53results about How to "Improve estimation accuracy" patented technology

This invention discloses a method for improving the accuracy of inertial guidance based on polynomial recursive least squares, comprising: constructing a guidance tool error model based on the difference between inertial guidance telemetry observations and a flight environment function, wherein the guidance tool error model satisfies a linear relationship; constructing a recursive formula based on polynomial recursive least squares based on the guidance tool error model; determining the estimated value of the guidance tool error coefficient at the current recursive time based on the difference between guidance telemetry observations at the current recursive time and the recursive formula of least squares, and using the estimated value of the guidance tool error coefficient to compensate for the guidance telemetry observations at the current recursive time. This invention can significantly improve estimation accuracy and efficiency, and has a wider range of applications and higher engineering value.

The application provides a kind of energy storage battery estimation method and system based on deep learning fusion, it is related to energy storage battery management technical field, the application collects voltage, current time series data and calculates the ratio of voltage variation and current variation of adjacent sampling time, obtains dynamic resistance sequence, finally as trajectory feature, trajectory feature and temperature time series data time alignment fusion are input into time convolution network, and output residual capacity and health state;At the same time, based on the open-circuit voltage mapped by the residual capacity estimation value, the predicted voltage value is reconstructed by combining the dynamic resistance sequence and the current time series data, and the deviation between the predicted voltage and the measured voltage is constructed as a physical consistency constraint loss, which is combined with the estimation error loss to form a joint loss function. The parameters of the time convolution network are updated by back propagation, thereby solving the problem of failing to capture the dynamic resistance evolution law and lacking physical consistency constraint, and improving the estimation accuracy and model generalization reliability under complex working conditions.

This invention discloses a method and system for quantitatively assessing the degree of fibrosis in kidney pathological sections, belonging to the field of medical image processing technology. The method includes: performing color normalization and adaptive contrast enhancement preprocessing on Masson stained section images; classifying pixel-level tissue components using a multi-component semantic segmentation network containing a channel-space dual-path attention module; calculating the fibrosis area ratio and outputting a CI score based on the Banff grading standard; generating a fibrosis spatial distribution heatmap; and calculating the annual fibrosis progression rate through longitudinal follow-up comparison.

This invention relates to the field of power system fault quantification technology, and discloses a method, system, equipment, and medium for quantifying distribution network line faults under typhoon weather. It calculates the wind-induced fault rate of distribution network lines by constructing a wind field correction model that incorporates micro-topography correction factors and wind direction-line angle correction factors. With the goal of minimizing power outage losses in the distribution network, a coupled influence model of transmission network faults on the distribution network line fault rate is constructed and solved to obtain the optimal load shedding amount for each load node in the distribution network and its corresponding operational constraint boundary. Under this boundary, the random process of load shedding allocation and load transfer of faulty lines within the distribution network is simulated using a double Monte Carlo sampling method, and the probability of line cascading faults caused by transmission-distribution coupling is calculated based on the simulation results. The combined time-varying fault rate and type of distribution network lines are determined by integrating the two fault rates, achieving accurate quantification of distribution network line faults under the influence of transmission-distribution coupling.

The driving range estimation method based on unit charge range and battery aging correction mainly includes four steps: online battery SOC estimation, periodic battery SOH update, unit SOC range estimation, and driving range estimation. This invention uses periodic battery SOH estimation to correct the battery SOC estimation, and combines unit SOC range estimation to achieve accurate driving range estimation. It has the advantages of simple model structure, low computational load, high estimation accuracy, and easy implementation in vehicle BMS. Under normal driving conditions, the maximum driving range estimation error of this invention is within 3km, which meets the operating requirements of electric vehicles.

This invention discloses a visibility estimation method and apparatus based on binocular vision. The method includes: simultaneously acquiring left and right views using a calibrated binocular camera; inputting the image pairs into a stereo matching deep neural network to obtain a disparity map and converting it into a depth map; inputting the left view and depth map into a dual-branch deep convolutional neural network to extract multi-scale features; fusing RGB features and depth features through a cross-modal feature fusion module; and finally outputting a visibility estimate through a feature aggregation and regression module. The apparatus includes a binocular image acquisition unit, a data processing and visibility estimation unit, and a result output unit. This invention solves the depth ambiguity problem of monocular vision by fusing binocular depth information and image appearance information, achieving high-precision, non-contact visibility surface measurement. It has the advantages of low cost and flexible deployment, and is suitable for visibility monitoring in traffic scenarios such as highways.

