2956 results about "Covariance matrix" patented technology

The invention relates to the technical field of online calibration, in particular to a multi-parameter fusion intelligent electric energy meter online calibration method and system, and the method comprises the following steps: collecting voltage waveforms, current harmonics and active power data, dividing windows, calculating a covariance matrix, and generating a feature set; a power factor curvature extreme value and a temperature inflection point offset are analyzed to generate an interference identifier, current density distribution and a voltage distortion spectrum are jointly analyzed to extract a harmonic energy ratio to generate a feature vector, and phase compensation is performed on a pulse sequence to generate a calibration instruction set. According to the method, the covariance matrix is constructed by synchronously collecting voltage and current power parameters, the abnormal mark section is generated by combining the temperature change and the covariance difference value, the environment disturbance and the real deviation are effectively distinguished, and the temperature hysteresis effect is identified through the power factor curvature extreme value and the temperature inflection point offset. And combining current density and voltage distortion spectrum analysis to extract a fundamental wave and harmonic wave energy ratio, establishing a composite calibration reference, and dynamically adjusting a pulse duty ratio to realize harmonic wave energy compensation.

The invention discloses a three-dimensional Gaussian sputtering scene reconstruction method based on structure perception refined Gaussian, and aims to solve the problems of Gaussian drift, edge blur, structure artifacts and the like of a reconstruction model due to the fact that sparse point cloud contains outliers, Gaussian morphology and normal are mismatched and a multi-dimensional optimization target is lacked in an existing three-dimensional Gaussian sputtering reconstruction method. A key frame is extracted by collecting target scene video data, sparse three-dimensional point clouds are reconstructed by using an SfM algorithm, a depth map and a normal map are generated through a Lotus model, three-dimensional Gaussian distribution is initialized after the sparse point clouds are filtered, a Gaussian covariance matrix is adjusted by using a normal consistency regular term, and the sparse point clouds are extracted. And after structure attribute analysis is carried out, a comprehensive scoring function is constructed to screen Gaussian points, and finally, a combined training framework including luminosity, normal consistency and structure continuity loss is adopted to optimize and generate a three-dimensional Gaussian scene model. The method is mainly applied to the field of three-dimensional reconstruction and multi-view rendering, and scene reconstruction precision and geometric consistency can be improved.

The invention relates to the technical field of battery management systems, and particularly discloses a battery signal acquisition precision optimization method of a BMS (Battery Management System), which comprises the following steps of: dynamically adjusting a covariance matrix of process noise and measurement noise by monitoring the voltage, current and temperature of a battery in real time so as to cope with the change of the working state of the battery; according to the change trend of the charge and discharge rate and the temperature, noise parameters are predicted and corrected, and the adaptability of the system in an extreme environment is improved; in combination with data from a plurality of sensors, weighted average and a self-adaptive adjustment mechanism of a Kalman filter are adopted, so that evaluation of the system on signal quality of different sensors and effective suppression of noise are enhanced; aiming at the sudden change of the battery state, the system can be ensured to quickly respond by automatically adjusting the filtering algorithm, the accurate monitoring of the battery health state is ensured, the stability and the accuracy of the battery management system can be improved, and the problem of estimation error under the extreme working condition of a traditional method is solved.

The invention relates to the field of civil engineering construction safety monitoring, and discloses an open caisson construction soil gushing dynamic early warning system based on multi-parameter fusion, which comprises a sensor array module, a data processing module, a dynamic parameter correlation analysis module, a self-adaptive covariance optimization module, a risk index generation module and an early warning output module, collecting data in real time through a multi-source sensor and generating a parameter vector; the dynamic parameter correlation analysis module updates the dynamic matrix on line and represents real-time correlation among soil pressure, displacement and water level; the adaptive covariance optimization module dynamically adjusts a covariance matrix and suppresses noise interference; the risk index generation module fuses the dynamic matrix, the covariance inverse matrix and the parameter vector calculation weight, and corrects the risk index in combination with the vibration state of the construction machinery; and the early warning output module triggers grading alarm and feeds back to form a closed loop optimization link. According to the invention, real-time accurate early warning and self-adaptive prevention and control of the soil gushing risk are realized.

