192 results about "Particle filtering algorithm" patented technology

The invention discloses an electrical equipment operation state monitoring method, system and terminal, full life cycle health management of equipment is realized through multi-dimensional perception and intelligent analysis, a composite sensor network can be constructed from the level of the method, and high-frequency current, ultrahigh frequency, fiber grating temperature vibration, multi-parameter gas and acoustic sensors are integrated. Electromagnetic characteristics, mechanical states, environmental parameters and voiceprint characteristics are covered; the adaptive signal processing technology performs classification and noise reduction on multi-source data, and the three-dimensional digital twin model realizes time-space fusion of a temperature field, a vibration field, an electric field and a sound field; a lightweight space-time convolutional network is deployed to fuse a time domain waveform, a spectrogram and spatial distribution characteristics for diagnosis, and a hidden semi-Markov model and a particle filter algorithm are combined to dynamically predict the residual service life of equipment. The system architecture comprises a self-organizing sensor network with edge computing capability, a time-sensitive industrial communication network and a containerized analysis engine, and supports mixed reality visual interaction.

The invention discloses an atmosphere laser radar data analysis method based on deep learning, and the method comprises the following steps: S1, collecting and preprocessing atmosphere laser radar echo signal data, and generating a time series data set; s2, constructing a long sequence prediction model based on Transform, and forming a preliminary prediction result sequence; s3, optimizing model structure parameters and training parameters by using a particle filtering algorithm to obtain an optimized model; s4, using the optimized model to predict current and future moment data, and generating a final prediction sequence; s5, performing residual analysis on the final prediction sequence and the real-time observation data, and identifying abnormal points; and S6, sudden disturbance is detected, particle filtering optimization is restarted, and the prediction model is dynamically updated. According to the invention, by fusing the deep learning long sequence prediction model and the particle filter optimization algorithm, high-precision prediction and abnormal dynamic identification of atmospheric laser radar data are realized.

The invention discloses a lithium battery health assessment method based on an adaptive extended particle filter algorithm. The method comprises the following steps: constructing a second-order RC equivalent circuit model of a lithium battery; determining all parameters in the lithium battery second-order RC equivalent circuit model by using a recursive least square algorithm with a forgetting factor to obtain a determined lithium battery second-order RC equivalent circuit; estimating SOC parameters of the lithium battery at the moment by combining a particle filtering algorithm with an adaptive extended Kalman filtering algorithm; correcting the terminal voltage of the second-order RC equivalent circuit of the lithium battery at the moment to obtain the terminal voltage of the equivalent circuit; and based on the lithium battery second-order RC equivalent circuit and the corrected terminal voltage, estimating the SOE parameter of the lithium battery at the moment k by using a particle filtering algorithm in combination with an extended Kalman filtering algorithm. The SOC and the SOE of the lithium battery are accurately estimated, and the sampling efficiency and the estimation stability of particle filtering are improved. Cooperative joint estimation of SOC and SOE complements each other, and the accuracy of overall state estimation is further improved.

The invention discloses an urban particulate matter migration path identification method based on data fusion of a dynamic diffusion model and multi-source sensing. According to the method, firstly, multi-source pollution related data of a fixed monitoring station, a mobile monitoring device, a meteorological observation node and a traffic sensing system are collected, and standardized input is constructed after time synchronization, coordinate mapping and exception handling. And then establishing a hybrid dynamic diffusion model fusing a two-dimensional Gaussian plume model and a Lagrange particle tracking mechanism, and realizing assimilation of monitoring data and model output in combination with an improved particle filtering algorithm to obtain a correction concentration field. Based on concentration gradient analysis and particle trajectory superposition, a pollution migration path is extracted, then indexes such as a migration intensity index (MII), a path stability factor (PSF) and path average correlation are calculated, and recognition and sorting of a migration direction, a pollution source position and path stability are achieved. Meanwhile, an alpha dynamic weight factor is introduced, adaptive weighting is realized between the Gaussian model and the LPDM model, and the path strength and consistency are considered. Experimental results show that the method is superior to a traditional method in average absolute deviation (MAD) and hot spot overlap ratio (IoU) indexes, diffusion and migration rules of particulate matters under complex urban conditions can be more accurately revealed, and the method has important environmental governance and emergency management application value.

