Aircraft flight mode identification method and system based on air monitoring system

Abstract

The invention discloses an aircraft flight mode identification method and system based on an air monitoring system, and aims to realize calculation of an aircraft flight route by carrying out spot flight association on fused monitoring data, and realize estimation of a target state by carrying out state estimation on an aircraft flight path generated by spot flight association. The course change rate is obtained by performing course calculation on the target state, and the target state and the course change rate are integrated as the flight state of the target aircraft, so that the problem that an existing model lacks recognition processing on aircraft course and turning rate related modes is solved; meanwhile, according to the method, the flight mode is identified through a point navigation association and state estimation method, sample data or a preset flight model does not need to be trained in advance, and the situation that the flight mode of the aircraft is suddenly changed can be responded in real time, so that the real-time performance is improved; the defects of deep learning and neural network algorithms in the aspects of time complexity and real-time performance are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated air traffic control, and in particular to an aircraft flight mode recognition method and system based on an air surveillance system. Background Art

[0002] As the main means of surveillance for military and civil air traffic control, the basic principle of air traffic control primary radar is to illuminate aircraft by transmitting radio frequency electromagnetic waves and receiving their echoes, and obtain the target's distance, azimuth, radial velocity, echo amplitude and other information by analyzing the echo signals; the air traffic control secondary radar monitoring system is a radar system that locates aircraft equipped with airborne transponders through the interrogation of ground interrogators and the response of airborne transponders in the air. It obtains target flight information and its attributes based on the response signal of the secondary radar airborne transponder installed on the aircraft, and provides ground control personnel with aircraft flight status monitoring; broadcast automatic dependent surveillance generates accurate aircraft self-positioning information by the airborne satellite-based navigation and positioning system, and broadcasts automatic monitoring information periodically through specific data links and formats, and is received and processed by specific ground station equipment or airborne equipment of other aircraft, thereby obtaining accurate aircraft position and status information.

[0003] Generally speaking, primary air traffic control radar, secondary air traffic control radar and automatic dependent surveillance-broadcast (ADS) together form a common integrated air traffic monitoring system. The integrated air traffic monitoring system mainly monitors military and civil aircraft, and the monitored status information serves as a reference for command and control by ground commanders and onboard operators. The flight pattern recognition and analysis of aircraft is extremely important for controllers to analyze the flight intentions of aircraft and verify the flight status of aircraft.

[0004] At present, there are certain deficiencies in flight mode recognition technology, which are mainly reflected in the following aspects:

[0005] 1. The current model for flight mode recognition research and classification is incomplete and incomplete. The model lacks recognition and processing of aircraft heading and turn rate related patterns;

[0006] 2. The current flight model is mainly reflected in the flight process of fixed-wing manned aircraft. However, the flight status of UAVs is quite different from that of manned aircraft. The maneuverability of UAVs is more variable and the rate of change is faster. In this mode, the aircraft is required to actively provide flight data and flight mode. However, the aircraft cannot provide relevant data.

[0007] 3. Some studies have used deep learning, neural network algorithms and other methods to identify aircraft flight modes. However, this method requires pre-training sample data and preset flight models. However, there are various sudden changes in flight modes during the flight of the aircraft, and the preset flight model cannot cope with the above emergencies. At the same time, the time complexity of deep learning and neural network algorithms is high and the real-time performance is insufficient. Summary of the invention

[0008] Based on the problems raised by the above background technology, the purpose of the present invention is to provide an aircraft flight mode recognition method and system based on an aerial surveillance system, which solves the problems that the current model for flight mode recognition research and classification is incomplete and incomplete, the model lacks recognition and processing of aircraft heading and turning rate related patterns, and the aircraft has various sudden changes in flight mode during flight, and the preset flight model cannot cope with the emergency.

[0009] The present invention is achieved through the following technical solutions:

[0010] A first aspect of the present invention provides an aircraft flight mode recognition method based on an air surveillance system, comprising the following steps:

[0011] Acquire surveillance data of the surveillance airspace, and pre-process the surveillance data;

[0012] Performing data fusion on the preprocessed monitoring data to generate fused monitoring data;

[0013] Performing point-to-voyage association on the fused surveillance data, and performing state estimation based on the result of the point-to-voyage association to obtain a target state;

[0014] The target state is estimated in heading to obtain a heading change rate, and an aircraft mode is generated by combining the target state and the heading change rate.

