor value, the higher the positioning accuracy.

[0083] In step S24, the carrier-to-noise ratio (SINR) of the BeiDou positioning quality data is obtained. This includes the SINR of observable satellites. d The range is 0 to 99 dB / Hz. The higher the carrier-to-noise ratio, the better the satellite signal quality, which is more conducive to high-precision positioning.

[0084] In step S25, the carrier-to-noise ratio is preprocessed according to formula (3).

[0085]

[0086] Among them, sigmoid(SINR) a SINR is the preprocessed value of the carrier-to-noise ratio. d This represents the carrier-to-noise ratio.

[0087] In step S26, the tower attitude measurement vectors for power poles in inertial navigation positioning and BeiDou satellite positioning are obtained. These tower attitude measurement vectors can be obtained from the combined positioning filtering algorithm module. Specifically, inertial navigation updates position information by measuring three-dimensional acceleration and velocity, while BeiDou uses carrier phase differential calculations between BeiDou satellites and a ground-based system to solve for position information.

[0088] In step S27, the error quality value of the combined positioning information of BeiDou satellite positioning and inertial navigation positioning is calculated according to formula (4).

[0089]

[0090] Where S is the error quality value of the combined positioning information of BeiDou satellite positioning and inertial navigation positioning, and Q is... INS The noise error cross-correlation matrix for inertial navigation and positioning sensors can be obtained from the sensor hardware manual. R BD The double-difference phase observation noise of the differential positioning algorithm between the BeiDou reference station and the positioning device can be obtained through real-time calculation results from the BeiDou positioning platform and the hardware manual of the BeiDou positioning module. INS p is the tower attitude measurement vector obtained for inertial navigation and positioning. BD Tower attitude measurements obtained for BeiDou satellite positioning.

[0091] In step S28, the error quality value is preprocessed according to formula (5).

[0092]

[0093] Where sigmoid(S) is the preprocessed value of the error quality value, and A is the value of S when CDF = 0.8 obtained from the Monte Carlo simulation of S.

[0094] In step S29, the data link status data is preprocessed according to formula (6).

[0095]

[0096] Among them, TCP aliveThis is a preprocessed value for the data link status. Specifically, when the positioning device uses BeiDou for positioning, it needs to interact with the CORS platform and establish a TCP connection. If the TCP connection fails, BeiDou positioning becomes unavailable. This variable is used to monitor the availability of the BeiDou positioning data link. Specifically, anomaly detection of the TCP connection is achieved by using heartbeat message transmission and reception at the application layer of the positioning device's core processing unit.

[0097] In steps S20 to S29, since the BeiDou positioning quality data, combined positioning quality data, and data link data acquired by the BeiDou positioning device have different dimensions and value ranges, in order to facilitate the unified processing of subsequent data, the BeiDou positioning quality data, combined positioning quality data, and data link data acquired by the BeiDou positioning device are normalized to obtain values ​​that can be used to train the diagnostic model for the operating status of the BeiDou positioning device on the power pole.

[0098] In this embodiment of the invention, after normalizing the BeiDou positioning quality data, combined positioning quality data, and data link data, it is necessary to input them into the operational status diagnostic model of the BeiDou positioning device on the power pole for training. The specific training steps can be as follows: Figure 3 As shown. Specifically, in Figure 3 The intelligent diagnostic method for the operational status of the BeiDou positioning device may also include:

[0099] In step S30, the preprocessed data is input into the operational status diagnostic model of the Beidou positioning device for power poles. The number of input layers is M, meaning there are M types of input parameters.

[0100] In step S31, the hidden layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (7).

[0101]

[0102] Among them, z n w is the output value of the nth hidden layer of the operational status diagnosis model for the BeiDou positioning device on power poles. nm The weights of the hidden layer, The preprocessed data is shown in the figure. M is the number of input layers, m is an integer number, and m≤M, n is an integer number.

[0103] In step S32, the output layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (8).

[0104]

[0105] Where, η kLet ELU() be the output value of the k-th output layer of the power pole Beidou positioning device operation status diagnosis model, and ELU() be the activation function. w kn b represents the weights of the output layer. k The output layer is biased as shown in the figure. N is the number of hidden layers, and n≤N, and k is an integer number.