The invention relates to a tunnel construction progress model generation method based on artificial intelligence. The method comprises the following steps: acquiring multi-source heterogeneous data such as tunnel field equipment operation and geological change, and performing multi-modal fusion to form a unified data set; based on this, a particle filter algorithm is used to correct equipment positioning deviation, and a real-time position optimization result is generated. Comparing the time and space with the progress plan, and identifying and quantifying deviation points through a critical path method and a deviation analysis algorithm to form deviation data. And constructing a construction progress model by combining construction basic parameters and adopting a genetic algorithm, generating an adjustment scheme by taking a construction period and resources as targets, and obtaining an optimal scheme through compliance screening and fitness calculation iterative optimization. By the adoption of the method, efficient integration of heterogeneous data can be achieved, the equipment positioning precision is improved to the centimeter level, multi-dimensional quantification of progress deviation is achieved, progress deviation recognition and resource allocation efficiency is improved, and a technical scheme is provided for tunnel intelligent construction.

The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving decision-making method and system with dynamic risk perception and attention focusing and a vehicle, and the method comprises the steps: predicting the track of a surrounding vehicle in real time through a multi-feature Gaussian weighted particle filtering algorithm, and improving the prediction precision through combining a vehicle kinematic model and resampling optimization; constructing a comprehensive evaluation model fusing transverse and longitudinal risks, and dynamically quantifying the collision risk of the vehicle and surrounding vehicles; and inputting the risk value as a key state feature into a double-depth Q network based on attention mechanism enhancement, focusing key information through a feature attention distribution mechanism, and generating an optimal driving decision in combination with a multi-target reward function. Compared with the prior art, the method solves the problems of insufficient quantification of uncertainty factors, incomplete risk assessment and low decision-making efficiency of automatic driving in a complex dynamic environment, and significantly improves the risk perception capability and decision-making safety of the automatic driving vehicle.

The invention relates to the technical field of attitude control, and discloses a method for realizing self-adaptive active leveling compensation, which comprises the following steps: acquiring real-time data of a vehicle, the data being provided by a plurality of sensors; processing the real-time data through a data fusion algorithm; according to the inclination state and the motion parameters of the vehicle, hydraulic supporting leg adjusting parameters are calculated through a multi-objective optimization algorithm; according to the calculated hydraulic supporting leg adjusting parameters, the action of the hydraulic supporting leg is adjusted through a PI D controller for vehicle balance recovery; the stability of the hydraulic supporting leg adjusting system is verified through the Lyapunov stability theory, and the hydraulic supporting leg adjusting system is used for enabling the adjusting process of the hydraulic supporting leg to be completed in all operation states; and the vehicle inclination state is fed back in real time. By fusing multi-sensor data and adopting a Kalman filtering or particle filtering algorithm, high-precision perception of the real-time inclination state and dynamic parameters of the vehicle is realized, and a more accurate and reliable vehicle attitude judgment effect is obtained.

The invention discloses an automatic control gradient LED lamp energy-saving illumination method, which comprises the following steps: S1, asynchronous sampling is carried out through an illumination sensor A and an illumination sensor B, ambient light change data is collected, a sampling timestamp is recorded, a time difference weight is obtained based on the timestamp, data fusion is carried out through the time difference weight, and ambient light intensity data is obtained; s2, performing data calibration on the ambient light intensity data through a state space model, and performing optimization through a weighted moving average method to obtain an ambient light intensity change rate; and S3, acquiring a light change condition based on an environment illumination intensity change rate, adjusting a brightness duty ratio through a probability model based on Bayesian reasoning to output an initial control variable, performing optimization based on the initial control variable in combination with a particle filtering algorithm to obtain a final control scheme, and performing optimization through the probability model and the algorithm to obtain a final control scheme. A relatively accurate brightness adjustment scheme can still be given, and the intelligent level of lamp control is improved.