The invention provides an automobile magnesium alloy pre-twin crystal deformation data analysis system, and relates to the technical field of data processing, and the system comprises a twin crystal correction module which is provided with a first target monitoring point and a second target monitoring point in a pre-twin crystal area, the first target monitoring point is located at a crystal boundary intersection, and the second target monitoring point is located at the center of a twin crystal zone; acquiring orientation difference angle and strain energy density difference data of the two monitoring points in real time, calculating a covariance matrix of change characteristics of the two monitoring points, and correcting a proliferation rate parameter and an orientation rotation parameter in the dynamic evolution matrix according to a correlation coefficient of the covariance matrix to obtain a corrected dynamic evolution matrix; and the optimization module is used for adjusting a hot extrusion process parameter group according to the twin crystal density gradient distribution output by the corrected dynamic evolution matrix, the parameter group comprises a mold temperature, an extrusion speed and a strain path, and the twin crystal density is dynamically controlled in a target interval. According to the invention, the complex stress state of the automobile part under the actual working condition can be accurately simulated.

The invention discloses a single-epoch GNSS-oriented PAR ambiguity precision factor determination method, and relates to the technical field of satellite navigation and positioning. Comprising the following steps: dividing pseudo-range and carrier wave observed quantities in a GNSS double-difference mathematical model into two groups, and constructing a function relationship between a floating point solution # imgabs1 # and a floating point solution # imgabs2 # variance-covariance matrix of an ambiguity vector # imgabs0 #; constructing a single-frequency single-epoch single-system P-ADOP expression and establishing a shrinkage factor k de-inversion transformation analytic expression, and simultaneously obtaining a single-frequency single-epoch single-system GNSS non-inverse transformation P-ADOP approximation formula; and performing analogy derivation on the single-frequency single-epoch single-system non-inverse transformation P-ADOP approximate formula to obtain a single-frequency multi-system or multi-frequency single-epoch GNSS non-inverse transformation P-ADOP general approximate formula. The method has important theoretical value and practical guiding significance for GNSS optimal ambiguity subset rapid selection and positioning and partial ambiguity fixing success rate influence mechanism analysis.

The invention relates to the technical field of underwater intelligent navigation and integrated navigation, in particular to a submersible integrated navigation multi-source data fusion method based on an elastic random model, which comprises the following steps: preprocessing multi-source navigation data output by an inertial navigation system (INS), a Doppler velocimeter, an ultra-short baseline / long baseline, an altimeter and a depthometer; constructing a state space model containing navigation parameter errors and sensor errors, and screening an optimal sensor combination mode; the method comprises the following steps: constructing an elastic correction parameter model and a dynamic adjustment state and observation noise covariance matrix by combining an elastic PNT framework, performing local filtering on multi-source data by adopting a plurality of parallel elastic self-adaptive robust volume Kalman filters (CKF), outputting a fusion resolving result, and realizing optimal estimation of a global navigation state through a dynamic information distribution strategy. The method has relatively high anti-interference performance, self-adaptive capability and combination switching robustness, and is suitable for navigation and positioning tasks of a high-precision submersible in a complex underwater environment.

The invention relates to the technical field of three-dimensional modeling in engineering surveying, in particular to a point cloud building component modeling method and system based on feature extraction. Three-dimensional point cloud data of building components are obtained, a multi-scale local neighborhood calculation covariance matrix is constructed with each point as the center, eigenvalues are decomposed, an edge probability graph is generated, corresponding component categories are semantically output, and corresponding key feature point sets are screened; taking the feature point cloud as a control point, constructing a three-level B-spline surface model, and adjusting the corresponding spatial distribution density; a weighted complete graph is formed through a key feature point set, a non-planar area is identified and processed through a Kurtowski theorem, a QEM algorithm is applied to carry out lightweight processing on a three-dimensional model, screening and optimization are carried out through automatically extracting key feature points of building components, and a concise and accurate lightweight model is constructed based on feature point topological optimization and a graph theory algorithm. The automation degree and efficiency of modeling are improved, and the contradiction between model lightweight and precision is effectively solved.

