337 results about "Covariance" patented technology

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 relates to the technical field of test bed operation monitoring, in particular to a fuel pump test bed operation monitoring method and system. The method comprises the following steps: acquiring monitoring time sequence data of operation of a fuel pump test bed, performing feature extraction, constructing a coupling prediction model of a space-time diagram attention network-unscented Kalman filter, and predicting a process noise covariance matrix and a measurement noise covariance matrix according to the coupling prediction model, and performing state estimation by using an unscented Kalman filter to obtain vector posterior probability distribution, constructing a fault evolution trajectory manifold, calculating a mahalanobis distance between the vector posterior probability distribution and the fault evolution trajectory manifold, and taking the mahalanobis distance as a monitoring index. According to the scheme of the invention, the deep features which can better reflect the inherent nonlinear and complex dynamic characteristics of the system can be extracted from the multi-source data, the estimation accuracy of the filter on the potential health state of the system is improved, and the defects that model parameters are fixed and gradual change faults are difficult to capture in a traditional method are overcome.

The invention discloses a physical field solving method based on a Bayesian physical information extreme learning machine, and the method comprises the steps: constructing a single-layer full-connection neural network, carrying out the random initialization, and fixing the weight of an input layer; based on a partial differential equation of a physical system and boundary conditions thereof, defining a training loss item containing physical information; a physical system solving problem is converted into a linear least square problem, and a linear equation set is constructed; supposing that an output layer weight parameter obeys Gaussian prior distribution with the mean value being zero, and controlling a covariance matrix by an adjustable hyper-parameter; constructing a Gaussian likelihood function based on the observation data, and calculating posterior distribution of the output weight in combination with the prior distribution; carrying out iterative optimization on the hyper-parameter by adopting an evidence maximization method to obtain a mean value and a covariance of posterior distribution; based on posterior distribution, adopting a Monte Carlo integral method to generate prediction output of the physical system; and performing uncertainty quantization based on the variance of prediction output, and outputting a prediction value and a confidence interval thereof.

The invention relates to an attitude estimation method based on gravity and magnetic dual-mode detection adaptive dynamic Kalman filtering. The method comprises the following steps: constructing an attitude resolving state equation and an observation equation of the gravity-magnetic dual-mode detection system; initializing the state value and the prior error covariance matrix; characterizing the noise dynamic change of the industrial tool in the movement process according to gravity-magnetic dual-mode detection, carrying out adaptive adjustment on the measurement noise covariance, and predicting and updating the measurement noise covariance by adopting kalman filtering; and carrying out attitude estimation by adopting a kalman filtering attitude estimation algorithm according to the self-adaptively adjusted measurement noise covariance at the current moment and the initialization values of the state and priori error covariance matrix. According to the method, a gravity vector dynamic detection mechanism and a magnetic interference detection mechanism are constructed, the two detection mechanisms are coordinated, the noise covariance matrix is adaptively adjusted, the attitude estimation precision is improved, and the method has a relatively strong suppression effect on dynamic noise characteristics.

The invention provides an attitude monitoring method and system in navigation of an aircraft, and the method comprises the steps: determining a process noise covariance matrix through a high-frequency energy component of an angular velocity signal measured by a current gyroscope in each filtering period; predicting a prior state vector and a prior covariance matrix at the current moment according to the state vector at the previous moment, the angular velocity measured by the current gyroscope and the process noise covariance matrix; generating an asymmetric Sigma point set and determining a measurement noise covariance matrix; the asymmetric Sigma point set is substituted into a measurement model, and a predicted measurement value and a predicted measurement covariance are obtained through unscented transformation; calculating Kalman gain based on the predicted measurement covariance and the measurement noise covariance matrix, and performing weighted gating test on innovation formed by a real measurement value and a predicted measurement value; and updating a state vector and a covariance matrix on the basis of the adjusted Kalman gain and information so as to obtain attitude information of the aircraft at the current moment.

The invention relates to the technical field of highway bridge safety monitoring, and discloses a bridge dynamic weighing algorithm based on likelihood estimation. A bridge is used as a carrier for vehicle weighing, an influence line of the bridge is obtained through a calibration test, and an influence line mean vector and an influence line covariance matrix are calculated; an influence line matrix is obtained based on the influence line mean vector, the vehicle speed and the axle distance, and an initial axle load value is calculated through a Moses algorithm; calculating a mean square error diagonal matrix of a measurement error according to the influence line matrix, the bridge load response and the axle load of the previous iteration step, and obtaining a covariance matrix of the bridge load response; calculating an axle load corresponding to the maximum likelihood probability based on the covariance matrix of the bridge load response in combination with the influence line matrix and the bridge load response; and repeating until the difference value between the axle weight updated this time and the axle weight obtained last time is smaller than a preset value, and taking the axle weight updated this time as a final result. According to the invention, the problem of low axle load identification precision of the existing bridge dynamic weighing system is solved.

