CN113344093B - Multi-source ADS-B data abnormal time scale detection method and system - Google Patents
Multi-source ADS-B data abnormal time scale detection method and system Download PDFInfo
- Publication number
- CN113344093B CN113344093B CN202110685630.7A CN202110685630A CN113344093B CN 113344093 B CN113344093 B CN 113344093B CN 202110685630 A CN202110685630 A CN 202110685630A CN 113344093 B CN113344093 B CN 113344093B
- Authority
- CN
- China
- Prior art keywords
- ads
- ground station
- time
- sample
- time scale
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a multi-source ADS-B data abnormal time scale detection method, which comprises the following steps: collecting the site information of the ADS-B ground station; selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark samples of all the ADS-B ground stations; preprocessing the four-tuple information of the time scale sample; selecting training samples from the processed time scale samples to establish iTrees; traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree; calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula; and judging whether the time scale is abnormal or not according to the target abnormal score. The method realizes the detection of the abnormal time scale of the real-time dynamic target track in a large-scale airspace, can quickly and effectively identify the abnormal time scale data, and improves the accuracy of the detection of the abnormal time scale.
Description
Technical Field
The invention relates to the technical field of aviation control, in particular to a multi-source ADS-B data abnormal time scale detection method and system.
Background
An ADS-B Data Center system (ADS-B Data Center, ADC system for short) is used for leading ADS-B Data of an ADS-B ground station and a next ADS-B Data Center in a district, and providing ADS-B real-time comprehensive monitoring information for an air traffic control department in the district after ADS-B Data analysis, fusion, verification and the like; aiming at the areas where the Chinese and western radars are not fully covered, the ADS-B monitoring technology can solve the problem of 'invisible' and simultaneously enhance the reliability of control operation, reduce the risks of control error, forgetting and missing, improve the utilization rate of ADS-B data, improve the airspace capacity and improve the guarantee level of flight safety.
ADS-B data information is rich, and the updating frequency is high, so that the requirement on time accuracy is high. The factors affecting the time in ADS-B data are mainly composed of two aspects: firstly, a global positioning system (GNSS) cannot provide time service; and secondly, the ADS-B ground station time service equipment has a fault. When the ADS-B ground station cannot receive a clock source signal in ADS-B practical application, the ADS-B data is output by taking a local clock as a clock source, so that the problem that the ADS-B track time scale is abnormal in a multiple coverage area is caused, and control operation is further influenced.
For example: if the system A is connected with ADS-B data in a leading mode, detecting abnormal time scale data in the multi-source ADS-B data connected with the system A in a traditional mode that the system A is connected with a time service signal of a GNSS system in a leading mode; and finishing local timing. Because each ADS-B ground station is guided and connected with a time service signal of a GNSS system, under the condition that the time service of the A system is normal, the local clock of the A system is compared with the time mark in CAT021 data reported by each ADS-B ground station by setting a time service threshold value, if the time mark exceeds the set threshold value, the ADS-B ground station is considered to be abnormal in time mark, and then the operation of removing the abnormal time mark is carried out. However, when the time service of the system A fails, when the time service of each ADS-B ground station is normal, all ADS-B ground station data time scale detection is abnormal, and further, the ADS-B monitoring signals cannot be provided for the rear-end air traffic control automation system, so that the control operation safety is seriously influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the embodiment of the invention provides a method and a system for detecting the abnormal time scale of multi-source ADS-B data, which can quickly process the abnormal time scale detection of a large batch of ADS-B dynamic target tracks, have high accuracy in detecting the abnormal time scale and improve the accuracy of track information.
In a first aspect, the invention provides a multi-source ADS-B data abnormal time scale detection method, which includes: collecting ADS-B ground station site time scale information;
selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample data of all ADS-B ground stations;
preprocessing the four-tuple information of the time mark sample data, and removing invalid four-tuple information to obtain processed time mark sample data;
selecting a training sample from the processed time scale sample data to establish an iTree;
traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree;
calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula;
and comparing the target abnormal score with a set threshold value, and judging whether the time mark is abnormal or not.
