CN117828527B - Multi-source data fusion and situation generation method and system - Google Patents
Multi-source data fusion and situation generation method and system Download PDFInfo
- Publication number
- CN117828527B CN117828527B CN202311849664.0A CN202311849664A CN117828527B CN 117828527 B CN117828527 B CN 117828527B CN 202311849664 A CN202311849664 A CN 202311849664A CN 117828527 B CN117828527 B CN 117828527B
- Authority
- CN
- China
- Prior art keywords
- data
- target
- fusion
- situation
- track
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention relates to a multi-source data fusion and situation generation method and system, wherein the method comprises the steps of obtaining original target data of a plurality of information sources, analyzing and preprocessing the original target data, and establishing an original target library; the method comprises the steps of adopting a fuzzy decision association strategy to carry out data association, adopting a D-S evidence theory algorithm to carry out data fusion processing and establish a fusion database, carrying out target track generation and establishing a target track library according to the data fusion processing result, carrying out target situation estimation and target threat assessment according to the target track generation result, outputting situation results and establishing an information situation library, and managing and displaying original target data, fusion data, target track data and situation data. According to the invention, the fuzzy decision association strategy is adopted to carry out data association, and the D-S evidence theory algorithm is adopted to carry out data fusion processing, so that the multi-source data is subjected to the reorganization processing, the data comprehensiveness and accuracy are improved, and efficient and credible information reference is provided for decision making.
Description
Technical Field
The invention relates to the technical field of situation generation, in particular to a multi-source data fusion and situation generation method and system.
Background
Situation generation is an information processing technology, and is mainly used for acquiring and presenting the current environment and form by analyzing and integrating multi-source data, and is applied to the military field, so that fighter can be helped to quickly, comprehensively and accurately master battlefield situation information.
Along with the development of application fields and objects of multi-source data fusion and situation generation, the multi-source data fusion and situation display analysis are a new technology for multi-dimensional information processing, and play an important role in geographic mapping. Under the application scene based on three-dimensional high-technology space-based information acquisition, massive geographic mapping information can be obtained in real time along with the continuous increase of the types and the number of sensors such as radar, infrared, laser, ESM, communication and the like. The geographical mapping information not only contains traditional structured data, but also contains massive unstructured data, and how to change the real-time, discrete and complex information data into valuable information which can be intuitively understood becomes an important problem to be solved when multi-source data fusion and situation generation are applied to the fields of geographical mapping and the like.
At present, the processing of multi-source data has the problems of difficult associated processing, insufficient co-location and fusion judgment capability, and meanwhile, the large data volume and low fusion speed in the data fusion process are the problems to be solved in the multi-source data fusion and situation exhibition analysis process.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention aims to provide a multi-source data fusion and situation generation method and system, which can realize association and collaborative processing of multi-source data, discover unknown target information with regularity or update new characteristic information of a known target according to a given rule, so that multi-dimensional information data processing plays an important role in actual battlefield application.
In order to achieve the above object, the present invention provides a method for multi-source data fusion and situation generation, comprising the following steps:
S1, acquiring original target data of a plurality of information sources, analyzing and preprocessing the original target data, and establishing an original target library;
S2, carrying out data association on the preprocessed target data by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data by adopting a D-S evidence theory algorithm, and establishing a fusion database;
S3, generating a target track according to the data fusion processing result, and establishing a target track library;
s4, carrying out target situation estimation and target threat assessment according to the generation result of the target track, outputting a situation result, and establishing an information situation library;
and S5, managing and displaying original target data of the original target library, fusion data of the fusion database, target track data of the target track library and situation data of the information situation library.
According to an aspect of the present invention, in the step S1, the preprocessing includes unified alignment processing of a time system, a space coordinate system, and a target feature parameter measurement unit of the original target data.
According to one technical scheme of the present invention, in the step S2, the data association is performed on the preprocessed target data by adopting a fuzzy decision association policy, which specifically includes:
Step S211, screening the preprocessed target data;
step S212, judging whether the screened target data meets the Euclidean distance membership degree between targets, if so, executing step S213, otherwise, executing step 217;
Step S213, judging whether the screened target data meets the Euclidean distance membership degree between the azimuth, if so, executing step S214, otherwise, executing step 217;
step S214, judging whether the screened target data meets the Euclidean distance membership degree between voyages, if so, executing step S215, otherwise, executing step 217;
step S215, judging whether the screened target data meets the Euclidean distance membership degree between the heading, if so, executing step S216, otherwise, executing step 217;
Step S216, the screened target data is associated information;
Step S217, the filtered target data fails to be associated.
According to one technical scheme of the invention, in the step S2, the data fusion processing for the associated target data by adopting the D-S evidence theory algorithm specifically includes:
step S221, inputting the associated target data according to the target task;
step S222, probability distribution is carried out on basic original data according to the attribute characteristics of target data;
Step S223, setting an inference rule according to the D-S fusion principle that for The D-S synthesis of a finite number of mass functions m 1,m2,…,mn on Θ is:
Wherein,
Step S224, reasoning about network uncertainty transfer according to the D-S principle;
Step S225, basic probability adjustment is carried out by comparing the probability after D-S synthesis with the original probability;
Step S226, carrying out different path decision fusion according to the associated processing results of different data sources;
step S227, calculating a fusion result and outputting fusion information.
