75 results about "Radar radiation" patented technology

The invention relates to the technical field of echo signal analysis, and discloses a radar radiation source signal identification method based on multi-task learning under physical feature constraint, which comprises the following steps of: 1, establishing a data set by a two-dimensional tensor and a physical feature tag; 2, the identification model comprises a feature extraction network and a multi-task learning network, and the multi-task learning network comprises a frame prediction branch, a classification branch, a parameter regression branch and a frequency spectrum prediction branch; 3, training the recognition model to obtain a trained recognition model; and step 4, inputting a two-dimensional tensor to be recognized into the trained recognition model, and outputting predicted physical characteristics, probability distribution of signal categories, predicted values of parameters and a remodeled two-dimensional STFT spectrogram. Physical priori knowledge and multi-task cooperative constraint are introduced, the physical nature of radar signals can be accurately captured, the interpretability and anti-noise capability of the model are improved, the expression capability of the model for key features is enhanced, and the method is suitable for scenes with sparse feature distribution or weak target signals.

The invention provides a radar model identification method and device and a storage medium, and belongs to the technical field of radar identification, and the method comprises the steps: obtaining original pulse description word data and original intermediate frequency data through electronic reconnaissance collection equipment; associating the original pulse description word data with the original intermediate frequency data to obtain associated pulse description word data and associated intermediate frequency data; and performing parameter analysis on the associated pulse description word data and the associated intermediate frequency data to obtain a target parameter group. According to the method, the fault tolerance is improved, the method can be used for identifying the model of the radar radiation source when signals are missing or distorted, the identification rate of the radar model is greatly improved, and meanwhile, the method does not need to depend on the type of radar radiation source signals in a database and the quality of collected parameters.

This application relates to the field of individual radiation source identification, specifically to a method and apparatus for individual radar radiation source identification in small-sample open-set scenarios. One specific implementation of the method includes: inputting the acquired target input signal into a pre-trained optimized feature extraction model to obtain the original target activation vector; determining the target activation distance vector based on the original target activation vector; inputting the target activation distance vector into a preset extreme value theoretical model to obtain a target reliability score; correcting the original target activation vector based on the target reliability score to generate a corrected target activation vector; normalizing the corrected target activation vector based on a preset normalization formula to generate a normalized probability; and determining target identification information based on the normalized probability, a preset threshold, and a preset identification formula. This implementation can achieve individual radiation source identification under small-sample conditions.

The invention relates to a radar sensor (10) having at least one antenna element (20-22, 25-27) and a converging radar lens (30); a focal point (40) of the converging radar lens for radar radiation has a predetermined focal length (FA) from a lens side (31) of the converging radar lens (30) facing the focal point (40). According to the invention, at least one antenna element (20-22, 25-27) is spatially arranged outside an area located between the focal point (40) and a lens side (31) of the converging radar lens (30) facing the focal point (40).

Seeker head (2) for a guided missile (1), comprising a detection device (3) having a first detection unit (6) for detecting infrared radiation and a second detection unit (8) for detecting radar radiation, wherein the detection unit (3) has a cooling device (14) configured to cool at least a first detection element (7) of the first detection unit (6), in particular a detector, and at least a second detection element (9) of the second detection unit (8), in particular an antenna element.

The application provides a radar waveform classification method and system based on effective area identification, and the method comprises the following steps: inputting a radar emitter time-frequency image into a preset SSD network trained in advance to obtain an effective area where a single intra-pulse signal is located and a corresponding radar waveform category output by the preset SSD network; the preset SSD network is trained by taking multiple radar emitter time-frequency images as training samples, taking the effective area where the single intra-pulse signal is located in each radar emitter time-frequency image and the corresponding radar waveform category as labels. The application identifies the effective area where the intra-pulse signal of the radar emitter time-frequency image is located by using the SSD network, and only classifies the category of the waveform in the effective area in the subsequent process, thereby avoiding the influence of signal characteristics in the invalid area on identification, and effectively improving the identification accuracy of the radar waveform.

The invention relates to an angle-resolved radar sensor (8), comprising a transmitting and receiving device and an evaluation device (32) for determining positioning data of a target (24) reflecting radar radiation, the evaluation device (32) being configured to identify a multi-path scene in which the radar radiation is reflected by the target (24). A portion of the received signal representative of the target is based on the reflection of the transmitted and / or received signal at the reflection surface (42), characterized in that the evaluation device (32) is further configured to automatically determine the azimuth angle (gamma) of the reflection surface (42) or to read it from an external source, and determining a tangential velocity (v [theta]) of the target (24) based on the different Doppler shifts of the signal portions obtained on the different paths.