The invention provides a flow battery energy storage power station full life cycle health degree assessment management method. The method comprises the following steps: constructing an initial health reference library, collecting electrochemical parameters through a reference electrode, collecting electrolyte physical parameters and environmental parameters through a sensor, synchronously recording operation and maintenance data, and carrying out time-space synchronization processing; introducing a hierarchical fusion assessment mechanism, assessing data integrity and constructing an attention mechanism model, calculating a dynamic weight according to a parameter relative change rate and a health degree correlation coefficient, generating a weighted feature vector, and predicting a short-term health degree index by adopting a bidirectional long-short-term memory network Bi-LSTM; a particle filter (PF) algorithm is introduced to be combined with a physical parameter drift distance to correct a long-term health degree index, and then a real-time health degree index is output through fuzzy comprehensive evaluation. The method can achieve the linkage evaluation of the health state in the operation period and the full life cycle trend, corrects the long-term SOH through the PF algorithm in combination with the physical parameter drift distance, and reduces the error of long-term prediction.

The invention relates to a radar point cloud real-time modeling water conservancy earthwork measurement method and device, equipment and a medium. According to the method, a vegetation root system interference area is scanned and recognized through a dual-frequency polarization radar, a coordinate set of the vegetation root system interference area is obtained, an elevation compensation model is constructed based on dielectric constant difference and fractal dimension to generate a compensation parameter set, and original point cloud is processed by combining a bare soil reference curved surface and adopting a dynamic constraint particle filtering algorithm to obtain real ground point cloud. Then, a corrected terrain curved surface is generated through parasitic energy field constraint optimization, and finally, compensation parameters are fused to realize high-precision earth volume calculation in a root system interference environment, so that point cloud distortion and a terrain curved surface systematic lifting effect caused by a vegetation root system are greatly reduced, and an earth measurement result of a complex vegetation coverage area meets an engineering acceptance standard.

The invention discloses a spacecraft sensor abnormal data recovery method based on spatio-temporal information fusion, and relates to a spacecraft sensor abnormal data recovery method. The method aims at solving the problems that in an existing spacecraft sensor abnormal data recovery technology, the signal-to-noise ratio is deteriorated due to environment interference, and multi-dimensional feature modeling has limitation and is insufficient in self-adaptive capacity. The method comprises the following steps: step 1, preprocessing original sensor data through a sliding mean filter; 2, constructing a time-space dual-scale feature extraction network based on Transform, mining a sensor time sequence dependency relationship from a time dimension, and analyzing multi-sensor association features from a space dimension; 3, introducing a particle filter algorithm to carry out optimal fusion on space-time dual-channel output, and quantifying the uncertainty of a data recovery result; and step 4, by comparing the actually measured data with the uncertainty confidence interval, abnormal detection and data recovery of sensor anomalies are realized. The invention belongs to the technical field of satellite sensor abnormal data recovery.

The invention relates to the technical field of hybrid power system power distribution, and provides a hybrid power operation platform power distribution method suitable for narrow lane operation. A state acquisition module, a fuzzy preprocessing unit, a particle filter estimation unit, a model prediction control unit and a self-adaptive control unit are designed, vehicle inclination angle, load and wheel speed data are acquired in real time, and terrain uncertainty factors are output through fuzzy logic processing; estimating hidden state variables such as the wheel slippage rate and the energy margin by adopting a particle filtering algorithm; performing multi-stage power distribution optimization by applying a model predictive control technology to realize coordinated control of the diesel engine and the electric pump; and finally, self-adaptive feedback and switching are executed, wherein the power modes are switched according to the uncertainty factors, inclination angle and load safety protection is implemented, and braking energy is recycled. The terrain adaptability, the power distribution precision and the energy utilization efficiency of the working platform in the narrow lane complex environment are effectively improved, and meanwhile the operation stability and the environment friendliness are enhanced.

The invention provides a ranging error compensation method for indoor positioning precision time measurement, and aims to improve the precision and robustness of an indoor positioning system. The error type identification method under the LOS / NLOS mixed environment is established by combining the difference between LOS and NLOS signals, RSSI (received signal strength indication) information and a power attenuation model so as to accurately distinguish LOS and NLOS error signals, and corresponding error compensation models are respectively established. Meanwhile, the particle filter algorithm is introduced, so that the adaptability and robustness of the positioning algorithm to complex signal conditions are improved. The error compensation methods are not only suitable for a precision time measurement (FTM) technology, but also can be expanded to other indoor positioning technologies based on time measurement. Through experimental verification, the indoor positioning precision can be effectively improved, and the method has important application value in scenes with high positioning precision requirements.

The invention discloses a radar-vision-I MU fused visual impaired person navigation system, which relates to the technical field of multi-source data processing, and is characterized in that a multi-source data collection module is arranged to collect obstacle distance information, ground feature image data and user motion state data in an environment; a time synchronization module is arranged to carry out space-time alignment on obstacle distance information and ground feature image data to generate multi-modal sensing data, a dynamic map generation module and a fusion model based on a particle filter algorithm are arranged, a dynamic environment map is constructed in combination with motion state data, and the spatial relationship between the current position of a user and surrounding obstacles is output. Setting a trajectory prediction module to perform path planning through a reinforcement learning algorithm to generate a prediction trajectory of user motion, and setting a multi-mode interaction module to output a voice navigation instruction to the visually impaired person through a bone conduction earphone based on the prediction trajectory and a dynamic environment map; the problem of intelligent navigation of a dynamic environment faced by visually impaired people is solved.

The invention relates to an unmanned aerial vehicle anti-interference passive positioning method and system based on GRU and particle filtering fusion, belongs to the field of navigation and positioning, and solves the problems that an unmanned aerial vehicle positioning signal is unstable and is easy to drop in a complex environment in the existing method. Comprising the following steps: acquiring the time difference of arrival of radio communication signals of at least one unmanned aerial vehicle by using a plurality of TDOA passive positioning nodes, and generating a historical state sequence of each unmanned aerial vehicle based on the time difference of arrival; wherein the state value in each historical state sequence is a TDOA observation value and comprises three-dimensional coordinate data and three-dimensional speed data; inputting the historical state sequence of each unmanned aerial vehicle into a plurality of pre-trained GRU neural networks, and generating proposed distribution of the state of each unmanned aerial vehicle at the next moment based on the GRU state sequences output by the plurality of networks; and obtaining a state prediction result of each unmanned aerial vehicle based on a proposal distribution fusion particle filtering algorithm of the state of each unmanned aerial vehicle at the next moment. And continuous, smooth and high-precision positioning of the unmanned aerial vehicle under the condition of discontinuous signals is realized.

The invention discloses a pollutant rapid tracing method and system, and belongs to the technical field of pollutant tracing, the pollutant rapid tracing method comprises the following specific steps: 1, reversely simulating a pollution trajectory: based on pollutant concentration data, meteorological data and topographic data of a real-time monitoring point, calculating a pollution trajectory according to the pollutant concentration data, the meteorological data and the topographic data of the real-time monitoring point; a pollutant migration space-time path is reconstructed through a particle filtering algorithm, and a probability thermodynamic diagram is generated by adopting a Gaussian diffusion correction model to lock a potential source region. Through multi-stage coupling analysis including reverse simulation, candidate source identification, evidence chain construction, traceability conclusion and a multi-dimensional evidence chain including a time sequence, space, path and responsibility fusion mechanism, traceability precision and speed are remarkably improved, pollution event response time is shortened from an hour level to a minute level, the false alarm rate is greatly reduced, and the method is suitable for large-scale popularization and application. And rapid locking and accurate positioning of the pollution source are realized.

The invention relates to the technical field of machining cutter wear prediction, and provides a milling cutter wear prediction method based on parallel spatial-temporal feature extraction and physical description, and the method comprises the steps: collecting a cutter wear monitoring signal, carrying out the denoising of the signal through VMD decomposition in combination with a PCC coefficient, and constructing a data set; inputting data in the data set into a CNN-BiGRU parallel structure prediction model, performing joint modeling on local and global features of tool wear, and introducing an improved space-time double attention mechanism to enhance features; selecting a prediction model hyper-parameter and constructing a training unit to carry out performance evaluation to obtain an optimal prediction result; and constructing a staged physical degradation model based on tool wear characteristics, introducing a particle filter algorithm, and dynamically updating parameters of the physical degradation model by taking a prediction result of a prediction model as an observed quantity to realize residual service life estimation. According to the method, the prediction precision, the physical interpretability and the result credibility are improved.

The invention relates to the technical field of coal conveying system intelligent management and control, in particular to a coal conveying system energy efficiency optimization and pollution source intelligent tracking method based on digital twinning, and the method comprises the steps: collecting a coal quality parameter and equipment state dynamic correction friction coefficient and system characteristics in real time through constructing a digital twinning model with a self-adaptive updating module; redundant sensor deployment and edge calculation are adopted to optimize data transmission, and 5G / optical fiber hybrid networking is combined to reduce delay; and energy efficiency optimization and pollution source tracking are realized through fuzzy control and a particle filter algorithm.

The invention discloses a virtual reality (VR)-based landscape design dynamic display method and system, and the method comprises the steps: collecting real-time environment data and plant growth cycle information through a multi-source sensor, carrying out the processing through a particle filtering algorithm, and obtaining a preliminary time-space alignment dynamic data set; according to the dynamic data set subjected to the preliminary time-space alignment, a neural network model is adopted to train the mutual influence relation among the key feature parameters, and a coupling coefficient matrix is determined; obtaining a logic rule of environment interaction from the coupling coefficient matrix to obtain an interaction graph containing time-space consistency; on the basis of a node connection structure in the interaction map, updating a dynamic state value of each node through iterative simulation equipment to obtain an optimized scene evolution sequence; if a part with inconsistent data exists in the optimized scene evolution sequence, determining a collaborative driving model; and generating a rendering data stream of virtual display according to the collaborative driving model, and generating a continuous landscape dynamic result.

The invention discloses a thermal management method for a power battery module of a new energy automobile, which comprises the following steps of: acquiring current and voltage data and temperature readings of each single battery through a sensor array to obtain an initial heating state data set; determining a real-time internal resistance estimation value of each single battery based on the initial heating state data set; the instantaneous heating power of each single battery is calculated by combining the real-time internal resistance estimation value with the current and voltage data, and a heating power distribution matrix is obtained; determining a local high temperature distribution pattern according to the heating power distribution matrix; obtaining total available flow resources of the cooling medium according to the local high-temperature distribution pattern to obtain a flow resource pool; according to the flow resource pool and the local high-temperature distribution pattern, a particle filtering algorithm is used for optimizing the distribution proportion, and the cooling medium flow share corresponding to each single battery is determined; and the opening degree of an actuator control valve is adjusted through the determined cooling medium flow share, and the overall temperature equilibrium state of the module is obtained.