According to one technical scheme of the invention, in the step S2, before the fusion result library is established, the method further comprises automatically compiling the fused target points to obtain a plurality of batches of fusion data, wherein each batch of fusion data has a unique target batch number.
According to one aspect of the present invention, the target track generation includes:
step S31, generating tracks for each batch of the fusion data in sequence through a track generation regression algorithm according to a plurality of batches of the fusion data, and generating one or more initial target track data;
step S32, eliminating target data which are free from the initial target track according to the track generation result obtained in the step S31;
S33, carrying out same-target track aggregation on a plurality of initial target track data generated based on same batch fusion data;
and step S34, performing track aggregation on a plurality of batches of initial target track data aggregated with the target track to generate target track data, and performing warehouse entry processing on the target track data.
According to one aspect of the present invention, there is provided a multi-source data fusion and situation generation management system for implementing the above method, including:
The access and display unit is used for acquiring and analyzing target data and situation data of various information sources and displaying and managing the target data and the situation data;
The data fusion unit is used for carrying out data association and data fusion on the target data and generating target track data according to the fused data;
And the situation generating unit is used for carrying out situation analysis according to the target track data to generate and output situation data.
According to one aspect of the present invention, the access and display unit includes:
The data input module is used for acquiring and analyzing target data of various information sources to form original target data;
The data preprocessing module is used for carrying out unified alignment processing on a time system, a space coordinate system and a target characteristic parameter measurement unit on the original target data;
The data management module is used for generating an original target library, a fusion database, a target track library and an information situation library, and performing data management operation through original target data in the original target library, fusion data in the fusion database, target track data in the target track library and situation data in the information situation library;
And the two-dimensional display module is used for displaying the original target data, the fusion data, the target track data and the situation data according to the original target library, the fusion database, the target track library and the information situation library and editing the target track data and the situation data.
According to one aspect of the present invention, the data fusion includes:
The data fusion module is used for carrying out association of the original target data based on a space coordinate distance threshold, a navigational speed course characteristic, target identity information and a plurality of moment relative position relation characteristics of a unified target by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data according to a D-S evidence theory algorithm, and generating fusion data;
and the track generation module is used for generating tracks for the target according to the fusion data and generating target track data.
According to one aspect of the present invention, the situation generating unit includes:
the situation generation unit includes:
The system comprises a target situation analysis module, a target model analysis module and a target model analysis module, wherein the target situation analysis module is used for carrying out target track display and speed and course prediction on a single target;
The target threat estimation module is used for extracting threat elements according to target attribute characteristics of the targets, calculating the priority degree of each target through quantization processing of the threat elements, calculating a target priority coefficient according to the target type, the platform type and the distance, and determining the target priority;
and the situation output module is used for outputting the situation data of the single target and the multiple targets into the information situation library.
Compared with the prior art, the invention has the following beneficial effects:
The invention provides a multisource data fusion and situation generation and management method and system, wherein the method is characterized in that a fuzzy decision association strategy is adopted to carry out data association on original target data from a plurality of information sources, and a D-S evidence theory algorithm is adopted to carry out data fusion processing on the associated target data so as to obtain more accurate and clear target data; and (3) performing target situation estimation and target threat assessment on the correlated and fused target data to form comprehensive and high-quality information for reference of a commander or directly assisting the commander in decision making.
According to the invention, a module decision association strategy is adopted, so that when data association is carried out on a plurality of observed values and target characteristics, the calculated amount is small, the accuracy is high, and real-time results can be output. The target data association strategy for fuzzy decision mainly utilizes a plurality of characteristics among a plurality of targets to carry out fuzzy decision, such as a space coordinate distance threshold value, a course speed characteristic, target identity information and a relative position relationship among a plurality of unified targets, and the like among the target data, and finally realizes the data association among the targets.
According to the invention, the D-S evidence theory algorithm is adopted as the data fusion algorithm, and can effectively infer and analyze incomplete information and uncertain information, and can more effectively and rapidly fuse multi-source heterogeneous data, so that a user is helped to obtain an effective fusion strategy and accurate synthesis, and finally, efficient and reliable information reference is provided for decision of a decision-making mechanism.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 schematically illustrates a flow chart of a multi-source data fusion and situation generation method provided in one embodiment of the invention;
FIG. 2 schematically illustrates a structural diagram of a multi-source data fusion and situation generation system provided in one embodiment of the invention;
FIG. 3 schematically illustrates an architecture diagram of a multi-source data fusion and situation generation system provided in accordance with one embodiment of the present invention;
FIG. 4 schematically illustrates a flow diagram of a multi-source data fusion and situation generation system provided in accordance with one embodiment of the invention;
FIG. 5 schematically shows a specific flow diagram of data association according to one embodiment of the invention;
FIG. 6 schematically shows a specific flow diagram of a data fusion process according to one embodiment of the invention.
