46 results about "State-transition equation" patented technology

The invention provides a Q / R dual-adaptive hybrid quantum filtering method for an OTFS (Over the The Over the File System) communication and inductance integrated system, and the method comprises the following steps: constructing an OTFS communication and inductance integrated signal model, and obtaining a target measurement vector; establishing a state vector for describing a target motion state, and constructing a state transition equation and a measurement equation; the method comprises the following steps: constructing a Q / R mixed quantum adaptive adjustment module based on dual-channel features to construct a dual-channel feature input vector, generating a dual-path adjustment factor through a mixed quantum neural network, and constructing an adaptive Q matrix and an adaptive R matrix; and performing adaptive state prediction and updating at each time step by using the adaptive Q and R matrixes constructed in the step 3 to realize tracking of the motion state of the target. According to the method, the hybrid quantum neural network is introduced for driving, collaborative optimization of filter parameters is achieved, and therefore the precision, robustness and response speed of target tracking are remarkably improved in a complex dynamic noise environment.

The invention discloses a wide-working-condition steam turbine system operation data correction method based on digital twinning, and relates to the technical field of steam turbine equipment digitalization, and the method comprises the steps: collecting operation data of a wide-working-condition steam turbine system in real time; constructing a digital twinborn model of the steam turbine system; performing prior covariance estimation on the operation data according to the statistical distribution condition and the design parameters; generating a Sigma point by adopting an unscented Kalman filtering algorithm, iteratively updating a state vector and a covariance in combination with a state transition equation and an observation equation, and outputting an updated known variable; performing smoothing processing on the updated known variable in a plurality of time point regions by adopting an RLOESS algorithm to obtain corrected operation data; according to the method, the real dynamic characteristics of the wide-working-condition steam turbine are approached by building the digital twinborn model, the calculation complexity of dynamic data fusion of a steam turbine system can be remarkably reduced, and the problems that the convergence speed is low and calculation is complex due to strong nonlinearity of a traditional method are solved.

This application provides a target localization method, apparatus, electronic device, and storage medium. The method obtains the initial position of the target object by allocating distance through optimal sub-patterns; it pre-constructs a motion state model of the target object, predicts the state vector of the target object at the next moment based on the state transition equation of the motion state model, and determines the prior position of the target; it filters the current real observation set based on the prior position of the target to obtain a first observation set; it searches and locates the target based on the first observation set, using the previous position of the target object as the center, and determines the real-time target position; it narrows the search range to improve the real-time performance of localization; it fuses the real-time target position with the prior position of the target to obtain a corrected target position, and uses the corrected target position as the target localization result. By fusing the prediction and observation, the respective errors are offset, solving the problem of excessive localization error and improving localization accuracy and reliability.

The application discloses a power distribution network prediction auxiliary state estimation method and system based on an improved iteration process, and the method comprises the following steps: establishing a nonlinear discrete time state space model; generating a group of Sigma points through an unscented transformation, and substituting the Sigma points into a state transition equation to calculate a state prediction value and a state prediction error covariance matrix at a current time; substituting the Sigma points into a measurement equation to obtain a measurement prediction value, and calculating a Kalman gain; calculating a process noise covariance matrix at a next time; and correcting the state prediction value and the state prediction error covariance matrix at the current time to obtain an optimal state estimation value and an error covariance matrix thereof. The application avoids the risk of losing semi-positive definiteness of the covariance matrix in the iteration process from the algorithm mechanism, significantly enhances the numerical stability and robustness of the UKF algorithm, and ensures reliable application in high-dimensional complex power distribution network state estimation.

The application discloses a dynamic programming-based electric vehicle V2G microgrid energy storage capacity optimization method and particularly relates to the technical field of microgrid energy storage optimization, and is used for solving the problem of the existing electric vehicle mobility-induced spatial dynamic characteristics leading to energy storage capacity optimization defects, collecting power grid topology parameters and electric vehicle moving track data, performing geographical grid division on node positions, generating a space-time matrix in combination with time stamps and identifying high-frequency access nodes; constructing a state transition equation based on an impedance matrix between nodes, setting a node-level safety boundary with a line capacity change rate as a dynamic constraint; adopting a phased reverse dynamic programming algorithm, preferentially performing spatial dimension optimization on the high-frequency access nodes, generating charging and discharging constraints that fuse voltage deviation and capacity overrun penalty items; performing global optimization with the minimum total operation cost as the target after integrating the constraints, outputting energy storage capacity configuration strategies in each period; and finally generating an energy storage deployment scheme.