[0015] In the above technical solution, the airspace is monitored jointly by the primary radar monitoring system, the secondary radar monitoring system, and the ADS-B system. The monitoring data of the monitored airspace is obtained from the above three systems, and the monitoring data is preprocessed. The monitoring data of the observation points that obviously do not meet the target characteristics are eliminated according to the target monitoring information. The monitoring data after preprocessing is fused to generate fused monitoring data. The above monitoring data does not rely on the data actively provided by the aircraft, but is obtained through an external monitoring system. In this way, even if the maneuverability of the drone is variable and the rate of change is fast, its flight status can be captured through the fusion of monitoring data, thereby solving the problem of large differences in the flight status of drones and manned aircraft. At the same time, obtaining data through three systems and performing data fusion overcomes the problem of the singleness of flight data.

[0016] By performing point-to-point association on the fused monitoring data, the calculation of the aircraft flight route is realized, and the state estimation of the aircraft track generated by the point-to-point association is performed to obtain the state information of the target aircraft, thereby realizing the estimation of the target state. By further calculating the heading of the target state, the heading change rate is obtained. The combined target state and heading change rate are the flight state of the target aircraft, and the flight state can be used to identify the flight mode of the aircraft. This step solves the problem that the existing model lacks recognition and processing of aircraft heading and turning rate related patterns; at the same time, the method identifies the flight mode through the method of point-to-point association and state estimation, does not require pre-training sample data or preset flight models, and can respond to the sudden change of the aircraft's flight mode in real time, thereby improving real-time performance and solving the shortcomings of deep learning and neural network algorithms in terms of time complexity and real-time performance.

[0017] In an optional embodiment, preprocessing the monitoring data includes:

[0018] Determine the reference site center, and transform the coordinates of the monitoring data to the reference site center;

[0019] The time of the monitoring data is unified to the time of the reference site center, and time deviation compensation is performed on the unified time of the monitoring data.

[0020] In an optional embodiment, data fusion is performed on the pre-processed monitoring data, including:

[0021] Extracting distance information, angle information and height information from the preprocessed surveillance data;

[0022] The distance information includes a data source distance observation result and a distance precision variance, and a weighted average calculation is performed on the data source distance observation result and the distance precision variance to obtain a fused distance;

[0023] The angle information includes the data source angle observation structure and the angle precision variance, and the data source angle observation result and the angle precision variance are calculated using the forward and reverse tangent functions to obtain the fused angle;

[0024] The height information includes a data source height observation result and a height accuracy variance. A weighted average calculation is performed on the data source height observation result and the height accuracy variance to obtain fused height information.

[0025] In an optional embodiment, performing point-to-point navigation association on the fused surveillance data includes:

[0026] Using the observation node that enters the associated wave gate in the fused surveillance data as the starting track hypothesis to create a hypothesis node;

[0027] Calculating the normalized distance of the hypothesis node through covariance, and taking the hypothesis node whose normalized distance is within the set wave gate as a candidate hypothesis node;

[0028] Traversing the candidate hypothesis nodes, using an improved multi-hypothesis tracking algorithm to perform point-to-navigation association on the candidate hypothesis nodes, and updating the candidate hypothesis nodes according to the point-to-navigation association results;

[0029] Perform node quality assessment on the updated candidate hypothesis nodes and determine the current track target based on the node quality assessment results.

[0030] In an optional embodiment, state estimation is performed based on the result of point navigation association, including: using an interactive multiple model algorithm to perform track state estimation on the current track target to obtain a target state; wherein the target state includes a horizontal direction state and a vertical direction state;

[0031] The horizontal state includes information describing the position, velocity and acceleration in the horizontal direction; wherein the velocity in the horizontal direction is used for heading estimation;

[0032] The vertical state includes information describing the position, velocity and acceleration in the vertical direction.

