Star-based ADS-B track prediction method and device

Abstract

The embodiment of the present specification provides a star-based ADS-B track prediction method and device, wherein the star-based ADS-B track prediction method comprises: acquiring initial data, analyzing the initial data based on an analysis strategy to determine analysis data; wherein the initial data comprises an ADS-B message; preprocessing the analysis data based on a preprocessing rule to obtain preprocessed data; quality evaluating the preprocessed data to determine an evaluation result; and based on the evaluation result, performing track prediction through the preprocessed data. By acquiring initial data, analyzing the initial data based on an analysis strategy to determine analysis data; wherein the initial data comprises an ADS-B message; preprocessing the analysis data based on a preprocessing rule to obtain preprocessed data; quality evaluating the preprocessed data to determine an evaluation result; and based on the evaluation result, performing track prediction through the preprocessed data, the accuracy and stability of track prediction can be improved.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of aerospace technology, and in particular to a satellite-based ADS-B trajectory prediction method. Background Technology

[0002] Satellite-based ADS-B (Automatic Dependent Surveillance-Broadcast) trajectory prediction is an advanced method that utilizes satellite technology to monitor and predict the position of aircraft. The core idea behind this technology is to improve flight safety, efficiency, and global flight monitoring capabilities by combining signals broadcast from airborne aircraft with the satellite's ability to receive and process these signals. Currently, there are many trajectory prediction methods, but few have been applied to practical engineering projects, and their stability and accuracy are insufficient.

[0003] Therefore, the application of theory to practice still needs further development and improvement. Summary of the Invention

[0004] In view of this, embodiments of this specification provide a satellite-based ADS-B trajectory prediction method. One or more embodiments of this specification also relate to a satellite-based ADS-B trajectory prediction device, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0005] According to a first aspect of the embodiments of this specification, a satellite-based ADS-B trajectory prediction method is provided, comprising:

[0006] Obtain initial data, and parse the initial data based on the parsing strategy to determine the parsed data; wherein, the initial data includes ADS-B messages;

[0007] The parsed data is preprocessed based on the preprocessing rules to obtain preprocessed data;

[0008] Perform a quality assessment on the preprocessed data and determine the assessment results;

[0009] Based on the evaluation results, trajectory prediction is performed using preprocessed data.

[0010] In one possible implementation, the initial data is parsed based on a parsing strategy to determine the parsed data, including:

[0011] Extract message capture time and ADS-B messages from the initial data at set time intervals;

[0012] Variable data is determined based on parsing strategy, message capture time, and ADS-B message;

[0013] Determine initial information by globally decoding based on variable data;

[0014] The parsed data is determined by local decoding based on the initial information.

[0015] In one possible implementation, the parsed data is preprocessed based on preprocessing rules to obtain preprocessed data, including:

[0016] Data integration and data removal rules are determined based on preprocessing rules;

[0017] The parsed data is integrated based on data integration rules to determine the integrated data;

[0018] Based on data removal rules, the integrated data is removed to obtain preprocessed data.

[0019] In one possible implementation, the preprocessed data is quality assessed, and the assessment results are determined, including:

[0020] Determine the constraints and the corresponding data volume thresholds;

[0021] Perform statistics on at least one data point in the preprocessed data to determine the data volume;

[0022] When the amount of data exceeds the data volume threshold, the update frequency information is determined based on the preprocessed data;

[0023] The evaluation results are determined based on the update frequency information.

[0024] In one possible implementation, trajectory prediction is performed based on the evaluation results using preprocessed data, including:

[0025] If the evaluation result is satisfactory, the preprocessed data is interpolated to determine the interpolated data;

[0026] Predict flight paths over a set time period based on interpolated data.

[0027] In one possible implementation, trajectory prediction over a given time period is performed based on interpolated data, including:

[0028] Sampling is performed based on interpolated data to determine the sampling time point, and the speed and heading data corresponding to the sampling time point are extracted;

[0029] Normalize the sampling time points and construct a time matrix;

[0030] Least square calculations are performed on velocity and heading data based on the time matrix to determine the least squares coefficient estimation vector;

[0031] Based on the least squares coefficient estimation vector, the trajectory is predicted for a set time period using the distance calculation formula.

[0032] In one possible implementation, trajectory prediction for a given time period is performed based on the least squares coefficient estimation vector using a distance calculation formula, including:

[0033] Determine the extrapolation time, and based on the least squares coefficient estimation vector and the extrapolation time, determine the predicted speed data and predicted heading data for a set time period;

[0034] Determine the radian data, and based on the radian data, predicted speed data, and predicted heading data, determine the latitude and longitude prediction data;

[0035] The predicted location is determined by converting latitude and longitude prediction data into radians.