[0106] In step S33, the softmax value of the output value of each output layer is calculated according to formula (9).

[0107]

[0108] Where, φ l Here, c represents the softmax value of the output of the l-th output layer, and c is an intermediate variable, where c = max(η). k η = η + ε, where ε is a very small positive number, as shown in the figure, and K is the number of output layers, k ≤ K, K = 5. l The output value of the output layer of the Beidou positioning device operation status diagnosis model for power poles is given by η, where l is an integer number and l ≤ L, as shown in the figure. L is the number of the Softmax layer, and L = K. Therefore, η l =η k Specifically, L = K = 5, which represents the number of fault types. Specifically, the fault types can include five categories: too few observable satellites, low precision of satellite positioning results, poor quality of observable satellite links, poor accuracy of combined positioning, and RTK link interruption. Specifically, formula (9) can be derived from formula (11).

[0109]

[0110] In step S34, the loss function is calculated according to formula (10).

[0111]

[0112] Where MSE is the value of the loss function, L is the number of softmax layers (l≤L), i is the fault sample index variable, I is the total number of fault samples (i.e., the total number of historical data), and l is an integer number. When the input sample is i, the softmax layer is the softmax value of the l-th layer.

[0113] In step S35, the loss function is minimized according to the stochastic gradient descent algorithm to obtain the model parameters of the power pole Beidou positioning device operation status diagnosis model.

[0114] In step S36, the operational status diagnosis model of the Beidou positioning device for power poles is corrected according to the model parameters of the model model.

[0115] In steps S30 to S36, the preprocessed data is input along the input layer, passes through the hidden layer and the output layer in sequence, and finally the loss function is minimized to obtain the model parameters used to correct the operation status diagnosis model of the Beidou positioning device for power poles. Thus, a complete operation status diagnosis model for the Beidou positioning device for power poles can be obtained. Combined with the real-time data collected by the Beidou positioning device, real-time monitoring and diagnosis of the Beidou positioning device can be realized, which is more intelligent and reliable, and has high diagnostic efficiency and reliability.

[0116] Through the above technical solution, the intelligent diagnostic method for the operation status of Beidou positioning devices considering power pole monitoring provided by the present invention constructs a diagnostic model for the operation status of Beidou positioning devices on power poles, corrects the diagnostic model based on operational status sample data, and then inputs real-time data of the Beidou positioning devices on power poles into the diagnostic model for real-time analysis, so as to realize the diagnosis of the operation status of the positioning devices on power poles. It can accurately determine whether the current Beidou positioning device is abnormal, that is, it can determine whether the quality of the positioning information obtained by the current Beidou positioning device meets the requirements, thereby effectively improving the positioning accuracy and reliability of the Beidou positioning device.

[0117] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0122] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0123] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0124] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0125] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for intelligent diagnosis of the operational status of a Beidou positioning device considering power pole monitoring, characterized in that, include: Obtain operational status sample data of the BeiDou positioning device on power poles, wherein the operational status sample data includes BeiDou positioning quality data, combined positioning quality data, and data link status data; Construct a diagnostic model for the operational status of BeiDou positioning devices on power poles; Preprocessing is performed on the BeiDou positioning quality data, the combined positioning quality data, and the data link status data; The preprocessed data is input into the operation status diagnosis model of the Beidou positioning device for power poles to obtain the optimal solution of the parameters of the operation status diagnosis model of the Beidou positioning device for power poles, so as to train the operation status diagnosis model of the Beidou positioning device for power poles. Acquire real-time BeiDou positioning quality data, combined positioning quality data, and data link status data of the BeiDou positioning device for the power pole tower; Based on the real-time BeiDou positioning quality data, combined positioning quality data and data link status data of the BeiDou positioning device for power poles, fault diagnosis and monitoring are performed on the BeiDou positioning device for power poles. Obtaining the optimal solution for the operational status diagnostic model parameters of the BeiDou positioning device for power poles includes: The preprocessed data is input into the operational status diagnostic model of the Beidou positioning device for power poles; The hidden layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (7). ，（7） in, This refers to the output value of the hidden layer of the operational status diagnosis model for the BeiDou positioning device on the power pole. The weights of the hidden layer, For the preprocessed data, The number of layers is the input layer. The number is an integer, and , Numbered by integer; The output layer of the power pole Beidou positioning device operation status diagnosis model is calculated according to formula (8). ，（8） in, This refers to the output value of the output layer of the operational status diagnosis model for the BeiDou positioning device on the power pole. It is an activation function, and , The weights of the output layer, The bias of the output layer. Let be the number of hidden layers, and , The number is an integer.