The invention relates to a method (100) for reconstructing elevation information (2a) from measurement data (2), which is recorded with at least one radar device (1) and contains a two-dimensional spatial distribution (3) of at least one physical measurement variable, wherein the measurement data (2) is delivered (110) as an input variable (5) to at least one generator module (4) configured as a neural network, and wherein at least one output variable (6) is called up (120) from the generator module (4), which is a measure of how great an elevation angle (6a) at which radar radiation is reflected by at least one object to the radar device (1). A method (200) for training a generator module (4) for use in the method (100) is also described. A method (300) with a complete chain of actions up to the maneuvering of a vehicle (50) is also described.

The invention relates to a method and an assembly (11) for calibrating at least one radar sensor (25) of a vehicle (30), the assembly (11) comprising a calibration device (1) which has: - a reflector plate (10) for reflecting radar radiation from the radar sensor (25), and - at least one camera (60), and the assembly (11) being designed to acquire orientation information relating to at least one of the vehicle (30), the radar sensor (25) and the reflector plate (10) on the basis of image information captured by the camera (60) and to generate, on the basis of this orientation information, control specifications for the actuator-based movement of the reflector plate (10).

The invention discloses a PRI sorting method and system in a complex electromagnetic environment, and the method specifically comprises the steps: carrying out the sorting and extraction of a pulse sequence through employing a dynamic two-dimensional feature vector matching algorithm, and obtaining a pulse sequence of a fixed and staggered PRI modulation signal; then carrying out sorting extraction on the residual pulses by using a square sine interpolation algorithm to obtain a pulse sequence of the jitter PRI modulation signal; then, through a feature recognition method, obtaining modulation features of the pulse sequences of the fixed and staggered PRI modulation signals and the pulse sequences of the jitter PRI modulation signals; and finally, carrying out intra-frame blending on the sorting result of the pulse stream, and carrying out inter-frame blending on the sorting result of the previous pulse stream to finish sorting. According to the method, the PRI sorting accuracy is improved, the batch increasing phenomenon is reduced, multiple PRI modulation patterns can be sorted and recognized, the pulse sequences belonging to different radar radiation sources are separated from a large number of mixed radar signals, and a reliable data basis is provided for subsequent recognition, positioning and confrontation.

Radar data fusion evaluation for classifying objects. Method (100) for classifying an object (4) from measurement data (2) recorded with at least one radar sensor (1), with the steps: • providing a spectrum (5) of time-dependent measurement data (2) of the radar sensor (1) (110); • determining positions (6) from the spectrum (5) (120), from which positions radar radiation reflected reaches the radar sensor (1); • determining at least one group (7) of such positions (6*) belonging to one and the same object (4) (130); • determining for each position (6*) in the group (7) a component (5*) of the spectrum (5) (140), which corresponds to the radar radiation reflected by the position (6*); • aggregating (150) all these components (5*) for the object (4) and delivering to a classifier (8) (160); • assigning the object (4) with the classifier (8) to one or more classes (3a-3c) of a predefined classification (3) (170).

The embodiment of the invention discloses a variable modulation radar signal individual identification method and device. A specific implementation mode of the method comprises the following steps: acquiring a variable modulation radar signal emitted by a radar radiation source individual; individual identification is carried out on the variable modulation radar signal through a preset radar signal identification model to generate a radar signal individual identification result, and the radar signal identification model comprises a feature extraction module, a deep variational auto-encoder, a label prediction module and a domain classification module. The feature extraction module is used for extracting fingerprint features of the variable modulation radar signals, and the domain classification module is used for judging a source domain or a target domain corresponding to the variable modulation radar signals. According to the embodiment, the accuracy of radar signal identification can be improved.

The invention relates to a lighting device (1) for visibly displaying at least one ornament (7), in particular for a motor vehicle, comprising a plurality of light units (3, 5) having a light source (11) for generating light and at least one light exit area (13), wherein at least one light-transparent cover element (17) encloses the at least one light exit area (13), wherein the light-transparent cover element (17) is arranged outside a radar coupling-in surface (19) of at least one radar-transparent section (9) for coupling-in radar radiation with respect to an optical axis (A) of the lighting device (1), and at least one radar-transparent section (9) having a radar coupling-in surface (19) for coupling-in radar radiation.