The invention discloses a teenager long-distance running strategy method fusing deep learning and an improved swarm intelligence optimization algorithm, and the method comprises the following steps: collecting multi-dimensional time sequence features in the historical training and competition process of athletes, and constructing and training a CNN-LSTM-Attention prediction model based on the multi-dimensional time sequence features; establishing an integral form long-distance running strategy optimization model framework with the goal of minimizing the game completion time; dividing the long-distance running process into a plurality of continuous time sequence windows, calling a CNN-LSTM-Attention model at the starting moment of each window to generate a state prediction result as a dynamic constraint, and constructing a state transition equation; and based on the state transition equation, solving the optimal speed under the current time sequence window through an improved dung beetle optimization algorithm, rolling to the next window after execution, and carrying out iterative execution until the optimal speeds under all time sequence windows are output.

The invention provides a reservoir area water level monitoring method and device based on Beidou signals and water level change characteristics, belongs to the technical field of water level monitoring, and can improve the monitoring precision of the reservoir area water level and the reliability of a monitoring result. The method comprises the steps of constructing a state transition equation by adopting water level change characteristics of a reservoir area; an inversion observation equation is constructed through the elevation angle of the signal receiver in the reservoir area and the observation signal received by the signal receiver; and solving to obtain the water level of the reservoir area at the current moment through a Kalman filtering method in combination with the state transition equation and the inversion observation equation.

This application discloses a knowledge- and data-driven elastic positioning method, system, and storage medium. The method includes: generating a knowledge graph based on a knowledge base in the positioning domain; the knowledge base includes multiple pieces of first knowledge information, including entity pairs in the positioning domain, relationships between entity pairs, and a first confidence level of the relationships; nodes in the knowledge graph represent entities, edges in the knowledge graph represent relationships between different entities, and the attributes of the edges include the first confidence level of the relationship represented by the edge; inferring a positioning model applicable to the target object based on currently available information sources, observation data of the available information sources for the target object, and the type of observation data; the positioning model includes positioning parameters, observation equations, and state transition equations; and locating the target object based on the observation data and the positioning model to obtain the positioning result of the target object.

The application relates to a heading fusion method based on GNSS speed observation, which comprises the following steps: acquiring gyro angular velocity measurement values and accelerometer measurement values, preprocessing the gyro angular velocity measurement values, preprocessing the accelerometer measurement values, obtaining navigation system speed increments based on the preprocessed acceleration computer system, constructing a state transition equation according to the navigation system speed increments and calculating a prediction covariance matrix, calculating a heading angle, and switching a heading source in the operation of a UAV. The heading fusion method based on GNSS speed observation can solve the problems that the heading observation is invalid when the RTK is affected, the heading output is discontinuous in the invalidation and recovery process, the mutation response of the flight control closed loop is easily induced, the risk actions such as the rapid swing of the aircraft head are caused, and the problems that the deviation accumulation or the unstable updating is caused due to the differences between the time stamps and the updating frequencies of the GNSS and the IMU.

This invention discloses a high-precision power reconstruction method and system for low-frequency sampling of electricity meters, belonging to the field of electricity meter sampling. The method includes: acquiring low-frequency sampled current and voltage sequences; obtaining coarse-grained power baseline and residual data by performing two-dimensional phase point pairing and feature vector mining, and reconstructing using Gaussian process regression; importing the current and voltage sequences into a hybrid differential model, and calculating transient power increments through state transition equation propagation analysis; for the residual data, extracting harmonic amplitude, phase, and frequency parameters, and obtaining the power contribution of each harmonic through line impedance mapping inversion; and superimposing the coarse-grained power baseline, transient power increments, and the power contributions of each harmonic to obtain a full-band power sequence. This application solves the technical problem that existing low-frequency sampling electricity meters are unable to capture rapid transient processes, resulting in insufficient full-band power metering accuracy.