[0036] According to a second aspect of the embodiments of this specification, a satellite-based ADS-B trajectory prediction device is provided, comprising:

[0037] The data parsing module is configured to acquire initial data and parse the initial data based on a parsing strategy to determine the parsed data; wherein, the initial data includes ADS-B messages;

[0038] The data processing module is configured to preprocess the parsed data based on preprocessing rules to obtain preprocessed data;

[0039] The data evaluation module is configured to perform quality assessment on preprocessed data and determine the evaluation results.

[0040] The trajectory prediction module is configured to predict trajectories based on the evaluation results and using preprocessed data.

[0041] According to a third aspect of the embodiments of this specification, a computing device is provided, comprising:

[0042] Memory and processor;

[0043] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the above-described satellite-based ADS-B trajectory prediction method.

[0044] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the above-described satellite-based ADS-B trajectory prediction method.

[0045] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described satellite-based ADS-B trajectory prediction method.

[0046] This specification provides a satellite-based ADS-B trajectory prediction method and apparatus. The satellite-based ADS-B trajectory prediction method includes: acquiring initial data; parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing quality assessment on the preprocessed data to determine the assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data. By acquiring initial data, parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing quality assessment on the preprocessed data to determine the assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data, the accuracy and stability of trajectory prediction can be improved. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of a scenario for a satellite-based ADS-B trajectory prediction method provided in one embodiment of this specification;

[0048] Figure 2 This is a flowchart of a satellite-based ADS-B trajectory prediction method provided in one embodiment of this specification;

[0049] Figure 3 This is a schematic diagram showing the altitude comparison of a satellite-based ADS-B trajectory prediction method provided in one embodiment of this specification.

[0050] Figure 4 This is a trajectory comparison diagram of a satellite-based ADS-B trajectory prediction method provided in one embodiment of this specification;

[0051] Figure 5 This is a schematic diagram of error analysis for a satellite-based ADS-B trajectory prediction method provided in one embodiment of this specification;

[0052] Figure 6 This is a schematic diagram of the structure of a satellite-based ADS-B trajectory prediction device provided in one embodiment of this specification;

[0053] Figure 7 This is a structural block diagram of a computing device provided in one embodiment of this specification. Detailed Implementation

[0054] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0055] The terminology used in one or more embodiments of this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of this specification. The singular forms “a” and “the” as used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0056] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this specification, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0057] First, the terms and concepts used in one or more embodiments of this specification will be explained.

[0058] The ADS-B system, or Automatic Dependent Surveillance-Broadcast system, consists of multiple ground stations and airborne stations, and completes two-way data communication in a mesh, multi-point-to-multi-point manner.

[0059] CPR identifier: This is an encoding method. The CPR identifier indicates whether the location message is odd or even encoded, with 0 representing even and 1 representing odd.

[0060] ICAO is an abbreviation for the International Civil Aviation Organization. It is a specialized agency of the United Nations dedicated to developing international civil aviation standards and regulations to ensure the safe, efficient, and sustainable development of civil aviation worldwide.

[0061] NACp: NACp is an abbreviation for Navigation Accuracy Category performance. This is a metric used to measure the accuracy of an aircraft navigation system, describing the accuracy of the position information provided by the navigation system.

[0062] This specification provides a satellite-based ADS-B trajectory prediction method, and also relates to a satellite-based ADS-B trajectory prediction device, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments.

[0063] See Figure 1 , Figure 1 A schematic diagram of a scenario for a satellite-based ADS-B trajectory prediction method provided according to an embodiment of this specification is shown.

[0064] exist Figure 1 In the application scenario, computing device 101 can acquire initial data and parse it based on a parsing strategy to determine parsed data 102. Then, computing device 101 can preprocess the parsed data 102 based on preprocessing rules to obtain preprocessed data 103. Afterward, computing device 101 can perform quality assessment on the preprocessed data 103 to determine the assessment result 104. Finally, computing device 101 can perform trajectory prediction based on the assessment result 104 and the preprocessed data, as shown by reference numeral 105 in the attached figure.

[0065] It should be noted that the aforementioned computing device 101 can be either hardware or software. When the computing device 101 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device 101 is software, it can be installed in the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0066] See Figure 2 , Figure 2 A flowchart of a satellite-based ADS-B trajectory prediction method according to an embodiment of this specification is shown, which specifically includes the following steps.