The invention discloses a regional numerical forecasting method and system based on multi-scale background field error covariance. The method comprises the following steps: firstly, constructing a multi-scale background field error covariance model containing different spatial scale error structures, then obtaining an initial atmospheric state and a boundary condition of a forecast area, and generating a background field set sample by using an ensemble forecast algorithm; thirdly, performing multi-scale decomposition on a background field set sample based on the model to obtain error components of different spatial scales, and determining a corresponding error covariance matrix; and combining the matrixes to form a complete multi-scale background field error covariance. Then, meteorological observation data are obtained, a variational assimilation algorithm is applied, optimal combination of the observation data and a background field set sample is achieved through multi-scale background field error covariance, and an optimal initial field is obtained; and finally, performing regional numerical forecasting based on the optimal initial field to obtain a future weather condition forecasting result of the forecast region. According to the method, the forecasting accuracy and reliability are improved.

A partial ambiguity resolving method suitable for a complex dynamic environment belongs to the field of high-precision dynamic satellite navigation relative positioning, and comprises the following steps: constructing a single-epoch carrier phase double-difference difference observation equation; and calculating a weight factor corresponding to each satellite through a standardized residual error and an IGG3 method, and substituting the weight factors into the double-difference factor matrix to obtain a corrected observation value. And resolving the updated observation equation through a weighted iterative least square method. And carrying out partial ambiguity fixation on the corrected ambiguity floating point solution to obtain a whole cycle ambiguity fixed solution. And carrying out Ratio-based posteriori consistency traversal detection, monitoring the number of satellites participating in calculation in a traversal search process, and if the number of the satellites is smaller than a threshold value, outputting a floating point solution. And if the number of satellites after traversal search is greater than or equal to And substituting the fixed solution of the integer ambiguity into the updated observation equation to obtain a fixed solution of a three-dimensional relative position vector and a covariance matrix of the three-dimensional relative position vector.

The invention relates to the technical field of cross-modal data fusion analysis of soil component detection and improvement agent preparation, in particular to a preparation method of a soil improvement agent based on component detection, which comprises the following steps: acquiring soil component data through a near infrared spectrometer, a high performance liquid chromatograph and an inductively coupled plasma mass spectrometer; an incremental principal component analysis algorithm is combined with an oscillation suppression function to update a covariance matrix in real time, a dynamic defect factor priority list is generated, a multi-objective optimization model improved based on NSGA-II is guided to integrate the soil pH value, humidity and organic matter content to construct a dose response curved surface, and a Pareto optimal solution set is solved. A sensor array collects environment feedback data, drives a transfer learning algorithm to calibrate parameters, a dynamic incidence matrix attenuation rate and optimal weight adaptive adjustment, iteratively outputs a modifier synergistic effect solution set through a closed-loop control mechanism, and solves the problems of difficult data fusion, principal component weight offset and component synergistic deviation. And the proportioning accuracy and stability are improved.

The invention provides a breakwater monitoring data preprocessing method and system based on Kalman filtering, and relates to the technical field of breakwater structure safety monitoring. The method comprises the following steps: acquiring original motion data of acceleration, inclination and displacement through a motion attitude sensor to obtain an original data sequence; initializing a state vector and an error covariance matrix; dynamically correcting the state transition matrix and calculating a prediction state vector and a prediction error covariance matrix; a Kalman gain is generated; updating a state vector and an error covariance matrix; and extracting the filtered motion data as a preprocessing result. According to the method, the state transition matrix is dynamically corrected by introducing the wave force feedback, so that the Kalman filtering algorithm can adapt to the wave impact environment, noise interference in monitoring data is effectively inhibited, and the accuracy and reliability of key motion parameter data of the breakwater are remarkably improved.

The invention discloses a vehicle state estimation method based on adaptive strong tracking extended Kalman filtering. The method comprises the following steps: constructing a nonlinear three-degree-of-freedom dynamic model containing a state equation and an observation equation based on an extended Kalman filtering algorithm to describe longitudinal, lateral and yaw states of a vehicle; state variables of the state equation are a side slip angle, a yaw velocity and a longitudinal vehicle speed; constructing a time-varying measurement noise statistical estimator based on a Sage-Husa algorithm to adaptively correct a measurement noise covariance matrix in the extended Kalman filtering algorithm; state prediction is carried out on the vehicle through the state equation, and a state prediction covariance matrix is calculated; and calculating the ratio of the sum of quadratic terms of the information sequence to the trace of the variance matrix of the information sequence based on an extended Kalman filtering algorithm, and judging whether filtering is really divergent or not. According to the method, the state quantity which is difficult to measure in the vehicle driving process is estimated in real time by establishing an adaptive strong tracking extended Kalman filter, and the vehicle state is accurately estimated.