The embodiment of the invention provides a wafer positioning method for a wafer transmission platform, electronic equipment and process equipment. The wafer positioning method comprises the following steps: acquiring a first image of a wafer in a wafer transmission platform; acquiring image features of the wafer; performing initial positioning on the wafer on the first image according to the image features to obtain initial positioning information; and based on the initial positioning information, tracking and positioning the wafer by adopting a particle filtering algorithm and an image positioning algorithm to obtain tracking and positioning information of the wafer. According to the scheme of the embodiment, the problem of a blind area caused by detecting the position of the wafer by using a sensor at a fixed position is solved, and real-time position tracking can be realized in a transmission area of the whole wafer, so that abnormity can be found in time when the transmission position of the wafer is wrong, and the detection accuracy of the position of the wafer is ensured; each frame of image shot in real time does not need to be compared and analyzed, the software computing power is greatly saved, and practicability and universality are high.

The invention relates to the technical field of unmanned aerial vehicle detection and tracking, in particular to a low-altitude unmanned aerial vehicle positioning and tracking method and system. The method comprises the following steps: acquiring sound spectrum time sequence data and radar plot data of an unmanned aerial vehicle; extracting a first sound spectrum characteristic parameter and a second sound spectrum characteristic parameter; extracting a first radar characteristic parameter and a second radar characteristic parameter; determining initial position estimation of the unmanned aerial vehicle through a first judgment condition; determining optimized position estimation of the unmanned aerial vehicle through a second judgment condition; and tracking the unmanned aerial vehicle by using an improved particle filtering algorithm to obtain a final position and a tracking trajectory of the unmanned aerial vehicle. According to the invention, through heterogeneous sensor data fusion, environment adaptive feature extraction, multistage intelligent judgment optimization and improved particle filter tracking, the precision, robustness and real-time performance of unmanned aerial vehicle detection in a complex environment are effectively improved, and the regional monitoring and countering capability is significantly enhanced.

The invention discloses an intelligent robot trajectory planning method and system based on visual inspection. The method comprises the following steps: acquiring obstacle motion state data through a sensor array, performing time alignment and multi-modal fusion, and constructing an initial state vector; iteratively updating the state by adopting a particle filter algorithm, and generating a smooth trajectory sequence through continuity correction and time sequence integration; determining a potential collision area based on polynomial fitting, and performing extension to obtain a predicted collision boundary; extracting passable grids to construct a dynamic risk map, screening low-risk routes, and sequencing to determine an optimized path; performing correction according to deviation feedback by simulating a forward verification path to generate a final execution instruction; state deviation is continuously monitored in the execution process, and the control scheme is dynamically adjusted. According to the invention, real-time trajectory planning and intelligent path optimization of the robot in a dynamic obstacle environment are realized, and the movement safety of the robot is remarkably improved.

The present invention discloses a sensor fusion indoor positioning method and system based on a particle filter algorithm, which is applied to a cloud server. The method includes: measuring the distance between each base station and a mobile intelligent terminal through a UWB transceiver; calculating the displacement vector generated by the user during the movement through an inertial sensor unit; then, using the channel response information of the UWB signal to obtain the number of effective ranging base stations; finally, using all the data calculated so far as the input of the particle filter fusion algorithm, completing data fusion using the fusion algorithm, and obtaining the location information of the mobile intelligent terminal. The present invention fully considers the impact of the complex indoor environment on the UWB channel and designs a fusion positioning method. Compared with single-source positioning, the method has stronger robustness to changes in the external environment, higher positioning accuracy, and greater practicality; compared with traditional multi-source fusion algorithms, the method has greater flexibility and portability.

The application relates to a river flood discharge capacity dynamic evaluation and hydrological early warning method. The method comprises the following steps: based on a parameter sensitive observation subset, sequentially updating an initial hidden variable in a low-dimensional hidden space through an unscented particle filter algorithm to obtain an optimized hidden variable, and inputting the optimized hidden variable into a river dynamic resistance field generator based on an initial dynamic roughness field to perform decoding processing to obtain a dynamic roughness field of a current period; based on the dynamic roughness field and a state sensitive observation subset, performing analysis and update processing on a state variable field of a hydrodynamic model through a deterministic ensemble Kalman filter algorithm to obtain an assimilated water level field and a flow velocity field; according to the water level field, the flow velocity field and the dynamic roughness field, the maximum flood discharge capacity of a section is calculated in combination with dike top elevation data, and a flood discharge capacity dynamic index is calculated based on the maximum flood discharge capacity of the section and a current actual flow. The method can realize real-time dynamic quantification of river flood discharge capacity and predictive evaluation of flood risk.

