Radar simulation data information integration processing system

Abstract

The invention provides a radar simulation data information integration processing system, and relates to the technical field of radar technology and data processing, and the system comprises the following modules: a data access module which receives a data signal generated by a radar signal simulator; the data processing and fusion module and the radar simulation and scene generation module are internally provided with various radar system models; the intelligent processing and analysis module is used for carrying out deep mining and analysis on the radar simulation data by adopting various preset processing algorithms and analysis models; the visualization module is used for displaying the result of the intelligent processing and analysis module in the forms of two-dimensional visualization, three-dimensional visualization and dynamic visualization; a management module; according to the invention, data signals of various types and formats produced by a radar signal simulator can be received, the data signals are preprocessed and fused, and then a complex battlefield and environment modeling are created by the data through the radar simulation and scene generation module, so that the practicability and adaptability of the system are enhanced.

Description

Technical Field

[0001] This invention relates to the fields of radar technology and data processing technology, and in particular to a radar analog data information integration and processing system. Background Technology

[0002] As a core sensing tool in modern national defense, aerospace, meteorological monitoring, and intelligent transportation, radar technology's performance directly affects the system's detection, tracking, identification, and decision-making capabilities. In the research, development, testing, operation training, and tactical studies of radar systems, there is a high reliance on a large amount of diverse and realistic radar simulation data. This data can simulate the complex electromagnetic environment and various target characteristics in the real battlefield environment.

[0003] However, existing systems often lack unified and flexible data access and standardization capabilities, making it difficult to seamlessly access and effectively integrate data from different sources and in different formats. This results in severe data silos and underutilization of data value. Secondly, the data generated by existing radar simulation systems is often limited in scenario complexity, making it difficult to accurately simulate highly complex battlefield environments. Furthermore, the target models are relatively simple, and the simulation of diverse dynamic behavior characteristics of targets is not realistic or flexible enough. Parameter adjustments are complex, making it difficult for simulation data to comprehensively and realistically reflect the actual working state of radar and target behavior characteristics under various extreme or typical combat scenarios. This limits its value in in-depth research on radar performance boundaries and analysis of the dynamic changes of targets in complex environments. In addition, existing systems lack the ability to deeply explore the movement patterns and cooperative relationships of target groups, making it difficult for users to comprehensively, quickly, and accurately grasp the battlefield situation, affecting the scientific nature and timeliness of decision-making. Summary of the Invention

[0004] The purpose of this invention is to provide a radar analog data information integration and processing system to solve the technical problems existing in the prior art.

[0005] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0006] A radar simulation data information integration and processing system includes the following modules: a data access module, which receives data signals generated by a radar signal simulator to enable access to multi-type and multi-format radar simulation data; a data processing and fusion module, which preprocesses the raw data received by the data access module and then uses a multi-source data fusion algorithm to achieve spatiotemporal alignment, feature fusion, and decision fusion of different radar simulation data; a radar simulation and scene generation module, which incorporates multiple radar system models to correlate, filter, and track the fused data from the data processing and fusion module, forming continuous target tracks, and generating corresponding complex battlefields and corresponding environmental models based on the target tracks and preset algorithms; an intelligent processing and analysis module, which uses multiple preset processing algorithms and analysis models to perform in-depth mining and analysis of radar simulation data; a visualization module, which displays the results of the intelligent processing and analysis module in the form of two-dimensional visualization, three-dimensional visualization, and dynamic visualization; and a management module, which monitors and manages the working status of each module.

[0007] Furthermore, the preprocessing steps in the data processing and fusion module include: data format conversion, converting data of different formats into the system standard format and verifying the integrity of the data; noise filtering and smoothing, using median filtering, mean filtering, and Fourier transform algorithms for noise reduction; data standardization and normalization, converting radar parameter data of different magnitudes into the same magnitude; and feature extraction, extracting key information from radar simulation data through pattern recognition and feature extraction algorithms.

[0008] Furthermore, the radar simulation and scene generation module includes various radar system models, such as: pulse model, continuous wave model, pulse Doppler model, phased array model, and synthetic aperture model.

[0009] Furthermore, the intelligent processing and analysis module includes the following units: a target detection and tracking unit, which employs a constant false alarm rate (CFAR) test algorithm to inspect targets in radar simulation data; a convolutional neural network algorithm for accurate detection of small targets; and Kalman filtering, extended Kalman filtering, and unscented Kalman filtering for target tracking. The Kalman filtering is used for tracking targets in a linear Gaussian system, calculating the target's position and velocity. A radar performance analysis unit analyzes the radar simulation data and evaluates various performance indicators of the radar system, including detection range, ranging accuracy, angle measurement accuracy, and resolution. It plots radar detection range curves by analyzing the maximum detection range at different distances. A threat assessment and situation analysis unit extracts target feature parameters and combines them with a preset threat assessment model to assess the threat level of the targets. It uses a clustering analysis algorithm to group targets and identify the movement patterns of target groups. It also analyzes the cooperative relationships between targets through association rule mining.

[0010] Furthermore, the threat levels in the threat assessment and situation analysis unit include: low-level threats, medium-level threats, and high-level threats.

[0011] Compared with the prior art, the present invention has the following beneficial effects:

[0012] (i) Through the setup of the data access module and the data processing and fusion module, this invention can receive various types and formats of data signals generated by the radar signal simulator, and preprocess and fuse them, thereby improving the accuracy and reliability of the data. Then, the above data is used to create complex battlefield and environment models through the radar simulation and scene generation module. This not only simulates diverse radar working scenarios, but also provides support for studying the characteristics of radar data and target behavior in different scenarios. This helps users to fully understand radar performance and the dynamic changes of targets in complex environments, thereby enhancing the practicality and adaptability of the system.

[0013] (II) Through the intelligent processing and analysis module, this invention can effectively identify and track targets with different characteristics, improve the monitoring capability of targets, and analyze the movement patterns and cooperative relationships of target groups through cluster analysis algorithms and association rules, so as to help users fully grasp the battlefield situation and make scientific decisions. Attached Figure Description

[0014] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0015] To make the content of this invention easier to understand, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Identical components are represented by the same reference numerals. It should be noted that the terms "front," "rear," "left," "right," "up," and "down" used in the following description refer to directions in the accompanying drawings, while the terms "inner" and "outer" refer to directions toward or away from the geometric center of a specific component, respectively.

[0016] like Figure 1 As shown, this embodiment provides a radar simulation data information integration and processing system, including the following modules:

[0017] The data access module receives data signals generated by the radar signal simulator to enable access to multiple types and formats of radar simulation data. This module is equipped with various physical interfaces, including: Ethernet interface, USB interface, RS-485 serial interface, and fiber optic interface.

[0018] The data processing and fusion module preprocesses the raw data received by the data access module, and then uses a multi-source data fusion algorithm to achieve spatiotemporal alignment, feature fusion, and decision fusion of different radar simulation data. The preprocessing steps in the data processing and fusion module include: data format conversion, converting data of different formats into the system standard format, covering various types such as binary streams, text logs, image arrays, and custom protocol data packets, and performing data integrity verification. Data that fails the verification is marked as abnormal data, stored in an independent abnormal buffer, and the reason for the abnormality is recorded; noise filtering and smoothing, using median filtering, mean filtering, and Fourier transform algorithms for denoising; the median filtering, mean filtering, and Fourier transform algorithms are existing technologies and will not be elaborated further here; after filtering, the denoising effect is quantitatively evaluated using indicators such as signal-to-noise ratio and root mean square error; data standardization and normalization, converting radar parameter data of different magnitudes into data of the same magnitude. To improve the accuracy of processing results: Feature extraction utilizes pattern recognition and feature extraction algorithms to extract key information from radar simulation data, including parameters such as range, azimuth, elevation, velocity, and radar cross-section. For complex radar image data, edge detection and contour extraction algorithms are used to extract target shape features. Spatiotemporal alignment employs timestamp synchronization technology to calibrate the timestamps of each radar simulation data using a unified system time base. Spatial alignment transforms the spatial coordinates of different radar simulation devices into a unified coordinate system with meter-level accuracy, ensuring spatial matching of radar simulation data from different sources. Feature fusion integrates feature information from different radar simulation data to generate more comprehensive and discriminative feature vectors. Multi-feature fusion algorithms are used to extract key feature components, reducing feature dimensions and improving subsequent data processing efficiency. Decision fusion comprehensively analyzes the decision results from different radar simulation data to generate the final decision conclusion.

[0019] The radar simulation and scene generation module incorporates multiple radar system models. It correlates, filters, and tracks the fused data from the data processing and fusion module, forming continuous target tracks. Based on these tracks and a preset algorithm, it generates corresponding complex battlefields and environmental models. It comprehensively considers factors such as terrain, weather conditions, and electromagnetic environment to generate highly realistic complex battlefield environments and matching environmental models. The multiple radar system models in the radar simulation and scene generation module include: pulse models, continuous wave models, pulse Doppler models, phased array models, and synthetic aperture models. The pulse model uses intermittent electromagnetic pulse signals to detect targets, simulating how traditional radar acquires targets by emitting brief, high-intensity pulse waves and analyzing the echoes. The radar operates by transmitting information such as distance and velocity. The continuous wave model continuously emits electromagnetic waves and detects targets by analyzing the frequency changes and other characteristics of the echo signal; it is commonly used for high-precision velocity measurement of moving targets. The pulse Doppler model not only accurately measures the target's distance but also obtains the target's radial velocity information by analyzing Doppler frequency shifts, making it important for monitoring high-speed moving targets in military and aviation fields. The phased array model simulates the unique operating mode of a phased array radar, which achieves rapid beam scanning and flexible pointing by electronically controlling the phase of each radiating element in the array antenna. The synthetic aperture model synthesizes an equivalent large-aperture antenna through radar platform movement and signal processing algorithms, greatly improving the radar's azimuth resolution.

[0020] The intelligent processing and analysis module employs multiple preset processing algorithms and analysis models to deeply mine and analyze radar simulation data. This module includes the following units: a target detection and tracking unit. For target detection, it uses a constant false alarm rate (CFAR) test algorithm, which can automatically and accurately adjust the detection threshold based on real-time noise statistical characteristics under various complex environmental conditions. Through in-depth and detailed statistical analysis of radar echo signals, it can keenly capture subtle differences between target signals and noise interference, effectively filtering target signals from a sea of ​​noise and verifying targets in the radar simulation data. The CFAR test algorithm can effectively distinguish between target signals and noise interference. It also employs a rolling... The convolutional neural network algorithm enables accurate detection of small targets. By constructing a deep neural network structure composed of multiple convolutional and pooling layers, the algorithm can automatically learn feature patterns in radar images. For target tracking, Kalman filtering, extended Kalman filtering, and unscented Kalman filtering are employed. The Kalman filter, for target tracking in a linear Gaussian system, calculates the target's position and velocity, accurately determining key state information such as position and velocity at each moment. Based on the aircraft's initial position, velocity, and flight direction, combined with real-time radar measurement data, it accurately predicts the aircraft's position at the next moment, providing reliable target information for air traffic control. The extended Kalman filter... By automatically adjusting tracking parameters in real time based on the target's nonlinear motion trajectory, the system adapts to changes in the target's motion state, ensuring uninterrupted continuous tracking. The unscented Kalman filter selects a set of sampling points to directly approximate the probability distribution of the nonlinear function, more accurately describing the state changes of the nonlinear system and ensuring extremely high precision in target monitoring and tracking. The radar performance analysis unit analyzes radar simulation data and evaluates various performance indicators of the radar system, including detection range, ranging accuracy, angle measurement accuracy, and resolution. By analyzing the maximum detection range at different distances, a radar detection range curve is plotted, with the maximum detection range as the vertical axis. The system depicts the changing trends of radar detection capabilities across different distance ranges. By observing these curves, users can understand the radar's performance characteristics at different distances, thus helping them rationally select the radar's operating mode and deployment location based on actual needs. The threat assessment and situation analysis unit extracts target characteristic parameters and combines them with a preset threat assessment model to evaluate the target's threat level. The threat levels in this unit include: low-level threat, medium-level threat, and high-level threat. Low-level threats represent unarmed or slow-moving targets that pose a relatively small threat. Medium-level threats represent targets with a certain degree of mobility and potential threat capabilities that can pose a direct threat.The advanced threat refers to targets with strong attack capabilities, high mobility, and the ability to directly threaten our side, requiring immediate and effective defensive measures to strike them; clustering analysis algorithms are used to group targets, identify the movement patterns of target groups, and take corresponding response measures to disrupt the enemy's combat plan; the cooperative relationship analysis is conducted by mining and analyzing the cooperative relationships between targets through association rules, which plays a crucial role in combat effectiveness;

[0021] The visualization module displays the results of the intelligent processing and analysis module through two-dimensional visualization, three-dimensional visualization, and dynamic visualization. Two-dimensional visualization presents the results of the intelligent processing and analysis module in a planar format, intuitively displaying various key information from the radar data. Using a two-dimensional coordinate system, different targets are marked on the plane as points or icons, clearly showing their relative positions and allowing users to quickly understand the approximate distribution of targets. Three-dimensional visualization comprehensively displays the spatial location, altitude information, and terrain of the radar monitoring area. When displaying aerial targets, it not only accurately presents the target's position on the two-dimensional plane but also shows its flight altitude through the altitude dimension, making the target's spatial location information more complete. Furthermore, combined with three-dimensional modeling of the terrain, operators can intuitively connect the relationship between the target and its surrounding environment, facilitating in-depth analysis of the complex relationship between the target and the environment. Dynamic visualization presents the dynamic changes of radar simulation data through continuous screen displays. It can reflect the target's trajectory, real-time fluctuations in radar performance indicators, and the dynamic evolution of the battlefield situation in real time, helping users to fully understand the evolution of the battlefield situation and make corresponding decisions.

[0022] The management module monitors and manages the working status of each module, and regularly checks each module to identify potential faults in advance and provide timely warnings and repairs.

[0023] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A radar analog data information integration and processing system, characterized in that: Includes the following modules: The data access module receives data signals generated by the radar signal simulator, enabling access to multiple types and formats of radar simulation data. The data processing and fusion module preprocesses the raw data received by the data access module, and then uses a multi-source data fusion algorithm to achieve spatiotemporal alignment, feature fusion, and decision fusion of different radar simulation data. The radar simulation and scene generation module has multiple built-in radar system models. It correlates, filters, and tracks the fused data from the data processing and fusion module, and forms continuous target tracks. Based on the target tracks and preset algorithms, it generates corresponding complex battlefields and corresponding environmental models. The intelligent processing and analysis module employs a variety of preset processing algorithms and analysis models to perform in-depth mining and analysis of radar simulation data. The visualization module displays the results of the intelligent processing and analysis module in the form of two-dimensional visualization, three-dimensional visualization, and dynamic visualization. The management module monitors and manages the working status of each module.

2. The radar analog data information integration and processing system according to claim 1, characterized in that: The preprocessing steps in the data processing and fusion module include: Data format conversion: Converts data from different formats into the system's standard format and performs data integrity verification. Noise filtering and smoothing are performed using median filtering, mean filtering, and Fourier transform algorithms for noise reduction. Data standardization and normalization convert radar parameter data of different magnitudes into the same magnitude; Feature extraction involves using pattern recognition and feature extraction algorithms to extract key information from radar simulation data.

3. The radar analog data information integration and processing system according to claim 1, characterized in that: The radar simulation and scene generation module includes various radar system models, such as pulse model, continuous wave model, pulse Doppler model, phased array model, and synthetic aperture model.

4. The radar analog data information integration and processing system according to claim 1, characterized in that: The intelligent processing and analysis module includes the following units: The target detection and tracking unit employs a constant false alarm rate (CFAR) test algorithm to verify targets in radar simulation data, and a convolutional neural network algorithm for accurate detection of small targets. For target tracking, Kalman filtering, extended Kalman filtering, and unscented Kalman filtering are used; the Kalman filtering is used for target tracking of linear Gaussian systems to calculate the target position and velocity; The radar performance analysis unit analyzes radar simulation data and evaluates various performance indicators of the radar system, including detection range, ranging accuracy, angle measurement accuracy, and resolution. It also plots radar detection range curves by analyzing the maximum detection range at different distances. The threat assessment and situation analysis unit evaluates the threat level of targets by extracting their characteristic parameters and combining them with a pre-set threat assessment model; it uses clustering analysis algorithms to group targets and identify the movement patterns of target groups; and it analyzes the collaborative relationships between targets through association rule mining.

5. The radar analog data information integration and processing system according to claim 4, characterized in that: The threat levels in the threat assessment and situation analysis unit include: low-level threats, medium-level threats, and high-level threats.

Images