The invention discloses a point cloud reconstruction method and system based on three-dimensional Gaussian sputtering, and is used for solving the technical problem that the structural stability of a final three-dimensional point cloud model is not good enough due to the fact that a traditional point cloud reconstruction method causes gradient propagation abnormity, and the optimization process is not convergent or falls into a local minimum value. The method comprises the following steps: firstly, acquiring a multi-view image and a reference view image, and constructing a covariance degradation risk probability graph; generating a plurality of Gaussian three-dimensional points to be regulated and controlled, performing three-dimensional point screening and fitting credibility score calculation, outputting secondary regulation three-dimensional points and corresponding scores, and constructing an initial three-dimensional point cloud model; performing secondary adjustment on the three-dimensional point by combining the multi-view image and fractional optimization to obtain a target Gaussian three-dimensional point, and updating the initial model into an intermediate model; and updating the intermediate model through a covariance updating gating mechanism based on gradient convergence dynamic monitoring, and outputting a target three-dimensional point cloud model.

The invention discloses a heat pump system state anomaly detection method based on a depth auto-encoder, and the method comprises the steps: collecting compressor data, and carrying out the standardization processing to construct a multi-dimensional time sequence; a spatial-temporal feature extraction depth auto-encoder with a thermodynamic coupling attention mechanism is constructed, coupling attention is utilized to calculate physical parameter coupling strength weights to extract spatial features, time features are extracted in combination with a long and short-term memory network, and normal state data are reconstructed and predicted through a decoder after fusion; residual vectors of predicted normal state data and original data are calculated, and a weighted mahalanobis distance is calculated by using a covariance matrix to generate an abnormal score; and constructing a sliding probability distribution model based on historical normal data, calculating a current score occurrence probability, and comparing the current score occurrence probability with a preset threshold to output an anomaly detection result. According to the method, a multi-physical parameter space coupling relationship and a time evolution rule are captured through a thermodynamic coupling attention mechanism, and the anomaly detection accuracy and robustness are improved.

The invention belongs to the technical field of intelligent early warning, and particularly relates to an intelligent early warning method for a DMF waste liquid purification and recovery control platform, and the method comprises the steps: carrying out the principal component analysis of long-period historical data, and constructing a principal component transformation matrix of a static reference model; for a moment to be diagnosed, calculating a reconstruction value by using the static reference model to obtain a residual vector, carrying out eigenvalue decomposition on a covariance matrix of a residual matrix of a sliding time window, calculating a drift coherence index according to the distribution of drift eigenvalues, modulating a drift principal component vector of the sliding time window by combining the residual vector, and carrying out diagnosis on the moment to be diagnosed; and obtaining a drift compensation vector, superposing the drift compensation vector with a reconstruction value of a real-time data vector at a to-be-diagnosed moment to obtain an adaptive reconstruction value at the to-be-diagnosed moment, calculating a reconstruction error, comparing the reconstruction error with a fault alarm threshold, judging whether a fault exists at the to-be-diagnosed moment, and performing early warning. According to the invention, the early warning accuracy and robustness are improved.

The invention provides a large-scale three-dimensional tunnel surrounding rock parameter random field model construction method and system, and relates to the technical field of tunnel surrounding rock modeling, and the method comprises the steps: carrying out the fitting construction of a probability distribution model reflecting surrounding rock parameters; selecting a plurality of surrounding rock parameters as clustering features, quantitatively classifying global geologic structures in tunnel surrounding rocks, and performing global decomposition on a tunnel model into continuous sub-domains containing overlapped buffer areas; for a first sub-domain from any direction of the whole domain of the tunnel model, performing covariance matrix spectral decomposition by adopting a KL decomposition method to generate a first sub-domain random field, and extracting random field values of overlapped regions among the sub-domains as boundary condition data of a recursive generation process; on the basis of the boundary condition data, conditional random fields of subsequent sub-domains are generated layer by layer; and seamlessly splicing the conditional random fields generated by recursion of the sub-fields into a global parameter random field, converting the global parameter random field into probability distribution by adopting a probability mapping method, and performing instruction encapsulation by developing a cross-platform data interface engine to realize a construction process of a parameter random field model.