[0067] Step 201: Obtain initial data and parse the initial data based on the parsing strategy to determine the parsed data; wherein, the initial data includes ADS-B messages.

[0068] In practical applications, the embodiments of this specification may include an ADS-B message parsing module, a data preprocessing module, a data quality assessment module, and a trajectory prediction and trajectory output module. The ADS-B message parsing module includes position message parsing, speed message parsing, and navigation integrity category parsing.

[0069] Specifically, the system parses the data packets received per second and transmits the data to the preprocessing module. When the preprocessing module passes the data to the data quality assessment module, it receives the data from the parsing module for the next second, and the parsing module then transmits the data to the preprocessing module for the next second.

[0070] In one possible implementation, the initial data is parsed and the parsed data is determined based on the parsing strategy, including: extracting the message capture time and ADS-B message from the initial data at set time intervals; determining variable data based on the parsing strategy, message capture time and ADS-B message; determining initial information based on the variable data through global decoding; and determining parsed data based on the initial information through local decoding.

[0071] In practical applications, the ADS-B message parsing module runs in a loop according to the second task, reading n data packets per second. For each data packet, it extracts the message capture time and the ADS-B message. The capture time and the newly formed binary number of the ADS-B message are stored row-by-row in the `adsbinfo` variable. After extracting all n data packets per second, it reads `adsbinfo` row-by-row, reads and parses the message's DF (Description Function). If the DF is 17 or 18, it reads the message's ME field and parses the TC (Tracking Time) value. If the TC belongs to [9, 18] or [20, 22], it parses the capture time and ICAO (Intelligent Communication Object), and extracts the parity flag and the corresponding position code. When the TC belongs to [9, 18], it parses the barometric altitude; when it belongs to [20, 22], it parses the GNSS altitude. The extracted data is stored in the variable `adsblonlat` according to the capture time, ICAO, altitude, CPR flag, and parity position encoding format. If TC is 19, speed, vertical speed, and heading are parsed. The speed message parsing result is stored in the variable `speed` according to the capture time, ICAO, speed, vertical speed, and heading format. When TC is 31, NACCp is parsed. The NACCp message parsing result is stored in the variable `adsbnacp` according to the capture time, ICAO, and NACCp format. This process is repeated line by line until `adsbinfo` is completely read. `adsblonlat` is first sorted in ascending order according to ICAO and then passed to the function `weizhijiexi`. This function has two main steps: global decoding and local decoding. The decoding process is based on the parity position reports in paired messages, meaning that each pair of messages should come from the same aircraft, have different parity flags, and the timestamps of the two messages should differ by no more than 10 seconds. In the global decoding stage, the function searches for a pair of parity messages in the dataset to initially determine the aircraft's approximate position. Two messages with the same ICAO address but different parity flags, and whose timestamps differ by no more than 10 seconds, are considered a valid message pair and can be used to perform global decoding. Once such a message pair is found, the `lonlatDncoder_Global` function is called to decode the aircraft's location.

[0072] If global decoding is successful, record the decoded location and the relevant aircraft ICAO address. This information will be used for subsequent local decoding. Next, remove the decoded messages from the dataset to reduce the dataset size.

[0073] Then, the local decoding phase begins. The function searches forward and backward in the dataset for messages that match the saved ICAO addresses and for unresolved messages. This step uses the reference position obtained in the previous global decoding phase as a base point and performs local decoding (lonlatDncoder_local) on each message found.

[0074] If local decoding is successful, the position information is added to decoded_positions, and the relevant message is removed from the dataset. If local decoding fails, or the message's ICAO address does not match the previously recorded one, it indicates that it is necessary to return to the global decoding step and start a new round of decoding.

[0075] The function will continue to execute this process until there are no more usable pairs of parity messages in the dataset. When there are no more valid pairs of messages in the dataset, the function stops, prints the message "Data parsing complete", assigns the undecoded data to remaining_data, and returns it.

[0076] Step 202: Preprocess the parsed data based on the preprocessing rules to obtain preprocessed data.

[0077] In practical applications, the data preprocessing module includes data classification, data removal, and data integration.

[0078] Specifically, the data preprocessing module receives and processes the parsed data, and then passes the initial data accumulation task (after one second) to the data quality assessment module for evaluation. If the assessment module evaluates the data quality and it passes, it sends a command to start the trajectory prediction and trajectory output module. If it fails, it returns a command to the preprocessing module, which then sends the next initial data accumulation task (after one second).