The invention discloses a PPP-RTK time delay processing method and device in conversion from SSR to OSR, and relates to the technical field of global navigation satellite system positioning, and the method comprises the steps: converting orbit, clock error, ionosphere and troposphere delay SSR parameters provided by a server into OSR virtual observation values through geometric distance calculation and projection function mapping; based on a constant velocity model and a static random process, predicting a correction amount of a future moment, and correcting an OSR virtual observation value through state transition matrix compensation time delay; combining server side parameters and user side observation data, recursively generating an error covariance matrix, dynamically adjusting a state prediction weight, and obtaining covariance information through adaptive filtering optimization positioning calculation; and realizing ambiguity rapid fixation and centimeter-level positioning by using the corrected OSR observation value and covariance information. According to the method, real-time centimeter-level positioning in a high-delay scene is realized through a dynamic correction value prediction method and a recursive covariance estimation method.

The invention discloses a sparse dynamic graph convolution-based electroencephalogram signal decoding method and system. The method comprises the following steps of: acquiring a multi-channel electroencephalogram signal and preprocessing the multi-channel electroencephalogram signal; performing multi-band filtering on each channel signal, extracting statistical characteristics on each band signal, calculating a covariance matrix of a task electroencephalogram signal, constructing image electroencephalogram data by taking an electroencephalogram channel as an image node, the multi-band spliced statistical characteristics on the channel as a node feature vector, and the covariance matrix between the channels as an adjacent matrix; finally, a dynamic graph convolutional neural network model is constructed, the model constructs a graph convolutional neural network based on an autoregression moving average filter, graph electroencephalogram data is used as input, the category of electroencephalogram signals is used as output, an adjacency matrix is dynamically generated in combination with bilinear mapping, fuzzy label learning and sparse constraint are added to improve the decoding capacity of the model, and the dynamic graph convolutional neural network model is obtained. And the frequency domain response capability and robustness of the model to the graph structure are enhanced.

A GNSS positioning slowly-varying fault detection method based on residual-SVR regression comprises the steps that an observation information sequence is acquired based on a Kalman filter, and a covariance matrix of the observation information sequence is calculated; accumulating multi-step information through a sliding window, and constructing chi-square statistics; based on the fault-free data, constructing a training set by taking an innovation sequence as input and chi-square statistics as output, and generating an innovation-statistics mapping function; and fitting a normal slope threshold value based on an SVR predicted value, carrying out least square fitting on an observation statistic curve by sliding a window in real time, and judging whether to start a slow change fault alarm or not. According to the method, the residual error sequence is directly used as model input, and the dynamic chi-square statistical magnitude is used for replacing a traditional dichotomy label, so that the detection delay is reduced; an SVR detection model based on grid search and cross validation collaborative optimization is utilized, and an optimal parameter combination of a minimum mean square error (MSE) is screened through logarithm uniform sampling, interval linear sampling and five-fold cross validation, so that the average absolute error of slowly varying fault detection is reduced.

The invention discloses a sodium ion battery SOC estimation method based on extended Kalman filtering. The method comprises the following steps: acquiring charging and discharging voltage, current and open-circuit voltage OCV data of a sodium battery through an HPPC test and a capacity test; and fitting a function relationship between the OCV and the SOC based on the standing balanced voltage data. And constructing a three-order RC equivalent circuit model, and identifying ohmic resistance, polarization resistance and polarization capacitance parameters in the model through curve fitting. Based on the model, a state vector containing SOC and polarization voltage is defined, and a nonlinear state equation and a terminal voltage observation equation are established. And predicting the state vector and the covariance matrix at the current moment according to the state vector and the covariance matrix at the previous moment by using an extended Kalman filtering algorithm, calculating Kalman gain by combining the actually measured terminal voltage, correcting the prediction result, and updating the SOC estimation value. And through loop iteration, real-time high-precision dynamic estimation of the SOC of the sodium-ion battery is realized. The method provides an efficient and accurate SOC estimation solution for a sodium ion battery management system.