The application belongs to the technical field of target tracking and fusion, and relates to a nonlinear filtering distributed target tracking method based on variational inference. Measurement noise parameters of a conventional nonlinear filtering distributed algorithm are assumed to be known, and the application extends the nonlinear filtering distributed algorithm based on variational inference to a single-target tracking scene under unknown measurement noise parameters. Under the distributed algorithm, weight likelihood parameters of each sensor to the target state tend to be consistent, so that the algorithm has strong robustness, small calculation amount, high flexibility and timeliness, and in combination with the variational inference method, the algorithm can achieve high-precision target tracking in a distributed multi-sensor scene under unknown measurement noise variance. The algorithm has close tracking precision to a distributed particle filtering algorithm with known measurement noise variance, and enhances practicability.

The application discloses a large-scale unmanned aerial vehicle group close-coupling positioning method based on IMU / TDOA fusion, which comprises the following steps: step 1, establishing an unmanned aerial vehicle system general model, including a kinematics model of unknown unmanned aerial vehicles, a time difference of arrival (TDOA) and an inertial navigation (IMU) observation model, and preprocessing TDOA measurement values through a moving average filtering (MAF); step 2, according to the measurement information of each unknown unmanned aerial vehicle, an improved particle filtering algorithm is adopted to perform particle initialization, state prediction, measurement update, resampling and state estimation on each unknown unmanned aerial vehicle, so that the optimal position estimation value of each unknown unmanned aerial vehicle at the current moment is obtained; and step 3, each unmanned aerial vehicle moves and continues to estimate the position of the next moment. The application can realize high-precision cooperative positioning of a large-scale unmanned aerial vehicle group in a GNSS denial environment, and the positioning accuracy and robustness are improved compared with a traditional algorithm.

The application discloses a molten silicon liquid level estimation method based on a hybrid adaptive resampling particle filter, and comprises the following steps: firstly, processing laser spot images collected by a CCD sensor to obtain observation data of the liquid level; then, establishing a system state equation of the molten silicon liquid level according to a kinematic principle to describe the movement of the liquid level; performing state estimation on a laser centroid vertical coordinate by using a particle filter algorithm, and obtaining a new particle set by using a hybrid adaptive resampling method; after re-normalizing all particle weights, outputting an optimal estimation value; and finally, smoothing the filtered data by using a moving weighted average method, and the smoothed result is the estimation value of the molten silicon liquid level. The application solves the problem that in the prior art, the variance of Gaussian variation is too large, particles jump out of a sampling range, and it is difficult to accurately estimate a real liquid level.

The application discloses a metallogenic fluid main channel inference model based on particle filtering. The model comprises the following steps: collecting relevant data of a target deposit, establishing an inference database, and defining a state sequence of spatial discrete elements; performing statistics on ore-bearing elements known in all exploration information, taking the known ore-bearing elements as an initial particle group of particle filtering, and generating a spatial channel path of each particle; establishing a metallogenic fluid ion state transfer model coupled with probability and velocity according to the spatial position of the particle and fluid dynamics; establishing a particle weight observation model based on a particle state transfer likelihood function, and dynamically updating the weight of the fluid particle; performing spatial sampling on the particle through a resampling algorithm, updating the weight particle, and outputting a maximum posterior probability path through particle number threshold judgment. The model combines multivariate data constraint and particle filtering algorithm to dynamically estimate the main channel path of the metallogenic fluid in a three-dimensional geological space, and fundamentally solves the problems of high cost and difficult sampling sample acquisition of the traditional method.