[0079] In one possible implementation, the parsed data is preprocessed based on preprocessing rules to obtain preprocessed data, including: determining data integration rules and data removal rules based on the preprocessing rules; integrating the parsed data based on the data integration rules to determine integrated data; and removing data from the integrated data based on the data removal rules to obtain preprocessed data.

[0080] In practical applications, the data preprocessing module first categorizes the parsed messages into three types: location messages, velocity messages, and NACp messages. Before data integration, each type of data undergoes a deduplication process according to specific rules. The deduplicated location, velocity, and NACp messages are then integrated, resulting in data including time, ICAO, altitude, latitude, longitude, velocity, vertical velocity, heading, and NACp. First, the ICAO sequence is retrieved from the three message types and duplicates are removed to obtain a unique ICAO sequence. Starting from the first ICAO in the sequence, the module iterates through the three message types, filling in the data according to time. Messages with the same time are merged into a single data entry, messages with different times are filled into their corresponding positions, and empty positions are left blank. This process continues until the ICAO sequence is fully iterated. The integrated data is then sorted in ascending order by ICAO, and data with the same ICAO are sorted in ascending order by time. After integration, duplicate data is removed, as well as data based on altitude and velocity conditions.

[0081] Specifically, after parsing, position, velocity, and other data are integrated. Duplicate waypoints, such as repeated 3D position points or repeated time points, can cause calculation errors. Therefore, duplicate data must be identified and deleted, and all waypoints must be traversed. The ADS-B position update frequency is 0.4–0.6 seconds; therefore, a minimum ADS-B position update interval of 0.4 seconds is required. If the time interval between consecutive messages is less than 0.4 seconds, there is reason to believe that the positions in these two messages may be the same. In parsing real data, the interval can be extended to one second. Data within the same whole second is almost always repeated and can be discarded, retaining only one instance.

[0082] Data for flights whose flight altitude consistently falls below a certain level must be removed. ADS-B may contain inaccurate or missing data at low and very low altitudes. To achieve accurate track prediction, inaccurate data must be removed before processing. This project requires removing data for all flights whose trackpoints are below 500m.

[0083] When civilian aircraft approach or exceed the speed of sound, they may encounter several problems, such as changes in aerodynamic effects, aerodynamic heating, and flight control stability. To ensure the safety and stability of aircraft flight, civilian aircraft generally adhere to speed limits to avoid exceeding the speed of sound.

[0084] Furthermore, for military aircraft, speed limits are usually more extensive, generally not exceeding 3200 km / h.

[0085] To improve the accuracy of the prediction, messages with significantly abnormal speeds, i.e., speeds greater than 1700 kt, are removed.

[0086] Based on the satellite coverage area, compare whether the aircraft's location is within the satellite coverage area. If ADS-B message data is received even though the aircraft is not within the satellite coverage area, it indicates that the parsing may be incorrect, and the message is discarded.

[0087] Step 203: Perform a quality assessment on the preprocessed data and determine the assessment results.

[0088] In practical applications, the data quality assessment module includes message update frequency assessment, navigation integrity assessment, and error assessment.

[0089] Specifically, the data quality assessment module receives data from the data preprocessing module, assesses the data, and sends a yes or no command. If yes, the command is sent to the trajectory prediction module to start trajectory prediction; if no, the command is sent to the data preprocessing module to read the next initial data accumulation task after the data preprocessing module has accumulated data.

[0090] In one possible implementation, the preprocessed data is quality-assessed, and the assessment result is determined, including: determining constraints and corresponding data volume thresholds; statistically analyzing at least one data point in the preprocessed data to determine the data volume; if the data volume exceeds the data volume threshold, determining update frequency information based on the preprocessed data; and determining the assessment result based on the update frequency information.

[0091] In practical applications, in order to reduce trajectory prediction errors, the data is evaluated before prediction. Reasonable constraints are set by using the trajectory prediction algorithm constraint boundary obtained from a large number of simulations. First, the amount of data of each ICAO at the current time is counted. For ICAOs with data amounts that meet the constraints, the update frequency of position information and velocity message in the data are calculated. If the constraints are met, prediction is performed. If the constraints are not met, the next second task is waited for re-evaluation.

[0092] Specifically, given the amount of data per second, a given second of data falls into three categories: 1) containing complete data for position, velocity, and NACCp; 2) lacking one or two types of data, with missing values ​​being null; and 3) containing no data at all. Because latitude, longitude, and altitude are interrelated during the parsing process, the parsing result is either all present or none present. To calculate the position update frequency, only the altitude data needs to be counted. The formula for calculating the position message update frequency s1 is:

[0093]

[0094] Where n1 is the position update amount in the given data, t end t0 represents the last second of the given data, and t0 represents the first second.