[0033] In an optional embodiment, using an interacting multiple model algorithm to estimate the track state of the current track target includes:

[0034] Constructing a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model;

[0035] Initializing the model probability and transition probability of the target estimation model;

[0036] Perform model interaction on the initialized target estimation model to obtain the model interaction state, model covariance matrix and model interaction probability;

[0037] Using Kalman filtering to filter the model interaction state and covariance matrix to obtain filtered information and covariance corresponding to the filtered information;

[0038] The model interaction probability is updated using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability;

[0039] Updating the target estimation model using the update probability to obtain an updated target estimation model;

[0040] The updated target estimation model is used to estimate the track state of the current track target to obtain the target state.

[0041] A second aspect of the present invention provides an aircraft flight mode recognition system based on an air surveillance system, comprising:

[0042] A preprocessing module, used to obtain the surveillance data of the surveillance airspace and preprocess the surveillance data;

[0043] A data fusion module is used to fuse the pre-processed monitoring data to generate fused monitoring data;

[0044] A state estimation module, used for performing point-to-point association on the fused monitoring data, and performing state estimation based on the result of the point-to-point association to obtain a target state;

[0045] The heading estimation module is used to estimate the heading of the target state, obtain the heading change rate, and generate an aircraft mode by combining the target state and the heading change rate.

[0046] In an optional embodiment, the preprocessing module includes:

[0047] A coordinate conversion unit, used to determine the center of the reference site and convert the coordinates of the monitoring data to the center of the reference site;

[0048] The time unification unit is used to unify the time of the monitoring data to the time of the reference site center and to perform time deviation compensation on the unified monitoring data.

[0049] In an optional embodiment, the data fusion module includes:

[0050] A data extraction unit, used to extract distance information, angle information and height information from the pre-processed monitoring data;

[0051] A distance fusion unit, used for performing weighted average calculation on the data source distance observation result and the distance accuracy variance when the distance information includes the data source distance observation result and the distance accuracy variance, so as to obtain a fused distance;

[0052] An angle fusion unit, used for calculating the angle information including the data source angle observation structure and the angle precision variance using the forward and reverse tangent functions on the data source angle observation result and the angle precision variance to obtain a fused angle;

[0053] The height fusion unit is used for performing weighted average calculation on the height observation result of the data source and the height accuracy variance to obtain the fused height information.

[0054] In an optional embodiment, the state estimation module includes:

[0055] A model building unit, used to build a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model;

[0056] An initialization unit, used to initialize the model probability and transition probability of the target estimation model;

[0057] An interaction unit, used to perform model interaction on the initialized target estimation model to obtain a model interaction state, a model covariance matrix, and a model interaction probability;

[0058] A filtering unit, used to filter the model interaction state and covariance matrix using Kalman filtering to obtain filtering information and covariance corresponding to the filtering information;

[0059] A probability updating unit, used to update the model interaction probability by using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability;

[0060] A model updating unit, configured to update the target estimation model using the update probability to obtain an updated target estimation model;

[0061] The target state estimation unit is used to use the updated target estimation model to perform track state estimation on the current track target to obtain a target state.

[0062] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0063] 1. By calculating the heading of the target state, the heading change rate is obtained. The combined target state and heading change rate are the flight state of the target aircraft, which solves the problem that the existing model lacks recognition and processing of the aircraft heading and turning rate related patterns; at the same time;

[0064] 2. The flight mode is identified through point-to-flight association and state estimation methods. There is no need to pre-train sample data or preset flight models. It can respond to sudden changes in the flight mode of the aircraft in real time, thereby improving real-time performance and solving the shortcomings of deep learning and neural network algorithms in terms of time complexity and real-time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0066] Figure 1A schematic diagram of the structure of aircraft flight mode recognition provided by Embodiment 1 of the present invention;

[0067] Figure 2 A schematic diagram of the structure of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0068] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0069] Example 1

[0070] Figure 1 A schematic diagram of the structure of aircraft flight mode recognition provided by Embodiment 1 of the present invention, such as Figure 1 As shown, a method for identifying an aircraft flight mode based on an air surveillance system comprises the following steps:

[0071] Acquire surveillance data of the surveillance airspace, and pre-process the surveillance data;

[0072] Performing data fusion on the preprocessed monitoring data to generate fused monitoring data;

[0073] Performing point-to-voyage association on the fused surveillance data, and performing state estimation based on the result of the point-to-voyage association to obtain a target state;

[0074] The target state is estimated in heading to obtain a heading change rate, and an aircraft mode is generated by combining the target state and the heading change rate.