The invention discloses a GRACE and Swarm time-varying gravity field fusion filtering method based on a state space model, and the method comprises the steps: taking a spherical harmonic coefficient as a state quantity, constructing a random walk process equation, introducing three types of observations, employing a quantization parameter for observation noise and process noise covariance, constructing according to an order / power law, and carrying out the self-adaptive updating along with the monthly; a Nelder-Mead method is adopted to search for spectral index parameters, and an EM algorithm and a statistical method are utilized to update other parameters in a closed / quasi-closed mode; obtaining the state and posterior covariance of a full time sequence by using Kalman filtering and RTS smoothing; in the GRACE and GRACE-FO window period, continuous reconstruction is carried out by means of a process model and Swarm; and outputting quality evaluation information including monthly gravity field coefficients, posterior covariance, innovative variance ratio, residual whitening test, space power spectrum, uncertainty band and the like. According to the method, while physical rationality and calculation feasibility are ensured, a continuous and stable monthly time-varying gravitational field sequence with quantifiable uncertainty is realized.

The invention discloses a mobile robot accurate docking method based on edge calculation, and aims to solve the problems that the dynamic docking precision is reduced and the collision risk is increased due to micro-motion or drifting of a target station. According to the method, unified time reference alignment is carried out on data of a camera, a laser radar, an inertial measurement unit, an ultra-wideband range finder, a station encoder and a programmable logic controller at an edge node, and a three-dimensional special Euclidean group equivariant multi-source fusion network is used for outputting relative pose estimation and covariance; the estimation in the time window is further used as a condition to be input into a conditional diffusion short-time prediction model to obtain a time-varying mean value and a time-varying covariance, an anisotropic probability tube is constructed, and prediction-measurement joint correction is carried out based on a score function; scenarized opportunity constraints are constructed under correction probability tube constraints, a tubular nonlinear model is adopted to predict, control and solve a reference trajectory, an actuator command is generated in combination with depth visual servo and compliance control, and the technical effects of high precision, robustness and safe docking under the station dynamic disturbance condition are achieved.

The invention discloses a non-uniform clutter and interference cooperative suppression target fusion detection method and system, and relates to the technical field of broadband radar signal processing, and the method comprises the steps: carrying out the unitary transformation of test data, a clutter covariance matrix, a target coordinate matrix and an interference coordinate matrix based on the skew symmetry of the clutter covariance matrix; constructing a distance extension target Gradient detection statistical magnitude under the condition of a known clutter skew symmetry covariance matrix; calculating the maximum likelihood estimation of the clutter skew symmetry covariance matrix; based on the maximum likelihood estimation of the clutter skew-symmetric covariance matrix and the distance expansion target Gradant detection statistic, constructing a target detection statistic of non-uniform clutter and interference cooperative suppression; performing target fusion detection on the target detection unit based on the target detection statistical magnitude and a preset detection threshold; according to the invention, the technical problems of complex construction process and high calculation complexity of the target detector in the prior art are solved.

The invention discloses a distillate oil property prediction method based on deep learning feature extraction and partial least squares regression. The method comprises the following steps: firstly, carrying out classification training on a near infrared spectrum through a convolution-attention double-branch fusion network, and extracting high-dimensional spectral features with local and global information; then, historical samples are retrieved from a database based on prediction categories, a plurality of most similar samples are selected by adopting cosine similarity measurement to construct a correction set, and the spectral features and property labels are subjected to standardization processing; and finally, carrying out partial least squares regression modeling on the correction set, extracting latent variables to maximize covariance between spectral features and physicochemical properties, and inputting feature vectors of an oil sample to be detected into the trained PLS model to obtain a corresponding property prediction result. According to the method, the modeling requirement and the category specificity characteristics under the small sample condition are considered while the prediction precision is guaranteed, and the method is suitable for rapid property detection and intelligent analysis in the refining process.

The invention discloses a corn seeding control method based on Kalman filtering, and relates to the technical field of seeding control, and the method comprises the steps: obtaining the speed data of a seeding machine, and initializing a filtering parameter; updating a filtering parameter based on the speed data to obtain a real-time state variable, obtaining a real-time error covariance based on the filtering parameter, and obtaining a real-time Kalman gain based on the real-time error covariance and the filtering parameter; obtaining a real-time innovation covariance matrix based on the real-time state variable, and obtaining a real-time system noise covariance and a real-time observation noise covariance based on the real-time error covariance, the real-time innovation covariance matrix and the real-time Kalman gain; circulating the above steps until a first preset condition is met, and ending the circulation to obtain filtering data; the motor rotating speed of the seeding machine is obtained based on the filtering data, the seeding machine performs seeding based on the motor rotating speed, and the problem that the speed data is inaccurate due to the fact that an existing corn seeding machine processes speed information through extended Kalman filtering can be solved.