In a second aspect, the invention provides a multi-source ADS-B data abnormal time scale detection system, which comprises an information acquisition module, an analysis module, a preprocessing module and an abnormal time scale detection module, wherein,
the information acquisition module is used for acquiring the site time scale information of the ADS-B ground station;
the analysis module is used for selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample data of all the ADS-B ground stations;
the preprocessing module is used for preprocessing the four-tuple information of the time mark sample data, removing invalid four-tuple information and obtaining processed time mark sample data;
the abnormal time scale detection module is used for selecting a training sample from the processed time scale sample data to establish an iTree;
traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree;
calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula;
and comparing the target abnormal score with a set threshold value, and judging whether the time mark is abnormal or not.
The invention has the beneficial effects that:
the method and the system for detecting the abnormal time marks of the multi-source ADS-B data realize the detection of the abnormal time marks of the real-time dynamic target track in a large-scale airspace, a standard reference clock source is not designated when the abnormal time marks are detected, a detection system clock is used as a detected sample, and the characteristics of ADS-B data are combined, so that the abnormal time mark data can be effectively identified, the abnormality of the time marks of all ADS-B ground stations connected by the system can be quickly detected, the abnormality of the self time marks of the detection system can be detected, the accuracy of the detection of the abnormal time marks is improved, and the accuracy of track information is improved.
Drawings
In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.
Fig. 1 shows a flowchart of a multi-source ADS-B data abnormal time scale detection method according to a first embodiment of the present invention;
fig. 2 shows a block diagram of a multi-source ADS-B data abnormal time scale detection system according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to a determination" or "in response to a detection". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.
As shown in fig. 1, a flowchart of a multi-source ADS-B data abnormal time scale detection method according to a first embodiment of the present invention is shown, where the method includes the following steps:
and S1, collecting the ADS-B ground station site time scale information.
And S2, selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample of all the ADS-B ground stations.
And S3, preprocessing the four-tuple information of the time mark sample data, and removing invalid four-tuple information to obtain the processed time mark sample data.
And S4, selecting training samples from the processed time scale sample data to establish iTree.
And S5, traversing each iTree by each ADS-B ground station time scale sample, and calculating the hierarchy height of each ADS-B ground station in each iTree.
And S6, calculating the target abnormal score of each ADS-B ground station time scale sample according to the target abnormal score formula.
And S7, comparing the target abnormal score with a set threshold value, and judging whether the time mark is abnormal or not.
The multi-source ADS-B data abnormal time scale detection method provided by the application adopts a different type of abnormal detection method based on iForest (isolation forest), and mainly screens false values. In order to realize the method, two main characteristics of the ADS-B time scale outlier are combined:
(a) they consist of fewer targets, occupying a minority of the population;
(b) they have physical properties different from normal values.
In summary, the so-called outliers are "small but different", which makes them easier to screen than normal spots. In the iForest algorithm, outliers are isolated closer to the root of the tree, while normal points are at the deeper end of the tree. This property of the tree, called iTree, forms the basis for a method of detecting anomalies.
An Isolation Tree (Isolation Tree) is set as a node of the iTree, T can be an external node without a child node, and can also be an internal node (T) of a test node and two child nodesl,Tr) (ii) a The test node consists of a certain attribute q and a segmentation threshold p, when q is equal to q<When p, data points are put into the set T respectivelylAnd Tr。
Set a data set X ═ X1,x2,…,xnAnd for n target construction isolation trees iTree, randomly selecting an attribute q and a partition value p to recursively divide X until the following conditions are met:
(a) the tree reached a height limit;
(b)abs(X)＝1；
(c) all data values in X differ by less than 1ms in absolute value.
An iTree is a true binary tree with 0 or 2 children per node in the tree. In the present embodiment, the same value of all data in the condition (c) X that the original recursive partitioning X satisfies is modified to be equal if the absolute value of the phase difference between all data values in X does not exceed 1ms by combining the ADS-B time scale data characteristics, so that the effect of simplifying the calculation can be achieved.
Path Length (Path Length): the present embodiment performs anomaly detection on data points by using anomaly scores based on path lengths, and defines the path lengths and the anomaly scores respectively as follows:
path length: the path length h (x) of point x is measured by the number of edges x that traverse the iTree from the root node until the traversal terminates at the outer node.