The invention provides a dual-antenna attitude and orientation and robust self-adaption method based on integrated navigation, which comprises the following steps: combining an INS (inertial navigation system) and a dual-antenna GNSS (global navigation satellite system), and enabling the system to output continuous and stable high-precision carrier attitude information when a GNSS signal is interfered by using dual-antenna integrated navigation. According to the method, most of satellite end clock correction, ionosphere and troposphere errors and receiver end clock correction are eliminated by using double-antenna GNSS pseudo-range and carrier phase double difference, robust statistics are calculated through heading prediction residual vectors to obtain robust factors, an observation noise covariance matrix is expanded to reduce the influence of system noise and observation noise, and the system performance is improved. A Mahalanobis distance based on a prediction residual vector is introduced to detect whether a system is abnormal or not, a state prediction covariance matrix is adjusted through a self-adaptive factor, weight reduction of an abnormal INS dynamic model is achieved, and the stability and reliability of system attitude information are improved through a noise covariance self-adaptive control mechanism.

The invention relates to the technical field of automobile part processing, and discloses an automobile part process parameter real-time optimization method and system based on machine learning, and the method comprises the steps: collecting the temperature gradient, pressure distribution, cutting speed and other multi-source process parameter data, extracting a process feature sequence through a self-attention mechanism and a time convolution network, and carrying out the real-time optimization of the process feature sequence; calculating a process fluctuation coefficient; and generating a process correlation weight through covariance matrix characteristic decomposition and Sigmoid function transformation, dynamically adjusting a reference parameter to generate an optimized parameter, and regulating and controlling equipment operation. The system comprises a multi-source data acquisition module, a process feature extraction module, a fluctuation coefficient calculation module and the like. And a multi-dimensional process parameter space is also constructed to monitor an abnormal state, and a joint optimization model is established to realize collaborative optimization of process and equipment control parameters. The real-time performance and accuracy of technological parameter optimization are improved, machining error accumulation is effectively restrained, the method is suitable for intelligent machining of automobile parts, and the machining quality and efficiency are guaranteed.

The invention discloses a dynamic Gaussian scene reconstruction method based on depth regularization. The method comprises the following steps: step (1), initializing a group of 3D Gaussian sets by using an SfM point cloud, wherein each Gaussian body is described by parameters such as a central position and a covariance matrix; (2) introducing a control network decoupling motion and a geometric structure, performing offset calculation by using a time variable and a Gaussian center position, and controlling dynamic transformation of a Gaussian body; (3) introducing a loss function of scale-independent depth alignment based on local depth normalization and Pearson correlation; and (4) a new loss function is obtained through calculation according to the rendered image, and the Gaussian field and the control network are optimized through reverse gradient return. Experiments on dynamic scene data sets such as D-NeRF and NeRF-DS show that the method is superior to an existing method in the aspects of reconstruction quality, geometric consistency and new view rendering effect, the stability and detail fidelity of the dynamic scene are improved, and the method has important research value and application prospect.

A system for extracting glacier boundaries using multiparametric analysis, consisting of: a data acquisition module configured to acquire Synthetic Aperture Radar (SAR) data of a glacial region; a data processing unit configured to process the SAR data to generate coherence images and backscatter intensity maps, to extract terrain parameters including slope and curvature information from a digital elevation model (DEM), to apply thresholds to the coherence images, backscatter intensity maps, and terrain parameters, to generate a multi-band stack comprising the thresholded coherence images, the thresholded backscatter intensity maps, the thresholded slope information, and the curvature information, and a principal component analysis module configured to standardize the multi-band stack, calculate a covariance matrix from the standardized data, calculate eigenvalues and eigenvectors of the covariance matrix, and transform the original data into a principal component space with reduced dimensionality; a texture feature extraction module configured to calculate first- and second-order statistics from the output of the principal component analysis; generating a texture feature set comprising at least one of the following: sum average, entropy, difference entropy, sum entropy, variance, difference variance, inverse difference moment, contrast, correlation, information measures of correlation, and maximum correlation coefficient; a connected component segmentation module configured to: convert the set of textural features into a binary format that distinguishes glacier ice from the background; group spatially connected pixels of similar intensity into segments; extract a vector shape file corresponding to the glacier boundary; an output generation module configured to generate a glacier boundary delineation output; and a user interface having a display configured to display the output generated by the output generation module.