According to the invisible watermark embedding method based on the wavelet domain statistical characteristics, the high-frequency sub-band in the wavelet domain is selected as the embedding area, and the robustness of the watermark to conventional attacks such as compression and noise is improved while invisibility is guaranteed. Based on a self-adaptive embedding weight mechanism of a covariance matrix eigenvalue, the embedding strength of different texture regions can be dynamically adjusted, the robustness is enhanced by a smooth region, and distortion is suppressed by an edge region. Nonlinear disturbance is generated by adopting a deep neural network and chaotic encryption preprocessing is combined, so that the predictability of a linear statistical rule is broken, and the method has a relatively good application prospect.

The invention relates to the technical field of attitude control, in particular to a moving object attitude control method based on an improved LKF. Predicting prior attitude estimation at the next moment; calculating a process error covariance matrix; calculating a measurement attitude; calculating a quaternion measurement error covariance matrix; constructing feature vectors of acceleration interference and geomagnetic interference amplitude levels, and calculating an interference amplitude level value by using a Gaussian function model; updating the process error covariance matrix and the measurement error covariance matrix by using the interference amplitude level value; calculating a priori attitude estimation error covariance matrix by using the updated process error covariance matrix; calculating a Kalman gain matrix by using the priori attitude estimation error covariance matrix and the updated measurement error covariance matrix; calculating attitude posteriori estimation at the next moment; and performing attitude estimation at the next moment. According to the method, the problems of insufficient estimation precision and poor interference suppression capability of the attitude observation error covariance matrix of the existing LKF are solved.

The invention relates to the technical field of highway bridge safety monitoring, in particular to a bridge dynamic weighing algorithm based on Bayesian maximum posterior probability. Obtaining influence lines through a bridge calibration test, and calculating an influence line matrix, a mean value and a covariance; using a Moses algorithm to obtain the vehicle axle load as the axle load of the initial main cycle i = 0; initial axle load distribution is set, the covariance of load response is obtained through the influence line covariance, the measurement noise and the axle load of the main cycle, and an axle load mean vector and a stable value of the covariance are iterated together with the influence line matrix, the initial axle load distribution and the load response to serve as the axle load distribution of the main cycle; according to the axle load distribution, the influence line matrix, the load response and the covariance thereof, the posterior probability of the axle load is obtained, and the axle load when the probability is the maximum serves as the axle load corresponding to the (i + 1) th main cycle; and repeating until the axle load update difference value is smaller than the preset value, and outputting the axle load result, thereby solving the problem of low axle load identification precision of the existing bridge dynamic weighing system.

The invention relates to a target track association method in a multi-target environment. The method comprises the following steps: firstly, preprocessing a new received trace point; secondly, predicting the next position of each track by using the existing track historical information and adopting a Kalman filtering algorithm, meanwhile, adjusting a state transition matrix and a process noise covariance matrix in real time by considering factors such as ocean current and wind direction in an offshore environment, and adjusting an observation noise covariance matrix according to meteorological information; then comprehensively considering distance, speed difference and motion direction difference to calculate a correlation degree magnitude between a new receiving trace point and each predicted track position; and finally, judging whether the newly received trace point belongs to the existing target track or forms a new target by adopting a threshold judgment method according to the correlation degree value, and updating the state of the track. The method can effectively cope with multi-target intersection, observation loss and clutter interference, improves the stability of a matching result, can realize continuous tracking of a marine target, can adjust parameters according to the environment and target characteristics, and has high adaptability.

Auto-tuning covariances associated with a set of noise models for a variety of sensor modalities and / or perception components such that the covariances are leveled respective to one another may include whitening the covariances and / or error models and determining scalars to apply to the covariances. Determining these scalars may comprise using the residuals that result from generating the set of noise model (e.g., such as may be determined as part of least squares estimation) along with the hat matrix of the process model to determine the scalars. The covariances may iteratively be updated until the scalar adjustments converge or until another end condition is met.