And (3) abnormal scoring: since h (x) requires normalization, direct comparison is not possible. But since the iTree has the same structure as a Binary Search Tree (BST). For external node termination, the estimate of average h (x) is the same as for the BST search failure case. Therefore, BST analysis is used in the application to estimate the average path length of iTree, and n targets are assumed, wherein n is more than or equal to 1:
c(n)＝2H(n-1)-(2(n-1)/n)
where h (i) is a harmonic function, and h (i) is ln (i) + 0.577216. The target anomaly score is defined as:
where E (h (x)) is the average of a set of quarantine trees h (x). The following important conclusions are drawn for the target anomaly score s:
(a) if s is 1, then abnormal;
(b) s is far less than 0.5, and is a safety value;
(c) s equals about 0.5 samples with no significant anomalies.
In a large-batch ADS-B track scene, because each ADS-B ground station system is connected with a Time service signal of a GNSS system, I021/073, Time of Message Reception for Position or I021/071 in track state report data CAT021 output by the ADS-B ground station, and Time of application for Position Time (TOA for short) are output by the ADS-B ground station; therefore, the accuracy of the track state report data time scale output by the ADS-B ground station is determined by whether the time service module works normally or not, and the time service module does not aim at a certain target but all targets of the station. Therefore, when the time scale samples are selected, the TOA time of ADS-B data of a frame output by each ADS-B ground station at last can be selected as the samples of the clock of the whole ground station. Considering that at least 1 ADS-B ground station is connected to one system in ADS-B data application; if the phenomenon that the abnormal time scale cannot be accurately detected due to too few samples occurs, in order to ensure enough sample quantity, the following logic is adopted for processing:
(1) under the condition of only leading and connecting 1 ADS-B ground station, if a detection system clock time service mark is set, abnormal time mark detection is carried out by taking the detection system clock as a standard; if the detection system clock time service mark is not set, the system clock of the ADS-B ground station to be detected is used as a standard, namely, abnormal time scale detection is not carried out.
(2) Under the condition of the ADS-B ground station of the leading-in 2 part, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of the TOA sample of the ADS-B.
And leading and connecting the ADS-B ground station of the 2 part under the condition that a detection system clock time service mark is not set, and taking the system clock of the detected ADS-B ground station as a standard, namely, not performing abnormal time mark detection.
(3) Under the condition of the ADS-B ground station of the leading-in part 3 and above, if a detection system clock time service mark is set, taking the detection system clock as a newly-added detection sample to perform iForest abnormal time scale detection on the basis of the TOA sample of the ADS-B; if the clock time service mark of the detection system is not set; then the TOA sample of the ADS-B ground station itself is used for iForest abnormal time scale detection.
The ADS-B ground station time scale sample data at time T (± Δ T) in the ADC system may use the following quadruple T: (SID, TOA, LTOA, DS) represents, where SID represents the ADS-B ground station number of sample data at time T, Δ T is set to 0.2s in combination with the ADS-B time scale data characteristics, TOA represents the TOA time of the last frame of ADS-B data at time T, LTOA represents the local time scale of the last frame of ADS-B data at time T, and DS is the distance from the station with SID number 1. A quadruplet T can uniquely determine the time scale information of the ADS-B ground station at the time T; and at time tsignal values occupy a small percentage of the population. Anomaly detection using iForest is a two-stage process. The first stage (training) builds the isolation tree using the subsamples of the training set. The second phase (test) passes the test cases through the isolation tree to obtain an anomaly score for each case.
A training stage:
random ADS-B ground station sample data set X ═ X from leading-in1，x2，…，xnPsi sample data of the data are selected as a training sample set, omega training sample sets are selected in total, and omega training iTrees are constructed through the method; selecting the number psi of training samples as 3; the number Ω of the training sample sets is also 3. Wherein xiFor the quadruple T: (SID, TOA, LTOA, DS).
And (3) an evaluation stage:
all ADS-B ground station sample data set X ═ X1,x2,…,xnSubstituting each element in the training stage into each iTree formed in the training stage, and calculating to obtain each element xiThe level height above each iTree; and then calculating the evaluation value of the element by using the target anomaly score formula.
Judging each element x using a target anomaly score conclusioniThe abnormal condition of (2).
The method for detecting the abnormal time mark of the multi-source ADS-B data provided by the embodiment realizes the detection of the abnormal time mark of the real-time dynamic target track in a large-scale airspace, does not appoint a standard reference clock source when detecting the abnormal time mark, takes a detection system clock as a detected sample, and combines the characteristics of the ADS-B data, so that the abnormal time mark data can be effectively identified, the abnormality of the time mark of each ADS-B ground station connected by the system can be quickly detected, the abnormality of the time mark of the detection system can be detected, the detection accuracy of the abnormal time mark is improved, and the accuracy of the track information is improved.
