71 results about "Autocorrelation matrix" patented technology

The invention discloses a fault identification method and device for a rotating mechanism, computer equipment and the rotating mechanism. The method comprises the following steps: acquiring rotating speed information and a time domain vibration signal of the rotating mechanism; converting the time domain vibration signal into an angular domain vibration signal based on the rotating speed information; performing feature extraction on the angular domain vibration signal based on the autocorrelation matrix of the angular domain vibration signal and the filter coefficient to update the filter coefficient and obtain a target filter coefficient; and determining fault characteristics of the rotating mechanism based on a target vibration signal obtained by processing the angular domain vibration signal based on the target filtering coefficient. According to the method provided by the invention, the fault features of the unsteady vibration signals of the rotating mechanism can be effectively extracted, so that reliable fault diagnosis of the rotating mechanism is realized.

The present disclosure provides a data processing method, apparatus and device, a vehicle, a medium, and a program product. The method comprises: acquiring millimeter-wave radar point voxel data corresponding to millimeter-wave radar data; encoding the millimeter-wave radar point voxel data to generate a target voxel sequence feature; performing multi-layer linear computation on the target voxel sequence feature to generate a query sequence feature, a key sequence feature, and a value sequence feature; computing the query sequence feature and the key sequence feature on the basis of an attention mechanism to obtain an autocorrelation matrix; and encoding the autocorrelation matrix and the value sequence feature, and performing residual connection on an encoding result and the target voxel sequence feature to generate a millimeter-wave radar autocorrelation-enhanced sequence feature.

The invention relates to the technical field of radar signal processing, in particular to a deep learning-based target detection method in a sea clutter environment, which comprises the following steps of: acquiring echo signals in the sea clutter environment, arranging the echo signals according to a high-speed time domain and a low-speed time domain, and sampling to obtain a complex data matrix; analyzing the complex data matrix to construct an autocorrelation matrix, and obtaining input data through the autocorrelation matrix; the method comprises the following steps: constructing a self-supervised learning model based on a Transform encoder by adopting input data, and carrying out training; and obtaining data to be detected, inputting the data to be detected into the trained self-supervised learning model based on the Transform encoder to output average similarity, and obtaining a detection result of the sea clutter environment through the average similarity. Conversion analysis is carried out based on the thunder wave signal, the expression ability is improved through the model, the target and the sea clutter are distinguished, the detection ability of the weak target under the strong clutter background is effectively improved, and the problem that the target is submerged by the sea clutter and is difficult to detect under the condition of a low signal-to-noise ratio is solved.

This invention provides a sound source localization method, apparatus, and product based on incremental learning and imbalance correction. The method includes: acquiring a dataset for a new task, a parameter-frozen feature extractor, and regularization parameters; enhancing the tail category of the new task dataset; initializing an autocorrelation matrix, a cross-correlation matrix, and a category count based on the number of categories in the new task dataset; iterating through each sample in the new task dataset, updating the autocorrelation matrix, cross-correlation matrix, and category count; calculating the category weight for each category and calculating the Gini coefficient describing the category distribution; adaptively adjusting the regularization parameters based on the Gini coefficient; and solving for and outputting the optimal weight matrix based on the adjusted regularization parameters and aggregating the global autocorrelation matrix and global cross-correlation matrix of different categories. The optimal weight matrix is ​​used to update the sound source localization model. This invention addresses the problem of intra-task and inter-task imbalance in sound source localization, improving the sound source localization effect.

The invention relates to the technical field of satellite communication, in particular to a low-orbit satellite beam self-adaptive acquisition method based on fused double architectures, which comprises the following steps: realizing local clock calibration by locking a high-orbit satellite broadcast channel and acquiring a target low-orbit satellite almanac; a terminal pose and an array surface temperature gradient are acquired in real time by using an inertial measurement unit and a temperature sensor network, and a multi-dimensional physical characteristic tensor is constructed. Then, inputting the feature tensor into a nonlinear compensation model integrating multi-scale cavity convolution and a spatial self-attention mechanism, and reasoning and outputting a phase pre-distortion matrix; and by executing channel-level Hadamard product operation of the pre-distortion matrix and the theoretical pointing matrix, generating a wave control driving matrix and synthesizing a physical receiving wave beam. After a downlink signal is captured, a real Doppler frequency shift residual error is extracted, an error autocorrelation matrix is constructed, and an almanac compensation weight is reversely corrected. According to the invention, through multi-dimensional feature perception and algorithm logic closed loop, robust beam capture is realized.