This invention discloses a dimension-reduction reliability assessment method for switched reluctance motors (SRMs) that considers repairability. This method analyzes the faults of the SRM at structural levels, comprehensively converting the failure probabilities of each underlying component into overall system state transition parameters. Based on this, the repairability rate is calculated according to the actual periodic maintenance cycle of the equipment, and a Markov state transition equation system containing maintenance recovery paths is established. To avoid complex calculus operations involving high-order matrices, this invention utilizes Laplace transform to convert the dynamic process into algebraic calculations in the complex frequency domain, achieving analytical order reduction of the model. By performing algebraic analysis on the complex frequency domain function, the dynamic reliability function and mean time between failures (MTBF) of the system are directly obtained. This invention overcomes the shortcomings of traditional models, such as cumbersome computation and unrealistic lifespan predictions. While effectively reducing the computational complexity of microcontrollers, it significantly improves the accuracy of lifespan prediction for motor drive systems and enhances their engineering application value.

The invention discloses a multi-logistics vehicle cooperation method with transportation limitation based on a pheromone sharing ant colony system, and the method comprises the following steps: firstly, obtaining task and vehicle information, constructing a cost and authority matrix, and building a synchronous optimization model; secondly, setting ant colony parameters, and performing greedy initialization on an information matrix; thirdly, initializing a plurality of ant colonies and distributing a task taboo table; then, the ant colony selects tasks through a state transition equation according to the authority and the taboo table, winning ants are screened according to the cost probability, pheromones are updated, and a preliminary scheme is formed; secondly, optimizing the scheme by using a local search algorithm fused by 2-opt and point migration; then, evaluating an adaptive value, updating a global optimal scheme and global pheromones, and sharing the pheromones to adjacent edges; and finally, iteration is carried out until convergence, and a final cooperation scheme is output. According to the invention, efficient scheduling under transportation limitation is realized, and the cost difference between vehicles is reduced while the total cost is minimized.

The embodiment of the invention relates to the field of unmanned aerial vehicles, and provides an unmanned aerial vehicle path planning method and device under the limitation of dynamic collection benefit and cache capacity, and a storage medium, and the method comprises the steps: obtaining initial model parameters needed by a representation process of a target task scene; aiming at a data collection process of the sensor, constructing a calculation expression of collection benefits; aiming at the whole flight process of the unmanned aerial vehicle, constructing a state transition equation of the unmanned aerial vehicle; according to the state transition equation of the unmanned aerial vehicle and the calculation expression of the collection benefits, the total collection benefits corresponding to all the sensors are obtained through calculation; and with the maximization of the total collection benefit as the target and the target constraint condition as the constraint, constructing an unmanned aerial vehicle path planning model according to the initial model parameters so as to solve and obtain a target path planning scheme. By adopting the method, the effectiveness of unmanned aerial vehicle path planning can be improved, so that the data collection effect is improved.

The invention relates to a course fusion method based on GNSS speed observation. Comprising the following steps: acquiring a gyroscope angular velocity measurement value and an accelerometer measurement value, preprocessing the gyroscope angular velocity measurement value, preprocessing the accelerometer measurement value, obtaining a navigation system velocity increment based on a velocity increment under a preprocessed acceleration computer system, and calculating a navigation system velocity increment; and constructing a state transition equation according to the navigation system speed increment, calculating a prediction covariance matrix, calculating a course angle, and performing course source switching during the operation of the unmanned aerial vehicle. By using the GNSS speed observation-based course fusion method designed by the invention, the problem that course observation fails when RTK is influenced can be solved, and the problem that if course output is discontinuous in the failure and recovery process, sudden change response of a flight control closed loop is easily induced, and risky actions such as quick swing of a machine head are brought can be solved; and the problem of deviation accumulation or unstable updating caused by difference between the time stamps of the GNSS and the IMU and the updating frequency is solved.

A keyless phase variable speed tip timing displacement measurement method, system, medium and equipment, in the method, the priori of the included angle between the blades can be determined according to the circumferential uniform installation of the whole rotor blade, and the predicted value of the included angle between the rotor blades is constructed; the arrival time sequence of the rotor blade is measured by the tip timing sensor installed circumferentially on the casing, the estimated speed between two adjacent rotor blades is estimated, the included angle between the rotor blades is calculated as a measurement value according to the estimated speed; according to the included angle between the blades, the angle position of the current rotor blade is inferred through the angle position of the last rotor blade and the included angle between the rotor blades in the rotation process, and a state transition equation is constructed; the Kalman filter is introduced, the updated value of the included angle between the blades is calculated according to the measurement value and the predicted value, the iterative recursive formula is constructed by inferring the angle position of the current blade every time, and the error variance and Kalman gain are calculated in the iteration process to reduce the measurement variance until the blade stops rotating.