Detailed Description
The description of the embodiments of this specification should be taken in conjunction with the accompanying drawings, which are a complete description of the embodiments. In the drawings, the shape or thickness of the embodiments may be enlarged and indicated simply or conveniently. Furthermore, portions of the structures in the drawings will be described in terms of separate descriptions, and it should be noted that elements not shown or described in the drawings are in a form known to those of ordinary skill in the art.
Any references to directions and orientations in the description of the embodiments herein are for convenience only and should not be construed as limiting the scope of the invention in any way. The following description of the preferred embodiments will refer to combinations of features, which may be present alone or in combination, and the invention is not particularly limited to the preferred embodiments. The scope of the invention is defined by the claims.
As shown in fig. 1, the method for multi-source data fusion and situation generation and management of the present invention includes the following steps:
S1, acquiring original target data of a plurality of information sources, analyzing and preprocessing the original target data, and establishing an original target library;
The preprocessing comprises unified alignment processing of a time system, a space coordinate system and a target characteristic parameter measurement unit of the original target data.
S2, carrying out data association on the preprocessed target data by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data by adopting a D-S evidence theory algorithm, and establishing a fusion database;
S3, generating a target track according to the data fusion processing result, and establishing a target track library;
s4, carrying out target situation estimation and target threat assessment according to the generation result of the target track, outputting a situation result, and establishing an information situation library;
and S5, managing and displaying original target data of the original target library, fusion data of the fusion database, target track data of the target track library and situation data of the information situation library.
The invention introduces the fuzzy decision target data association algorithm to carry out multidimensional association on multi-source data, can carry out fuzzy decision by utilizing a plurality of characteristics among a plurality of targets, finally realizes the data association among the targets, and has the advantages of wider applicability, less constraint conditions, capability of carrying out data association through a plurality of observation values and target characteristics, small calculated amount and higher precision and capability of outputting results in real time.
According to the invention, a D-S evidence theory algorithm is introduced to fuse multi-source data, compared with other data fusion algorithms, the D-S evidence theory can effectively infer and analyze incomplete information and uncertain information, and can more effectively and rapidly fuse multi-source heterogeneous data, so that a user is helped to obtain an effective fusion strategy and accurate synthesis, and finally, an efficient and reliable information reference is provided for decision making of a decision making mechanism, the problems of difficult association processing, insufficient co-location and fusion judgment capability of the conventional multidimensional data association algorithm at present are solved, and meanwhile, the problems of large data quantity and low fusion speed in the data fusion process are solved.
As shown in fig. 2, the invention further provides a multi-source data fusion and situation generation system, which is used for implementing the method, and comprises an access and display unit, a data fusion unit and a situation generation unit.
The access and display unit is used for acquiring and analyzing target data and situation data of various information sources and displaying and managing the target data and the situation data, and specifically comprises the following components:
The data input module is used for acquiring and analyzing target data of various information sources to form original target data;
The data preprocessing module is used for carrying out unified alignment processing on a time system, a space coordinate system and a target characteristic parameter measurement unit on the original target data;
The data management module is used for generating an original target library, a fusion database, a target track library and an information situation library, and performing data management operation through original target data in the original target library, fusion data in the fusion database, target track data in the target track library and situation data in the information situation library;
And the two-dimensional display module is used for displaying the original target data, the fusion data, the target track data and the situation data according to the original target library, the fusion database, the target track library and the information situation library and editing the target track data and the situation data.
The data fusion unit is used for carrying out data association and data fusion on the target data and generating target track data according to the fused data, and specifically comprises the following components:
The data fusion module is used for carrying out association of the original target data based on a space coordinate distance threshold, a navigational speed course characteristic, target identity information and a plurality of moment relative position relation characteristics of a unified target by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data according to a D-S evidence theory algorithm, and generating fusion data;
and the track generation module is used for generating tracks for the target according to the fusion data and generating target track data.
And the situation generating unit is used for carrying out situation analysis according to the target track data to generate and output situation data. Specifically, the situation generating unit includes:
The system comprises a target situation analysis module, a target model analysis module and a target model analysis module, wherein the target situation analysis module is used for carrying out target track display and speed and course prediction on a single target;
The target threat estimation module is used for extracting threat elements according to target attribute characteristics of the targets, calculating the priority degree of each target through quantization processing of the threat elements, calculating a target priority coefficient according to the target type, the platform type and the distance, and determining the target priority;
and the situation output module is used for outputting the situation data of the single target and the multiple targets into the information situation library.
The present invention will be specifically described by way of examples.
The architecture of the multi-source data fusion and situation generation system provided in this embodiment is shown in fig. 3, and includes an infrastructure layer, a software service layer, and an application layer.
The infrastructure layer is used as a channel for collecting information, acquires the information through various platform sensors such as a space base, an air base and a shore base, and provides data support for the data fusion and situation generation system.