The invention discloses an image semantic segmentation method and system based on cross-modal hierarchical knowledge distillation, and the method comprises the steps: inputting an image to a multi-modal teacher model and a multi-modal student model, obtaining teacher features and student features of each stage, and outputting a prediction map; the teacher features of all the stages are fused, common modal features are enhanced, fusion features corresponding to all the stages are obtained, and the fusion features and the student features are divided into high-level features and low-level features according to different stages; the low-level teacher fusion features and the low-level student features are converted into frequency domain graphs respectively, and high-frequency parts are taken out to transmit detail knowledge; respectively calculating a cross-correlation matrix and an autocorrelation matrix by using the high-level teacher fusion features and the high-level student features, and transmitting structural knowledge; and aligning the teacher output prediction map and the student output prediction map, and transmitting response knowledge. According to the invention, the multi-modal features are fused in a mode of modal enhancement, the modal gap between the teacher fusion features and the student features is reduced, and the single-modal student model segmentation precision is improved.

The present application relates to the field of radio signal identification, and particularly relates to a cross-domain few-shot specific emitter identification method based on self-supervised learning and transfer learning, comprising: adopting a self-supervised joint embedding method, pre-training a first model and a second model by using an upstream task pre-training dataset, regularizing a first autocorrelation matrix output by the first model by using von Neumann entropy, calculating the cosine similarity between the feature projections output by the first model and the second model, and updating the parameters of the first model based on the regularized autocorrelation matrix and the cosine similarity; migrating the pre-trained first encoder to a feature extractor, inputting a downstream task fine-tuning dataset into the connected feature extractor and classification head to fine-tune the feature extractor and the classification head; inputting a wireless signal into the fine-tuned feature extractor and classification head to obtain the predicted transmitter category of the signal. The present application achieves good identification accuracy under the conditions of few samples and low cost.

The invention discloses a sparse array DOA estimation method based on a residual network, and the method comprises the following steps: reconstructing an ideal Here-Toeplitz covariance matrix of a virtual uniform linear array through deep learning, and achieving the end-to-end training in combination with the differentiability of a Root-MUSIC algorithm. By introducing the multi-delay autocorrelation matrix tensor and residual learning, the method can effectively process challenging scenes such as coherent signals, a small number of snapshots and broadband signals. The effectiveness of the method is verified in the embodiment, high-precision estimation can be achieved under various conditions, the target that the number of estimated information sources is larger than the number of physical array elements is successfully achieved, and a new solution is provided for sparse array DOA estimation.

This invention discloses a time series forecasting method, apparatus, program product, storage medium, and its applications, relating to the field of time series analysis, to address the problems of high computational complexity and poor reliability of prediction results in time series forecasting tasks. This invention trains an inference model using time series data. This inference model extracts dependencies between variables based on the autocorrelation matrix of the input original time series; integrates these dependencies into the original time series to obtain key time-series features; learns long-term dependencies between variables from these key time-series features; and maps the time series for future time steps from these long-term dependencies. This invention achieves accurate time series forecasting with high reliability at a computationally low level.

The invention relates to a deception jamming detection method based on spatial domain processing gain dynamic change. The method comprises the following steps: receiving and processing a satellite navigation signal by using an array antenna, and estimating an airspace autocorrelation matrix of the satellite navigation signal; then, through actively constructing virtual interference which periodically changes in a direction, calculating and obtaining an array weighting vector which dynamically changes along with time by combining the matrix; then, performing spatial filtering on the signals by using the vector, independently tracking each navigation signal, and estimating a carrier-to-noise ratio time sequence of each navigation signal; if the correlation coefficient exceeds a set threshold, it is judged that the two signals are from the same direction due to the same airspace gain modulation, and the signals are classified as deception signals; and finally, rejecting the identified deception signal from the positioning solution, updating a navigation result and triggering an alarm, thereby realizing robust deception detection in a strong interference environment.