The invention discloses a heterogeneous sensor fusion method and system for dynamic covariance optimization, and the method comprises the steps: constructing a multi-source heterogeneous sensor network which comprises an underwater inertial navigation unit, a Doppler velocity sensor, an ultra-short baseline positioning system, a submarine topography matching device and a geomagnetic gradient detector; the method comprises the following steps: designing a distributed integrated navigation system by adopting a hierarchical fusion architecture, establishing a sensor confidence coefficient dynamic evaluation model based on online estimated error covariance matrix eigenvalue analysis, carrying out state prediction on a local filter level by applying Kalman filtering, and then carrying out measurement updating by adopting a novel variational Bayesian algorithm; a sensor autonomous switching and adaptive weighted dual-mode adjustment mechanism is developed on the main filter level, and self-healing improvement of navigation precision in a non-stationary environment is realized, so that the problems of dynamic reliability evaluation and fusion efficiency optimization in underwater multi-sensor multi-source navigation are solved.

The invention discloses a marine environment forecasting method based on combination of machine learning and numerical forecasting, and particularly relates to the field of marine environment forecasting, which comprises the following steps: extracting marginal region features based on real-time observation data, constructing a forecasting field through a double-loss function, extracting extreme event features through space-time decoupling, and constructing a forecasting field through a double-loss function; and outputting a forecasting result of the target sea area. According to the marine environment forecasting method based on the combination of machine learning and numerical forecasting, the problem of initial field optimization failure caused by covariance matrix estimation deviation when marginal sea area data are sparse is relieved by embedding vorticity conservation equation residual calculation in a hidden layer; the dependence on the number of extreme event samples is reduced by realizing the targeted extraction of the extreme ocean event features; through a physical hard constraint layer technology of a residual error correction network, an initial field error of a data sparse region is corrected in combination with sea surface height and a flow velocity field constraint residual error feature map, and the problem of a large prediction error of an edge sea area is relieved.

The invention discloses a CAN bus intrusion detection method based on adaptive unscented Kalman filtering, and the method comprises the steps: obtaining real-time message data, and carrying out the preprocessing of the real-time message data, and obtaining a time sequence feature vector; constructing a nonlinear state space model based on the time sequence feature vector; performing unscented Kalman filtering state prediction based on the nonlinear state space model; inputting the time sequence feature vector as an actual observation value, calculating a Kalman gain to correct an unscented Kalman filtering state prediction result, and outputting a state estimation residual error; dynamically updating a process noise covariance matrix through exponentially weighted moving average based on the state estimation residual, and adjusting a measurement noise covariance matrix according to the measurement innovation sequence; calculating the mahalanobis distance of the state estimation residual error, comparing the mahalanobis distance with a self-adaptive anomaly detection threshold value, and judging whether an intrusion behavior occurs or not; and if the abnormal score exceeds a threshold value, triggering a multi-level alarm mechanism, recording a suspicious message and executing a safety protection operation.

The invention discloses a knowledge cross validation question-answering method and system for reducing hallusion of a large language model, and belongs to the technical field of artificial intelligence, and the method is implemented by the following steps: generating results through multiple times of sampling: when a user puts forward a question, controlling the large model to perform multiple times of sampling, and generating a specified number of results; calculating hidden state related indexes: extracting the hidden state of the last token of the middle layer of the large model corresponding to the result, and calculating covariance matrixes and answer discrete feature values of the hidden states; mLP model prediction: inputting the discrete feature value of the answer and the length of the answer into a multilayer perceptron MLP, and outputting a hallucination-free probability; querying and summarizing a knowledge graph; and calculating a final illusion-free score and outputting a result. According to the method, the answer quality and credibility of a large language model can be remarkably improved, and the method is particularly suitable for application scenes with extremely high requirements on the accuracy of single-mode text generation contents.