The embodiment of the invention provides a synchronization point adjusting method and device, electronic equipment, a storage medium and a product. The method comprises the steps of determining a communication state of terminal equipment at a target moment according to an adjustment request; in response to the condition that the communication state is a non-initial access state, determining a previous moment corresponding to the target moment, and determining a historical time delay vector prediction value of the previous moment; a target state transition model is determined according to the motion information of the terminal device and the network device, a state transition equation is determined according to the target state transition model, and the target state transition model is used for representing a change rule of a time delay vector; determining a time delay vector predicted value of the target moment according to the historical time delay vector predicted value and the state transition equation; and adjusting the initial synchronization point of the terminal equipment according to the time delay vector prediction value to obtain a target synchronization point. According to the scheme, the synchronization point is adjusted through the time delay vector prediction value, dependence on pilot signals is reduced, and therefore the communication quality is improved.

This invention discloses a hand-eye calibration method using mutual observation between two cameras. The two cameras include an external camera (eye-on-hand camera) and an end-effector camera (eye-on-hand camera) mounted on a robotic arm, with the two cameras in a mutual observation posture. The external camera observes the end-effector, constructing the state transition equation and state observation equation for the end-effector's pose, and then using Kalman filtering to correct the end-effector's pose. The end-effector observes the external camera, utilizing the properties of coordinate transformation to construct the state transition equation and state observation equation for the external camera's pose, and then using Kalman filtering to correct the external camera's pose. A calibration loss function is then constructed to achieve hand-eye calibration using both cameras. This invention requires no additional calibration equipment, can simultaneously calibrate both cameras and perform online calibration, and achieves high calibration efficiency by iteratively correcting the calibration results using Kalman filtering.

The application provides a satellite cluster precise orbit determination method based on multi-source data fusion, and belongs to the technical field of satellites. Basic parameters are set, a dynamic model and a state transition equation of a satellite are established, absolute positions and velocities of the satellite cluster are taken as observation quantities, an observation equation of the absolute state of the satellite is established, inter-satellite relative positions and velocities of the satellite cluster are taken as observation quantities, an observation model of the relative state of the satellite is established, a state quantity optimal estimation value is obtained by solving a cluster positioning state updating equation by using a Newton method, and the spatial position and velocity of the satellite cluster are calibrated. The method fuses the absolute state observation and the inter-satellite relative state observation of the satellite cluster, overcomes the limitation of a single measurement method in measurement accuracy, has expansibility, can fuse various observation methods, and further improves the orbit determination accuracy of the satellite cluster.

The application discloses a missile guidance control integration method based on a neural network mechanism modeling, which comprises the following steps: in a continuous time system, a vertical plane missile guidance control integration model is established; according to the dynamic equation of the vertical plane missile guidance control integration, a state transition equation in a discrete time system is established; a data set for fitting the dynamic model of a neural network is established, and a neural network parameter model obtained through neural network regression calculation is used as a non-mechanism fitting model of a missile control system; and according to the neural network parameter model, a guidance control integration mechanism model used in a control cycle is obtained. The method uses the input and output data of a control process to perform self-modeling of a time-varying control system, meanwhile, the model is equivalent to a mechanism method, and the modeling result can be used for the control of a discrete time system, and the modeling principle has interpretability and reliability.

The invention discloses a real-time motion track analysis system and method based on multi-sensor fusion, and relates to the field of track analysis. Original data are collected through multiple sensors, a three-dimensional state vector containing particle radial positions, radial attenuation parameters and angular velocity is constructed, a prior state transition equation and an observation equation are established, and a real-time motion track analysis result is obtained. Real-time analysis and output of a radial attenuation parameter estimated value are achieved through extended Kalman filtering, the problems of noise interference and model uncertainty under complex working conditions are solved, the optimal angular velocity is dynamically calculated by fusing original data collected by a high-speed camera, an encoder and a pressure sensor, and the optimal angular velocity is obtained. The particle centripetal migration efficiency is maximized under the anti-splashing safety constraint, the particle motion trail is estimated and corrected based on the posterior state, the adsorption efficiency is calculated in real time, accurate analysis and dynamic regulation and control of the particle motion trail in the rotary adsorption process are achieved, and the adsorption efficiency and the system stability in the complex environment are effectively improved.

The present invention relates to a method for estimating a rotor position without a position sensor in an active magnetic bearing system, wherein a voltage including a voltage component of the Nyquist frequency is applied to a winding, a current flowing through the winding is measured, a state-space model including state transition equations and output equations for state variables is derived from an electrical circuit model based on the voltage applied to the winding and the current, a predicted value of the current is calculated based on the state-space model, an estimated value of the state variable is corrected based on the error between the measured value and the predicted value of the current, and the rotor position is estimated from the corrected estimated value of the state variable.

This application discloses a BIM-based method and system for large-space pipeline installation, involving pipeline installation: BIM model data is processed into a three-dimensional mesh to generate a meshed spatial model, constructing the pipeline installation space; the load per unit length of the pipeline is calculated based on the pipeline's self-weight and the weight of the medium inside the pipeline, according to physical parameters; dynamic programming is used to optimize the arrangement of supports and hangers; a state transition equation is constructed based on the pipeline's unit length load and a continuous beam model of structural mechanics; based on the state transition equation, the optimal decision sequence is obtained through reverse recursion, backtracking from the pipeline end to the starting point, and at each decision stage, the support point position that minimizes the cumulative deflection of all subsequent pipe segments is selected, generating a globally optimal support and hanger arrangement sequence; based on the globally optimal support and hanger arrangement sequence and the pipeline's unit length load, the deflection value of each pipe segment is calculated; this application avoids the problem of uneven deflection distribution caused by traditional local optimization methods.

Embodiments of the present application provide a product residual life prediction method and device, electronic equipment and storage medium. The method comprises: obtaining degradation data of a product, and extracting a degradation curve according to the degradation data; performing degradation modeling on the degradation curve according to a Wiener process to obtain a degradation model, and determining offline parameters according to the degradation model; dividing the degradation curve into a training set, a test set and a validation set, and performing long short-term neural network training; establishing a state transition equation and a measurement equation according to the Wiener process, and sampling from the offline parameters; predicting a system state at an n-th moment according to a long short-term memory neural network, recursively performing the state transition equation to the n-th moment according to a particle parameter at a current moment, and synthesizing a particle weight in a recursive process as a particle weight at the current moment; performing normalization according to the particle weight to obtain a residual life probability density of the product at the current moment; and performing parameter updating according to real state data obtained at each moment.

This invention discloses a method for fusing InSAR and GNSS heterogeneous surface deformation based on an adaptive sparse spatial basis, belonging to the field of geological disaster monitoring and data processing technology. The method first acquires and aligns InSAR and GNSS deformation sequences; calculates the InSAR deformation feature field and its spatial gradient magnitude; sparsifies control points according to gradient thresholds to construct an adaptive sparse spatial basis set that is sparse in low-gradient regions and dense in high-gradient regions; models the deformation observations, combines the spatial basis set with the state transition equation, and uses filtering smoothing and the EM algorithm for iterative solution to reconstruct a high spatiotemporal resolution deformation sequence. This invention can adaptively match deformation spatial features, reducing the computational dimensionality while preserving local deformation details, and achieving high-precision fusion of heterogeneous data.

The invention belongs to the technical field of digital twinning, and particularly relates to a digital twinning-based power grid engineering area underground pipe network modeling method, which comprises the following steps of: initializing a digital twinning model of an underground pipe network, carrying out gridding on the digital twinning model, and calibrating static parameters; based on a state transition equation of a coupled multi-physical field, performing state propagation on particles representing grid node states to obtain predicted particles; evaluating the engineering risk degree of each grid node, wherein the engineering risk degree is determined based on the construction risk coefficient, the state uncertainty and the safety margin; redistributing the particles according to the engineering risk degree; and fusing heterogeneous sensor data, calculating the weight of the prediction particle, calculating the optimal state estimation value of the grid node according to the normalized weight of the prediction particle, and updating the digital twinborn model. According to the method, non-uniform distribution of the computing resources to the key area is realized, and the model estimation precision and the real-time performance of risk early warning are improved.