The application provides an improved sparse learning out-of-grid direction-of-arrival estimation method based on variational Bayesian. The method is characterized in that: the original data received by a hydrophone array is preprocessed, a real value transformation is used to convert a vectorized covariance matrix signal in a complex number field to a real number field, and the idea of variational sparse Bayesian learning and grid evolution is combined to make the grid evolve from an initial uniform grid to a non-uniform grid adaptively in an iteration process. The evolution process includes grid updating and grid fission. The evolved grid points are gradually close to the real source position through the alternately iterative grid updating process and grid fission process. Compared with the traditional compressed sensing method, the method has higher DOA estimation accuracy, reduces the operation complexity, optimizes the operation efficiency, improves the resolution capacity of the source, and has higher application value in actual engineering, especially in the case of few snapshots and low signal-to-noise ratio.

The application discloses a point pair registration method and system based on feature guidance and double constraints, and belongs to the technical field of computer vision and robot grabbing. The method aims to solve the problems of recognition failure and insufficient estimation accuracy of traditional methods when parts are blocked and stacked, and point cloud features are not obvious. The scheme adopts a two-stage optimization strategy. Firstly, in the coarse registration stage, an adaptive sampling PPF algorithm guided by geometric features is proposed. By preferentially sampling points in the edge, curvature and other feature obvious areas, the robustness and efficiency of matching are improved. Secondly, in the fine registration stage, an ICP algorithm with multi-constraint optimization is proposed. The pose result obtained by coarse registration is used as the initial value. Through rotation and angle constraint, a multi-objective optimization function is constructed to guide the fine registration process to converge in the correct direction and avoid falling into local optimum, thereby ensuring the accuracy and physical feasibility of the final pose estimation. The application significantly improves the accuracy of industrial part pose recognition.

This invention discloses an underwater image enhancement method based on cascaded correction and multi-scale fusion, mainly including the following steps: (1) establishing an underwater image dataset to form a first dataset; (2) constructing an underwater image enhancement model based on cascaded correction and multi-scale fusion; (3) inputting the first dataset into the model for image enhancement; (4) evaluating the enhanced underwater image to meet the index requirements, thus obtaining the final underwater image enhancement model based on cascaded correction and multi-scale fusion. Compared with the prior art, the underwater image enhancement method disclosed in this invention significantly enhances the clarity and color fidelity of underwater images, effectively improving the visual quality of underwater images.

This invention discloses an online prediction method for battery SOC based on an incremental correlation vector machine (RVM) strategy using a multi-kernel ensemble approach. The method includes the following steps: Step 1, data preprocessing; Step 2, training set sampling; Step 3, kernel function selection; Step 4, model training; Step 5, model validation; Step 6, adaptive kernel parameters; Step 7, RVM model ensemble; Step 8, model prediction; Step 9, incremental learning strategy; and Step 10, online incremental prediction. From a practical perspective, this invention addresses the complexities and diverse needs of various applications. Drawing on the ideas of incremental learning and ensemble learning, it generates highly differentiated RVM individual learning models containing multiple kernel functions through dual perturbation of training samples and kernel functions. Combined with a novel incremental ensemble strategy, it avoids the problem of model overlearning, improves the model's generalization ability and robustness, and expands its application scope.

The application discloses a kind of based on sea condition multimodal perception's offshore dynamic docking sealing method, obtains propagation path parameter and calculates initial fluctuation index, obtains the deviation value sequence corresponding to path fluctuation;Get the corrected attitude vector;By weighted fusion method, reduce the credibility weight of corresponding direction data, and recalculate overall credibility distribution;Determine the optimized attitude vector;Judge whether path fluctuation is stable, if unstable then iteration updates deviation value sequence;Get final position attitude calculation result, for the correction of docking position deviation, output accurate docking instruction sequence.The application enhances the buffering and absorption capacity of equipment to external impact, prevents rigid collision and sealing failure caused by sudden surge or flow field pulsation, improves the safety, flexibility and sealing reliability of offshore dynamic docking.