The invention discloses a non-stationary industrial process early fault diagnosis method based on a common trend model, and belongs to the field of industrial process monitoring and fault diagnosis. The method comprises the following steps: collecting training data of a non-stationary industrial process under a normal working condition, performing denoising by using singular spectrum analysis, and obtaining a stationary projection matrix and a stationary data matrix by using a common trend model; orthogonal conversion is carried out on the stationary data matrix, a conversion projection matrix is calculated, and an orthogonal conversion data matrix and a statistic data matrix thereof are obtained; calculating a mean value and a covariance matrix of the statistic data matrix to obtain a control limit; the method comprises the following steps: acquiring test data under a real-time working condition of an industrial process, processing to obtain statistic data, calculating a mahalanobis distance index, and comparing with a control limit to judge whether a fault occurs; and if a fault is detected, realizing fault separation according to fault reconstruction and a mapping relation. According to the method, the interference of the non-stationary characteristic on the fault diagnosis model can be reduced, and fault detection and separation in the non-stationary process are realized.

The invention provides a polarization / inertial navigation integrated navigation method based on a deep Kalman filter network, and belongs to the field of bionic polarization navigation. Establishing a priori prediction error covariance matrix estimation network and a measurement residual covariance matrix estimation network in polarization / inertial navigation filtering, and training the priori prediction error covariance matrix estimation network and the measurement residual covariance matrix estimation network at the same time by adopting a two-stage training strategy; the state and measurement are predicted, the optimal gain in polarization / inertial navigation filtering is calculated, state prediction and innovation are fused according to the calculated optimal gain, and estimation of the state at the current moment is obtained. According to the invention, high-precision navigation of the polarization / inertial navigation integrated navigation system is realized, and the environment adaptability of the system is improved.

The invention provides a coherent signal arrival direction estimation method and device based on a deep convolutional network, and belongs to the field of array signal processing. The method comprises the following steps: receiving a to-be-detected signal containing a coherent signal by using a uniform linear array antenna to obtain an array receiving data matrix and extract a covariance matrix; forming an input feature vector by right upper triangular elements divided from a diagonal line in the covariance matrix, inputting the input feature vector into a covariance estimation model formed by a deep convolutional network, obtaining an estimation value of the right upper triangular elements under an ideal incoherent condition, and reconstructing the estimation value to obtain a covariance matrix estimation value; and performing characteristic decomposition on the covariance matrix estimation value, and generating a spatial spectrum by using a MUSIC algorithm to obtain an estimation result of the signal arrival direction. According to the method, the noise-containing mixed signal covariance matrix is mapped into the ideal incoherent noise-free signal covariance matrix through a physical constraint supervised learning framework, so that the estimation precision and robustness of the MUSIC algorithm in a coherent scene are improved.

The invention discloses a self-adaptive battery life calibration method for cloud-side cooperation, and belongs to the crossing field of an energy storage system and cloud-side cooperation calculation. According to the invention, a cloud-edge double-layer collaborative framework is provided; an edge end estimates the health state and the residual life of a battery in real time through a recursive least square extended Kalman filtering model; the error observer calculates a prediction error based on a sliding window, and a dynamic threshold triggers an uploading mechanism; the edge end adopts an auto-encoder to compress original time sequence features into abstract vectors, and the abstract vectors and error statistics are uploaded together; the cloud performs incremental learning by using a deep sequential network, and only finely adjusts tail level parameters of which the gradient sensitivity exceeds a threshold value to generate a correction value; and the correction value is compressed and issued to an edge end, local model parameters are updated through weighted fusion, and a covariance matrix is adjusted. The method realizes high-precision life prediction and dynamic calibration, remarkably reduces the communication load, and is suitable for electric vehicles, power grid energy storage and other scenes.

The invention discloses a phased array computing terminal real-time beam forming and interference reduction method, which comprises the following steps of: 1, acquiring an observation signal by an observation target, calculating an independent narrow-band beam former for each sub-band channel for a channelized frequency domain baseband signal, and further realizing frequency domain real-time beam forming on all baseband signals at the same time, based on the dynamic change of the propagation environment, the beam forming weight is updated, the beam shape and direction are adjusted, and the maximum signal-to-noise ratio beam forming is realized; and 2, effective interference reduction is realized by adopting spatial filtering in phased array calculation terminal equipment, a spatial filter is constructed in combination with a subspace projection method, identification and elimination of interference signals are realized through calculation and characteristic decomposition of a covariance matrix, and finally filtered signal data are obtained. According to the method, a large number of independent tasks in matrix operation can be efficiently processed, so that the calculation time is remarkably shortened, and the observation capability of a system and the adaptability of an application scene are improved.