The software service layer comprises two processing functions of data fusion and situation analysis, is a core working unit of the system and is responsible for the whole processing links of data management, fusion processing, situation analysis and the like.
The application layer is an interactive interface for providing system application, and comprises calling of a software service layer, interface display of situation information, track information, threat information and the like, situation information output and the like.
The service workflow of the multi-source data fusion and situation generation system provided in this embodiment is shown in fig. 3, and is specifically described as follows:
S1, acquiring original target data of a plurality of information sources, analyzing and preprocessing the original target data, and establishing an original target library.
Detecting external data access according to the software start of the multi-source data fusion and situation generation system, analyzing the accessed information data, and preprocessing the accessed original target data to ensure that a time system, a space coordinate system and a target characteristic parameter measurement unit are uniformly aligned. The multisource data is information obtained through various platform sensors such as a space base, an air base and a shore base.
Because the setting positions of various investigation equipment and platform sensors used for information collection by the infrastructure layer are different, the detection scanning period is also inconsistent, and the unified alignment processing of a time system is required to be carried out on the original target data acquired by the system.
The unified alignment of the time system relates to two cases of inconsistent time sampling intervals and inconsistent acquisition moments:
1. non-uniform time sampling interval
When the time sampling intervals of the original target data are not uniform, there are a plurality of high-frequency data in the low-frequency data retention time interval. Thus, the unified alignment of the time system for the original target data with inconsistent time sampling intervals generally employs the following three methods:
1) And selecting the original target data with the largest occurrence number in the high-frequency original target data as the substitute of the high-frequency original target data in the whole low-frequency data retention time period. If 100 communication signal samples are received in a1 second interval, and the modulation mode with the largest occurrence number is BPSK (with a ratio of 80%), the BPSK type signal is received in the whole 1 second interval.
2) And receiving the data in real time, and establishing a time data table according to the receiving time according to the data received in real time. The time data table is used for acquiring data at regular intervals according to a set time threshold, and integrating and warehousing the data, wherein the data are regarded as being sent by the same target.
And receiving the data sent by the same target in a fixed time interval through a time data table, so as to realize the time system unification of the original information data of the unified target from a plurality of information sources.
3) And selecting an intermediate frequency according to the acquisition frequency of the low-frequency original target data and the acquisition frequency of the high-frequency original target data, and screening all the acquired original target data according to the intermediate frequency.
For example, in 1 second interval, 100 times of changed data are reported according to 10 times of reporting states, so that the screened data can partially show the change trend and cannot bring too much data pressure.
2. The data acquisition time is not at the same time
And taking the union set of the update moments of the acquired multipath original target data as a data update time point. And taking the latest data state as the attribute state of the time point at each data updating moment.
And storing the preprocessed original target data into different database forms according to data sources.
And step S2, carrying out data association on the preprocessed target data by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data by adopting a D-S evidence theory algorithm, and establishing a fusion database.
One key to data fusion is the association between data. In a multisensor fusion system, where the data obtained is numerous, it is not a simple and easy matter how to select correlations among the numerous data. In data association, there is a general need to solve association of time axis, association of space axis and association of time and space axis. There are different algorithms in different fields of data association.
The data correlation processing comprises three processing modes, namely time axis correlation (data correlation processing is carried out according to time sequence, and is suitable for data fusion of single sensors), space axis correlation (correlation processing is carried out on each sensor data at the same moment, and is suitable for primary fusion processing of multi-sensor data), and time axis correlation (correlation processing is carried out on all measurement data of all sensors, and is suitable for a large-scale data fusion system).
The core problem of data correlation is how to overcome the correlation caused by inaccuracy and interference of sensor measurement, namely to maintain the consistency of data, and how to control and reduce the complexity of correlation calculation, and develop algorithms and models for correlation processing, fusion processing and system simulation.
Specifically, as shown in fig. 5, the data association includes the following steps:
Step S211, screening the preprocessed target data;
and screening the preprocessed target data according to the effective target data range, and removing scattered points outside the effective target data range to avoid the scattered points from interfering with subsequent data association.
Step S212, judging whether the screened target data meets the Euclidean distance membership degree between targets, if so, executing step S213, otherwise, executing step 217;
The data association processing of the target data based on the space coordinate threshold features of the target data is realized by judging whether the target data meets the Euclidean distance membership between the targets;
Step S213, judging whether the screened target data meets the Euclidean distance membership degree between the azimuth, if so, executing step S214, otherwise, executing step 217;
The data association processing of the target data based on the azimuth characteristics of the target data is realized by judging whether the target data meets the inter-azimuth Euclidean distance membership of the target data;
step S214, judging whether the screened target data meets the Euclidean distance membership degree between voyages, if so, executing step S215, otherwise, executing step 217;
And judging whether the target data meets the Euclidean distance membership degree between the speeds, so as to realize the data association processing of the target data based on the speed characteristics of the target data.