In the first embodiment, a method for detecting an abnormal time scale of multi-source ADS-B data is provided, and correspondingly, a system for detecting an abnormal time scale of multi-source ADS-B data is also provided. Please refer to fig. 2, which is a block diagram of a multi-source ADS-B data anomaly timestamp detection system according to a second embodiment of the present invention. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.
As shown in fig. 2, a block diagram of a multi-source ADS-B data anomaly timestamp detection system according to a second embodiment of the present invention is shown, where the system includes: the system comprises an information acquisition module, an analysis module, a preprocessing module and an abnormal time scale detection module, wherein the information acquisition module is used for acquiring the site information of the ADS-B ground station; the analysis module is used for selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample data of all the ADS-B ground stations; the preprocessing module is used for preprocessing the four-tuple information of the time mark sample data, removing invalid four-tuple information and obtaining processed time mark sample data; the abnormal time scale detection module is used for selecting a training sample from the processed time scale sample data to establish an iTree; traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree; calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula; and comparing the target abnormal score with a set threshold value, and judging whether the time mark is abnormal or not.
In this embodiment, the selecting, by the parsing module, the time scale sample specifically includes: and selecting the TOA time of ADS-B data of one frame output by each ADS-B ground station at last as a sample of the clock of the whole ground station.
In this embodiment, in the case of connecting the ADS-B ground station of part 1 in the system, if a detection system clock time service flag is set, the detection system clock is used as a standard for performing abnormal time scale detection, and if the detection system clock time service flag is not set, the system clock of the detected ADS-B ground station is used as a standard;
under the condition that 2 ADS-B ground stations are connected in a leading mode in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station;
under the condition that an ADS-B ground station is connected with a part 3 or more in a leading way in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station; and if the clock time service mark of the detection system is not set, performing iForest abnormal time scale detection on the TOA sample of the ADS-B ground station.
The above is a description of a multi-source ADS-B data abnormal time scale detection system provided in the second embodiment of the present invention.
The system for detecting the abnormal time marks of the multi-source ADS-B data realizes the detection of the abnormal time marks of the real-time dynamic target flight path in a large-scale airspace, does not designate a standard reference clock source when the abnormal time marks are detected, takes the detection system clock as a detected sample, and combines the characteristics of the ADS-B data, so that the abnormal time mark data can be effectively identified, the system can quickly detect whether the time marks of all ADS-B ground stations connected by the system are abnormal or not, and can detect whether the self time marks of the detection system are abnormal or not, thereby improving the accuracy of the detection of the abnormal time marks and the accuracy of the flight path information.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (6)
1. A multi-source ADS-B data abnormal time scale detection method is characterized by comprising the following steps:
collecting ADS-B ground station site time scale information;
selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample data of all ADS-B ground stations;
preprocessing the four-tuple information of the time mark sample data, and removing invalid four-tuple information to obtain processed time mark sample data;
selecting a training sample from the processed time scale sample data to establish an iTree;
traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree;
calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula;
comparing the target abnormal score with a set threshold value, and judging whether the time scale is abnormal or not;
the selecting the timestamp sample specifically includes: selecting TOA time of ADS-B data of a frame output by each ADS-B ground station at last as a sample of the whole ground station clock; under the condition that 1 ADS-B ground station is connected in a leading way in the system, if a detection system clock time service mark is set, abnormal time scale detection is carried out by taking the detection system clock as a standard, and if the detection system clock time service mark is not set, the system clock of the detected ADS-B ground station is taken as a standard; under the condition that 2 ADS-B ground stations are connected in a leading mode in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station; under the condition that an ADS-B ground station is connected with a part 3 or more in a leading way in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station; and if the clock time service mark of the detection system is not set, performing iForest abnormal time scale detection on the TOA sample of the ADS-B ground station.
2. The method of claim 1, wherein selecting training samples from the processed time scale sample data to create an iTree comprises:
set a data set X ═ X1,x2,…,xnAnd for n target building isolation trees iTree, selecting an attribute q and a partition value p at random to recursively divide X until the following conditions are met: the tree has reached a high limit, abs (X) 1, with all data values in X differing by less than 1ms in absolute value.