The invention provides an electric power spot transaction strategy generation method and device based on conditional value-at-risk optimization, equipment and a medium, and relates to the technical field of electric power. The method comprises the following steps: acquiring power market transaction data, power consumption data of a user and attribute data; dividing the power consumers into different power consumption mode classes according to the power consumption data and the attribute data, establishing a power consumption elastic model for each class of power consumers, and determining the power consumption elastic capacity of the target time period according to the power consumption elastic model; determining a price signal reference of the target time period according to the electricity market transaction data, and calculating an electricity consumption deviation cost and a financial arbitrage space according to the price signal reference; and according to the electricity consumption deviation cost and the financial arbitrage space, constructing an objective function and a state transition equation which take revenue maximization as an objective, and solving by taking the electricity consumption elastic capacity as a constraint to obtain the newly added future locking electric quantity, the elastic adjustment quantity and the spot declaration quantity of the target time period. According to the invention, a reasonable day-ahead transaction strategy can be formulated.

The application discloses a kind of based on filtering smooth airborne video SAR image stabilization method and device, the method includes: the two-dimensional interframe shift observation vector sequence of computer airborne video SAR image sequence is calculated;Based on Kalman filter model, with the two-dimensional interframe shift observation vector of each frame in two-dimensional interframe shift observation vector sequence as input, Kalman filtering is executed, obtains full-frame posteriori state estimation sequence and full-frame posteriori error covariance sequence, Kalman filter model includes state equation, observation equation and filter recursion equation, and observation equation is determined according to two-dimensional interframe shift observation vector, and observation equation is two-dimensional Singer-random walk joint state transition equation;According to full-frame posteriori error covariance sequence, RTS reverse state smoothing is carried out to full-frame posteriori state estimation sequence, and video SAR image stabilization result is obtained.The application can effectively solve the problem of interframe shift of airborne video SAR image.

The application provides a marine drilling working condition recognition method and device, and relates to the technical field of oil and gas drilling. The method comprises the following steps: obtaining drilling working condition data to be recognized; recognizing the drilling working condition data to be recognized based on a preset drilling working condition recognition model to obtain a drilling working condition recognition result; wherein the preset drilling working condition recognition model aggregates normal working condition characteristics and risk working condition characteristics, and is obtained according to a real-time state transition equation combined with a comprehensive loss function of normal working conditions and risk working conditions; the real-time state transition equation is the sum of the probability of transition to the corresponding working condition state at the current time and the sum of the working condition local probability paths from the initial state to the working condition state at the current time. The device executes the above method. The marine drilling working condition recognition method and device provided in the application embodiment can improve the timeliness and accuracy of drilling working condition recognition.

The invention belongs to the field of power equipment monitoring, and discloses a mechanism data fused transformer state prediction method and related device.The method comprises the steps that a health state prediction value is obtained through a state transition equation, an extended Kalman filtering algorithm is used for fusing observation index actual values, and a more accurate health state estimation value is obtained; self-adaptive adjustment of the model is realized by updating a drift coefficient and an observation noise covariance of a state transition equation, and a final prediction result is jointly determined by an observation index estimation value based on a physical mechanism and a data-driven observation index prediction residual error. According to the method, a physical model and a data driving method are combined, so that the accuracy of long-term trend prediction is ensured, short-term fluctuation characteristics are effectively captured, and the prediction precision is remarkably improved. The method is high in calculation efficiency, high in environmental adaptability and easy to deploy and implement in an existing monitoring system, and a reliable technical means is provided for transformer state evaluation.

The invention relates to the technical field of Internet of Things multi-sensor data fusion, and discloses a multi-source spatio-temporal data fusion method based on Kalman filtering, and the method comprises the steps: obtaining multi-source spatio-temporal data, unifying the spatio-temporal scale of the multi-source spatio-temporal data, constructing a system state transition equation and a measurement equation integrated with environmental factors, carrying out the whitening processing of process noise and measurement noise, and obtaining the multi-source spatio-temporal data fusion. And removing abnormal data by combining preliminary screening and deep screening, and predicting and updating the system state by using Kalman filtering to obtain a fused state estimation value. The method can adapt to multi-source data of different spatial and temporal scales, the noise processing precision and the comprehensiveness of abnormal data recognition are improved, the state prediction model is optimized, and the fusion precision and reliability are remarkably improved. And the scheme is high in expansibility and can be widely applied to scenes such as urban traffic state estimation and environmental parameter monitoring.