Step S215, judging whether the screened target data meets the Euclidean distance membership degree between the heading, if so, executing step S216, otherwise, executing step 217;
the data association processing of the target data based on the heading characteristics of the target data is realized by judging whether the target data meets the Euclidean distance membership degree between the headings;
Step S216, outputting the associated information;
And S217, outputting, wherein the association fails.
The system adopts a fuzzy decision strategy to carry out data association, and carries out association of original target data by calculating and judging the relative position relation characteristics of a plurality of moments based on a space coordinate distance threshold, a navigational speed course characteristic, target identity information and a unified target.
Due to insufficient information or the complexity of decision problems, it is often difficult to obtain accurate data or information, resulting in some ambiguity and uncertainty in the decision process. Compared with a common multi-attribute decision method, the fuzzy multi-attribute decision method adopts the theory and method of fuzzy mathematics, and can better express and process the ambiguity of data. Therefore, the research on the fuzzy multi-attribute decision method based on the association rule mining algorithm can better cope with the ambiguity and uncertainty in the decision process and can improve the accuracy of the decision result.
Firstly, searching candidate data in a database, including vectors of state estimation such as position, speed or identity of target measurement in the previous sampling period. Correcting the alternative data to the observation time, calculating the predicted position of the alternative target, filtering the threshold, removing incorrect measurement data, interference factors and the like in the association process, calculating an association matrix according to a fuzzy association formula, and describing the relationship between the information data and a certain state vector through an allocation strategy.
As shown in fig. 6, the data fusion includes the steps of:
step S221, inputting the associated target data according to the target task;
step S222, probability distribution is carried out on basic original data according to the attribute characteristics of target data;
Step S223, setting an inference rule according to the D-S fusion principle that for The D-S synthesis of a finite number of mass functions m 1,m2,…,mn on Θ is:
Wherein,
Step S224, reasoning about network uncertainty transfer according to the D-S principle;
Step S225, basic probability adjustment is carried out by comparing the probability after D-S synthesis with the original probability;
Step S226, carrying out different path decision fusion according to the associated processing results of different data sources;
step S227, calculating a fusion result and outputting fusion information.
In data fusion, the information provided by each sensor is typically incomplete, inaccurate, ambiguous, and may even sometimes be contradictory, i.e., contain a significant amount of uncertainty. To perform fusion, reasoning is performed according to the uncertainty information so as to achieve the purposes of target identity recognition and attribute judgment.
Uncertainty reasoning is the basis of target identification and attribute information fusion, is also the reasoning based on uncertainty knowledge based on non-classical logic, and starts from initial evidence of uncertainty, and by applying the uncertainty knowledge, a conclusion with a certain degree of uncertainty and reasonable or near-reasonable is deduced. DS evidence theory is an important tool to deal with uncertainty information reasoning, and can deal with uncertainty caused by "unaware". It uses a trust function instead of probability as a measure, builds a trust function by constraining the probability of some events, without having to account for the exact, difficult to obtain probability, which becomes a probability theory when the constraint is limited to strict probabilities. Static reasoning or deduction includes all possible states of the system or common assumptions, which are then assigned probabilities or quality allocation functions and combined to make the final decision.
Step S2 further comprises the step of automatically compiling the fused target points to obtain a plurality of batches of fused data, wherein each batch of fused data has a unique target batch number.
Multiple batches of fusion data are obtained through data fusion, each batch of fusion data being usable to describe a set of targets. The targets include individual targets or group targets.
The fused targets are automatically compiled to generate target lot numbers serving as unique identification codes, a series of follow-up operations such as track generation, track management and situation analysis are conveniently performed on the fused targets, meanwhile, the targets are conveniently clustered and the intention analysis of group targets is conveniently performed, and therefore the regularity of data management and the data processing efficiency during analysis are improved.
S3, generating a target track according to the data fusion processing result, and establishing a target track library;
step S31, generating tracks for each batch of the fusion data in sequence through a track generation regression algorithm according to a plurality of batches of the fusion data, and generating one or more initial target track data;
step S32, eliminating target data which are free from the initial target track according to the track generation result obtained in the step S31;
And when the target data does not accord with the track generation rule, the target data is regarded as a free target point, and the free target point is deleted.
S33, carrying out same-target track aggregation on a plurality of initial target track data generated based on same batch fusion data;
In the actually acquired target data, interference clutter is usually accompanied, and the interference possibly appears around the real track, so that the track needs to be extracted after the same-target-point track is aggregated, and a time monotonous sequence is used for describing the motion track of a target.
When there are multiple target tracks at the same time, the trace point data will be mixed with each other, and the clutter and false alarm will generate larger interference. The same-target trace aggregation is to classify original trace data and aggregate trace data generated by the same target, so that subsequent trace extraction is facilitated.
And step S34, performing track aggregation on a plurality of batches of initial target track data aggregated with the target track to generate target track data, and performing warehouse entry processing on the target track data.
Before the generated target track data is subjected to warehouse-in management, the method further comprises track fusion.