The application discloses a transformer residual magnetism content evaluation method and device, a terminal and a medium. The technical scheme provided by the application is based on the correlation between the fitting single-phase current waveform evolution law and the transformer residual magnetism content, a residual magnetism content evaluation formula based on the negative amplitude of the single-phase differential current signal of the transformer core is constructed, three-phase current signals of the transformer are collected during evaluation, the negative amplitude of the single-phase differential current signal, that is, the minimum value of the single-phase differential current signal, is calculated, the transformer core residual magnetism content estimation formula is calculated, the residual magnetism content evaluation result is determined according to the calculation result, and the transformer residual magnetism content estimation accuracy is improved.

The application discloses a multi-extended target data association and tracking method based on appearance and motion information feedback, and is applied to the technical field of radar target tracking, and aims at the problem of estimation precision reduction caused by the traditional "clustering first and then associating" algorithm due to neglecting target appearance information; the closed-loop system of tracking is constructed, the extended target appearance parameterization modeling is a rectangle, and the target appearance and motion information are estimated simultaneously in the tracking process; then, the geometric relation between the target appearance and the point cloud distribution and the spatial constraint among the multiple targets are utilized to construct multiple hypothesis association events and perform feasibility inspection; the problem of insufficient data association accuracy caused by mutual interference of adjacent extended targets, point cloud aliasing in the complex multi-extended target scene is effectively solved; and the tracking performance of the radar system in the multi-extended target scene is significantly improved.

The application discloses a kind of coupling deep learning and physical mechanism's leaf water use efficiency estimation method, first, the environmental data and leaf water use efficiency of target area historical monitoring period are acquired;Then, construct the carbon dioxide concentration prediction model inside leaf, the trained carbon dioxide concentration prediction model inside leaf is used to predict carbon dioxide concentration inside leaf, the predicted value of carbon dioxide concentration inside leaf is substituted into formula to calculate leaf water use efficiency, the error between leaf water use efficiency estimation value and measured value is calculated, and the model is optimized by back propagation;Finally, the environmental data of target area monitoring period are acquired, and are input into the trained carbon dioxide concentration prediction model inside leaf, to obtain carbon dioxide concentration inside leaf;Leaf water use efficiency is calculated by carbon dioxide concentration formula inside leaf, and the estimation of leaf water use efficiency is completed.The method improves the estimation accuracy of leaf water use efficiency, and realizes continuous estimation.

This invention proposes a video power grid frequency estimation method and system based on illumination region detection and fusion. The invention constructs a power grid frequency estimation region dataset and uses this dataset to train an illumination region detection model, resulting in an optimized illumination region detection network. Feature frames to be estimated from the video are extracted. These feature frames are then input into the optimized illumination region detection network for detection, yielding multiple estimation regions. The average pixel intensity within each estimation region is calculated, resulting in multiple illumination sequences. Each illumination sequence is preprocessed to obtain a preprocessed illumination sequence. A short-time Fourier transform is performed on the preprocessed illumination sequences, and quadratic interpolation is used to estimate the power grid frequency signal for each region. Finally, the multiple power grid frequency signals from each region are fused to obtain the final power grid frequency estimation result. This invention improves the efficiency of illumination region detection, the accuracy of video power grid frequency estimation, removes noisy regions from the image, and expands the applicability of video power grid frequency estimation.

An air conditioning system has an air conditioner having a refrigerant circuit in which a prescribed amount of refrigerant is filled, the refrigerant circuit being configured by connecting an outdoor unit and at least one indoor unit by a refrigerant pipe, and a server communicatively connected to the air conditioner. The air conditioner has a first communication section that detects a state quantity related to control of the air conditioner, acquires a detected detection value, and transmits the acquired detection value to the server. The server has a second communication section for receiving the detection value from the air conditioner, an estimation section that estimates a residual refrigerant amount remaining in the refrigerant circuit using the detection value of a first characteristic quantity when a state quantity related to the amount of refrigerant filled in the refrigerant circuit is the first characteristic quantity, and a determination section for determining whether the detection value of the first characteristic quantity is a detection value that should be used in estimation of the residual refrigerant amount. As a result, even in the case where the characteristic quantity used to estimate the residual refrigerant amount is affected by other failures, it is possible to improve the estimation accuracy of the residual refrigerant amount.

This invention discloses a method for estimating the road adhesion coefficient based on a dynamic model and support vector regression, relating to the field of vehicle parameter estimation and control. The method includes the following steps: S1, establishing a training data acquisition module to collect data on the vehicle's four-wheel wheel speed, vehicle speed, longitudinal acceleration, lateral velocity, lateral acceleration, yaw rate, steering wheel angle, tire lateral force, tire longitudinal force, and road adhesion coefficient; S2, using the features in the training dataset formed in S1 as input to the support vector regression (SVR) to obtain a pseudo-measured value of the road adhesion coefficient; S3, establishing a three-degree-of-freedom vehicle dynamics model and a Dugoff tire model, and designing an AEKF algorithm model; S4, using the pseudo-measured value of the road adhesion coefficient obtained in step S2 as an extension of the measurement vector in step S3 of the AEKF algorithm to achieve optimal road adhesion coefficient estimation. Compared with existing technologies, this invention comprehensively considers the model accuracy problem and the nonlinear relationship capture capability of support vector regression, and the estimation method that integrates the two can simultaneously possess robustness and accuracy.

The application provides a mobile robot self-learning robust control method based on a hybrid Kalman filter and belongs to the technical field of robots.The technical scheme comprises the following steps: step 1, a dynamic model of an uncertainty factor;step 2, real-time estimation of state parameters and model parameters of the mobile robot to optimize the original dynamic model;step 3, introduction of an adaptive forgetting factor recursive least square method to dynamically adjust filter parameters;step 4, design of a non-singular fast terminal sliding mode controller based on a saturation function as a system main controller;step 5, establishment of an error correction RBF neural network and introduction of an adaptive error learning strategy;step 6, completion of stability analysis and proof of the control system by means of Lyapunov stability theory and simulation experiment of the optimized model.The application effectively suppresses the chattering of the sliding mode control and significantly improves the control precision and robust performance of the four-wheel robot.

This invention belongs to the field of state estimation technology and relates to a lithium battery state of charge estimation method based on adaptive dual-fusion Kalman filtering. The method includes: constructing an equivalent circuit model; obtaining battery parameters based on the equivalent circuit model; obtaining battery measurement values ​​and measurement estimates based on the battery parameters; using a corresponding Kalman filter to estimate the battery state of charge based on the absolute value of the error between the measurement values ​​and the measurement estimates, and obtaining the battery state of charge estimate; and obtaining the battery state of charge estimation result based on the battery state of charge estimate. This invention combines the advantages and disadvantages of both EKF and XKF filters, employing different estimation schemes at different times, which can improve estimation efficiency while ensuring accuracy.

This invention belongs to the field of wireless communication and relates to a machine learning-based method for wireless communication channel estimation. The method includes: acquiring pilot signals, antenna array geometric parameters, and multipath propagation parameters from the transceiver end of a millimeter-wave massive MIMO system to construct a three-dimensional propagation structure model; determining candidate regions for the channel sparse support set and generating a prior constraint matrix for the channel sparse support; inputting the prior constraint matrix and pilot observation data into a sparse reconstruction algorithm for channel sparse feature extraction and dimensionality reduction; performing super-oscillatory feature enhancement on the dimensionality-reduced channel sparse features to form an enhanced channel feature vector; inputting the enhanced channel feature vector and the prior support vector matrix into a complex domain deep expansion network to output the channel estimation result; and outputting the final beamforming weights. Its beneficial effects are improved sparse support set matching accuracy and channel estimation precision with low pilot overhead, and enhanced system throughput and interference suppression capabilities.

The invention relates to a temperature self-adaptive real-time correction method and device for the SOC of a ship lithium battery, and belongs to the technical field of ship battery management systems.The method comprises the steps that when the ship lithium battery is in a standing state, a corresponding OCV-SOC curve is selected from multiple sections of pre-constructed OCV-SOC curves based on the current temperature of the ship lithium battery; solving the actually measured OCV of the ship lithium battery based on the corresponding OCV-SOC curve, and determining an SOC reference value; when a difference value between the SOC reference value and the SOC estimation value is greater than a preset threshold value, performing correction based on the SOC reference value and the SOC estimation value to obtain an SOC correction value; the SOC estimation value is determined based on cluster voltage, current, temperature and SOC historical value of the ship lithium battery. According to the ship lithium battery SOC temperature adaptive real-time correction method provided by the invention, when the temperature fluctuates, the SOC error is reduced, and the SOC estimation precision is improved.

The application provides a radar signal processing method and device based on joint ESPRIT, acquires non-uniform slow time sampling data of a radar, and constructs a corresponding signal model; calculates a time difference according to the sampling data, and constructs a corresponding equivalent shift relationship in combination with the signal model; extracts a subspace for the sampling data to obtain a corresponding signal subspace; stacks the equivalent shift relationship and the signal subspace to obtain a joint shift relationship; and calculates a target Doppler frequency according to the joint shift relationship. Without changing the existing radar hardware structure, the method realizes coherent fusion of cross-frame data by unified modeling and subspace processing on segmented sampling data, thereby significantly improving the Doppler estimation accuracy and resolution.

This invention relates to a NOMP-based RIS-assisted millimeter-wave MIMO system channel estimation method, belonging to the category of channel estimation methods. Taking the downlink of a RIS-assisted millimeter-wave MIMO system as an example, the channel model of the base station (BS)-RIS and the RIS-mobile station (MS) is represented as a concatenated channel model in Khatri-Rao product form. One-dimensional NOMP, two-dimensional NOMP, and least squares (LS) algorithms are used to estimate multiple parameters in the concatenated channel, thereby achieving channel estimation. The advantages are that the proposed RIS-assisted millimeter-wave MIMO system channel estimation method estimates channel parameters with lower pilot overhead, providing effective CSI for RIS-assisted systems; applying the NOMP method to RIS-assisted millimeter-wave MIMO channel estimation can solve the grid mismatch problem existing in traditional compressed sensing algorithms, improve the accuracy of joint parameter estimation, and thus improve the channel estimation accuracy.

A kind of wheel hub motor drive system comprehensive energy efficiency optimization control strategy method, construct integrated stator water cooling structure wheel hub motor drive assembly, stator inside is laid with multiple groups of spiral distribution cooling liquid pipeline;Collect real-time temperature data, rotational speed data and chassis attitude data when wheel hub motor operates;Based on real-time temperature data, the flow and flow rate of cooling liquid are adjusted by double wheel hub motor intelligent cooling system to maintain stator temperature within the preset threshold range;Based on rotational speed data and chassis attitude data, the target torque distribution value of each wheel hub motor is calculated using multi-motor collaborative differential control system.The present application is laid with multiple groups of cooling liquid pipeline in the stator of motor, the wheel hub motor stator water cooling new structure of high heat dissipation efficiency, construct double wheel hub motor intelligent cooling system and control method based on enhanced heat transfer, and the comprehensive use efficiency of drive assembly is more than 80%.

The invention provides a portable PD quick-release battery module and an electric quantity management method thereof. The method belongs to the technical field of portable energy storage and intelligent power supply management. The method comprises the following steps: carrying out magnetic attraction state sensing on a portable PD quick-release battery module to generate module connection state data; identifying a current working mode according to the module connection state data, and generating a state judgment result of an equipment power supply mode or a PD output mode; through the combination of magnetic attraction state perception and multi-source electric quantity parameter acquisition, the working mode can be accurately identified and the electric quantity estimation strategy can be dynamically adjusted when the battery module is quickly assembled or disassembled, so that mode misjudgment caused by poor contact of a mechanical switch is effectively prevented, and the reliability of electric quantity management is greatly improved.

The invention belongs to the technical field of water meter assembly. The invention provides a single-workbench water meter assembly method and system based on body intelligence. A four-layer framework of perception, prediction, planning and execution is adopted. The sensing module outputs a water meter part state and a structured scene map based on the 3D scene reconstruction network; the prediction module generates collision risk and assembly execution time prediction based on the Transform multi-task sequential network; the planning module generates an optimal assembly action sequence through hierarchical reinforcement learning; and the execution layer executes operation in a position-force hybrid control mode, and feeds back data in real time to form a closed loop. According to the scheme, the problems that traditional manual assembly is low in efficiency and existing automatic equipment lacks self-adaptive capacity are solved, the defects that sudden working conditions are difficult to deal with and multi-model adaptation is poor are overcome, the assembly efficiency and consistency are improved, manual intervention is reduced, assembly interruption and part damage are avoided, and flexible automation of the whole water meter assembly process is achieved.

The application provides a pose information processing method and device and a storage medium. The method comprises the following steps: obtaining to-be-processed pose information of a plurality of cameras in an image acquisition system, wherein the to-be-processed pose information comprises intrinsic parameters of the plurality of cameras, relative extrinsic parameters and absolute extrinsic parameters of a predetermined main camera in the plurality of cameras; obtaining a plurality of target images of a target object, wherein the plurality of target images are obtained by photographing the target object placed on a turntable by using the plurality of cameras based on the to-be-processed pose information; determining depth information of the plurality of target images according to the intrinsic parameters of the plurality of cameras and the relative extrinsic parameters; performing minimum re-projection error processing on the absolute extrinsic parameters according to the depth information to obtain optimized absolute extrinsic parameters; and determining the optimized absolute extrinsic parameters, the relative extrinsic parameters and the intrinsic parameters of the plurality of cameras as final pose information of the plurality of cameras. The application improves the pose information estimation accuracy of a weak texture object, reduces the error caused by the relative sliding between the camera and the turntable, and improves the accuracy of the pose information.

This invention proposes a method and apparatus for estimating vehicle tire force, comprising: acquiring vehicle state response data and control quantity data within a continuous time window, and performing normalization processing to obtain input feature data; inputting the input feature data into a pre-constructed fully connected neural network model, and outputting the estimated lateral force values ​​of each wheel of the vehicle through nonlinear mapping processing of the fully connected neural network model; inputting the estimated lateral force values ​​as intermediate physical variables into a vehicle dynamics mechanism model that includes the effects of pitch angle and roll angle, and calculating the predicted vehicle state value at the next moment based on the Newton-Euler theorem; constructing a loss function based on the deviation between the predicted vehicle state value and the actual measured vehicle state response data at the next moment, and using the loss function to iteratively optimize the parameters of the fully connected neural network model until the convergence condition is met, and outputting the final tire force estimation result.

The application discloses a kind of estimating method and system of vehicle welding deformation quantity, comprising: using modeling unit to obtain the welding point information of welding piece, the welding point information includes welding point name, welding point coordinate, welding point corresponding plate number;Using coupling unit to format conversion is carried out to the welding point information obtained;Using simulation unit receives the welding point information after format conversion, and determines welding deformation simulation data in combination with the material information, fixture information and welding information of the welding piece;According to welding deformation simulation data, the model of the welding piece is made, and the actual deformation data in the model welding process is measured;Using computing unit, the welding deformation curve of the model is fitted according to the actual deformation data of the model;According to the welding deformation curve of the model, the welding deformation quantity of the welding piece is determined.

This invention belongs to the field of agricultural remote sensing technology and relates to a method for estimating farmland-scale evapotranspiration, comprising: 1) acquiring basic data of the study area based on a UAV; the basic data includes multispectral image data, thermal infrared image data, and meteorological data; 2) preprocessing the multispectral image data and thermal infrared image data obtained in step 1); 3) obtaining instantaneous farmland evapotranspiration based on the meteorological data in step 1) and the multispectral image data and thermal infrared image data preprocessed in step 2); 4) extending the instantaneous farmland evapotranspiration obtained in step 3) to a daily scale to complete the estimation of farmland-scale evapotranspiration. This invention provides a method for estimating farmland-scale evapotranspiration that can effectively estimate farmland-scale evapotranspiration while ensuring high estimation accuracy.