A method and system for predicting the maintenance time of an omnidirectional beacon device

Abstract

The present application provides a method and system for predicting the maintenance time of an omnidirectional beacon device, which relates to the field of aviation navigation technology and is used to improve the accuracy of predicting the maintenance time of an omnidirectional beacon device. The method includes: obtaining the monitoring data of the omnidirectional beacon ground station and obtaining the operation data of the omnidirectional beacon ground station; the omnidirectional beacon receiver operating in the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data respectively; determining whether the omnidirectional beacon device is abnormal based on the absolute position and the relative position of the operating aircraft; if it is abnormal, obtaining the historical operation data and historical climate data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period; determining the feature vector matrix according to the historical operation data and historical climate data in the preset time period; inputting the feature vector matrix into the omnidirectional beacon device maintenance time prediction model to predict the maintenance time of the omnidirectional beacon device.

Description

Technical Field

[0001] This application relates to the field of aviation navigation technology, and particularly to a method and system for predicting the maintenance time of an omnidirectional beacon device. Background Art

[0002] The omnidirectional beacon device is a ground device widely used in modern aviation radio navigation. It began to be widely applied in the 1960s. It has the advantages of high precision and stable indication, and is one of the reliable land-based navigation systems in civil aviation. Since most current transport aircraft are equipped with omnidirectional beacon receivers, a certain scale of omnidirectional beacon station network still needs to be maintained and newly built to support the operation of terminals and airways.

[0003] Due to the long operation life, special operation conditions, maintenance guarantee and other related index requirements of the omnidirectional beacon device, currently, the omnidirectional beacon device is usually maintained when a fault occurs or at regular intervals. As a result, the omnidirectional beacon device is maintained only when a problem occurs, so the current maintenance efficiency of the omnidirectional beacon device is low, thus reducing the safety of aviation radio navigation. Summary of the Invention

[0004] The embodiments of this application provide a method and system for predicting the maintenance time of an omnidirectional beacon device, which is used to improve the accuracy of predicting the maintenance time of the omnidirectional beacon device.

[0005] The embodiments of the present invention provide a method for predicting the maintenance time of an omnidirectional beacon device. The method is applied to a system for predicting the maintenance time of an omnidirectional beacon device. The system includes: an omnidirectional beacon device and a monitoring device. The omnidirectional beacon device includes an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is set within a preset range of the airport where it is located, and the omnidirectional beacon receiver is set inside the aircraft. The method includes:

[0006] Monitoring and obtaining the monitoring data of the omnidirectional beacon ground station through the monitoring device, and obtaining the operation data of the omnidirectional beacon ground station;

[0007] The omnidirectional beacon receiver running inside the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data respectively;

[0008] Based on the absolute position of the operating aircraft and the relative position, determining whether the omnidirectional beacon device is abnormal;

[0009] If the omnidirectional beacon device is abnormal, obtaining the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period; and the historical climate data corresponding to the preset time period;

[0010] Determine the eigenvector matrix according to the historical operation data and historical climate data of the preset time period; each row of data in the eigenvector matrix is the historical operation data and historical climate data corresponding to the time.

[0011] Input the eigenvector matrix into the omnidirectional beacon equipment maintenance time prediction model, and predict the maintenance time of the omnidirectional beacon equipment; the omnidirectional beacon equipment maintenance time prediction model is trained according to the sample data of continuous N days and the corresponding maintenance time labels, and the sample data includes the historical climate data of continuous N days and the historical operation data of the omnidirectional beacon equipment.

[0012] In an optional embodiment provided by the present invention, the omnidirectional beacon receiver operating in the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data respectively, including:

[0013] Obtain the reference signal with fixed phase and the variable phase signal with continuously changing angular phase around the omnidirectional beacon ground station in the operation data and the monitoring data respectively.

[0014] Calculate the first relative position of the operating aircraft through the phase difference between the reference signal and the variable phase signal corresponding to the operation data.

[0015] Calculate the second relative position of the operating aircraft through the phase difference between the reference signal and the variable phase signal corresponding to the monitoring data.

[0016] In an optional embodiment provided by the present invention, determining whether the omnidirectional beacon equipment is abnormal based on the absolute position and the relative position of the operating aircraft includes:

[0017] Calculate the absolute value of the data difference between the operation data and the monitoring data.

[0018] If the absolute value of the data difference is less than the second preset value, calculate the first position deviation between the first absolute position and the first relative position of the operating aircraft.

[0019] If the first position deviation is greater than the first preset value, determine that the omnidirectional beacon ground station is abnormal.

[0020] If the first position deviation is less than or equal to the first preset value, calculate the second position deviation between the second absolute position and the second relative position of the operating aircraft.

[0021] If the second position deviation is greater than the first preset value, determine that the omnidirectional beacon receiver is abnormal.

[0022] If the absolute value of the data difference is greater than or equal to the second preset value, it is determined that there is an interference signal within the preset range of the VOR ground station.

[0023] In an optional embodiment provided by the present invention, if the VOR equipment is abnormal, the historical operation data of the VOR ground station or the VOR receiver within a preset time period is obtained, including:

[0024] If the VOR ground station is abnormal, the historical operation data of the VOR ground station within a preset time period is obtained;

[0025] If the VOR receiver is abnormal, the historical operation data of the VOR receiver within a preset time period is obtained.