The track fusion is to fuse the multi-source data and one of the tracks of the data by a certain algorithm, so that the fused precision is higher than that of a single sensor, namely the precision is closer to that of a real track, meanwhile, the complexity of an integrated navigation display system interface can be reduced after the tracks are fused, and inconvenience to operators due to redundancy of multi-source information is avoided.
And establishing a target track library, and warehousing and managing the generated target track data. When a certain target has new data access, updating the track data corresponding to the target according to the new access target data, and updating the target track library at the same time, and when a certain target is confirmed to be destroyed, stopping the target track after manual confirmation.
S4, carrying out target situation estimation and target threat assessment according to the generation result of the target track, outputting a situation result, and establishing an information situation library;
predicting target dynamics such as navigation, speed and the like according to target track data, carrying out target grouping according to fused target point information, carrying out intention prediction according to target groups, calculating target threat coefficients, evaluating target threat degree and threat range, carrying out standard curve on a plurality of target situations of the same target group through a single color, outputting situation data according to a standard format, and carrying out warehouse entry management on the output situation data.
The method comprises the steps of carrying out target track display and speed and course prediction on a single target through a target situation analysis module, dividing the single target into different groups through carrying out target rough classification on a plurality of targets, determining group types according to target attribute characteristics through a D-S evidence theory, and carrying out intention judgment on the group targets.
Target prediction is a prerequisite for threat assessment. The output of threat assessment is theoretically to give the conditional probability of various hypotheses for reference by the commander. Future target prediction refers to predicting situation situations which may occur in the future based on understanding of the current situation and the result of threat analysis.
On the basis of the analysis result of the target situation analysis module, threat elements are extracted through a target threat estimation module according to target attribute characteristics of the targets, the priority degree of each target is calculated through quantitative processing of the threat elements, a target priority coefficient is calculated according to the type of the target, the type of the platform and the distance, and the target priority is determined.
Threat assessment mainly involves an estimate of risk, weak links to enemy-constrained my forces. The threat assessment method is to describe the whole environment elements in the battlefield according to the battlefield situation comprehensive view, and quantise the estimation of enemy force to form threat analysis of enemy and me in the battlefield situation, and the main content of the threat assessment method is to infer enemy behaviors and action attempts, namely what the result of the situation actions is under the current event condition, and what influence is on me. Threat assessment is carried out on the results formed by the situations, threat analysis element extraction is carried out, a proper hypothesis set is formed, and abstract understanding of threat analysis is completed. Threat assessment involves analysis of the movement parameters of the entity in the two-party situation of the friend or foe and the intention of the fight, giving various inferences of the situation of the battlefield in real time.
The situation output can output situation data to the outside of the system or to the data input module through the situation output module, and the formats of the output situation data comprise situation XML, thematic map JPG, thematic report PDF and the like.
And S5, managing and displaying original target data of the original target library, fusion data of the fusion database, target track data of the target track library and situation data of the information situation library.
The original target data of the original target library, the fusion data of the fusion database, the target track data of the target track library and the situation data of the information situation library can be subjected to data management operation by a data management module, including display and editing of various data.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
It is finally pointed out that the above description of the preferred embodiments of the invention, it being understood that although preferred embodiments of the invention have been described, it will be obvious to those skilled in the art that, once the basic inventive concepts of the invention are known, several modifications and adaptations can be made without departing from the principles of the invention, and these modifications and adaptations are intended to be within the scope of the invention. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Claims (7)
1. The multi-source data fusion and situation generation method is characterized by comprising the following steps of:
S1, acquiring original target data of a plurality of information sources, analyzing and preprocessing the original target data, and establishing an original target library;
S2, carrying out data association on the preprocessed target data by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data by adopting a D-S evidence theory algorithm, and establishing a fusion database;
S3, generating a target track according to the data fusion processing result, and establishing a target track library;
s4, carrying out target situation estimation and target threat assessment according to the generation result of the target track, outputting a situation result, and establishing an information situation library;
S5, managing and displaying original target data of the original target library, fusion data of the fusion database, target track data of the target track library and situation data of the information situation library;
In the step S2, the performing data association on the preprocessed target data by using a fuzzy decision association policy specifically includes:
Step S211, screening the preprocessed target data;
step S212, judging whether the screened target data meets the Euclidean distance membership degree between targets, if so, executing step S213, otherwise, executing step 217;
Step S213, judging whether the screened target data meets the Euclidean distance membership degree between the azimuth, if so, executing step S214, otherwise, executing step 217;
step S214, judging whether the screened target data meets the Euclidean distance membership degree between voyages, if so, executing step S215, otherwise, executing step 217;
step S215, judging whether the screened target data meets the Euclidean distance membership degree between the heading, if so, executing step S216, otherwise, executing step 217;
Step S216, the screened target data is associated information;
Step S217, the screened target data fails to be associated;
Firstly searching candidate data in a database, including a vector of position, speed or identity state estimation of target measurement in a previous sampling period, correcting the candidate data to observation time, calculating a predicted position of the candidate target, filtering by a threshold, removing incorrect measurement data and interference factors in the association process, calculating an association matrix according to a fuzzy association formula, and describing the relationship between information data and a certain state vector by an allocation strategy;
in the step S2, the performing data fusion processing on the associated target data by using the D-S evidence theory algorithm specifically includes:
step S221, inputting the associated target data according to the target task;
step S222, probability distribution is carried out on basic original data according to the attribute characteristics of target data;
Step S223, setting an inference rule according to the D-S fusion principle that for The D-S synthesis of a finite number of mass functions m 1,m2,…,mn on Θ is:
Wherein,
Step S224, reasoning about network uncertainty transfer according to the D-S principle;
Step S225, basic probability adjustment is carried out by comparing the probability after D-S synthesis with the original probability;
Step S226, carrying out different path decision fusion according to the associated processing results of different data sources;
step S227, calculating a fusion result and outputting fusion information;
In the step S2, a plurality of batches of fusion data are obtained through data fusion, each batch of fusion data is used for describing a group of targets, the targets comprise single targets or group targets, before a fusion database is established, the method further comprises the step of automatically compiling the fused target points to obtain a plurality of batches of fusion data, and each batch of fusion data has a unique target batch number and is used for carrying out track generation, track management, situation analysis and intention analysis on the fused targets and grouping targets.