[0095] Similarly, for speed messages, only the amount of speed data in the speed message needs to be counted. The formula for calculating the update frequency s2 of the speed message is:

[0096]

[0097] Where n2 is the velocity update amount in the given data, t end t0 represents the last second of the given data, and t0 represents the first second.

[0098] If the location message update frequency and the speed message update frequency meet the constraints, proceed to the next task.

[0099] Step 204: Based on the evaluation results, predict the trajectory using preprocessed data.

[0100] In practical applications, the trajectory prediction and output module includes trajectory prediction and trajectory output. Before performing trajectory prediction and output, the existing data needs to be supplemented with missing data using piecewise linear interpolation. The trajectory prediction module will predict the aircraft's position and speed information for at least 20 seconds based on the supplemented data. The supplemented data is marked as 0, the predicted data is marked as 1, and the unmarked data is the real data. All data is stored in the trajectory data table in the database. The trajectory output module outputs the current time and the predicted aircraft trajectory data for at least 20 seconds as required. As the parsed data is updated, the real data will replace the supplemented data and predicted data in the trajectory data table. The predicted trajectory will continue to be predicted, and the predicted data is stored in the trajectory data table in the database.

[0101] In one possible implementation, trajectory prediction is performed based on the evaluation results using preprocessed data, including: if the evaluation results are satisfactory, interpolating the preprocessed data to determine interpolated data; and predicting the trajectory for a set time period based on the interpolated data.

[0102] Specifically, before the trajectory prediction and output modules are executed, the existing data needs to be supplemented with missing data using piecewise linear interpolation. The trajectory prediction module will predict the aircraft's position and speed information for at least 20 seconds based on the supplemented data. All data is stored in the trajectory data table in the database. The trajectory output module outputs the current time and the predicted aircraft trajectory data for at least 20 seconds as required, and outputs position and speed information in the data frame format according to technical requirements. If there is no real data at the current time, interpolated data is output. As the parsed data is updated, the real data will replace the supplemented data and predicted data in the trajectory data table. The trajectory prediction will also continue, and the predicted data is stored in the trajectory data table in the database.

[0103] Before trajectory prediction, piecewise linear interpolation is needed to complete the data, including latitude, longitude, altitude, speed, vertical speed, and heading. First, it's confirmed that the data sequence is arranged chronologically. Since the data preprocessing module has already sorted the data, re-sorting is unnecessary in this module. Based on the time series, the data is segmented into 5-second intervals. Within each adjacent interval, the missing data point t3 is retrieved. Linear interpolation is possible only if each segment contains at least 2 seconds of data. If a segment contains less than 2 seconds of data, it is expanded, and the data is added to the adjacent segment. This process continues until the linear interpolation condition is met. Then, based on the known data points, a linear function is used to estimate the value of the missing points. The calculation formulas for each data point are as follows:

[0104] lat3=lat1+(lat2-lat1)*(t3-t1) / (t2-t1)

[0105] lon3=lon1+(lon2-lon1)*(t3-t1) / (t2-t1)

[0106] alt3=alt1+(alt2-alt1)*(t3-t1) / (t2-t1)

[0107] spd3=spd1+(spd2-spd1)*(t3-t1) / (t2-t1)

[0108] vspd3=vspd1+(vspd2-vspd1)*(t3-t1) / (t2-t1)

[0109] hed3=hed1+(hed2-hed1)*(t3-t1) / (t2-t1)

[0110] Where (t1, lat1), (t2, lat2), (t1, lon1), (t2, lon2), (t1, alt1), (t2, alt2), (t1, spd1), (t2, spd2), (t1, vspd1), (t2, vspd2), (t1, hed1), and (t2, hed2) are known data points within the interval, representing latitude, longitude, altitude, speed, vertical velocity, and heading, respectively. t3 is the time to be interpolated, and t3 only needs to be within the segmented interval, not necessarily between (t1, t2). The missing data can be calculated using the formula.

[0111] In one possible implementation, trajectory prediction for a set time period based on interpolated data includes: sampling based on interpolated data, determining sampling time points, and extracting speed and heading data corresponding to the sampling time points; normalizing the sampling time points and constructing a time matrix; performing least squares calculations on the speed and heading data based on the time matrix to determine the least squares coefficient estimation vector; and predicting the trajectory for the set time period based on the least squares coefficient estimation vector using a distance calculation formula.

[0112] Specifically, after calculating the interpolation results for each segment, the interpolation results for each time interval are merged into a complete data sequence, and it is checked whether all missing values ​​have been filled. If there are still missing values, interpolation will continue to complete the data.