The invention discloses an improved WaveGAN radar radiation source sequence signal augmentation method based on physical constraints, and relates to the technical field of radar radiation source signal processing, and the method comprises the steps: carrying out the preprocessing of an original radar time domain signal, and constructing a one-dimensional radar signal sequence data set; an improved WaveGAN model is constructed, a generator of the improved WaveGAN model adopts a deep deconvolution neural network containing a pyramid type multi-scale convolution kernel and introduces a self-attention mechanism, and a discriminator adopts a convolution neural network containing an inverted pyramid type multi-scale convolution kernel and introduces a self-attention mechanism; inputting a data set into the model for adversarial training, wherein a total loss function of a generator is formed by weighting adversarial loss and mean square error loss of constraint signal physical characteristics; and synthesizing a radar radiation source signal sequence for data augmentation by using the trained generator. According to the method, the quality of the generated signal is remarkably improved.

This invention proposes a method and apparatus for synthesizing array radar radiation patterns using space-time joint modulation. The method includes: determining initial values ​​of the array radar element excitation coefficients; acquiring the array far-field radiation pattern under the influence of the initial values ​​of the element excitation coefficients; dividing the array far-field radiation pattern into main lobe and side lobe regions based on its characteristics; setting the random modulation phase of the main lobe region to zero, maintaining the same main lobe phase across different pulses, while modulating the phase of the side lobe region regularly or randomly, while keeping the array far-field radiation pattern amplitude constant, thus obtaining array radiation patterns with different phase characteristics under multiple pulses; performing Fourier transforms on the array radiation patterns under different pulses to obtain the space-time two-dimensional element excitation coefficients; and applying the space-time two-dimensional element excitation coefficients to the array radar system to synthesize the array radar radiation pattern after space-time joint modulation. This invention significantly improves the array radar's resistance to sidelobe clutter and interference.

The invention belongs to the technical field of radar radiation source identification. The invention provides a radar radiation source identification method based on relation perception and prototype optimization. According to the embodiment of the invention, through channel gating and a soft attention mechanism, invalid frequency band features are automatically inhibited, and the weight of a bad sample which deviates from the center is reduced. And a GCN is introduced to construct a sparse prototype graph, so that the model can perceive a similarity relationship between categories, and local consistency is enhanced through a graph propagation mechanism. And in cooperation with prototype comparison loss, centers of similar categories are forcibly pushed away, so that a clearer isolation strip is formed at a decision boundary, and the false identification rate is remarkably reduced. A residual mean fusion structure is also designed. When an attention mechanism may fail due to extremely small sample size, a mean value prototype on a residual path can play a role in guaranteeing the bottom, so that the stability of model training is ensured; and when the sample size is slightly large, the attention mechanism can provide finer feature expression, so that the universality of the model under different small sample settings is realized.

The invention discloses an available power time-varying radar radiation power distribution method. The method comprises the following steps: acquiring the currently available total power of a radar in real time; determining available radiation power of the radar from the currently available total power; according to the pulse width, the pulse repetition period and the task execution data rate of each radar task in the current scheduling interval, calculating the average power of each task; in the current working mode, the priority of each task is analyzed; gradually adjusting the pulse width or the data rate according to the task priority; the tasks to be executed by the radar are arranged according to the scheduling interval, the power consumption in the current scheduling interval is counted in real time, and if the instantaneous power exceeds the available radiation power, the low-priority tasks are added into a delay list; and calculating the detection capability of a specific radar cross section (RCS) target under the current power in real time. According to the invention, available power fluctuation can be responded in real time, radar emission resources are dynamically optimized, and the execution success rate of high-priority tasks is preferentially guaranteed.

The invention discloses a small sample radiation source individual identification method based on multi-scale feature fusion. Firstly, signal quality analysis and data screening are carried out on a data set, and useless data with poor quality is removed; secondly, dividing the data set, and dividing the screened data set into a large sample data set with sufficient samples and small sample data with less samples; constructing a neural network based on self-supervised learning and multi-scale feature fusion; then performing self-supervised pre-training on the neural network by using all the data sets; performing structure fine tuning and parameter fine tuning on the pre-trained neural network by using the small sample data set; and finally, realizing radar radiation source individual identification under the condition that the number of samples is limited by using the fine-tuned neural network. According to the method, a large sample data set can be reasonably utilized, and the radar radiation source individual recognition accuracy under the condition that the number of samples is limited is effectively improved.

The invention relates to a radar reflector (1) for reflecting radar radiation (2), comprising at least one reflection element (5) rotatable about a central axis (4) of the radar reflector (1) and an adjusting device (7) for changing and / or parameterizing a characteristic of a radar echo (3) of the radar reflector (1). At least one of the following parameters can be changed by means of the adjusting device (7): the angular velocity ω of rotational motion of the at least one reflection element (5) about the central axis (4); an effective reflection area of the at least one reflection element (5); and a fastening position p of the at least one reflection element (5) relative to the central axis (4). The invention also relates to a system for controlling automated operation of a motor vehicle, comprising at least one radar reflector of this type, and to a motor vehicle (23), which has a radar sensor (24) and is designed to automatedly carry out a predefined sequence of driving maneuvers in accordance with a sensed characteristic of the radar echo of the radar reflector.