2. The intelligent diagnostic method for the operating status of a Beidou positioning device according to claim 1, characterized in that, Preprocessing of the BeiDou positioning quality data includes: Obtain the number of observable satellites from the BeiDou positioning quality data; The number of observable satellites is preprocessed according to formula (1). ，（1） in, The number of observable satellites is the preprocessed value. The number of observable satellites; Obtain the strength of the precision value from the BeiDou positioning quality data; The strength of the precision value is preprocessed according to formula (2). ，（2） in, This is the value after preprocessing the precision strength value. The precision value represents the strength or weakness of the value. Obtain the carrier-to-noise ratio from the BeiDou positioning quality data; The carrier-to-noise ratio is preprocessed according to formula (3). ，（3） in, The value after preprocessing the carrier-to-noise ratio. The carrier-to-noise ratio is denoted as .

3. The intelligent diagnostic method for the operating status of a Beidou positioning device according to claim 2, characterized in that, Preprocessing the combined positioning quality data includes: Obtain the tower attitude measurement vector in inertial navigation positioning and BeiDou satellite positioning; The error quality value of the combined positioning information of Beidou satellite positioning and inertial navigation positioning is calculated according to formula (4). ，（4） in, This refers to the error quality value of the combined positioning information from BeiDou satellite positioning and inertial navigation positioning. To measure the noise error cross-correlation matrix of the inertial navigation positioning sensor, The double-difference phase observation noise in the differential positioning algorithm between the BeiDou reference station and the positioning device. The tower attitude measurement vector obtained for inertial navigation positioning. Tower attitude measurement obtained for BeiDou satellite positioning; The error quality value is preprocessed according to formula (5). ，（5） in, This is the preprocessed value of the error quality value. To When the CDF obtained from the Monte Carlo simulation is 0.8 The value of .

4. The intelligent diagnostic method for the operating status of a Beidou positioning device according to claim 3, characterized in that, Preprocessing the data link status data includes: The data link status data is preprocessed according to formula (6). ，（6） in, The value after preprocessing for the data link status.

5. The intelligent diagnostic method for the operating status of a Beidou positioning device according to claim 1, characterized in that, Obtaining the optimal solution for the parameters of the power pole Beidou positioning device operation status diagnosis model also includes: The softmax value of the output value of each output layer is calculated according to formula (9). ，（9） in, The softmax value of the output value of the output layer. This refers to the output value of the output layer of the operational status diagnosis model for the BeiDou positioning device on the power pole. Numbered by integer. As an intermediate variable, , It is a very small positive number. The number of output layers, and , .

6. The intelligent diagnostic method for the operating status of a Beidou positioning device according to claim 5, characterized in that, Obtaining the optimal solution for the operational status diagnostic model parameters of the BeiDou positioning device for power poles also includes: The loss function is calculated according to formula (10). ，（10） in, The value of the loss function, Let be the number of softmax layers, and , For fault sample index variables, The total number of fault samples. For input samples The softmax layer is the first The softmax value of the layer; The loss function is minimized using the stochastic gradient descent algorithm to obtain the model parameters of the power pole Beidou positioning device operation status diagnosis model; The operational status diagnosis model of the BeiDou positioning device for power poles is corrected based on the model parameters of the model model.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that are read by a machine to cause the machine to execute the intelligent diagnostic method for the operating status of the BeiDou positioning device as described in any one of claims 1 to 6.

Images