[0075] It should be noted that this method jointly monitors the airspace through the primary radar monitoring system, the secondary radar monitoring system, and the ADS-B system, obtains the monitoring data of the monitored airspace from the above three systems, pre-processes the monitoring data, and eliminates the monitoring data of the observation points that obviously do not meet the target characteristics according to the target monitoring information. And the monitoring data after preprocessing is fused to generate fused monitoring data. The above monitoring data does not rely on the data actively provided by the aircraft, but is obtained through an external monitoring system. In this way, even if the maneuverability of the drone is variable and the rate of change is fast, its flight status can be captured through the fusion of monitoring data, thereby solving the problem of large differences in the flight status of drones and manned aircraft. At the same time, obtaining data through three systems and performing data fusion overcomes the problem of the singleness of flight data.

[0076] By performing point-to-point association on the fused monitoring data, the calculation of the aircraft flight route is realized, and the state estimation of the aircraft track generated by the point-to-point association is performed to obtain the state information of the target aircraft, thereby realizing the estimation of the target state. By further calculating the heading of the target state, the heading change rate is obtained. The combined target state and heading change rate are the flight state of the target aircraft, and the flight state can be used to identify the flight mode of the aircraft. This step solves the problem that the existing model lacks recognition and processing of aircraft heading and turning rate related patterns; at the same time, the method identifies the flight mode through the method of point-to-point association and state estimation, does not require pre-training sample data or preset flight models, and can respond to the sudden change of the aircraft's flight mode in real time, thereby improving real-time performance and solving the shortcomings of deep learning and neural network algorithms in terms of time complexity and real-time performance.

[0077] In an optional embodiment, preprocessing the monitoring data includes:

[0078] Determine the reference site center, and transform the coordinates of the monitoring data to the reference site center;

[0079] The time of the monitoring data is unified to the time of the reference site center, and time deviation compensation is performed on the unified time of the monitoring data.

[0080] It should be noted that the preprocessing in this embodiment has two purposes: one is to perform time and space calibration on the target data received from multiple monitoring data sources; the other is to eliminate observation points that obviously do not meet the target characteristics based on the target monitoring information.

[0081] In an optional embodiment, data fusion is performed on the pre-processed monitoring data, including:

[0082] Extracting distance information, angle information and height information from the preprocessed surveillance data;

[0083] The distance information includes a data source distance observation result and a distance precision variance, and a weighted average calculation is performed on the data source distance observation result and the distance precision variance to obtain a fused distance;

[0084] The angle information includes the data source angle observation structure and the angle precision variance, and the data source angle observation result and the angle precision variance are calculated using the forward and reverse tangent functions to obtain the fused angle;

[0085] The height information includes a data source height observation result and a height accuracy variance. A weighted average calculation is performed on the data source height observation result and the height accuracy variance to obtain fused height information.

[0086] It should be noted that data fusion is the process of combining information from multiple data sources into a consistent, accurate, and useful information representation. In the embodiment of the present invention, the unique target information of each monitoring data source is retained, and (2) the common target information of each monitoring data source is fused.

[0087] In this embodiment, data fusion involves the fusion of distance, angle and altitude information. The fusion of distance, angle and altitude information is crucial for aircraft state estimation. Among them, for distance information, it can determine the distance between itself and surrounding objects or target points or the distance between the aircraft and specific landmarks or navigation points. At the same time, it is also used for subsequent aircraft speed estimation and heading estimation; for angle information, it can help identify the attitude of the aircraft, sense the direction of the aircraft in space, and be used for subsequent identification of the aircraft's turning, rolling and other actions; altitude information can be used to monitor the vertical movement of the aircraft, which is very important for the control of flight modes such as take-off, landing and hovering.

[0088] Specifically, the calculation formula for distance information fusion with k data sources is as follows:

[0089]

[0090] In the above formula, is the distance after fusion, r i is the observation result of the distance of the i-th data source, Represents the distance accuracy variance of the i-th data source observation.

[0091] Specifically, the calculation formula for angle information fusion with k data sources is as follows:

[0092]

[0093] In the above formula, is the angle after fusion, θ i is the observation result from the angle of the i-th data source, Represents the angular accuracy variance of the i-th data source observation.

[0094] Specifically, the calculation formula for high-level information fusion with k data sources is as follows:

[0095]

[0096] In the above formula, is the height after fusion, h i is the height observation result of the i-th data source, Represents the height accuracy variance of the i-th data source observation.

[0097] In an optional embodiment, performing point-to-point navigation association on the fused surveillance data includes:

[0098] Using the observation node that enters the associated wave gate in the fused surveillance data as the starting track hypothesis to create a hypothesis node;

[0099] Calculating the normalized distance of the hypothesis node through covariance, and taking the hypothesis node whose normalized distance is within the set wave gate as a candidate hypothesis node;

[0100] Traversing the candidate hypothesis nodes, using an improved multi-hypothesis tracking algorithm to perform point-to-navigation association on the candidate hypothesis nodes, and updating the candidate hypothesis nodes according to the point-to-navigation association results;

[0101] Perform node quality assessment on the updated candidate hypothesis nodes and determine the current track target based on the node quality assessment results.

[0102] It should be noted that this step corresponds to Figure 1 The track management in the process aims to realize point-to-point association by adopting an improved multi-hypothesis tracking algorithm. Among them, the gate is a threshold used to determine whether an observation value matches multiple tracks, thereby avoiding erroneous updates. It plays a key role in multi-target track association and helps determine whether an observation value is associated with a specific track. In this embodiment, the association gate refers to the gate threshold of the track match. All observation points that enter the association gate, that is, within the gate threshold, are regarded as hypotheses of the started track, and hypothesis nodes are created for updating. When performing the association, an improved nearest neighbor algorithm is used for target association.

[0103] The normalized distance is calculated by the target prediction's innovation and covariance. Considering the influence of target measurement noise, the target with normalized distance within the set wave gate becomes a candidate hypothesis. Among them, the innovation of the target is a key concept, which represents the difference between the actual observation value and the predicted observation value. The innovation is an intermediate variable in the filtering process, which is used to update the state estimate and covariance matrix of the filter.

[0104] Traverse all the hypothesis nodes of all existing targets for association update, and delete nodes according to the filtering status during the target hypothesis node update process. Node quality evaluation is performed through the continuous filtering results of each observation node of the target, and the most likely hypothesis is selected as the update result of the current track target according to the evaluation score.

[0105] Furthermore, this embodiment adopts the mn logic criterion for track initiation and track termination. Specifically, in the m observation windows, if there are n observations that meet the conditions, the track can be started; in the m observation windows, if there are n observations that do not meet the conditions, the track can be terminated.

[0106] In an optional embodiment, state estimation is performed based on the result of point navigation association, including: using an interactive multiple model algorithm to perform track state estimation on the current track target to obtain a target state; wherein the target state includes a horizontal direction state and a vertical direction state;

[0107] The horizontal state includes information describing the position, velocity and acceleration in the horizontal direction; wherein the velocity in the horizontal direction is used for heading estimation;

[0108] The vertical state includes information describing the position, velocity and acceleration in the vertical direction.

[0109] It should be noted that the state estimation is divided into horizontal plane and vertical direction.<x,Vx,Ax,y,Vy,Ay> Describes the horizontal position, velocity, and acceleration information, and the vertical<z,Vz,Az> Describes the vertical position, velocity, and acceleration information.

[0110] Among them, the states of the target heading and the turning rate are added in the embodiment itself. Specifically, the heading is estimated by the information of Vx and Vy of the target, and the heading change rate is obtained by continuous differentiation of the heading estimation.

[0111] In an optional embodiment, using an interacting multiple model algorithm to estimate the track state of the current track target includes:

[0112] Constructing a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model;

[0113] Initializing the model probability and transition probability of the target estimation model;

[0114] Perform model interaction on the initialized target estimation model to obtain the model interaction state, model covariance matrix and model interaction probability;

[0115] Using Kalman filtering to filter the model interaction state and covariance matrix to obtain filtered information and covariance corresponding to the filtered information;

[0116] The model interaction probability is updated using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability;

[0117] Updating the target estimation model using the update probability to obtain an updated target estimation model;

[0118] The updated target estimation model is used to estimate the track state of the current track target to obtain the target state.