The application discloses a channel estimation method and related device, wherein the method comprises: performing minimum mean square error (MMSE) channel estimation based on the product of the first amplitude factor and the first noise power of the first dimension, the first channel autocorrelation matrix of the first dimension, and the first diagonal matrix to obtain the channel estimation value matrix of the first dimension; wherein the channel estimation value matrix of the first dimension is obtained by performing MMSE channel estimation in the non-last step of the multi-dimensional step-by-step MMSE channel estimation; the first amplitude factor is a positive number less than or equal to 1; and performing MMSE channel estimation based on the channel estimation value matrix of the first dimension, the second channel autocorrelation matrix of the last dimension, the second noise power and the second diagonal matrix to obtain the multi-dimensional channel estimation value matrix. The method can improve the performance of the multi-dimensional step-by-step MMSE channel estimation.

The application relates to a through-wall radar signal enhancement method and device for human motion, wherein the method comprises the following steps: acquiring a to-be-enhanced through-wall spectrogram; inputting the to-be-enhanced through-wall spectrogram into a generator in a network model based on spectrogram processing to obtain an enhanced through-wall spectrogram, so as to monitor human motion. The training method of the network model comprises the following steps: training a pre-training model through free space spectrograms and corresponding free space flip spectrograms in a data set; inputting a through-wall spectrogram into the generator to obtain a corresponding enhanced through-wall spectrogram; inputting the enhanced through-wall spectrogram and a non-paired free space spectrogram into the pre-training model which has been trained to obtain corresponding channel dimension autocorrelation matrices; inputting the enhanced through-wall spectrogram and the non-paired free space spectrogram into a discriminator to obtain a discrimination result; and constructing a loss function to optimize the generator and the discriminator, so that the generator can perform signal enhancement and improve the accuracy of downstream semantic recognition.

The invention discloses a continuous learning method of a neuromorphic classification network and a neuromorphic classification method, and belongs to the field of image classification. In order to solve the problems that a model in continuous learning CL of a neuromorphic data set easily forgets old knowledge when learning a new task, stability and plasticity are difficult to consider at the same time, and generalization ability is poor in a multi-scene and cross-architecture condition, the invention provides a parameter importance estimation and constraint method based on a gradient statistical structure. By calculating an autocorrelation matrix of gradient information and taking each network layer in the neural morphological classification network as a target, consistency and task correlation of parameter updating directions of each structural unit in each network layer are described, so that fine-grained structural importance representation is obtained. When a new task is learned, the continuous learning method utilizes the autocorrelation matrix to carry out regularization constraint on parameter updating, so that excessive adjustment on a sensitive direction of a historical task is inhibited, and disastrous forgetting is effectively avoided.

An apparatus for encoding a speech signal that determines a codebook vector of a speech coding algorithm includes a matrix determiner for determining an autocorrelation matrix R, and a codebook vector determiner for determining the codebook vector depending on the autocorrelation matrix R. The matrix determiner determines the autocorrelation matrix R by determining vector coefficients of a vector r, wherein the autocorrelation matrix R includes a plurality of rows and a plurality of columns, wherein the vector r indicates one of the columns or one of the rows of the autocorrelation matrix R, wherein R(i, j)=r(|i−j|), wherein R(i, j) indicates the coefficients of the autocorrelation matrix R, wherein i is a first index indicating one of a plurality of rows of the autocorrelation matrix R, and wherein j is a second index indicating one of the plurality of columns of the autocorrelation matrix R.

This application provides a data processing method and a communication apparatus, and relates to the field of communication technologies. The method can be used for downlink data processing and uplink data processing. The communication apparatus may receive a reference signal, and obtain a first matrix based on the reference signal. The first matrix is an autocorrelation matrix whose dimension is N rows and N columns, and N indicates a quantity of channels of an antenna array. Based on the first matrix, channels in different rows of the antenna array are averaged to obtain a second matrix, where a dimension of the second matrix is N / (x×R) rows and N / (x×R) columns; R represents a quantity of channel rows of the antenna array; x represents polarization of the antenna array.