[0113] Speed ​​prediction based on least squares

[0114] For a set of observation data Interpolation methods are used to obtain continuous time-series data and estimate key physical quantities. Specifically, the estimation of velocity (SPD), vertical velocity (V_SPD), and heading (HED) is the focus.

[0115] First, extract the sampling time points t∈{t1,t2,…,t N The corresponding velocity, vertical velocity, and heading data are represented as vectors spd, v_spd, and hed, respectively. During the calculation, the large time values ​​can lead to inaccuracies in the least squares coefficients. Therefore, time must first be normalized to ensure the accuracy of the least squares calculation and to reflect the chronological order of events. The normalization formula is:

[0116]

[0117] Where floor is the floor function, t is the time series, and t1 is the first time point.

[0118] Constructing a design matrix The first column is a vector of all 1s, and the second column is the time vector t:

[0119]

[0120] For each physical quantity, calculate its linear least squares solution. To find the best linear fit:

[0121]

[0122]

[0123]

[0124] here and These are the least squares coefficient estimation vectors for velocity, vertical velocity, and heading, respectively.

[0125] In one possible implementation, trajectory prediction for a set time period is performed based on the least squares coefficient estimation vector and the distance calculation formula, including: determining the extrapolation time; determining the predicted speed data and predicted heading data for the set time period based on the least squares coefficient estimation vector and the extrapolation time; determining the radian data; determining the latitude and longitude prediction data based on the radian data, the predicted speed data, and the predicted heading data; and performing radian conversion based on the latitude and longitude prediction data to determine the predicted position.

[0126] Finally, the extrapolation time interval (t) is determined. N+1 ,t N+2 ,…,t N+50 For each time point t in this time interval. j Calculate the corresponding predicted values ​​for velocity, vertical velocity, and heading:

[0127]

[0128]

[0129]

[0130] Where A extrap It is a design matrix constructed at the extrapolation time point.

[0131] Furthermore, the position prediction based on the Haversine formula is as follows.

[0132] Based on spherical trigonometry, this method is used to calculate the latitude and longitude of a point on a great circle route between two points. First, using the current time's data (latitude, altitude, speed, vertical speed, and heading), the Haversine formula and an improved distance calculation formula are used to calculate the predicted latitude, longitude, and altitude for the 1st second. Then, using the calculated latitude, longitude, and altitude, and the speed, heading, and vertical speed predicted in (2) for the corresponding time, the latitude, longitude, and altitude for the next second are calculated. This process is repeated until 20 seconds of data are obtained, which is the predicted data. The formula uses sine and cosine functions, as well as arcsine and inverse cosine functions, to calculate the latitude and longitude of the next point. This formula considers the curved surface characteristics of a sphere, allowing for more accurate calculation of the route between two points; the vertical direction is not considered. During calculation, latitude and longitude are first converted to radians using the following formula:

[0133]

[0134] Where φ1 is latitude, This refers to the radians corresponding to latitude.

[0135]

[0136] Where λ1 is longitude, This represents the radians corresponding to longitude.

[0137] Calculate the distance D traveled within time t:

[0138]

[0139] Where t represents the time interval, which is set to one second here, v is the aircraft speed at the corresponding time in kt, and D is in nautical miles.

[0140] The formula for calculating the latitude and longitude of the next second is:

[0141]

[0142]

[0143]

[0144] Convert radians to degrees:

[0145]

[0146]

[0147] z t =z0+v T t

[0148] Where (λ1, φ1, z0) represents the initial position, λ1 represents longitude in degrees, φ1 represents latitude in degrees, z0 represents altitude in feet per minute, t represents the time interval (set to one second here), and v T The vertical velocity is expressed in feet per minute, θ is the aircraft's heading angle, and R represents the Earth's radius of 3440 nautical miles.

[0149] See Figure 3 , 4 Figures 5 and 6 represent height comparison analysis, trajectory comparison analysis, and error comparison analysis, respectively; from... Figure 3 As can be seen, after data interpolation, the obtained height is consistent with the actual height, and the data is more stable. Figure 4 The predicted trajectory is consistent with the actual trajectory, and the data is stable. Figure 5 As can be seen, the vertical error can be controlled within 50 meters, and the horizontal error can be controlled within 100 meters.

[0150] This specification provides a satellite-based ADS-B trajectory prediction method and apparatus. The satellite-based ADS-B trajectory prediction method includes: acquiring initial data; parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing quality assessment on the preprocessed data to determine the assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data. By acquiring initial data, parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing quality assessment on the preprocessed data to determine the assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data, the accuracy and stability of trajectory prediction can be improved.