[0119] Specifically, the calculation process of the model interaction state is as follows:

[0120]

[0121] In the above formula, is the state estimate of the jth model at time k, u k-∥k-1 (i|j) is the transition probability from the i-th model to the j-th model, and N is the total number of models.

[0122] Specifically, the model covariance matrix calculation process is as follows:

[0123]

[0124] In the above formula, is the covariance matrix of the jth model at time k-1.

[0125] Specifically, the model interaction probability calculation process is as follows:

[0126]

[0127]

[0128] In the above formula, is the transition probability of the i-th sub-model to the j-th sub-model at the next moment; u k-1 (i) is the probability of the i-th sub-model at time k-1; is the normalization factor.

[0129] Wherein, Kalman filtering is used to filter the model interaction state and covariance matrix, including:

[0130] State transfer: X k =F k X k-1 +B k u k +w k

[0131] Covariance prediction: P k =F k P k-1 F k ′ +Q k

[0132] Filter gain: K k =P k H ′ k (H k P k H ′ k +R k ) -1

[0133] Status Update:

[0134] Covariance update: P k =(IK k H k ) k|k-1

[0135] The model interaction probability is updated using the filtered new information and the covariance corresponding to the filtered new information, including calculating the likelihood function of the model, the filtered new information and the covariance corresponding to the new information, wherein the calculation is as follows:

[0136] The likelihood function of the model is:

[0137] Filter innovation of the model:

[0138] Covariance corresponding to the filtered information:

[0139] Model probability update: in

[0140] In the above formula, is the likelihood function of the jth model at time k, indicating the matching degree of the observed data under the model; m is the dimension of the observation vector; is the determinant of the information covariance of the jth model at time k; is the new information of the j-th sub-model at time k, indicating the difference between the observed value and the predicted value; is the information covariance of the jth model at time k; H j (k) is the observation matrix of the jth model at time k, which is used to map the state space to the observation space; R(k) is the observation noise covariance at time k.

[0141] The target estimation model is updated using the update probability, including integrating the states of each model and calculating the covariance matrix of each model. The calculation process is as follows:

[0142] Comprehensive model status:

[0143] The comprehensive model covariance matrix:

[0144]

[0145] Furthermore, the communication interface and communication protocol of the target data acquisition channel are configured and managed; the start / end criteria of the track management data, filter parameters, and multi-model initialization parameters are configured and managed. Statistics are collected on the processing status of the entire system to manage the processing load. If the system processing capacity is exceeded, the long-distance target is automatically excluded, and the system load management is adaptively performed;

[0146] The display terminal displays the original target information received from each data source; and displays the target and its mode information after state estimation and mode analysis.

[0147] Example 2

[0148] Embodiment 2 of the present invention provides an aircraft flight mode recognition system based on an air surveillance system, comprising:

[0149] A preprocessing module, used to obtain the surveillance data of the surveillance airspace and preprocess the surveillance data;

[0150] A data fusion module is used to fuse the pre-processed monitoring data to generate fused monitoring data;

[0151] A state estimation module, used for performing point-to-point association on the fused monitoring data, and performing state estimation based on the result of the point-to-point association to obtain a target state;

[0152] The heading estimation module is used to estimate the heading of the target state, obtain the heading change rate, and generate an aircraft mode by combining the target state and the heading change rate.

[0153] In an optional embodiment, the preprocessing module includes:

[0154] A coordinate conversion unit, used to determine the center of the reference site and convert the coordinates of the monitoring data to the center of the reference site;

[0155] The time unification unit is used to unify the time of the monitoring data to the time of the reference site center and to perform time deviation compensation on the unified monitoring data.

[0156] In an optional embodiment, the data fusion module includes:

[0157] A data extraction unit, used to extract distance information, angle information and height information from the pre-processed monitoring data;

[0158] A distance fusion unit, used for performing weighted average calculation on the data source distance observation result and the distance accuracy variance when the distance information includes the data source distance observation result and the distance accuracy variance, so as to obtain a fused distance;

[0159] An angle fusion unit, used for calculating the angle information including the data source angle observation structure and the angle precision variance using the forward and reverse tangent functions on the data source angle observation result and the angle precision variance to obtain a fused angle;

[0160] The height fusion unit is used for performing weighted average calculation on the height observation result of the data source and the height accuracy variance to obtain the fused height information.

[0161] In an optional embodiment, the state estimation module includes:

[0162] A model building unit, used to build a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model;

[0163] An initialization unit, used to initialize the model probability and transition probability of the target estimation model;

[0164] An interaction unit, used to perform model interaction on the initialized target estimation model to obtain a model interaction state, a model covariance matrix, and a model interaction probability;

[0165] A filtering unit, used to filter the model interaction state and covariance matrix using Kalman filtering to obtain filtering information and covariance corresponding to the filtering information;

[0166] A probability updating unit, used to update the model interaction probability by using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability;

[0167] A model updating unit, configured to update the target estimation model using the update probability to obtain an updated target estimation model;

[0168] The target state estimation unit is used to use the updated target estimation model to perform track state estimation on the current track target to obtain a target state.

[0169] Example 3

[0170] Figure 2 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention is shown in FIG. Figure 2 As shown, the electronic device includes a processor 21, a memory 22, an input device 23 and an output device 24; the number of processors 21 in the computer device can be one or more. Figure 2 A processor 21 is taken as an example; the processor 21, the memory 22, the input device 23 and the output device 24 in the electronic device can be connected by a bus or other means. Figure 2 The example of connecting through bus is taken in the following.

[0171] The memory 22 is a computer-readable storage medium that can be used to store software programs, computer executable programs, and modules. The processor 21 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 22, that is, implements the aircraft flight mode recognition method based on the air surveillance system of Example 1.

[0172] The memory 22 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 22 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 22 may further include a memory remotely arranged relative to the processor 21, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0173] The input device 23 can be used to receive the ID and password input by the user, etc. The output device 24 is used to output the network configuration page.

[0174] Example 4

[0175] Embodiment 4 of the present invention further provides a computer-readable storage medium, wherein the computer-executable instructions, when executed by a computer processor, are used to implement an aircraft flight mode recognition method based on an air surveillance system as provided in Embodiment 1.

[0176] A storage medium containing computer executable instructions provided in an embodiment of the present invention, wherein the computer executable instructions are not limited to the method operations provided in Example 1, but can also execute related operations in an aircraft flight mode recognition method based on an air surveillance system provided in any embodiment of the present invention.

[0177] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying aircraft flight modes based on an air surveillance system, characterized in that: The steps include: Acquire surveillance data of the surveillance airspace, and pre-process the surveillance data; Performing data fusion on the preprocessed monitoring data to generate fused monitoring data; Performing point-to-voyage association on the fused surveillance data, and performing state estimation based on the result of the point-to-voyage association to obtain a target state; The target state is estimated in heading to obtain a heading change rate, and an aircraft mode is generated by combining the target state and the heading change rate.

2. The method for identifying an aircraft flight mode based on an air surveillance system according to claim 1, characterized in that: Preprocessing the monitoring data includes: Determine the reference site center, and transform the coordinates of the monitoring data to the reference site center; The time of the monitoring data is unified to the time of the reference site center, and time deviation compensation is performed on the unified time of the monitoring data.

3. The method for identifying an aircraft flight mode based on an air surveillance system according to claim 1, characterized in that: The pre-processed monitoring data is fused, including: Extracting distance information, angle information and height information from the preprocessed surveillance data; The distance information includes a data source distance observation result and a distance precision variance, and a weighted average calculation is performed on the data source distance observation result and the distance precision variance to obtain a fused distance; The angle information includes the data source angle observation structure and the angle precision variance, and the data source angle observation result and the angle precision variance are calculated using the forward and reverse tangent functions to obtain the fused angle; The height information includes a data source height observation result and a height accuracy variance. A weighted average calculation is performed on the data source height observation result and the height accuracy variance to obtain fused height information.