The invention belongs to the technical field of power load prediction, and discloses a power load probability prediction model construction method and application, and the method comprises the steps: constructing a power load probability prediction model, and training the power load probability prediction model through employing a training sample set; the power load probability prediction model comprises a Mama encoder and a Gaussian process decoder; the Mamba encoder is used for capturing a time sequence dependency relationship of an input training sample so as to obtain a corresponding feature vector; the Gaussian process decoder is used for modeling a mutual relation between features in the feature vector to obtain a corresponding covariance matrix and a mean value; gaussian distribution formed by the covariance matrix and the mean value serves as predicted power load probability distribution under the next time step; according to the model, by efficiently processing long sequence data, capturing a complex time sequence dependency relationship and providing interpretable uncertainty quantization, high-precision, expandability and robustness load prediction is achieved, and the model is suitable for complex requirements of a modern power grid.

The invention relates to a seismic liquefaction assessment method based on conditional random field simulation, which comprises the following steps: firstly, obtaining a logarithmic normal distribution random field of a target area under a corresponding SPT-N value, then resampling through a Bootstrap method, constructing a weighted prior probability density function of the target area in combination with a likelihood function, and finally calculating the seismic liquefaction of the target area according to a Bayesian theory. A Markov chain Monte Carlo sampling method is combined, through posterior probability density distribution, an optimal horizontal direction correlation distance is determined, a covariance matrix is constructed to generate a conditional random field, and then through multiple times of simulation, the conditional random field is converged; and finally, aiming at the target area, through calculation of a cyclic stress ratio and a cyclic resistance ratio, constructing a liquefaction probability distribution diagram corresponding to the target area. According to the method, a conditional random field simulation method is inferred and improved by combining Bootstrap and Bayesian theories, the precision and reliability of geological parameter simulation are remarkably improved, and reliable data support is provided for seismic liquefaction assessment of deep and uneven site engineering.

The invention discloses an efficient time-varying anti-fact data analysis method and device based on a state space model, and the method comprises the steps: building a Mama basic model based on a time-varying anti-fact prediction standard, and determining a causal relationship between variables in the Mama basic model; a 1-d convolution layer in the Mama basic model architecture is replaced by a Dropout layer, and an anti-fact Mama model is constructed; the anti-fact Mama model is optimized by selecting a parameter decoupling strategy based on covariance, and an optimized anti-fact Mama model is obtained; historical information and current intervention are input into the optimized anti-fact Mama model for analysis and prediction, and an analysis and prediction result is obtained. According to the method, the problem of excessive balance caused by a direct covariable balance method in the TCP task can be effectively solved, and the prediction performance and the operation efficiency of the model are improved.

The invention relates to the technical field of data processing, in particular to a covariance inverse matrix recursive updating method for on-satellite hyperspectral anomaly detection, which comprises the following steps: acquiring a hyperspectral data stream; carrying out adaptive dimension reduction processing on the data stream and loading an initial background model; extracting local background statistics by adopting a sliding window mechanism, generating a background spectrum dictionary by utilizing online dictionary learning, calculating a reconstruction error between a current pixel and the dictionary and a Mahalanobis distance between the current pixel and a background model, and fusing to generate an abnormal score; performing abnormal confidence coefficient evaluation by combining the spatial context information and the spectral angle matching degree, and updating a spectral mean vector by using an exponential weighted moving average algorithm based on non-abnormal pixel data; and the updated model is injected into the next round of processing to form a recursive chain. According to the method, the high calculation complexity of direct inversion of a covariance matrix is avoided, real-time anomaly detection on a satellite is realized, the downloading amount of original data is remarkably reduced, and the congestion of a satellite-ground communication link is relieved.

The invention belongs to the field of radar data processing, and particularly relates to a sliding window interval track smoothing method based on interactive multiple models. The method comprises the following steps: calculating a reverse model transition probability; calculating a reverse mixing probability; calculating a state mean value and a covariance of output prediction of a corresponding model; calculating a smooth value of the corresponding model; calculating the mode probability after smoothing; and solving an estimator and a corresponding covariance matrix by using a weighting method, and the like. The method is suitable for improving the flight path tracking precision by using the flight path smoothing technology under the conditions that the radar is long in scanning period, noise exists in measurement, the target motion mode is uncertain and the like, and is suitable for a radar data processing process.