3. The method of claim 1, wherein a quadruple T of ADS-B ground station time scale sample data at time T (± Δ T) in the ADC system: (SID, TOA, LTOA, DS) represents, where SID represents the ADS-B ground station number of sample data at time T, Δ T is set to 0.2s in combination with the ADS-B time scale data characteristics, TOA represents the TOA time of the last frame of ADS-B data at time T, LTOA represents the local time scale of the last frame of ADS-B data at time T, and DS is the distance from the station with SID number 1.
4. A multi-source ADS-B data abnormal time scale detection system is characterized by comprising: an information acquisition module, an analysis module, a preprocessing module and an abnormal time scale detection module, wherein,
the information acquisition module is used for acquiring the site time scale information of the ADS-B ground station;
the analysis module is used for selecting a time mark sample, and analyzing the site ID of the ADS-B ground station and the distance between the first ground station to obtain four-tuple information of the time mark sample data of all the ADS-B ground stations;
the preprocessing module is used for preprocessing the four-tuple information of the time mark sample data, removing invalid four-tuple information and obtaining processed time mark sample data;
the abnormal time scale detection module is used for selecting a training sample from the processed time scale sample data to establish an iTree;
traversing each iTree by each ADS-B ground station time scale sample, and calculating the level height of each ADS-B ground station in each iTree;
calculating the target abnormal score of each ADS-B ground station time scale sample according to a target abnormal score formula;
comparing the target abnormal score with a set threshold value, and judging whether the time scale is abnormal or not;
the analyzing module specifically selects the time scale sample, and includes: selecting TOA time of ADS-B data of a frame output by each ADS-B ground station at last as a sample of the whole ground station clock;
under the condition that 1 ADS-B ground station is connected in a leading way in the system, if a detection system clock time service mark is set, abnormal time scale detection is carried out by taking the detection system clock as a standard, and if the detection system clock time service mark is not set, the system clock of the detected ADS-B ground station is taken as a standard;
under the condition that 2 ADS-B ground stations are connected in a leading mode in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station;
under the condition that an ADS-B ground station is connected with a part 3 or more in a leading way in the system, if a detection system clock time service mark is set, the detection system clock is used as a newly added detection sample to carry out iForest abnormal time scale detection on the basis of a TOA sample of the ADS-B ground station; and if the clock time service mark of the detection system is not set, performing iForest abnormal time scale detection on the TOA sample of the ADS-B ground station.
5. The system of claim 4, wherein the abnormal time scale detection module selects a training sample from the processed time scale sample data to create an iTree, and the iTree comprises:
set a data set X ═ X1,x2,…,xnAnd (4) constructing isolation trees iTree for n targets, and randomly selecting an attribute q and a partition value p for recursionDivide X until satisfying: the tree has reached a height limit, abs (X) 1, with all data values in X differing by less than 1ms in absolute value.
6. The system of claim 4, wherein the parsing module uses a four-tuple T: (SID, TOA, LTOA, DS), where SID denotes the ADS-B ground station number of sample data at time T, Δ T is set to 0.2s in combination with the ADS-B time scale data characteristic, TOA denotes the TOA time of the ADS-B data of the last frame at time T, LTOA denotes the local time scale of the ADS-B data of the last frame at time T, and DS is the distance from the station with SID number 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110685630.7A CN113344093B (en) | 2021-06-21 | 2021-06-21 | Multi-source ADS-B data abnormal time scale detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110685630.7A CN113344093B (en) | 2021-06-21 | 2021-06-21 | Multi-source ADS-B data abnormal time scale detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113344093A CN113344093A (en) | 2021-09-03 |
| CN113344093B true CN113344093B (en) | 2022-07-05 |
Family
ID=77478312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110685630.7A Active CN113344093B (en) | 2021-06-21 | 2021-06-21 | Multi-source ADS-B data abnormal time scale detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113344093B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11955014B2 (en) | 2022-01-31 | 2024-04-09 | Honeywell International S.R.O. | ADS-B traffic filter |