4. The method for identifying an aircraft flight mode based on an air surveillance system according to claim 1, characterized in that: Performing point-to-navigation association on the fused surveillance data includes: Using the observation node that enters the associated wave gate in the fused surveillance data as the starting track hypothesis to create a hypothesis node; Calculating the normalized distance of the hypothesis node through covariance, and taking the hypothesis node whose normalized distance is within the set wave gate as a candidate hypothesis node; Traversing the candidate hypothesis nodes, using an improved multi-hypothesis tracking algorithm to perform point-to-navigation association on the candidate hypothesis nodes, and updating the candidate hypothesis nodes according to the point-to-navigation association results; Perform node quality assessment on the updated candidate hypothesis nodes and determine the current track target based on the node quality assessment results.

5. The method for identifying aircraft flight modes based on an air surveillance system according to claim 4, characterized in that: The state estimation is performed based on the result of the point navigation association, including: using an interactive multiple model algorithm to perform track state estimation on the current track target to obtain a target state; wherein the target state includes a horizontal direction state and a vertical direction state; The horizontal state includes information describing the position, velocity and acceleration in the horizontal direction; wherein the velocity in the horizontal direction is used for heading estimation; The vertical state includes information describing the position, velocity and acceleration in the vertical direction.

6. The method for identifying aircraft flight modes based on an air surveillance system according to claim 5, characterized in that: The interactive multiple model algorithm is used to estimate the track state of the current track target, including: Constructing a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model; Initializing the model probability and transition probability of the target estimation model; Perform model interaction on the initialized target estimation model to obtain the model interaction state, model covariance matrix and model interaction probability; Using Kalman filtering to filter the model interaction state and covariance matrix to obtain filtered information and covariance corresponding to the filtered information; The model interaction probability is updated using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability; Updating the target estimation model using the update probability to obtain an updated target estimation model; The updated target estimation model is used to estimate the track state of the current track target to obtain the target state.

7. An aircraft flight mode recognition system based on an air surveillance system, characterized in that: include: A preprocessing module, used to obtain the surveillance data of the surveillance airspace and preprocess the surveillance data; A data fusion module is used to fuse the pre-processed monitoring data to generate fused monitoring data; A state estimation module, used for performing point-to-point association on the fused monitoring data, and performing state estimation based on the result of the point-to-point association to obtain a target state; The heading estimation module is used to estimate the heading of the target state, obtain the heading change rate, and generate an aircraft mode by combining the target state and the heading change rate.

8. The aircraft flight mode recognition system based on the air surveillance system according to claim 7, characterized in that: The preprocessing module comprises: A coordinate conversion unit, used to determine the center of the reference site and convert the coordinates of the monitoring data to the center of the reference site; The time unification unit is used to unify the time of the monitoring data to the time of the reference site center and to perform time deviation compensation on the unified monitoring data.

9. The aircraft flight mode recognition system based on the air surveillance system according to claim 7, characterized in that: The data fusion module comprises: A data extraction unit, used to extract distance information, angle information and height information from the pre-processed monitoring data; A distance fusion unit, used for performing weighted average calculation on the data source distance observation result and the distance accuracy variance when the distance information includes the data source distance observation result and the distance accuracy variance, so as to obtain a fused distance; An angle fusion unit, used for calculating the angle information including the data source angle observation structure and the angle precision variance using the forward and reverse tangent functions on the data source angle observation result and the angle precision variance to obtain a fused angle; The height fusion unit is used for performing weighted average calculation on the height observation result of the data source and the height accuracy variance to obtain the fused height information.

10. The aircraft flight mode recognition system based on the air surveillance system according to claim 7, characterized in that: The state estimation module comprises: A model building unit, used to build a target estimation model; wherein the target estimation model includes a uniform speed model, a uniform acceleration model and a weak maneuvering model; An initialization unit, used to initialize the model probability and transition probability of the target estimation model; An interaction unit, used to perform model interaction on the initialized target estimation model to obtain a model interaction state, a model covariance matrix, and a model interaction probability; A filtering unit, used to filter the model interaction state and covariance matrix using Kalman filtering to obtain filtering information and covariance corresponding to the filtering information; A probability updating unit, used to update the model interaction probability by using the filtered new information and the covariance corresponding to the filtered new information to obtain an updated probability; A model updating unit, configured to update the target estimation model using the update probability to obtain an updated target estimation model; The target state estimation unit is used to use the updated target estimation model to perform track state estimation on the current track target to obtain a target state.

Images