[0151] Corresponding to the above method embodiments, this specification also provides an embodiment of a satellite-based ADS-B trajectory prediction device. Figure 6 A schematic diagram of a satellite-based ADS-B trajectory prediction device according to one embodiment of this specification is shown. Figure 6 As shown, the device includes:

[0152] The data parsing module 601 is configured to acquire initial data and parse the initial data based on a parsing strategy to determine the parsed data; wherein, the initial data includes ADS-B messages;

[0153] Data processing module 602 is configured to preprocess the parsed data based on preprocessing rules to obtain preprocessed data;

[0154] Data evaluation module 603 is configured to perform quality evaluation on preprocessed data and determine the evaluation results;

[0155] The trajectory prediction module 604 is configured to predict trajectories based on the evaluation results and using preprocessed data.

[0156] In one possible implementation, the data parsing module 601 is further configured as follows:

[0157] Extract message capture time and ADS-B messages from the initial data at set time intervals;

[0158] Variable data is determined based on parsing strategy, message capture time, and ADS-B message;

[0159] Determine initial information by globally decoding based on variable data;

[0160] The parsed data is determined by local decoding based on the initial information.

[0161] In one possible implementation, the data processing module 602 is further configured as follows:

[0162] Data integration and data removal rules are determined based on preprocessing rules;

[0163] The parsed data is integrated based on data integration rules to determine the integrated data;

[0164] Based on data removal rules, the integrated data is removed to obtain preprocessed data.

[0165] In one possible implementation, the data evaluation module 603 is further configured as follows:

[0166] Determine the constraints and the corresponding data volume thresholds;

[0167] Perform statistics on at least one data point in the preprocessed data to determine the data volume;

[0168] When the amount of data exceeds the data volume threshold, the update frequency information is determined based on the preprocessed data;

[0169] The evaluation results are determined based on the update frequency information.

[0170] In one possible implementation, the trajectory prediction module 604 is further configured as follows:

[0171] If the evaluation result is satisfactory, the preprocessed data is interpolated to determine the interpolated data;

[0172] Predict flight paths over a set time period based on interpolated data.

[0173] In one possible implementation, the trajectory prediction module 604 is further configured as follows:

[0174] Sampling is performed based on interpolated data to determine the sampling time point, and the speed and heading data corresponding to the sampling time point are extracted;

[0175] Normalize the sampling time points and construct a time matrix;

[0176] Least square calculations are performed on velocity and heading data based on the time matrix to determine the least squares coefficient estimation vector;

[0177] Based on the least squares coefficient estimation vector, the trajectory is predicted for a set time period using the distance calculation formula.

[0178] In one possible implementation, the trajectory prediction module 604 is further configured as follows:

[0179] Determine the extrapolation time, and based on the least squares coefficient estimation vector and the extrapolation time, determine the predicted speed data and predicted heading data for a set time period;

[0180] Determine the radian data, and based on the radian data, predicted speed data, and predicted heading data, determine the latitude and longitude prediction data;

[0181] The predicted location is determined by converting latitude and longitude prediction data into radians.

[0182] This specification provides a satellite-based ADS-B trajectory prediction method and apparatus. The satellite-based ADS-B trajectory prediction apparatus includes: acquiring initial data; parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing a quality assessment on the preprocessed data to determine an assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data. By acquiring initial data, parsing the initial data based on a parsing strategy to determine parsed data; wherein the initial data includes ADS-B messages; preprocessing the parsed data based on preprocessing rules to obtain preprocessed data; performing a quality assessment on the preprocessed data to determine an assessment result; and performing trajectory prediction based on the assessment result using the preprocessed data, the accuracy and stability of trajectory prediction can be improved.

[0183] The above is a schematic scheme of a satellite-based ADS-B trajectory prediction device according to this embodiment. It should be noted that the technical solution of this satellite-based ADS-B trajectory prediction device and the technical solution of the aforementioned satellite-based ADS-B trajectory prediction method belong to the same concept. Details not described in detail in the technical solution of the satellite-based ADS-B trajectory prediction device can be found in the description of the technical solution of the aforementioned satellite-based ADS-B trajectory prediction method.

[0184] Figure 7 A structural block diagram of a computing device 700 according to one embodiment of this specification is shown. The components of the computing device 700 include, but are not limited to, a memory 710 and a processor 720. The processor 720 is connected to the memory 710 via a bus 730, and a database 750 is used to store data.