The invention provides a channel estimation method for a minimum mean square error, which comprises the following steps of: performing Fourier transform on a received baseband signal to obtain OFDM (Orthogonal Frequency Division Multiplexing) frequency domain data, and obtaining frequency domain data of all symbols on a receiving side through solution resource mapping; the method comprises the following steps: processing by utilizing frequency domain data of a pilot symbol at a receiving side and a priori known pilot symbol sequence to obtain channel responses of SNR (Signal to Noise Ratio) estimation and LS (Least Square) channel estimation; processing according to the channel response of the LS channel estimation to obtain root-mean-square delay expansion; calculating a data-pilot frequency cross-correlation matrix and a pilot frequency self-correlation matrix according to root mean square time delay expansion, and calculating to obtain an MMSE filtering channel estimation coefficient according to the data-pilot frequency cross-correlation matrix and the pilot frequency self-correlation matrix; mMSE filtering is carried out according to the MMSE filtering channel estimation coefficient, and finally a final channel estimation value is obtained. According to the method, channel response is accurately estimated while operation is simplified, so that reliable communication and low operation delay are ensured.

This application discloses a fault identification method, apparatus, computer equipment, and rotating mechanism for a rotating mechanism. The method includes: acquiring the rotational speed information and time-domain vibration signal of the rotating mechanism; converting the time-domain vibration signal into an angular-domain vibration signal based on the rotational speed information; extracting features from the angular-domain vibration signal based on the autocorrelation matrix and filtering coefficients to update the filtering coefficients and obtain target filtering coefficients; and determining the fault characteristics of the rotating mechanism based on the target vibration signal obtained by processing the angular-domain vibration signal using the target filtering coefficients. The method provided in this application can effectively extract fault characteristics from the unsteady-state vibration signal of a rotating mechanism, thereby achieving reliable fault diagnosis of the rotating mechanism.

The invention provides a low-altitude flexible HMIMO-oriented spatial characteristic evaluation and port configuration method and system, and the method comprises the steps: constructing the array geometry of a flexible HMIMO array, and setting a user position and an electromagnetic propagation environment model; secondly, visibility judgment and gating processing are carried out on the sight distance model; then, the whole array is divided into sub-arrays, and available sub-arrays are screened out; calculating an autocorrelation matrix and quantizing a channel statistical difference distance between any two sub-arrays to generate a spatial non-stationary heat map; meanwhile, the full-aperture space freedom degree is calculated; and finally, obtaining an average achievable port mode number by taking a statistical expectation from a target direction domain, and obtaining a port configuration engineering upper bound by integrating a theoretical degree of freedom and hardware constraints. According to the method, the problems of spatial non-stationary quantization, sub-array availability judgment and port-level realizable mode number determination of the flexible curved surface array under near-field and shielding conditions are solved, and a direct basis is provided for engineering design and resource allocation of flexible HMIMO in low-altitude communication.

This invention discloses a high-resolution corner detection method and system for images based on the second-order Gaussian directional derivative, belonging to the field of image detection. The method includes the following steps: acquiring raw image data and performing second-order Gaussian directional derivative filtering at different directional angles using a preset response separability scale to obtain the directional derivative response value of each pixel in each direction; constructing a directional response vector for each pixel based on the directional derivative response value, and generating an autocorrelation matrix based on the directional response vector; calculating the corner response metric value of each pixel based on the eigenvalues ​​of the autocorrelation matrix; performing local nonmaximum suppression processing based on the corner response metric value, and filtering pixels that meet a preset response threshold to obtain a set of corner coordinates. This invention can solve the problem in the prior art where corner response functions are difficult to effectively separate in structurally similar edge regions.

In some implementations, a device may obtain information associated with one or more targets, wherein the information associated with the one or more targets includes sensing information and a communication performance control parameter. The device may determine a sensing beampattern based at least in part on the information associated with the one or more targets. The device may determine a target sensing autocorrelation matrix for the sensing beampattern. The device may identify a candidate sensing autocorrelation matrix for a joint communication and sensing transmission based at least in part on the target sensing autocorrelation matrix. The device may determine a target sensing precoder based at least in part on the candidate sensing autocorrelation matrix. The device may generate a joint communication and sensing precoder based at least in part on the target sensing precoder and the communication performance control parameter.