2. The method according to claim 1, wherein in the step S1, the preprocessing includes unified alignment processing of the time system, the space coordinate system, and the target feature parameter measurement unit of the original target data.
3. The multi-source data fusion and situation generation method according to claim 1, wherein in the step S3, the target track generation includes:
step S31, generating tracks for each batch of the fusion data in sequence through a track generation regression algorithm according to a plurality of batches of the fusion data, and generating one or more initial target track data;
step S32, eliminating target data which are free from the initial target track according to the track generation result obtained in the step S31;
S33, carrying out same-target track aggregation on a plurality of initial target track data generated based on same batch fusion data;
and step S34, performing track aggregation on a plurality of batches of initial target track data aggregated with the target track to generate target track data, and performing warehouse entry processing on the target track data.
4. A multi-source data fusion and situation generation system for implementing the method of any one of claims 1 to 3, comprising:
The access and display unit is used for acquiring and analyzing target data and situation data of various information sources and displaying and managing the target data and the situation data;
The data fusion unit is used for carrying out data association and data fusion on the target data and generating target track data according to the fused data;
And the situation generating unit is used for carrying out situation analysis according to the target track data to generate and output situation data.
5. The multi-source data fusion and situation generation system of claim 4, wherein the access and display unit comprises:
The data input module is used for acquiring and analyzing target data of various information sources to form original target data;
The data preprocessing module is used for carrying out unified alignment processing on a time system, a space coordinate system and a target characteristic parameter measurement unit on the original target data;
The data management module is used for generating an original target library, a fusion database, a target track library and an information situation library, and performing data management operation through original target data in the original target library, fusion data in the fusion database, target track data in the target track library and situation data in the information situation library;
And the two-dimensional display module is used for displaying the original target data, the fusion data, the target track data and the situation data according to the original target library, the fusion database, the target track library and the information situation library and editing the target track data and the situation data.
6. The multi-source data fusion and situation generation system of claim 4, wherein the data fusion unit comprises:
The data fusion module is used for carrying out association of the original target data based on a space coordinate distance threshold, a navigational speed course characteristic, target identity information and a plurality of moment relative position relation characteristics of a unified target by adopting a fuzzy decision association strategy, carrying out data fusion processing on the associated target data according to a D-S evidence theory algorithm, and generating fusion data;
and the track generation module is used for generating tracks for the target according to the fusion data and generating target track data.