[0026] In an optional embodiment provided by the present invention, the determining the feature vector matrix according to the historical operation data and the historical climate data within the preset time period includes:

[0027] If the VOR ground station is abnormal, the forward carrier power, reverse carrier power, upper sideband power, lower sideband power, signal spectrum are extracted from the historical operation data, and the temperature, relative humidity and site air pressure are extracted from the historical climate data;

[0028] The extracted forward carrier power, reverse carrier power, upper sideband power, lower sideband power, signal spectrum, and the extracted temperature, relative humidity and site air pressure are converted into feature vectors in units of days;

[0029] The converted feature vectors are arranged in chronological order to obtain the feature vector matrix.

[0030] In an optional embodiment provided by the present invention, the determining the feature vector matrix according to the historical operation data and the historical climate data within the preset time period includes:

[0031] If the VOR receiver is abnormal, the power, modulation degree and angle are extracted from the historical operation data;

[0032] The extracted power, modulation degree and angle are converted into feature vectors;

[0033] The converted feature vectors are arranged in chronological order to obtain the feature vector matrix.

[0034] In an optional embodiment provided by the present invention, the inputting the feature vector matrix into the maintenance time prediction model of the VOR equipment to predict the maintenance time of the VOR equipment includes:

[0035] Input the feature vector matrix into the first sub-prediction model, and obtain the first data feature corresponding to the feature vector matrix and its corresponding data weight value through the first sub-prediction model;

[0036] Input the feature vector matrix into the second sub-prediction model, and obtain the second data feature corresponding to the feature vector matrix and its corresponding data weight value through the second sub-prediction model;

[0037] Input the first data feature, the second data feature and their respectively corresponding data weight values into the omnidirectional beacon device maintenance time prediction model, and predict the maintenance time of the omnidirectional beacon device.

[0038] In an optional embodiment provided by the present invention, the training process of the omnidirectional beacon device maintenance time prediction model is as follows:

[0039] Obtain sample data and its corresponding sample label, and determine a sample feature vector matrix according to the sample data; the sample data includes the historical operation data and historical climate data of the omnidirectional beacon ground station and the omnidirectional beacon receiver;

[0040] Input the sample feature vector matrix into the first sub-prediction model to obtain the first sample data feature corresponding to the sample feature vector matrix and its corresponding data weight value;

[0041] Input the sample feature vector matrix into the second sub-prediction model to obtain the second sample data feature corresponding to the sample feature vector matrix and its corresponding data weight value;

[0042] Input the first sample data feature, the second sample data feature and their respectively corresponding data weight values into the omnidirectional beacon device maintenance time prediction model to obtain the prediction label corresponding to the sample data;

[0043] Calculate the loss value of the omnidirectional beacon device maintenance time prediction model according to the prediction label and the sample label;

[0044] When the loss value is less than a preset value, stop training the omnidirectional beacon device maintenance time prediction model.

[0045] In an optional embodiment provided by the present invention, the step of inputting the first sample data feature, the second sample data feature and their respectively corresponding data weight values into the omnidirectional beacon device maintenance time prediction model to obtain the prediction label corresponding to the sample data includes:

[0046] Obtain a first predicted label corresponding to the sample data based on the first sample data feature and its corresponding data weight value; obtain a second predicted label corresponding to the sample data based on the second sample data feature and its corresponding data weight value;

[0047] Obtain a third predicted label corresponding to the sample data based on the first sample data feature, the second sample data feature, and their respectively corresponding data weight values;

[0048] Obtain a predicted label corresponding to the sample data based on the first predicted label, the second predicted label, and the third predicted label.

[0049] An embodiment of the present invention provides a system for predicting the maintenance time of an omnidirectional beacon device. The system includes: an omnidirectional beacon device, a monitoring device, and a prediction device. The omnidirectional beacon device includes an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is set within a preset range of the airport where it is located, and the omnidirectional beacon receiver is set inside the aircraft. The prediction device includes:

[0050] An acquisition module, configured to acquire the monitoring data of the omnidirectional beacon ground station and acquire the operation data of the omnidirectional beacon ground station;

[0051] A calculation module, configured to calculate the relative position of the operating aircraft by the omnidirectional beacon receiver operating inside the aircraft according to the monitoring data and the operation data;

[0052] The calculation module is further configured to determine whether the omnidirectional beacon device is abnormal based on the absolute position of the operating aircraft and the relative position;

[0053] The acquisition module is further configured to, if the omnidirectional beacon device is abnormal, acquire the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver within a preset time period; and the historical climate data corresponding to the preset time period;

[0054] A determination module, configured to determine a feature vector matrix according to the historical operation data and the historical climate data within the preset time period; each row of data in the feature vector matrix is the historical operation data and the historical climate data corresponding to the corresponding time;

[0055] A prediction module, configured to input the feature vector matrix into an omnidirectional beacon device maintenance time prediction model to predict the maintenance time of the omnidirectional beacon device; the omnidirectional beacon device maintenance time prediction model is trained according to the sample data of continuous N days and the corresponding maintenance time labels, and the sample data includes the historical climate data of continuous N days and the historical operation data of the omnidirectional beacon device.

[0056] The present invention provides a method and system for predicting the maintenance time of an omnidirectional beacon device. The system includes: an omnidirectional beacon device, a monitoring device, and a prediction device. The omnidirectional beacon device includes an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is set within a preset range of the airport where it is located, and the omnidirectional beacon receiver is set inside the aircraft. The prediction device first monitors and obtains the monitoring data of the omnidirectional beacon ground station and the operation data of the omnidirectional beacon ground station through the monitoring device; the omnidirectional beacon receiver operating inside the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data respectively; based on the absolute position and the relative position of the operating aircraft, it is determined whether the omnidirectional beacon device is abnormal; if the omnidirectional beacon device is abnormal, the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period and the historical climate data corresponding to the preset time period are obtained; a feature vector matrix is determined according to the historical operation data and the historical climate data in the preset time period; the feature vector matrix is input into the omnidirectional beacon device maintenance time prediction model, and the maintenance time of the omnidirectional beacon device is predicted. Compared with the existing method of maintaining the omnidirectional beacon device when a fault occurs or at regular intervals, the present application determines whether the omnidirectional beacon device is abnormal based on the monitoring data and the operation data of the omnidirectional beacon ground station, and when the omnidirectional beacon device is abnormal, the maintenance time of the omnidirectional beacon device is predicted based on the historical operation data and the historical climate data in a preset time period. Thus, the prediction of the maintenance time of the omnidirectional beacon device is realized through the present application, thereby improving the accuracy of the maintenance time of the omnidirectional beacon device through the present application, and further improving the safety of aviation radio navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a flowchart of a method for predicting the maintenance time of an omnidirectional beacon device provided by the present application;

[0058] Figure 2 It is a flowchart of a method for training an omnidirectional beacon device maintenance time prediction model provided by the present application;

[0059] Figure 3 It is a schematic structural diagram of a system for predicting the maintenance time of an omnidirectional beacon device provided by the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] In order to better understand the above technical solutions, the technical solutions of the embodiments of the present application will be described in detail below through the drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present application and the embodiments are detailed descriptions of the technical solutions of the embodiments of the present application, rather than limitations on the technical solutions of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0061] Such as Figure 1As shown in the figure, this embodiment provides a method for predicting the maintenance time of an omnidirectional beacon device. The method is applied to a system for predicting the maintenance time of an omnidirectional beacon device, which system includes: an omnidirectional beacon device, a monitoring device, and a prediction device. The omnidirectional beacon device includes an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is set within a preset range of the airport where it is located, and the omnidirectional beacon receiver is set inside the aircraft. The prediction device is communicatively connected to the omnidirectional beacon device and the monitoring device, and the prediction device is used to perform the following steps:

[0062] S101, monitor and obtain the monitoring data of the omnidirectional beacon ground station through the monitoring device, and obtain the operation data of the omnidirectional beacon ground station.

[0063] Among them, the monitoring device has passed metrological verification and is within the validity period, and the error of the monitoring device should be less than one-third of the allowable error of the measured parameter. The monitoring devices used include: a spectrum analyzer and an omnidirectional antenna. Among them, the frequency range of the spectrum analyzer can include 108 MHz - 117.975 MHz, and the radio frequency input impedance is 50 Ω; the frequency range of the omnidirectional antenna can be: 108 MHz - 117.975 MHz, the input impedance is 50 Ω, the polarization mode is horizontal polarization, the direction ≤ ±0.5 dB, etc. This embodiment does not specifically limit the various parameters of the monitoring device.

[0064] Specifically, the monitoring data of the omnidirectional beacon ground station can include frequency, signal occupancy bandwidth, field strength, modulation, etc. The operation data of the omnidirectional beacon ground station is the actual operation data of the omnidirectional beacon ground station. By comparing the monitoring data and the operation data, it can be determined whether there is an abnormality in the omnidirectional beacon ground station or its surroundings.

[0065] It should be noted that the omnidirectional beacon ground station in this embodiment is used for en-route navigation, and the various parameters of its operation can be: 112 - 117.925 MHz, channel interval 50 kHz, transmit power 200 W, operating range 200 nautical miles; the omnidirectional beacon receiver is used for terminal guidance of the aircraft to approach, and the various parameters of its operation can be 108 - 112 MHz, channel interval 50 kHz, transmit power 50 W, operating range 25 nautical miles.

[0066] S102, the omnidirectional beacon receiver operating inside the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data respectively.

[0067] In this embodiment, the signals transmitted by the VOR ground station are two: one is a reference signal with a fixed phase, and the other is a variable-phase signal with a continuously changing phase angle around the beacon station. The VOR receiver in the aircraft can calculate its own azimuth relative to the VOR ground station based on the phase difference between the two received signals, that is, calculate the relative position of the operating aircraft according to the monitoring data and the operating data respectively.

[0068] In an alternative embodiment provided by the present application, the VOR receiver operating in the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operating data respectively, including: respectively obtaining the reference signal with a fixed phase and the variable-phase signal with a continuously changing phase angle around the VOR ground station in the operating data and the monitoring data; calculating the first relative position of the operating aircraft through the phase difference between the reference signal and the variable-phase signal corresponding to the operating data; calculating the second relative position of the operating aircraft through the phase difference between the reference signal and the variable-phase signal corresponding to the monitoring data. Wherein, the first relative position and the second relative position are the positions of the aircraft relative to the VOR ground station, so as to determine whether the VOR ground station is abnormal according to the first relative position and whether the VOR receiver is abnormal according to the second relative position in subsequent steps.

[0069] S103. Determine whether the VOR device is abnormal based on the absolute position and relative position of the operating aircraft.

[0070] In an alternative embodiment provided by the present application, the determining whether the VOR device is abnormal based on the absolute position and the relative position of the operating aircraft includes:

[0071] S1031. Calculate the absolute value of the data difference between the operating data and the monitoring data.

[0072] S1032A. If the absolute value of the data difference is less than the second preset value, calculate the first position deviation between the first absolute position and the first relative position of the operating aircraft.

[0073] In this embodiment, if the absolute value of the data difference between the operating data and the monitoring data is less than the second preset value, it means that the area near the VOR ground station is not affected by signal interference, that is, the external signal interference factor is excluded. At this time, it is necessary to calculate the first position deviation between the first absolute position and the first relative position of the operating aircraft, and thus determine whether the VOR ground station has an abnormal operation.

[0074] S1033A1. If the first position deviation is greater than the first preset value, determine that the VOR ground station is abnormal.

[0075] Among them, the first absolute position of the operating aircraft is the position obtained according to the positioning device of the aircraft itself, such as the position obtained through the Global Positioning System or the Beidou positioning system. In this embodiment, if the first position deviation is greater than the first preset value

[0076] S1033A2, if the first position deviation is less than or equal to the first preset value, then calculate the second position deviation between the second absolute position and the second relative position of the operating aircraft.

[0077] In this embodiment, if the first position deviation is less than or equal to the first preset value, it indicates that the VOR ground station is normal. At this time, it is necessary to calculate the second position deviation between the second absolute position and the second relative position of the operating aircraft to determine whether the VOR receiver is abnormal.

[0078] S1034, if the second position deviation is greater than the first preset value, it is determined that the VOR receiver is abnormal.

[0079] If the second position deviation is less than the first preset value, it is determined that the VOR receiver is abnormal.

[0080] S1032B, if the absolute value of the data difference is greater than or equal to the second preset value, it is determined that there is an interference signal within the preset range of the VOR ground station.

[0081] Among them, step S1032B is a parallel step to step S1032A. If the absolute value of the data difference is greater than or equal to the second preset value, it indicates that the nearby area of the VOR ground station is affected by signal interference, and thus it is determined that there is an interference signal within the preset range of the VOR ground station.

[0082] S104, if the VOR equipment is abnormal, obtain the historical operation data of the VOR ground station or the VOR receiver within the preset time period; and the historical climate data corresponding to the preset time period.

[0083] Specifically, if the VOR ground station is abnormal, obtain the historical operation data of the VOR ground station within the preset time period; if the VOR receiver is abnormal, obtain the historical operation data of the VOR receiver within the preset time period.

[0084] Among them, the historical climate data includes temperature, relative humidity, site air pressure, etc., and this embodiment does not make specific limitations on this.

[0085] S105, determine the eigenvector matrix according to the historical operation data and historical climate data within the preset time period; each row of data in the eigenvector matrix is the historical operation data and historical climate data corresponding to the corresponding time.

[0086] In an alternative embodiment provided by the present application, the determining the feature vector matrix according to the historical operation data and historical climate data of the preset time period includes: if the VOR ground station appears abnormal, extracting the carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum from the historical operation data, and extracting the temperature, relative humidity and site air pressure from the historical climate data; converting the extracted carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum, and the extracted temperature, relative humidity and site air pressure into feature vectors in units of days; arranging the converted feature vectors in chronological order to obtain the feature vector matrix.

[0087] In an alternative embodiment provided by the present application, the determining the feature vector matrix according to the historical operation data and historical climate data of the preset time period includes: if the VOR receiver appears abnormal, extracting the power, modulation degree, and angle from the historical operation data; converting the extracted power, modulation degree, and angle into feature vectors; arranging the converted feature vectors in chronological order to obtain the feature vector matrix.

[0088] S106. Input the feature vector matrix into the maintenance time prediction model of the VOR equipment to predict the maintenance time of the VOR equipment.

[0089] Wherein, the maintenance time prediction model of the VOR equipment is trained according to the sample data of consecutive N days and the corresponding maintenance time labels. The sample data includes the historical climate data of consecutive N days and the historical operation data of the VOR equipment. The maintenance time label is manually marked, which is the time for maintaining the VOR equipment on any day after consecutive N days.

[0090] In an alternative embodiment provided by the present application, the inputting the feature vector matrix into the maintenance time prediction model of the VOR equipment to predict the maintenance time of the VOR equipment includes: inputting the feature vector matrix into the first sub-prediction model, and obtaining the first data feature corresponding to the feature vector matrix and its corresponding data weight value through the first sub-prediction model; inputting the feature vector matrix into the second sub-prediction model, and obtaining the second data feature corresponding to the feature vector matrix and its corresponding data weight value through the second sub-prediction model; inputting the first data feature, the second data feature and their respective corresponding data weight values into the maintenance time prediction model of the VOR equipment to predict the maintenance time of the VOR equipment.

[0091] Among them, the first sub-prediction model and the second sub-prediction model are existing pre-trained neural network models, which adopt network models with two different structures. In this embodiment, by inputting the feature vector matrix into the first sub-prediction model and the second sub-prediction model respectively, the first data feature, the second data feature and their corresponding data weight values can be obtained respectively. The data weight value is used to indicate the importance degree of the corresponding data in the first data feature and the second data feature for obtaining the prediction value.

[0092] In this embodiment, the omnidirectional beacon equipment maintenance time prediction model is a pre-trained time prediction model, that is, it is obtained by training the time prediction model according to the sample data composed of the first data feature, the second data feature and their corresponding data weight values, and the maintenance time corresponding to the sample data. Therefore, the maintenance time of the omnidirectional beacon equipment can be predicted through this omnidirectional beacon equipment maintenance time prediction model.

[0093] A method for predicting the maintenance time of an omnidirectional beacon equipment provided by an embodiment of the present application. First, the prediction device monitors and obtains the monitoring data of the omnidirectional beacon ground station through a monitoring device and obtains the operation data of the omnidirectional beacon ground station; the omnidirectional beacon receiver running in the aircraft calculates the relative position of the operating aircraft according to the monitoring data and the operation data; based on the absolute position and the relative position of the operating aircraft, it is determined whether the omnidirectional beacon equipment is abnormal; if the omnidirectional beacon equipment is abnormal, the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period and the historical climate data corresponding to the preset time period are obtained; the feature vector matrix is determined according to the historical operation data and the historical climate data in the preset time period; the feature vector matrix is input into the omnidirectional beacon equipment maintenance time prediction model, and the maintenance time of the omnidirectional beacon equipment is predicted. Compared with the existing method of maintaining the omnidirectional beacon equipment when a fault occurs or at regular intervals, the present application determines whether the omnidirectional beacon equipment is abnormal based on the monitoring data and operation data of the omnidirectional beacon ground station, and when the omnidirectional beacon equipment is abnormal, predicts the maintenance time of the omnidirectional beacon equipment based on the historical operation data and historical climate data in a preset time period. Thus, the prediction of the maintenance time of the omnidirectional beacon equipment is realized through the present application, thereby improving the accuracy of the maintenance time of the omnidirectional beacon equipment through the present application, and further improving the safety of aeronautical radio navigation.

[0094] As Figure 2 shown, in an optional embodiment provided by the present application, the training process of the omnidirectional beacon equipment maintenance time prediction model is as follows:

[0095] S201. Obtain the sample data and its corresponding sample labels, and determine the sample feature vector matrix according to the sample data; the sample data includes the historical operation data and historical climate data of the VOR ground station and the VOR receiver.

[0096] Specifically, in this embodiment, Figure 1 The sample feature vector matrix is determined through the corresponding steps, which will not be elaborated in this embodiment.

[0097] S202. Input the sample feature vector matrix into the first sub-prediction model to obtain the first sample data features corresponding to the sample feature vector matrix and their corresponding data weight values.

[0098] S203. Input the sample feature vector matrix into the second sub-prediction model to obtain the second sample data features corresponding to the sample feature vector matrix and their corresponding data weight values.

[0099] S204. Input the first sample data features, the second sample data features and their respectively corresponding data weight values into the VOR equipment maintenance time prediction model to obtain the prediction labels corresponding to the sample data.

[0100] Specifically, inputting the first sample data features, the second sample data features and their respectively corresponding data weight values into the VOR equipment maintenance time prediction model to obtain the prediction labels corresponding to the sample data includes:

[0101] S2041. Obtain the first prediction label corresponding to the sample data through the first sample data features and their corresponding data weight values; obtain the second prediction label corresponding to the sample data through the second sample data features and their corresponding data weight values.

[0102] S2042. Obtain the third prediction label corresponding to the sample data through the first sample data features, the second sample data features and their respectively corresponding data weight values.

[0103] S2043. Obtain the prediction label corresponding to the sample data according to the first prediction label, the second prediction label and the third prediction label.

[0104] Specifically, in this embodiment, the prediction label corresponding to the sample data can be determined by the following formula:

[0105]

[0106] Among them, yi is the predicted label corresponding to the i-th sample data, xij is the j-th predicted label obtained from the i-th sample data, where j = 1 to 3, aij is the predicted probability value corresponding to the predicted label xij, and bij and cij are the predicted probability values corresponding to the other two predicted labels. α and β are preset constant values.

[0107] For example, the predicted label of xi1 is 1, and the corresponding predicted probability value is 70%; the predicted label of xi2 is 1, and the corresponding predicted probability value is 80%; the predicted label of xi3 is 2, and the corresponding predicted probability value is 70%. Then, by calculating, the average probability of the predicted label 1 is 75%, and the average probability of the predicted label 2 is 70%. If β = 70%, then the predicted label of the obtained sample data is 1.

[0108] S205. Calculate the loss value of the omnidirectional beacon equipment maintenance time prediction model according to the predicted label and the sample label.

[0109] S206. When the loss value is less than the preset value, stop training the omnidirectional beacon equipment maintenance time prediction model.

[0110] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0111] In one embodiment, a system for predicting the maintenance time of an omnidirectional beacon equipment is provided. The system includes: an omnidirectional beacon equipment, a monitoring device, and a prediction device. The omnidirectional beacon equipment includes an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is set within a preset range of the airport where it is located, and the omnidirectional beacon receiver is set inside the aircraft. The prediction device corresponds one-to-one to the method for predicting the maintenance time of the omnidirectional beacon equipment in the above embodiment. As Figure 3 shown, the detailed description of each functional module of the prediction device is as follows:

[0112] An acquisition module 31, configured to acquire the monitoring data of the omnidirectional beacon ground station and acquire the operation data of the omnidirectional beacon ground station;

[0113] A calculation module 32, configured to calculate the relative position of the operating aircraft by the omnidirectional beacon receiver operating inside the aircraft according to the monitoring data and the operation data;

[0114] The calculation module 32 is further configured to determine whether the omnidirectional beacon equipment is abnormal based on the absolute position of the operating aircraft and the relative position;

[0115] The obtaining module 31 is further configured to, if the omni-directional beacon device has an abnormality, obtain the historical operation data of the omni-directional beacon ground station or the omni-directional beacon receiver in a preset time period; and the historical climate data corresponding to the preset time period;

[0116] The determining module 33 is configured to determine a feature vector matrix according to the historical operation data and the historical climate data in the preset time period; each row of data in the feature vector matrix is the historical operation data and the historical climate data corresponding to the corresponding time;

[0117] The prediction module 34 is configured to input the feature vector matrix into an omni-directional beacon device maintenance time prediction model to predict the maintenance time of the omni-directional beacon device; the omni-directional beacon device maintenance time prediction model is trained according to the sample data of continuous N days and the corresponding maintenance time labels, and the sample data includes the historical climate data of continuous N days and the historical operation data of the omni-directional beacon device.

[0118] In an optional embodiment provided by the present invention, the calculation module 32 is specifically configured to:

[0119] Obtain the reference signal with a fixed phase and the variable phase signal with a continuously changing angular phase around the omni-directional beacon ground station in the operation data and the monitoring data respectively;

[0120] Calculate the first relative position of the operating aircraft through the phase difference between the reference signal and the variable phase signal corresponding to the operation data;

[0121] Calculate the second relative position of the operating aircraft through the phase difference between the reference signal and the variable phase signal corresponding to the monitoring data.

[0122] In an optional embodiment provided by the present invention, the calculation module 32 is further specifically configured to:

[0123] Calculate the absolute value of the data difference between the operation data and the monitoring data;

[0124] If the absolute value of the data difference is less than a second preset value, calculate the first position deviation between the first absolute position and the first relative position of the operating aircraft;

[0125] If the first position deviation is greater than a first preset value, determine that the omni-directional beacon ground station has an abnormality;

[0126] If the first position deviation is less than or equal to the first preset value, calculate the second position deviation between the second absolute position and the second relative position of the operating aircraft;

[0127] If the second position deviation is greater than a first preset value, it is determined that the VOR receiver is abnormal;

[0128] If the absolute value of the data difference is greater than or equal to a second preset value, it is determined that there is an interference signal within the preset range of the VOR ground station.

[0129] In an optional embodiment provided by the present invention, the calculation module 32 is specifically configured to:

[0130] If the VOR ground station is abnormal, obtain the historical operation data of the VOR ground station within a preset time period;

[0131] If the VOR receiver is abnormal, obtain the historical operation data of the VOR receiver within a preset time period.

[0132] In an optional embodiment provided by the present invention, the determination module 33 is specifically configured to:

[0133] If the VOR ground station is abnormal, extract the carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum from the historical operation data, and extract the temperature, relative humidity, and site air pressure from the historical climate data;

[0134] Convert the extracted carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum, and the extracted temperature, relative humidity, and site air pressure into feature vectors on a daily basis;

[0135] Arrange the converted feature vectors in chronological order to obtain the feature vector matrix.

[0136] In an optional embodiment provided by the present invention, the determination module 33 is specifically configured to:

[0137] If the VOR receiver is abnormal, extract the power, modulation degree, and angle from the historical operation data;

[0138] Convert the extracted power, modulation degree, and angle into feature vectors;

[0139] Arrange the converted feature vectors in chronological order to obtain the feature vector matrix.

[0140] In an optional embodiment provided by the present invention, the prediction module 34 is specifically configured to:

[0141] Input the feature vector matrix into the first sub-prediction model, and obtain the first data feature and its corresponding data weight value corresponding to the feature vector matrix through the first sub-prediction model;

[0142] Input the feature vector matrix into the second sub-prediction model, and obtain the second data feature corresponding to the feature vector matrix and its corresponding data weight value through the second sub-prediction model;

[0143] Input the first data feature, the second data feature and their corresponding data weight values into the omnidirectional beacon device maintenance time prediction model, and predict the maintenance time of the omnidirectional beacon device.

[0144] In an optional embodiment provided by the present invention, the prediction device further includes a training module 35 for training the omnidirectional beacon device maintenance time prediction model. The training module 35 is used for:

[0145] Obtain sample data and its corresponding sample label, and determine a sample feature vector matrix according to the sample data; the sample data includes the historical operation data and historical climate data of the omnidirectional beacon ground station and the omnidirectional beacon receiver;

[0146] Input the sample feature vector matrix into the first sub-prediction model, and obtain the first sample data feature corresponding to the sample feature vector matrix and its corresponding data weight value;

[0147] Input the sample feature vector matrix into the second sub-prediction model, and obtain the second sample data feature corresponding to the sample feature vector matrix and its corresponding data weight value;

[0148] Input the first sample data feature, the second sample data feature and their corresponding data weight values into the omnidirectional beacon device maintenance time prediction model, and obtain the prediction label corresponding to the sample data;

[0149] Calculate the loss value of the omnidirectional beacon device maintenance time prediction model according to the prediction label and the sample label;

[0150] When the loss value is less than a preset value, stop training the omnidirectional beacon device maintenance time prediction model.

[0151] In an optional embodiment provided by the present invention, the training module 35 is specifically used for:

[0152] Obtain the first prediction label corresponding to the sample data through the first sample data feature and its corresponding data weight value; obtain the second prediction label corresponding to the sample data through the second sample data feature and its corresponding data weight value;

[0153] Obtain the third prediction label corresponding to the sample data through the first sample data feature, the second sample data feature and their corresponding data weight values;

[0154] Obtain the prediction label corresponding to the sample data according to the first prediction label, the second prediction label, and the third prediction label.

[0155] For the specific limitations of the prediction device, reference can be made to the limitations of the method for predicting the maintenance time of the omnidirectional beacon device in the above text, which will not be elaborated here. Each module in the above device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0156] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system is divided into different functional units or modules to complete all or part of the functions described above.

[0157] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for predicting maintenance time of an omnidirectional beacon device, characterized in that: The method is applied to a system for predicting the maintenance time of an omnidirectional beacon device, the system comprising: an omnidirectional beacon device, a monitoring device, and a prediction device, the omnidirectional beacon device comprising an omnidirectional beacon ground station and an omnidirectional beacon receiver, the omnidirectional beacon ground station is arranged within a preset range of an airport, the omnidirectional beacon receiver is arranged in an aircraft, and the prediction device is used to execute the following method: Acquiring monitoring data of the omnidirectional beacon ground station through the monitoring device, and acquiring operation data of the omnidirectional beacon ground station; The omnidirectional beacon receiver running in the aircraft calculates the relative position of the running aircraft according to the monitoring data and the running data; Determining whether the omnidirectional beacon device is abnormal based on the absolute position of the operating aircraft and the relative position; If the omnidirectional beacon device is abnormal, the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period is obtained; and the historical climate data corresponding to the preset time period; Determine a characteristic vector matrix according to the historical operation data and historical climate data of the preset time period; each row of data of the characteristic vector matrix is ​​the historical operation data and historical climate data of the corresponding time; The characteristic vector matrix is ​​input into the maintenance time prediction model of the omnidirectional beacon device to predict the maintenance time of the omnidirectional beacon device; the maintenance time prediction model of the omnidirectional beacon device is trained based on N consecutive days of sample data and corresponding maintenance time labels, and the sample data includes N consecutive days of historical climate data and historical operation data of the omnidirectional beacon device; The step of inputting the characteristic vector matrix into an omnidirectional beacon device maintenance time prediction model to predict the maintenance time of the omnidirectional beacon device includes: Inputting the feature vector matrix into a first sub-prediction model, and obtaining a first data feature corresponding to the feature vector matrix and a corresponding data weight value thereof through the first sub-prediction model; Inputting the feature vector matrix into a second sub-prediction model, and obtaining second data features corresponding to the feature vector matrix and corresponding data weight values ​​thereof through the second sub-prediction model; The first data feature and the second data feature and their corresponding data weight values ​​are input into the omnidirectional beacon device maintenance time prediction model to predict the maintenance time of the omnidirectional beacon device.

2. The method according to claim 1, characterized in that The omnidirectional beacon receiver running in the aircraft calculates the relative position of the running aircraft according to the monitoring data and the running data, including: Respectively acquiring a reference signal with a fixed phase and a variable phase signal with an angle phase continuously changing around the omnidirectional beacon ground station in the operation data and the monitoring data; Calculating a first relative position of the operating aircraft by using a phase difference between the reference signal and the variable phase signal corresponding to the operating data; The second relative position of the operating aircraft is calculated by the phase difference between the reference signal and the variable phase signal corresponding to the monitoring data.

3. The method according to claim 2, characterized in that The determining whether the omnidirectional beacon device is abnormal based on the absolute position and the relative position of the operating aircraft includes: Calculating the absolute value of the data difference between the operating data and the monitoring data; If the absolute value of the data difference is less than a second preset value, calculating a first position deviation between the first absolute position of the operating aircraft and the first relative position; If the first position deviation is greater than a first preset value, it is determined that an abnormality occurs in the omnidirectional beacon ground station; If the first position deviation is less than or equal to the first preset value, calculating a second position deviation between the second absolute position of the operating aircraft and the second relative position; If the second position deviation is greater than a first preset value, it is determined that an abnormality occurs in the omnidirectional beacon receiver; If the absolute value of the data difference is greater than or equal to a second preset value, it is determined that an interference signal appears within the preset range of the omnidirectional beacon ground station.

4. The method according to claim 3, characterized in that If the omnidirectional beacon device is abnormal, obtaining historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period includes: If the omnidirectional beacon ground station is abnormal, obtaining historical operation data of the omnidirectional beacon ground station in a preset time period; If the omnidirectional beacon receiver is abnormal, historical operation data of the omnidirectional beacon receiver in a preset time period is obtained.

5. The method according to claim 4, characterized in that The determining of the characteristic vector matrix according to the historical operation data and the historical climate data of the preset time period includes: If the omnidirectional beacon ground station is abnormal, extracting carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum from the historical operation data, and extracting temperature, relative humidity and site air pressure from the historical climate data; The extracted carrier forward power, carrier reverse power, upper sideband power, lower sideband power, signal spectrum, and extracted temperature, relative humidity, and site air pressure are converted into feature vectors in units of days; The transformed eigenvectors are arranged in chronological order to obtain the eigenvector matrix.

6. The method according to claim 4, characterized in that The determining of the characteristic vector matrix according to the historical operation data and the historical climate data of the preset time period includes: If the omnidirectional beacon receiver is abnormal, extracting power, modulation and angle from the historical operation data; Convert the extracted power, modulation degree and angle into feature vectors; The transformed eigenvectors are arranged in chronological order to obtain the eigenvector matrix.

7. The method according to claim 6, characterized in that The training process of the omnidirectional beacon device maintenance time prediction model is as follows: Acquire sample data and its corresponding sample labels, and determine a sample feature vector matrix according to the sample data; the sample data includes historical operation data of the omnidirectional beacon ground station and the omnidirectional beacon receiver and historical climate data; Inputting the sample feature vector matrix into the first sub-prediction model to obtain the first sample data feature corresponding to the sample feature vector matrix and its corresponding data weight value; Inputting the sample feature vector matrix into the second sub-prediction model to obtain second sample data features corresponding to the sample feature vector matrix and corresponding data weight values; Inputting the first sample data feature and the second sample data feature and their corresponding data weight values ​​into the omnidirectional beacon device maintenance time prediction model to obtain a prediction label corresponding to the sample data; Calculate the loss value of the omnidirectional beacon device maintenance time prediction model according to the prediction label and the sample label; When the loss value is less than a preset value, the training of the maintenance time prediction model of the omnidirectional beacon device is stopped.

8. The method according to claim 7, characterized in that The step of inputting the first sample data feature and the second sample data feature and their corresponding data weight values ​​into the omnidirectional beacon device maintenance time prediction model to obtain a prediction label corresponding to the sample data includes: Obtain a first prediction label corresponding to the sample data through the first sample data feature and its corresponding data weight value; obtain a second prediction label corresponding to the sample data through the second sample data feature and its corresponding data weight value; Obtain a third prediction label corresponding to the sample data through the first sample data feature and the second sample data feature and their corresponding data weight values; The prediction label corresponding to the sample data is obtained according to the first prediction label, the second prediction label and the third prediction label.

9. A system for predicting maintenance time of omnidirectional beacon equipment, the system implementing the method according to claim 1, characterized in that: The system comprises: an omnidirectional beacon device, a monitoring device, and a prediction device. The omnidirectional beacon device comprises an omnidirectional beacon ground station and an omnidirectional beacon receiver. The omnidirectional beacon ground station is arranged within a preset range of an airport, and the omnidirectional beacon receiver is arranged in an aircraft. The prediction device comprises: An acquisition module, used to acquire monitoring data of the omnidirectional beacon ground station and to acquire operation data of the omnidirectional beacon ground station; A calculation module, used for the omnidirectional beacon receiver running in the aircraft to calculate the relative position of the running aircraft according to the monitoring data and the running data; The calculation module is further used to determine whether the omnidirectional beacon device is abnormal based on the absolute position and the relative position of the operating aircraft; The acquisition module is further used to acquire the historical operation data of the omnidirectional beacon ground station or the omnidirectional beacon receiver in a preset time period if an abnormality occurs in the omnidirectional beacon device; and the historical climate data corresponding to the preset time period; A determination module, used to determine a characteristic vector matrix according to the historical operation data and historical climate data of the preset time period; each row of data of the characteristic vector matrix is ​​the historical operation data and historical climate data of the corresponding time; A prediction module is used to input the feature vector matrix into an omnidirectional beacon device maintenance time prediction model to predict the maintenance time of the omnidirectional beacon device; the omnidirectional beacon device maintenance time prediction model is trained based on N consecutive days of sample data and corresponding maintenance time labels, and the sample data includes N consecutive days of historical climate data and historical operation data of the omnidirectional beacon device.

Images