The invention relates to a channel estimation method and device, communication equipment, a chip and a chip module. The method comprises the following steps: performing singular value decomposition on a time domain autocorrelation matrix and a frequency domain autocorrelation matrix of a target channel to obtain a time domain unitary matrix and a time domain eigenvalue corresponding to the time domain autocorrelation matrix and a frequency domain unitary matrix and a frequency domain eigenvalue corresponding to the frequency domain autocorrelation matrix; updating the time domain feature value based on the frequency domain feature value to obtain an updated time domain feature value; updating the frequency domain feature value based on the updated time domain feature value to obtain an updated frequency domain feature value; obtaining a time domain filtering coefficient based on the updated time domain characteristic value, and obtaining a frequency domain filtering coefficient based on the updated frequency domain characteristic value; and obtaining a filter coefficient based on the time domain filter coefficient and the frequency domain filter coefficient, and performing channel estimation based on the filter coefficient to obtain a channel estimation result of the target channel. By adopting the method, the channel estimation performance loss can be reduced.

The invention discloses a communication anti-interference method based on conjugate space, which relates to the technical field of communication anti-interference, and comprises the following steps: constructing a received signal model; constructing a new received signal model according to the received signal model and the conjugate of the received signal model; constructing a correlation matrix of the new received signal model and conjugate transpose of the new received signal model, and constructing an autocorrelation matrix of the new received signal model according to mathematical expectation of the correlation matrix; constructing a new useful signal steering vector according to the receiving steering vector of the useful signal and the conjugate of the receiving steering vector; constructing an optimization problem based on a conjugate space by taking minimization of output power as an optimization criterion according to a weight vector of a beam former and conjugate transpose thereof, an autocorrelation matrix and a signal steering vector; and solving the optimization problem based on the conjugate space according to a Lagrange multiplier method. According to the method, the problem that a large signal is suppressed due to a small error factor is solved, and the method has very strong guiding significance for anti-interference engineering.

A method comprising: receiving an image block unit of a frame, the image block unit comprising samples in color channels comprising at least one chrominance channel and one luminance channel (1100); reconstructing samples of said luminance channels of the image block unit (1102); determining a reference area for predicting target samples of at least one color channel of the image block unit, wherein said reference area comprises one or more of reference samples in a neighboring block in current color channel / frame, in the neighboring of a co-located block in reference color channel / frame; and / or inside the co-located block in reference color channel / frame (1104); determining filter coefficients of a filter for said predicting based the reference samples and a shape of the filter (1106); reconstructing the target samples of at least one color channel of the image block unit using said prediction based on the samples of said reference area and the filter coefficients (1108); computing an autocorrelation matrix for the reconstructed target samples of the image block unit (1110); computing autocorrelation matrices for a plurality of neighboring image blocks units of said image block unit (1112); mixing the autocorrelation matrices of each of the plurality of neighboring image blocks units separately with the autocorrelation matrix of said image block unit (1114); and storing the mixed autocorrelation matrices for said image block unit (1116).

The invention relates to a channel estimation method and device, communication equipment, a chip and a chip module. The method comprises the following steps: performing discrete Fourier transform channel estimation in a frequency domain based on least square channel estimation of a target channel in the frequency domain to obtain frequency domain channel estimation; determining a power compensation factor corresponding to the frequency domain channel estimation, and obtaining a time domain filtering coefficient based on the power compensation factor, the time domain cross-correlation matrix of the target channel, the time domain symbol autocorrelation matrix of the target channel and the noise variance; and obtaining target channel estimation of the target channel based on the time domain filtering coefficient and the frequency domain channel estimation. By adopting the method, the channel estimation accuracy can be improved.

Systems, devices, methods, and instructions for performing beamforming on a signal by an electronic apparatus are provided, including training a deep neural network associated with beamforming on a signal, identifying an input signal input through an antenna array element, obtaining an autocorrelation matrix corresponding to the input signal, obtaining a weight vector from the autocorrelation matrix based on the deep neural network, and obtaining an output signal of the antenna array element corresponding to the input signal based on the weight vector.