7. The multi-source data fusion and situation generation system according to claim 6, wherein the situation generation unit comprises:
The system comprises a target situation analysis module, a target model analysis module and a target model analysis module, wherein the target situation analysis module is used for carrying out target track display and speed and course prediction on a single target;
The target threat estimation module is used for extracting threat elements according to target attribute characteristics of the targets, calculating the priority degree of each target through quantization processing of the threat elements, calculating a target priority coefficient according to the target type, the platform type and the distance, and determining the target priority;
and the situation output module is used for outputting the situation data of the single target and the multiple targets into the information situation library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311849664.0A CN117828527B (en) | 2023-12-29 | 2023-12-29 | Multi-source data fusion and situation generation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311849664.0A CN117828527B (en) | 2023-12-29 | 2023-12-29 | Multi-source data fusion and situation generation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117828527A CN117828527A (en) | 2024-04-05 |
| CN117828527B true CN117828527B (en) | 2025-06-13 |
Family
ID=90511024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311849664.0A Active CN117828527B (en) | 2023-12-29 | 2023-12-29 | Multi-source data fusion and situation generation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117828527B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118070231B (en) * | 2024-04-17 | 2024-07-02 | 中国人民解放军95859部队 | Multi-source multi-target measurement data real-time fusion method based on cluster association |
| CN119513167B (en) * | 2024-10-24 | 2025-09-23 | 中国长江三峡集团有限公司 | Method and system for data acquisition storage, modeling development and sharing service of IT and OT scene coverage |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| CN110866887A (en) * | 2019-11-04 | 2020-03-06 | 深圳市唯特视科技有限公司 | Target situation fusion sensing method and system based on multiple sensors |
| CN113283516A (en) * | 2021-06-01 | 2021-08-20 | 西北工业大学 | Multi-sensor data fusion method based on reinforcement learning and D-S evidence theory |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103903101B (en) * | 2014-04-14 | 2016-02-24 | 上海航天电子通讯设备研究所 | A kind of General Aviation multi-source information supervising platform and method thereof |
| CN108763793A (en) * | 2018-06-01 | 2018-11-06 | 电子科技大学 | A kind of Weighted Fuzzy type D-S evidence theory frame |
| CN109785064A (en) * | 2019-01-14 | 2019-05-21 | 南京信息工程大学 | A kind of mobile e-business recommended method and system based on Multi-source Information Fusion |
| CN110070118A (en) * | 2019-04-10 | 2019-07-30 | 广东电网有限责任公司 | A kind of multi-space data fusion method |
| CN115085948B (en) * | 2021-03-02 | 2024-02-09 | 中国石油化工股份有限公司 | Network security situation assessment method based on improved D-S evidence theory |
| CN113157678B (en) * | 2021-04-19 | 2022-03-15 | 中国人民解放军91977部队 | Multi-source heterogeneous data association method |
-
2023
- 2023-12-29 CN CN202311849664.0A patent/CN117828527B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105390029A (en) * | 2015-11-06 | 2016-03-09 | 武汉理工大学 | Ship collision avoidance assisted decision-making method and system based on track fusion and track prediction |
| CN110866887A (en) * | 2019-11-04 | 2020-03-06 | 深圳市唯特视科技有限公司 | Target situation fusion sensing method and system based on multiple sensors |
| CN113283516A (en) * | 2021-06-01 | 2021-08-20 | 西北工业大学 | Multi-sensor data fusion method based on reinforcement learning and D-S evidence theory |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117828527A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117828527B (en) | Multi-source data fusion and situation generation method and system | |
| CN113157800B (en) | Identification method for discovering dynamic target in air in real time | |
| CN113822366A (en) | Service index abnormality detection method and device, electronic equipment and storage medium | |
| US20220004163A1 (en) | Apparatus for predicting equipment damage | |
| CN116340876A (en) | Spatial target situation awareness method for local multisource data fusion | |
| CN112907632A (en) | Single-towing ship target identification method and device | |
| CN118093290A (en) | Method, device, equipment and medium for detecting server heat dissipation abnormality | |
| Cao et al. | Cluster-based correlation of severe driving events with time and location | |
| CN118711421A (en) | A method for aerial target trajectory recognition and prediction based on big data mining | |
| Oveis et al. | LIME-assisted automatic target recognition with SAR images: Toward incremental learning and explainability | |
| Choi et al. | Stochastic conformal anomaly detection and resolution for air traffic control | |
| Garcez Duarte et al. | An experimental study of existing tools for outlier detection and cleaning in trajectories | |
| Ferrero-López et al. | Bluetooth low energy indoor positioning: A fingerprinting neural network approach | |
| Salfinger et al. | Maintaining Situation Awareness over Time--A Survey on the Evolution Support of Situation Awareness Systems | |
| CN114580482A (en) | Radio signal characteristic acquisition method based on edge computing node and data center | |
| Lana et al. | Measuring the confidence of single-point traffic forecasting models: Techniques, experimental comparison, and guidelines toward their actionability | |
| CN117749448A (en) | Intelligent early warning method and device for network potential risk | |
| Laña et al. | Measuring the confidence of traffic forecasting models: Techniques, experimental comparison and guidelines towards their actionability | |
| CN117724059A (en) | Multi-source sensor fusion track correction method based on Kalman filtering algorithm | |
| Brax | Anomaly detection in the surveillance domain | |
| CN113381827A (en) | Electromagnetic signal spectrum sensing method based on deep clustering network | |
| Hiremath et al. | Assertion of Soil Data Consistency by Detecting and Removing Spatial Outliers Using Iterative Techniques for Precision Agriculture | |
| CN119475199B (en) | A method and system for detecting Jupiter magnetic reconnection events based on deep learning algorithm | |
| CN117610601B (en) | Logistics equipment intelligent positioning method and system based on Internet of things | |
| CN115731020B (en) | Data processing method, device and server |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20250830 Address after: No.104 Youyi Road, Haidian District, Beijing 100094 Patentee after: China Academy of Space Technology Country or region after: China Patentee after: 63921 TROOPS OF PLA Address before: No.104 Youyi Road, Haidian District, Beijing 100094 Patentee before: China Academy of Space Technology Country or region before: China |