[0185] The computing device 700 also includes an access device 740, which enables the computing device 700 to communicate via one or more networks 760. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 740 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0186] In one embodiment of this specification, the above-described components of the computing device 700 and Figure 7 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 7 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0187] The computing device 700 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 700 can also be a mobile or stationary server.

[0188] The processor 720 executes the following computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned satellite-based ADS-B trajectory prediction method. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned satellite-based ADS-B trajectory prediction method belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned satellite-based ADS-B trajectory prediction method.

[0189] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described satellite-based ADS-B trajectory prediction method.

[0190] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the satellite-based ADS-B trajectory prediction method described above. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the satellite-based ADS-B trajectory prediction method described above.

[0191] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described satellite-based ADS-B trajectory prediction method.

[0192] The above is an illustrative example of a computer program according to this embodiment. It should be noted that the technical solution of this computer program belongs to the same concept as the technical solution of the aforementioned satellite-based ADS-B trajectory prediction method. Details not described in detail in the computer program's technical solution can be found in the description of the aforementioned satellite-based ADS-B trajectory prediction method.

[0193] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0194] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0195] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0196] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0197] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. A satellite-based ADS-B trajectory prediction method, characterized in that, include: Obtain initial data, and parse the initial data based on the parsing strategy to determine the parsed data; wherein, the initial data includes ADS-B messages; The parsed data is preprocessed based on the preprocessing rules to obtain preprocessed data; The preprocessed data is subjected to quality assessment, and the assessment results are determined. Based on the evaluation results, trajectory prediction is performed using the preprocessed data; The preprocessing of the parsed data based on preprocessing rules yields preprocessed data, including: Based on the preprocessing rules, data integration rules and data removal rules are determined; The parsed data is integrated based on the data integration rules to determine the integrated data; Based on the data removal rules, the integrated data is removed to obtain preprocessed data; The step of performing a quality assessment on the preprocessed data and determining the assessment result includes: Determine the constraints and the corresponding data volume thresholds; At least one data point in the preprocessed data is statistically analyzed to determine the data volume; If the amount of data is greater than the data volume threshold, update frequency information is determined based on the preprocessed data; The evaluation result is determined based on the update frequency information; The step of predicting the trajectory based on the evaluation results and the preprocessed data includes: If the evaluation result is satisfactory, the preprocessed data is interpolated to determine the interpolated data. Based on the interpolated data, predict the flight path for a set time period; The trajectory prediction based on the interpolated data for a set time period includes: Based on the interpolated data, sampling is performed to determine the sampling time point, and the speed data and heading data corresponding to the sampling time point are extracted; The sampling time points are normalized, and a time matrix is ​​constructed; Based on the time matrix, least squares calculations are performed on the velocity data and the heading data to determine the least squares coefficient estimation vector; Based on the least squares coefficient estimation vector, the trajectory is predicted for a set time period using the distance calculation formula.

2. The method according to claim 1, characterized in that, The step of parsing the initial data based on the parsing strategy to determine the parsed data includes: Extract message capture time and ADS-B messages from the initial data at set time intervals; Based on the parsing strategy, the message capture time, and the ADS-B message, variable data is determined. The initial information is determined by global decoding based on the variable data. Based on the initial information, local decoding is performed to determine the parsed data.

3. The method according to claim 1, characterized in that, Based on the least squares coefficient estimation vector, trajectory prediction for a set time period is performed using the distance calculation formula, including: Determine the extrapolation time, and based on the least squares coefficient estimation vector and the extrapolation time, determine the predicted speed data and predicted heading data for the set time period; Determine the radian data, and based on the radian data, the predicted speed data, and the predicted heading data, determine the latitude and longitude prediction data; Based on the latitude and longitude prediction data, radian conversion is performed to determine the predicted location.

4. A satellite-based ADS-B trajectory prediction device, implementing the steps of the satellite-based ADS-B trajectory prediction method according to any one of claims 1 to 3, characterized in that, include: The data parsing module is configured to acquire initial data and parse the initial data based on a parsing strategy to determine parsed data; wherein, the initial data includes ADS-B messages; The data processing module is configured to preprocess the parsed data based on preprocessing rules to obtain preprocessed data; The data evaluation module is configured to perform a quality evaluation on the preprocessed data and determine the evaluation result; The trajectory prediction module is configured to predict trajectories based on the evaluation results and the preprocessed data.

5. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the satellite-based ADS-B trajectory prediction method according to any one of claims 1 to 3.

6. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the satellite-based ADS-B trajectory prediction method according to any one of claims 1 to 3.

Images