The present application belongs to the field of radio direction finding, and particularly relates to a kind of integrated reference signal extraction and phase tracking direction finding method.The present application determines the autocorrelation matrix of array snapshot signal, the data matrix of bidirectional parallel beam forming according to the relevant parameters of direction finding equipment and frequency equipment;Then the linear constraint vector of bidirectional parallel beam forming, the linear constraint matrix of bidirectional parallel beam forming are determined;Then the linear constraint vector of bidirectional parallel beam forming, the phase tracking direction finding space spectrum of search direction are determined;Finally, the direction corresponding to the maximum value in the phase tracking direction finding space spectrum set of search direction is determined to determine the direction finding result of integrated reference signal extraction and phase tracking direction finding, and the reference signal extraction result is determined simultaneously.The present application can improve the coherent signal detection probability and direction finding accuracy in the case that the spatial spectrum direction finding method based on space processing fails to direction find coherent interference source signal.

The application discloses a kind of sensor array beam response sidelobe arbitrary nulling accurate control implementation method.This method is first according to sensor array relevant parameter and constructs array manifold and selects desired nulling area;Then in combination with the thought of sensor array beam response accurate control, iteration formula of beam pattern weighting vector is constructed;Finally, the iteration solution of beam pattern weighting vector is carried out, and beam pattern design is realized.The method of the application introduces the autocorrelation matrix formed by the array manifold corresponding to the desired nulling area in the objective function of CAPON beamformer, so as to realize the effective minimization of the beam output power in the area;At the same time, in combination with the design idea of sensor array beam response accurate control, beam response control and nulling area control are organically integrated, and the accuracy of nulling area control is significantly improved.

The present application belongs to the field of radio direction finding, and particularly relates to a weak signal high resolution direction finding method of random passive matched filtering. According to the direction finding device and the related parameters of random matched filtering, the array receiving signal of the direction finding device and the reference signal of passive matched filtering are determined; then the random matched filtering sample extraction matrix is determined, and the reference signal of random matched filtering is determined from the reference signal of passive matched filtering according to the random matched filtering sample extraction matrix; then the snapshot signal outputted by random matched filtering and its autocorrelation matrix are determined from the reference signal of random matched filtering and the array receiving signal of the direction finding device; finally, the high resolution spatial spectrum is determined from the autocorrelation matrix, and the direction finding result of random passive matched filtering is determined from the spectral peak position of the high resolution spatial spectrum. The present application can realize the purpose of improving the resolution capability and direction finding precision of signals with similar directions of arrival under the condition of low signal to noise ratio.

This invention discloses an image semantic segmentation method and system based on cross-modal hierarchical knowledge distillation. The method includes inputting an image into a multimodal teacher model and a student model to obtain teacher features and student features at each stage and an output prediction map; fusing teacher features at each stage and enhancing common modal features to obtain corresponding fused features for each stage; dividing the fused features and student features into high-level features and low-level features according to different stages; converting low-level teacher fused features and low-level student features into frequency domain maps respectively, extracting high-frequency components to convey detailed knowledge; calculating cross-correlation matrices and autocorrelation matrices using high-level teacher fused features and high-level student features respectively, and conveying structural knowledge; aligning teacher output prediction maps and student output prediction maps, and conveying response knowledge. This invention fuses multimodal features through modal enhancement, reducing the modal gap between teacher fused features and student features, and improving the segmentation accuracy of the single-modal student model.

The invention discloses an implementation method of sensor array wave beam response side lobe arbitrary null accurate control. The method comprises the following steps: firstly, constructing an array manifold according to related parameters of a sensor array, and selecting an expected null region; constructing an iterative formula of a beam pattern weighted vector in combination with the idea of accurate control of sensor array beam response; and finally, carrying out iterative solution on the weighted vector of the beam pattern to realize the design of the beam pattern. According to the method, an autocorrelation matrix formed by array manifolds corresponding to an expected null region is introduced into a target function of a CAPN beam former, so that effective minimization of beam output power of the region is realized; meanwhile, in combination with the design thought of sensor array beam response accurate control, beam response control and null region control are organically fused, and the precision of null region control is remarkably improved.