The invention discloses a radar radiation source antenna pattern parameter estimation method based on multi-scale semantic segmentation, and the method comprises the steps: constructing a radar radiation source pattern TOA-PA sequence intercepted by a reconnaissance receiver, and considering the non-ideal observation conditions of pulse loss and noise pulse; the identification of the main lobe pulse and the side lobe pulse and the estimation of the beam width and the main-to-side ratio are realized. According to the method provided by the invention, high identification accuracy and high-precision beam width and main-to-side ratio estimation can be realized under the conditions of pulse loss and stray pulse interference.

This invention discloses a method for extracting radio frequency (RF) features from radar radiation sources. The method involves acquiring and preprocessing the RF signal from which features are to be extracted, then inputting it into pre-trained networks 1 and 2 for feature extraction. Both networks 1 and 2 are stacked autoencoder networks and contain multi-layer encoders and decoders of the same number of layers. The last encoder layer of network 2 outputs the extracted RF features. The training process includes inputting an ideal RF signal dataset and a modeled RF signal dataset into networks 1 and 2 respectively for hierarchical pre-training and global training until training is complete, resulting in trained networks 1 and 2. This invention can separate the signal features and RF features of a radiation source signal under the constraint of signal features, resulting in more complete extracted RF features. The extracted RF features can be used in applications requiring high accuracy of RF features, such as individual radiation source identification and interference suppression.

The invention relates to a Ku / Ka dual-band space radiometric calibration method for a satellite-borne rainfall measurement radar, and the method specifically comprises the steps: S1, carrying out the radiometric calibration of the satellite-borne rainfall measurement radar through a space radiometric calibrator, obtaining a corresponding relation between a radar working parameter and a radiation measurement error, and constructing a satellite-borne rainfall measurement radar radiation measurement error database; s2, training and learning the neural network through the satellite-borne rainfall measurement radar radiation measurement error database, and generating a satellite-borne rainfall measurement radar radiation measurement error estimation model; and S3, obtaining radar working parameters of the spaceborne rainfall measurement radar, performing radiation measurement error estimation of the spaceborne rainfall measurement radar through the spaceborne rainfall measurement radar radiation measurement error estimation model, and performing radiation error compensation according to a radiation measurement error estimation result. According to the invention, the calibration precision of the spaceborne rainfall measurement radar is effectively improved, and the rainfall inversion precision is further improved.

The invention discloses a broadband linear frequency modulation signal splicing and real-time identification method, which comprises the following steps of: judging whether pulse description words of pulse strings containing linear frequency modulation type identifiers have correlation in time or not, if the pulse description words have the correlation, splicing the pulse strings with the correlation in time, and if the pulse description words do not have the correlation in time, splicing the residual pulse strings which do not meet the correlation in time, the method comprises the following steps of: determining whether the modulation slope meets a preset threshold, if the modulation slope is within a preset threshold range, considering that the modulation slope belongs to the same pulse string sequence and splicing the modulation slope, and then splicing cross-local oscillator target signals which are detected in a time-sharing manner and are obtained by splicing in a pulse data stream and carrying out radar radiation source identification. According to the scheme, time-frequency domain association fusion is gradually carried out on channelized full-pulse data by fully utilizing the time-frequency domain characteristics of the signals, split original signals are spliced and fused to form a new signal, and parameters of the new signal are recalculated, so that adverse effects caused by digital channelized detection and a frequency synthesizer module are reduced, and the detection accuracy is improved. And the target interception probability is improved.

The invention provides a self-adaptive decision-making method based on multi-unmanned aerial vehicle cooperative interference. The method comprises the following steps: constructing a multi-unmanned aerial vehicle cooperative interference task decision-making model in an electronic countermeasure scene containing a radar and multiple unmanned aerial vehicles; based on the multi-unmanned aerial vehicle cooperative interference task decision model, performing parametric modeling on the interference behavior of the interference unmanned aerial vehicle to generate an interference action space; training the multi-unmanned aerial vehicle cooperative interference task decision model based on the interference action space to obtain a cooperative interference decision model; a cooperative interference decision model is deployed on each interference unmanned aerial vehicle, each interference unmanned aerial vehicle extracts radar signal features and constructs a local observation state only based on radar radiation signals intercepted by an airborne electronic support measure system of the interference unmanned aerial vehicle, and an interference decision is independently output under the condition of no centralized control and no explicit communication, so that a cooperative interference task is completed; according to the method, through a global value evaluation mechanism in a centralized training stage, multiple unmanned aerial vehicles can form implicit cooperation in interference target selection, interference modes and interference power control levels in an execution stage, and redundant interference and interference resource conflicts of the multiple unmanned aerial vehicles on the same target are avoided.