| CN116107847B (en) * | 2023-04-13 | 2023-06-27 | 平安科技（深圳）有限公司 | Multi-element time series data anomaly detection method, device, equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917273A (en) * | 2010-08-26 | 2010-12-15 | 四川大学 | ECC certificate-based ADS-B data authentication method |
| CN104992574A (en) * | 2015-06-24 | 2015-10-21 | 成都民航空管科技发展有限公司 | ADS-B data distribution system |
| CN111612048A (en) * | 2020-04-30 | 2020-09-01 | 中国西安卫星测控中心 | Unsupervised clustering anomaly detection method |
| CN111951612A (en) * | 2020-07-23 | 2020-11-17 | 中国民用航空总局第二研究所 | Data fusion method, device and system |
| CN111951611A (en) * | 2020-07-03 | 2020-11-17 | 中国空气动力研究与发展中心计算空气动力研究所 | ADS-B weak signal detection device and method based on multi-feature fusion |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IL228789A (en) * | 2013-10-08 | 2016-03-31 | Israel Aerospace Ind Ltd | Missile system including ads-b receiver |
| EP3154046B1 (en) * | 2015-10-05 | 2021-12-08 | The Boeing Company | System and method for verifying ads-b messages |
| US11068593B2 (en) * | 2017-08-03 | 2021-07-20 | B. G. Negev Technologies And Applications Ltd., At Ben-Gurion University | Using LSTM encoder-decoder algorithm for detecting anomalous ADS-B messages |
-
2021
- 2021-06-21 CN CN202110685630.7A patent/CN113344093B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101917273A (en) * | 2010-08-26 | 2010-12-15 | 四川大学 | ECC certificate-based ADS-B data authentication method |
| CN104992574A (en) * | 2015-06-24 | 2015-10-21 | 成都民航空管科技发展有限公司 | ADS-B data distribution system |
| CN111612048A (en) * | 2020-04-30 | 2020-09-01 | 中国西安卫星测控中心 | Unsupervised clustering anomaly detection method |
| CN111951611A (en) * | 2020-07-03 | 2020-11-17 | 中国空气动力研究与发展中心计算空气动力研究所 | ADS-B weak signal detection device and method based on multi-feature fusion |
| CN111951612A (en) * | 2020-07-23 | 2020-11-17 | 中国民用航空总局第二研究所 | Data fusion method, device and system |
Non-Patent Citations (1)
| Title |
|---|
| 一种小波变换下的ADS-B信号增强算法;李佳芯等;《电讯技术》;20191128;第1312-1318页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113344093A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113344093B (en) | Multi-source ADS-B data abnormal time scale detection method and system | |
| CN104699835B (en) | For determining that Webpage includes the method and device of point of interest POI data | |
| CN105676085A (en) | Extra-high voltage GIS partial discharge detection method based on multi-sensor information fusion | |
| CN112104495B (en) | System fault root cause positioning method based on network topology | |
| CN112394372A (en) | Method and system for evaluating multipoint positioning performance based on ADS-B recorded data | |
| JP6789872B2 (en) | Analytical methods, analyzers, and programs | |
| CN113645182B (en) | Denial of service attack random forest detection method based on secondary feature screening | |
| CN116386081A (en) | Pedestrian detection method and system based on multi-mode images | |
| CN105959321A (en) | Passive identification method and apparatus for network remote host operation system | |
| CN113608072B (en) | Electric power self-healing rapid fault positioning method based on non-sound condition | |
| CN113742927B (en) | Meteorological forecast data quality detection method | |
| CN113268730B (en) | Smart power grid false data injection attack detection method based on reinforcement learning | |
| CN113987476A (en) | Method and device for determining defect host, electronic equipment and storage medium | |
| CN117436005A (en) | Abnormal data processing method in automatic ambient air monitoring process | |
| CN110632191A (en) | Transformer chromatographic peak qualitative method and system based on decision tree algorithm | |
| CN114661700A (en) | Artificial influence weather operation effect inspection method based on AI | |
| CN105868538A (en) | A high speed railway CPII conductor plane control network closed loop search and loop closure error calculation method | |
| CN113340308B (en) | Correction logic law flight path starting method based on self-reporting point | |
| CN104333489B (en) | Detection method, apparatus and system to blank pipe supervision equipment | |
| CN111309561B (en) | Method and device for monitoring state of big data system | |
| CN113870620A (en) | Ship identification method for simultaneously starting multiple AIS (automatic identification system) devices | |
| CN113075498A (en) | Power distribution network traveling wave fault positioning method and system based on residual error clustering | |
| CN106205219B (en) | The aircraft monitoring method and device of fusion based on more radar informations | |
| CN112749370B (en) | Fault tracking and positioning method and system based on Internet of things | |
| CN111860688A (en) | Target type identification method and system and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |