214 results about "Particle filter" patented technology

The invention relates to the technical field of automatic workpiece grabbing and visual servo control, and discloses a workpiece grabbing method and system based on visual feedback, and the method comprises the steps: obtaining a real-time image through a front-view camera, a side-view camera and a top-view camera, and extracting surface features through a feature fusion network; inputting the features into a pose estimation model based on a particle filtering framework, and iteratively updating the pose in combination with a multi-dimensional observation likelihood function to generate prediction parameters; constructing a multi-target path planning model based on the parameters, and optimizing the path by adopting a dynamic planning algorithm with the shortest path and the minimum joint movement as targets; a hierarchical control model is established, a strategy layer performs global planning, an adjustment layer corrects a local path, and an execution layer realizes trajectory tracking through visual servo control and outputs a control instruction to complete grabbing. Through multi-view perception, robust pose estimation, global optimization path planning and hierarchical control, the precision, efficiency and stability of workpiece grabbing in a complex environment are improved.

The invention discloses a digital twinning system and a construction method thereof, and relates to the technical field of digital twinning, and the construction method comprises the steps: carrying out the classified collection of multi-source heterogeneous data of a digital twinning entity, carrying out the filtering and denoising through a self-adaptive wavelet threshold, mapping the data into a multi-dimensional feature vector, screening key features, and outputting the key feature data; the method comprises the following steps: establishing a physical mechanism layer based on a general physical rule, defining core physical parameters and a constraint equation, initializing a particle swarm to establish a data driving layer, constructing an LSTM time sequence prediction module, executing particle filter state calibration, and selecting a model to configure a communication protocol to establish a virtual-real interaction layer, so as to realize state mapping and instruction feedback of a digital twin entity and a virtual model; and calculating virtual and real state deviation in real time and performing attribution diagnosis, adjusting model parameters or key features according to a deviation source, generating an optimization parameter combination based on a long time sequence prediction result and performing simulation verification in a virtual environment, and controlling entity parameter adjustment through an instruction feedback channel so as to realize predictive optimization.

The invention discloses an intelligent target detection system based on multi-sensor data fusion, particularly relates to the field of intelligent target detection, and comprises a heterogeneous sensor module, a data fusion module and a self-calibration module. According to the invention, at night or under low illumination, infrared thermal imaging dominates target detection, and the data weight of the visible light camera is reduced; under strong electromagnetic interference, the laser radar starts polarization filtering, and the millimeter wave radar performs frequency hopping interference resistance; data fusion adopts a three-level architecture: the first level is based on an improved D-S evidence theory to solve cross-modal data conflicts; in the second stage, aiming at sampling frequency and position difference, a time-space stamp compensation algorithm is used for alignment; the third level uses a bidirectional LSTM neural network of an attention mechanism to distribute weights; when the confidence coefficient of the sensor is low, a particle filter compensation mechanism is started, the deviation of the sensor is corrected, health assessment and predictive maintenance are carried out, historical data are recorded and calibrated, a health degree index is calculated, the remaining service life is predicted, and an alarm is triggered when the confidence coefficient is lower than a threshold value.

The invention discloses a method and a system for monitoring the temperature of an energy storage battery in a high-altitude area. Through environment adaptive feature reconstruction, thermodynamic model correction and multi-frequency EIS fusion feature extraction are utilized to generate a feature vector adaptive to the plateau environment. The thermodynamic model correction adjusts the convective heat transfer coefficient by introducing an air pressure correction coefficient; the multi-frequency EIS fusion feature selects a specific frequency point impedance value to construct a vector, and the weight is dynamically adjusted through a random forest algorithm. The lightweight hybrid machine learning model integrates the advantages of LightGBM, 1D-CNN and a physical constraint particle filter model, and realizes accurate prediction for different working conditions. The plateau exclusive training mechanism covers data enhancement, transfer learning and online calibration, and the generalization ability and adaptability of the model are improved. According to the method, the problems of low temperature monitoring precision and poor model adaptability of the energy storage battery in the high-altitude area are solved, the monitoring precision and the system reliability are remarkably improved, and a guarantee is provided for safe and stable operation of a high-altitude energy storage system.

The invention relates to the technical field of laser ranging, in particular to an unmanned aerial vehicle dynamic laser ranging method based on multi-source fusion and adaptive compensation, and the method comprises the following steps: obtaining a ranging pulse of a laser ranging module, and carrying out three-axis rotation and coordinate translation in combination with an IMU angle to generate a geographic registration coordinate set; radar and ultrasonic ranging are fused to construct redundant distance compensation data, particle filtering is executed based on IMU acceleration angular velocity to generate an attitude constraint distance, SLAM weight is adjusted according to illumination and meteorological parameters, and an unmanned aerial vehicle dynamic ranging coordinate result set is generated. Spatial registration is executed by combining longitude and latitude height data, by establishing dynamic association between the ranging data and IMU attitude data, smoothness and continuity of the ranging data can be kept when attitude disturbance is severe, the weight proportion of the vision ranging data in multi-source fusion is dynamically adjusted, and the high-precision estimation capacity of the target distance in the dynamic flight state is improved.

The invention discloses a generator state estimation method and system considering noise and parameter uncertainty constraints. The method comprises the following steps: acquiring model parameters and dynamic state vectors of a generator, and establishing augmented state vectors; performing unscented transformation on the augmented state vector to obtain a particle set; improving to obtain robust mixed Kalman particle filtering, and in the process of performing unscented Kalman filtering on an augmented state vector, taking correlation entropy maximization of a measurement information sequence as a target function, and solving by adopting a fixed point iteration method to obtain a filtering gain; determining a filtering gain according to the updated state of the measurement information; robust mixed Kalman particle filtering is executed, physical constraints of model parameters serve as a feasible region, after resampling, projections of the model parameters in new-generation particles exceed the feasible region, the model parameters are set to be closest boundary points, and then resampling is conducted again; a weighted average value of the particle set is an optimal joint estimation value, a dynamic state estimation value and a model parameter identification result are separated, and reliable uncertainty quantization is provided for state and parameter estimation.

The invention discloses an environmental event dynamic risk assessment method and system based on a Bayesian network, belongs to the technical field of artificial intelligence, and aims to solve the technical problems that in existing environmental risk assessment, dynamic data adaptability is poor, multi-source heterogeneous data fusion is difficult, and real-time performance is insufficient. Comprising the following steps: acquiring environment data through a sensor cluster deployed in an environment, and uploading the environment data to an edge computing node; performing data preprocessing on the environmental data through the edge computing node; extracting time series data fragments from the standardized data stream based on a predefined sliding time window; constructing a risk prediction model based on the dynamic Bayesian network; and taking the extracted time series data fragments as input, performing risk level analysis through a risk prediction model in combination with particle filter reasoning, predicting and outputting a risk level, a risk level probability value and a risk conduction path as prediction results, and constructing a visual risk conduction map based on the prediction results.

The invention relates to the field of gas leakage identification, and discloses a gas leakage identification method and system based on sound localization, a medium and equipment, and the method comprises the steps: collecting a leakage sound wave signal through a microphone array, and extracting acoustic features in a complex background; simulating a diffusion process of gas in a turbulence environment after gas leakage through an established leakage gas convection-diffusion model, and combining gas concentration distribution in the simulated diffusion process with acoustic characteristics to predict sound source localization at a leakage position; modeling a sound source localization search process as POMDP, and iteratively updating a confidence state of a sound source position through a particle filter; spatial distribution features are extracted from the confidence state through DBSCAN clustering to serve as input of the LSTM-DQN network, spatial and temporal features are fused through the constructed LSTM-DQN network, cross-scene generalization is achieved through transfer learning, and sound source coordinates are dynamically optimized and output through the Q network. According to the invention, the positioning accuracy and real-time performance in a complex environment are improved.

The invention discloses a rail transit intelligent inspection robot positioning system based on laser SLAM and inertial navigation, and relates to the field of real-time positioning, the rail transit intelligent inspection robot positioning system is characterized in that data are synchronously acquired through a laser radar, an IMU, a speedometer and an RGB-D camera, and high precision in rail positioning is realized; the point cloud filtering module extracts orbit feature points through an improved voxel grid algorithm, and the inertial navigation initialization module calculates an initial pose based on IMU data and establishes a motion constraint model; the map feature layering module divides the point cloud into a track surface, equipment and a background layer; and the data tight coupling module optimizes the pose, and the dynamic object elimination module eliminates obstacles, so that the SLAM optimization precision is ensured. And the global positioning compensation module performs repositioning through particle filtering to generate a 6DoF pose estimation semantic map. The method has the advantages that by fusing the laser SLAM and inertial navigation technologies, high-precision and stable rail transit inspection is realized, the positioning precision and the environmental adaptability are optimized, and the intelligent operation and maintenance efficiency is improved.

The invention discloses a fuel cell vehicle control method integrating fault diagnosis and energy management. According to the method, vehicle key operation parameters are collected in real time, a whole vehicle operation state vector is constructed, and fuel cell health diagnosis and preliminary power action generation are carried out at the same time based on the state vector. The diagnosis module obtains a health factor and a severity index through residual calculation, particle filtering and generalized likelihood ratio test, and the action generation module outputs an intelligent agent power distribution vector. And according to the severity index, the dynamic reconstruction power, the SOC and the power change rate constraint, optimal power distribution is obtained through optimization solution, and meanwhile, a high-severity state is intervened in combination with a hierarchical fault-tolerant strategy. The method also comprises a demand power prediction and online learning module which is used for improving the robustness and the adaptive capability of the optimization strategy. According to the invention, by tightly combining the health state of the fuel cell with energy management optimization, high-energy-efficiency, long-service-life and reliable dynamic control of the fuel cell system is realized.

The invention discloses an intelligent substation virtual loop online transmission verification method based on GOOSE / SV closed loop test, and relates to the technical field of intelligent substation operation and maintenance. Through precise clock synchronization and an improved cross-correlation algorithm, in combination with wavelet noise reduction and spectral clustering analysis, nanosecond synchronization quality evaluation of GOOSE / SV signals is realized, and the hidden transmission risk discovery time is shortened from regular maintenance to real-time monitoring; a hierarchical hidden Markov model is adopted to analyze equipment-level to system-level behavior modes, real-time probabilistic reasoning is realized in combination with a dynamic Bayesian network and particle filtering, a multi-dimensional evaluation system is constructed, the reliability evaluation capability under complex working conditions is remarkably improved, an optimization scheme is generated based on network path characteristic analysis and bottleneck identification, and the reliability of the system is improved. Multi-scene closed-loop verification is carried out by means of a digital twin technology, safety and reliability of parameter optimization are ensured, and full-process intelligent operation and maintenance of the virtual circuit of the intelligent substation from state perception to optimization verification are realized.

The invention relates to the technical field of mine environment positioning, in particular to a mine scene self-adaptive repositioning method based on multi-modal perception, which comprises the following steps of: S1, acquiring information, and acquiring visual images, spatial features, wireless signal features and inertial motion data of an internal environment of a mine by using a multi-modal sensor; s2, extracting information, namely extracting the feature data obtained in the step S1, forming a dynamic topological map, and marking temporary obstacle information at the same time; s3, information processing: adaptively adjusting data fusion weights of different sensors according to the information extracted in the step S2 based on a dynamic environment sensing result; and S4, information updating: combining particle filtering and a graph optimization algorithm to realize robust pose estimation and real-time map updating. According to the invention, the failure risk of a single sensor is reduced through multi-mode complementation, and the positioning error is reduced by more than 40%; and through semantic auxiliary matching, the relocation time consumption is reduced.

The invention discloses an end-to-end automatic driving long tail scene data acquisition and automatic labeling method. The method comprises the following steps: firstly, collecting multi-modal time series data including images, point cloud and odometer information; thirdly, calculating a comprehensive long-tail scene judgment coefficient by constructing an occupation map and fusing perception uncertainty and prediction uncertainty, thereby automatically identifying a high-risk and high-uncertainty long-tail scene; then, only for the data judged as the long-tail scene, starting a particle filtering-based track truth value generation process, fusing the motion speculation of the odometer and the map matching of the laser radar point cloud in the process, and carrying out state prediction, observation updating, resampling and weighted averaging to obtain a track truth value of the long-tail scene; and generating a high-quality self-vehicle track point sequence conforming to the vehicle kinematics constraint as a truth value label. According to the method, accurate screening and true value automatic generation of the long-tail scene are realized, the data acquisition efficiency and the labeling quality are improved, and the safety and generalization ability of an end-to-end automatic driving model in a complex scene are enhanced.

The invention provides a pipeline defect prediction and evaluation method and system based on AKF and SR-UPF. The method comprises the following steps: obtaining observation data of a pipeline; based on the observation data, a growth rule of pipeline defects is obtained through a preset mechanism model; introducing random disturbance in the defect growth process through a preset random process model based on the growth rule of the pipeline defect, and generating a pipeline defect prediction result; wherein the mechanism model carries out dynamic estimation and correction on parameter uncertainty and noise distribution through adaptive Kalman filtering, and the random process model carries out particle weight and distribution optimization through square root unscented particle filtering. The problems that in the prior art, a pipeline corrosion and crack growth reliability evaluation method is insufficient in prediction precision and low in calculation efficiency are solved.

The invention discloses a dynamic scene laser mapping and positioning method based on semantic information visual enhancement, and belongs to the field of navigation positioning. Comprising the steps that observation data of multiple sensors are acquired, and the multiple sensors comprise a laser radar and a visual sensor; establishing a coordinate conversion relation of the visual sensor relative to the laser radar according to the observation data; according to the coordinate conversion relation, mapping the visual semantic information to a laser radar coordinate system to obtain semantic enhancement data; according to the semantic enhancement data, pose estimation of the robot is updated under a particle filtering framework; constructing a composite map containing semantic information and geometric information according to the updated pose estimation; and executing a navigation task according to the composite map. Through deep fusion of visual semantic information and laser radar data, the positioning precision and navigation efficiency of the robot in a dynamic scene are effectively improved, and reliable technical support is provided for intelligent upgrading of the manufacturing industry.

The invention relates to the technical field of batteries, in particular to a battery capacity prediction method and system and a computer program product. The invention provides a battery capacity prediction method, which comprises the following steps of: obtaining a constant voltage stage time characteristic sequence of a battery, and inputting the constant voltage stage time characteristic sequence into a bidirectional long short-term memory network to obtain an initial prediction sequence; generating a capacity degradation sequence including battery capacity corresponding to the battery based on the capacity degradation model; constructing a mapping relation between the initial prediction sequence and the capacity degradation sequence through a dynamic time warping strategy; determining a target prediction residual error through a particle filtering model and based on the initial prediction sequence and the capacity degradation sequence which have the mapping relation; and correcting the initial prediction sequence through the target prediction residual error to obtain a capacity prediction value. The problem of reference correction error caused by time migration in a traditional battery capacity prediction method is solved, and the prediction precision and long-term stability in a capacity jump scene are improved.

A system is provided for localizing an autonomous work vehicle within mapped agricultural environments when GPS may be unavailable. Range sensors capture LiDAR images that are segmented by a trained model into features such as trunks and canopy. Trunk points are clustered to compute centroids, which are used to estimate left and right tree lines and a lane centerline relative to the vehicle. This sensor-derived centerline is compared with georeferenced lane and row geometry stored in a digital map. A particle filter maintains multiple pose hypotheses, propagates them using vehicle odometry, and weights them according to alignment between the lane centerline relative to the vehicle and the mapped lane geometry for the particle. Resampling and averaging of high-weight hypotheses produces an adjusted pose that corrects for lateral and heading errors. The adjusted pose serves as input to a navigation controller that issues steering and speed commands, enabling accurate autonomous operation.

The invention provides an indoor single-station sensing integrated SLAM positioning method based on 5G NR, which only uses a single base station to provide state information of multipath signals for a receiving end by using 5G NR signals reflected and scattered in an indoor environment, and then obtains the positions of a receiver and a virtual base station and environment information through double-layer particle filtering calculation. The positioning cost is greatly reduced, and the utilization rate of signal resources is increased. According to the invention, the problems of poor effect and high cost of the existing positioning technology in the indoor environment are solved, and the sensing mapping function of the surrounding environment is realized at the same time. According to the invention, under the condition that the existing signal mode and the number of base stations are not changed, trajectory tracking and environment perception of the user are realized, the cost is effectively reduced, and the utilization rate of signal resources is improved.

The invention discloses an intelligent heating control method and system based on a liquid heating container, and the method comprises the following steps: obtaining an observation sequence, completing time alignment and scale normalization, and forming a synchronous observation sequence; carrying out duration inference by using a semi-Markov model, and calculating a residence constraint parameter; constructing a discrete-continuous mixed state space model and executing Rao-Blackwell particle filtering to obtain a particle weight, a phase sequence and posterior edge distribution, and calculating a weight degradation index; generating a noise portrait, and giving a quantile vector, a tail ratio and polarity bias; implementing quantile gating correlation entropy re-calibration according to the noise portrait, and refreshing a weight degradation index; a discrete Schrodinger bridge is constructed in a window with the phase state kept unchanged, deterministic carrying is carried out, and a calibration prior transfer kernel and proposal distribution are formed; and in combination with the weight degradation index and the resident constraint parameter, self-adaptive resampling is carried out, and a heating power track and a safety constraint parameter are output. The state judgment stability and the power control precision are improved.

The invention discloses a tool remaining service life prediction method based on FODPGPFM, and belongs to the technical field of tool remaining service life prediction. The invention provides a prediction scheme giving consideration to small sample adaptability and nonlinear degradation description capability, effectively solves the problems of low prediction precision and insufficient reliability of the existing method in small sample and nonlinear milling cutter wear scenes, and improves the prediction accuracy of the small samples and nonlinear milling cutter wear scenes through the advantages of processing the small samples and capturing fine nonlinear trends by fusing the fractional derivative grey model. A residual service life prediction model suitable for milling cutter full wear stages (initial stage, middle stage and rapid wear) is constructed according to the ability of particle filtering to deal with dynamic uncertainty in a complex processing environment, and a prediction result with higher precision and narrower confidence interval is realized.

The invention discloses a fusion filtering method, system, equipment and medium for power transformer winding state monitoring, and belongs to the technical field of power equipment state monitoring, and the method comprises the steps: obtaining an original state monitoring signal of a transformer winding; performing multi-scale decomposition on the original state monitoring signal by adopting self-adaptive wavelet transform; an improved particle filter is embedded, and a suggested distribution function of relative entropy optimization and a dynamic weight updating mechanism are combined; the filtered sub-signals are reconstructed through inverse wavelet transformation; weight parameters are adjusted in a self-adaptive mode; and outputting the key state parameters for transformer winding health assessment. Under the complex electromagnetic environment and the dynamic load fluctuation working condition, the signal-to-noise ratio of the state data of the transformer winding can be remarkably improved, the comprehensive accuracy rate of state evaluation is improved, and reliable data support is provided for health management and preventive maintenance of the transformer winding. And the operation reliability of the transformer and the intelligent level of state evaluation can be obviously improved.

The invention discloses a marine ranch fish school monitoring method based on acoustic imaging, and belongs to the field of fish school intelligent monitoring, and the method comprises the steps: obtaining a noise interference component from compensated coverage range data, correcting signal fusion through employing Kalman filtering, and obtaining a fusion signal with noise suppression; acquiring a trajectory tracking sequence from the three-dimensional motion vector, and predicting motion complexity by adopting particle filtering to obtain centimeter-level accurate positioning coordinates; extracting a density model and body length estimation parameters from the reliable monitoring data set, and fusing biomass measurement logic to obtain a final fish school biomass value; aiming at the final fish school biomass value analysis distribution mode, correcting deviation by adopting a statistical model, and determining an optimized biomass distribution diagram; and generating an alarm signal according to the optimized biomass distribution diagram, and if the biomass distribution is judged to be abnormal, triggering real-time notification to obtain monitoring response data. According to the invention, the precision and real-time performance of fish school monitoring are obviously improved.

The invention relates to the technical field of positioning and navigation, in particular to a two-dimensional laser positioning method and system in a sparse scene, and the method comprises the steps: endowing a point cloud with a corner semantic label through a semantic segmentation model through fusing two-dimensional laser radar and camera data, and removing a dynamic object; extracting wall corner line and wall corner point features, performing data association with a pre-constructed semantic map, performing coarse positioning to obtain an initial pose, and performing fine optimization by using a semantic PLICP algorithm to obtain a fine positioning pose; and finally, carrying out confidence evaluation and fusion on the fine positioning pose in a particle filtering mode, and outputting a final optimized pose. According to the invention, the wall corner instance and features in the wall corner semantic point cloud are extracted, nearest neighbor search association and coarse positioning are carried out on the semantic map, the initial pose is obtained, semantic PLICP fine optimization is carried out, and particle filtering fusion is supplemented, so that high-precision and robust positioning independent of manual marking in a sparse scene is realized.

The invention provides a hetero-variance migration network and particle filter-based battery life prediction method, and relates to the technical field of battery health management, and the method comprises the steps: collecting a part of charging data fragments from a target battery under an actual operation condition, and extracting an incremental capacity feature; processing the incremental capacity characteristics by using a heterovariance migration network trained on a tagged source domain and an untagged target domain, outputting a mean value and a variance of a battery health state, and describing an evolution process of the battery health state by using a parameterized double-index degradation function; generating an initial parameter particle by taking a degradation function parameter of source domain fitting as a mean value, and updating the parameter particle by taking a state prediction value output by the heterovariance neural network as an observation value and a corresponding uncertainty variance as observation noise; and finally, predicting the remaining life of the battery based on the updated parameter result. According to the method, cross-working-condition and cross-battery-type residual life prediction is realized, and the prediction precision and robustness are improved.

The invention discloses a battery pack health state prediction method and system driven by a data fusion model, and the method comprises the steps: extracting aging features according to battery test data, and obtaining feature data; according to the feature data, constructing a state space model based on Gaussian process regression, and obtaining an initial prediction model; carrying out transfer learning on the initial prediction model according to the pre-training data set to obtain a transfer model adaptive to the target battery pack; constructing a particle filtering framework according to the migration model, inputting real-time characteristic data acquired on line into the particle filtering framework for state updating and parameter correction, and obtaining a closed-loop estimation result; and outputting a health state prediction value of the battery pack according to a closed-loop estimation result. According to the method, high-precision and high-robustness online prediction of the full-life-cycle health state of the power battery pack is realized, and the generalization ability of the model in a data scarcity scene and the long-term estimation stability in a dynamic environment are remarkably improved.

The invention relates to the technical field of battery state prediction, in particular to a battery state prediction method and system integrating time-frequency analysis and physical modeling. Comprising the following steps: S1, collecting real-time data of a battery, including voltage, current and temperature data; s2, integrating and preprocessing the data, wherein the preprocessing operation comprises denoising and standardization; s3, extracting time-frequency characteristics of the voltage signals through short-time Fourier transform; s4, estimating the internal resistance and open-circuit voltage of the battery through a random forest estimation model; s5, predicting the voltage of the single battery through a gating circulation unit; s6, predicting the voltage of the battery through a single-particle model in combination with physical constraints; s7, obtaining predicted values of SOC and SOH states by using particle filtering; and S8, displaying and storing the predicted SOC and SOH results, and transmitting the SOC and SOH results to a battery management system at the same time. Compared with the prior art, the method improves the richness of the features and the robustness of the prediction model, reduces the dependence on a large amount of training data, and is more suitable for the dynamic prediction of the state of the battery.

The invention discloses a nonlinear system dynamic boundary constraint particle filtering method, and belongs to the technical field of deep space exploration. The implementation method comprises the following steps: independently sampling all nodes of the flexible lander, and introducing constraints in a particle filtering initial sampling link to enable initial particles to meet the constraints; in the filtering process, as many particles as possible fall within the constraint range in the initial stage of filtering by widening the constraint boundary, and the constraint boundary is continuously shrunk to be gradually close to the real constraint range, so that the situation that a large number of particles fall out of the constraint boundary due to the fact that the real constraint range is too narrow is avoided. According to the method, the constraint boundary is dynamically adjusted, the number of effective particles is increased, and a higher-precision multi-node state estimation result of the flexible lander is obtained; according to the multi-node state of the flexible lander, the particle diversity is ensured through dynamic scaling constraint boundaries, and filtering stop caused by particle degradation is prevented; and realizing real-time trajectory planning and guidance control of the flexible lander by using a node state estimation result.

The invention discloses a multi-beam sounding attitude error adaptive compensation method. The method comprises the following steps: synchronously acquiring inertial measurement unit data and multi-beam sounding footprint point cloud data of a platform; the method comprises the following steps: calculating an initial attitude estimation value after data of an inertial measurement unit is preprocessed, generating a terrain curved surface model through point cloud data space fitting, and extracting a terrain fitting error and a multi-frame point cloud registration drift vector to represent a residual term and a drift trend term of an attitude error; constructing a state transition and observation model based on a particle filter framework, taking a terrain fitting error and a drift vector as observation correction items, and dynamically evaluating system disturbance intensity and adjusting particle filter parameters by using an attitude stability index; and outputting a corrected attitude angle by using a feedback compensation system, applying the corrected attitude angle to a multi-beam echo orientation model, and generating depth data after error correction, thereby effectively improving the sounding precision and reliability of the multi-beam sounding system in a complex environment.

The invention belongs to the technical field of positioning and navigation, and provides a geomagnetic sequence positioning method based on BiLSTM and multi-head attention. The method comprises the following steps: firstly, acquiring data of geomagnetism, an accelerometer, a gyroscope and other sensors by using a smart phone, and dividing a geomagnetism sequence into a plurality of subsequences to enhance the time sequence modeling capability; then constructing a multi-scale feature extraction model: extracting deep time sequence features of each sub-sequence by adopting a bidirectional long-short term memory network (BiLSTM), and constructing global representation through splicing; a self-adaptive multi-head attention mechanism is introduced, magnetic signal key features are captured from multiple dimensions, feature weights are dynamically adjusted in combination with a gating mechanism, and important information enhancement is achieved. And the fused multi-scale features output initial position estimation through a full connection layer. In order to further improve the positioning precision, data of a magnetometer and a gyroscope are fused through complementary filtering to correct a course angle, a geomagnetic positioning result serves as an observation value, a pedestrian track plotting result serves as a state prediction value, and final fusion positioning is achieved through particle filtering.

The invention discloses an airborne three-dimensional graphic engine display optimization method based on particle filter optimization, and relates to the technical field of airborne avionics graphics. According to the method, optimization strategies such as a particle filtering optimization technology, a three-dimensional pixelating technology, dynamic scene management, resource optimization management, hardware acceleration, an asynchronous shader technology and optimization renderer design are introduced, so that the rendering efficiency, the display quality and the resource utilization rate of the graphics engine are remarkably improved, and the rendering efficiency of the graphics engine can be greatly improved in a resource limited environment. And high-precision and low-delay three-dimensional graphic rendering is realized, the requirement of the aircraft on real-time display is met, and the method has important application value and popularization prospect.