The application discloses a radar radiation source working mode recognition method and device based on GCN, relates to the technical field of radar signal classification, and comprises the following steps: simulating each working mode of a radar radiation source; extracting feature parameters of each simulated working mode and forming a feature matrix; wherein the feature parameters comprise pulse repetition frequency, pulse width, duty cycle, intra-pulse modulation mode, frequency visibility, echo, the number of pulses on each CPI, and bandwidth; performing normalization processing on the feature matrix; training a preset GCN recognition network by using the processed feature matrix, so as to obtain a radar radiation source recognition model; identifying the processed radar radiation source signals to be identified by using the radar radiation source recognition model, so as to obtain the working mode of the radar radiation source signals; and performing dimension reduction and visualization on the working mode of the radar radiation source signals. The application can solve the problem that the connection between feature parameters of different working modes of the existing radar radiation source is weak and sparse.

The application relates to a kind of incremental radar radiation source individual intelligent identification method based on K center feature distribution reconstruction, belong to radar data processing technical field. Including: initial category data set is generated by simulation, initial category data set is used as the input of feature extractor, feature extractor is trained based on improved supervised contrast loss function, feature extraction is carried out using feature extractor to obtain training set features;The training set features of each class are extracted based on K-means multi-center, obtain each cluster center of each class as the K center set of this class feature and the point number contained in the cluster where the K center is located, generate point number noise around K center as pseudo-feature;Pseudo-feature and new class feature are merged, and network classifier is trained. The method can process the task of radar radiation source individual incremental identification under small sample condition, and significantly improve the generalization of the model.

A multispectral emission device includes at least one transmitting unit for LiDAR radiation, one receiving unit for LiDAR radiation, and at least a LiDAR radiation manipulating device, and a radar radiation manipulating device. The LiDAR radiation manipulating device and the transmitting unit for LiDAR-S are arranged such that the LiDAR radiation manipulating device redirects LiDAR radiation emitted by the transmitting unit for LiDAR radiation and the LiDAR radiation manipulating device is set up such that LiDAR radiation passing through the headlight cover from the outside is guided to the receiving unit for LiDAR radiation. The radar radiation manipulating device is set up such that radar radiation passing through the headlight cover from the outside is guided to the receiving unit for radar radiation. The transmitting unit for LiDAR radiation, the LiDAR radiation manipulating device, the radar module, and the radar radiation manipulating device are arranged such that at least one radiation cone of diverted LiDAR radiation and at least one radiation cone of diverted radar radiation are aligned.

The application discloses a radar antenna directional diagram parameter estimation method based on a key point recognition network, constructs a radar radiation source directional diagram TOA-PA sequence intercepted by a reconnaissance receiver, maps a one-dimensional pulse into a two-dimensional gray scale image, directly extracts key point coordinates representing a directional diagram structure from the directional diagram by using a key point detection model, and then high-precision estimation of 3dB beam width and a peak side lobe ratio is realized. The method can realize robust inversion of the directional diagram parameters in a complex electromagnetic environment, and significantly improves the reliability of radar radiation source characteristic inversion.

This invention discloses a radar source sorting method based on deep embedded clustering (DEC) and temporal feature reconstruction. First, the amplitude (AMP), radio frequency (RF), pulse width (PW), and time of arrival (TOA) of the radar pulses are extracted. After cleaning anomalies based on the radio frequency (RF) and pulse width (PW), the data is input into a one-stage DEC network for initial clustering. For each cluster, the multi-order cumulative temporal difference of TOA is calculated. Lost pulses are identified and equivalently restored using cumulative jitter relaxation tolerance, or a soft smooth reconstruction is performed using a boundary truncation mechanism to extract the pulse repetition interval (PRI). Next, [RF, PW, PRI] are combined to construct a three-dimensional enhanced feature, which is input into a two-stage DEC network for secondary clustering to complete the final sorting. The amplitude feature (AMP) is then used for cross-validation. This invention effectively overcomes the problems of feature aliasing, pulse loss, and high jitter, and achieves high-purity sorting of fixed, jittery, and staggered mode radiation sources, significantly improving robustness in complex electromagnetic environments.