The invention provides a wind profile radar spectrum peak estimation method based on a three-parameter dynamic cost function, and the method comprises the steps: 1, carrying out the preprocessing of distance and Doppler spectrum data, and carrying out the three-point moving average smoothing; step 2, noise level estimation based on statistics is carried out; step 3, carrying out candidate spectrum peak selection based on space Doppler window smoothing; 4, performing dynamic weight calculation based on covariance matrix eigenvalue decomposition; step 5, constructing a three-parameter cost function of a distance spectrum peak value RSP power item, a continuity item and a spectrum width consistency item, and performing optimization; and step 6, outputting the optimal spectrum peak trajectory to form a complete wind speed profile trajectory. According to the method, the spectrum peak identification precision and stability in a complex environment can be improved, and the u and v wind correlation coefficients of the estimation method are verified to reach 0.880 and 0.879 through a data set disclosed by an atmospheric radiation measurement website.

The invention provides an intention-driven digital twinning modeling object selection method and device, and relates to the technical field of digital twinning. The method comprises the following steps: acquiring a multi-business demand; defining modeling object parameters according to multi-business requirements; the modeling object parameters comprise attributes of a multi-dimensional QoS target and a modeling object; according to the attributes of the multi-dimensional QoS target and the modeling object, a multi-target Gaussian process regression method is adopted for prediction, and predicted QoS distribution is obtained; the predicted QoS distribution comprises predicted mean values and covariances of the plurality of QoS targets; according to the predicted mean value and covariance of the multiple QoS targets, KL divergence is adopted for evaluation, and the comprehensive importance of each modeling object is obtained; according to the comprehensive importance of each modeling object, a recursive feature elimination method is adopted to adaptively select the modeling objects, and the modeling objects are ranked to select the most relevant modeling object meeting the current task demand. By adopting the method, the construction complexity of the twinborn model can be reduced.

The invention discloses an installation error calibration method based on Student's T distribution and variational Bayes, which comprises the following steps: firstly, constructing an installation error calibration geometric model of an SINS / USBL system, defining coordinate systems, establishing an attitude transfer matrix between the coordinate systems, and designing a state equation and a measurement equation by taking installation error angles in three directions as state variables; time updating and measurement updating are carried out based on a Kalman filtering framework; the method comprises the following steps of: embedding Student's T distribution into a variational Bayesian filtering framework, alternately updating distribution parameters of a state variable, a noise covariance and an auxiliary variable through a variational iterative optimization process, maximizing a variational lower bound until convergence, and outputting an optimized installation error angle estimated value. According to the method, acoustic measurement noise is modeled by using the heavy tail characteristic of the SINS / USBL combined system, the interference of outliers on installation error angle estimation is remarkably inhibited, the positioning accuracy of the SINS / USBL combined system in a complex underwater environment can be effectively improved, and the calibration robustness is enhanced.

The invention discloses a motor multi-parameter identification method based on sampling noise excitation and bias compensation, and the method comprises the steps: firstly obtaining the voltage and sampling current of a motor, and enabling the sampling current to comprise sampling noise; then constructing an information evaluation index, and adjusting a proportional parameter of a current controller to improve the identification information amount; then, shaft voltage feed-forward compensation is constructed to suppress electromagnetic torque pulsation; recursion is carried out by adopting a least square method based on the discrete linear parameterization model to obtain a parameter initial value and a covariance matrix; secondly, estimating offset-containing parameters on line, and calculating a sampling noise variance by using an estimated residual error; and finally, obtaining unbiased parameter estimation according to bias compensation iteration updating so as to output online estimation values of stator resistance, direct-axis inductance Ld, quadrature-axis inductance Lq and permanent magnet flux linkage.

The invention belongs to the technical field related to deep learning, and discloses a training method and application of a three-dimensional flow field prediction system of an underwater vehicle, and the training method comprises the steps: calculating the mass center of a neighbor point set for each surface grid point of a vehicle model, constructing a covariance matrix between the neighbor point set and the centroid of the neighbor point set, and performing eigenvalue decomposition to obtain a normal vector of the point; calculating a normal vector included angle between the surface grid point and each point in the neighbor point set, taking the obtained maximum included angle as the geometric feature measurement of the point, and converting the geometric feature measurement into a weight through a Sigmoid function, thereby obtaining the sampling probability of each point; randomly extracting surface grid points from the original surface grid of the aircraft based on the obtained sampling probability to obtain a point cloud of a corresponding model; and training a point cloud neural network by using the sampled point cloud data to obtain the three-dimensional flow field prediction system of the underwater vehicle. Based on the method, the prediction precision and the flow field detail recovery capability can be improved while the calculation efficiency is maintained.