24results about How to "Reliable estimate" patented technology

The invention belongs to the field of underwater target navigation and positioning, and discloses an underwater multi-station speed measurement technology based on acoustic beacons, which comprises the following specific steps: 1) establishing a coordinate system, acquiring measurement information, and estimating the initial position of a navigation body; 2) sound velocity correction and position parameter estimation are carried out point by point, and speed parameter estimation is carried out after iterative calculation of position parameter convergence; and 3) estimating a constraint polynomial coefficient, and optimizing the position and speed parameters of the navigation body. The technology has the characteristics that the observation process does not depend on a navigation body, the measurement precision is high, the result can be accurately obtained in real time and the like, reliable estimation of position and speed parameters based on polynomial constraint under a complex navigation working condition is realized, and the problems of functional expression of observation motion under a high-dynamic motion condition and provision of continuous and smooth motion parameters are solved; the method has good adaptability to the complex motion process of an underwater target, has a wide technical application prospect, and can provide a data processing and analysis technology for underwater motion performance analysis and evaluation of a navigation body.

The invention discloses a maximum heart rate estimation method, a maximum heart rate estimation system and an estimation interaction system. The estimation method comprises the following steps: screening a power cache sequence and a heart rate cache sequence from historical riding data sequences of sports users; fitting a function relationship between the maximum heart rate and the maximum power by adopting the screened power cache sequence and the heart rate cache sequence; on the basis of a preset model, the corresponding maximum aerobic power is estimated by using the weight, the height and the FTP of the exercise user; on the basis of the function relation and the maximum aerobic power, the corresponding heart rate is obtained to serve as the estimated maximum heart rate; wherein the power threshold FTP is updated based on the physical fitness change of the exercise user; the preset model describes the relationship among the maximum aerobic power, the weight, the height and the power threshold value of the exercise user. According to the method, the maximum heart rate of the exercise user can be reliably and accurately obtained without extreme exercise.

The invention discloses a centrifuge liquid flow detection system based on a fuzzy recognition and classification technology, and relates to the technical field of centrifuge flow detection, and the centrifuge liquid flow detection system comprises the following steps: collecting an image set, and carrying out preprocessing and marking processing to obtain a segmentation flow rate; obtaining characteristic parameters; obtaining a preferred fuzzy model; characteristic parameters of the real-time liquid image are obtained, and flow detection is conducted on the real-time liquid; the method is used for solving the problems that in an existing method for detecting the liquid flow, when the liquid surface is irregular or liquid fluctuation exists, the accuracy and stability of data received by a sensor can not be affected, and consequently the collected liquid flow is different from the actual liquid flow; and the operation of the centrifugal machine is influenced.

The present application relates to a method for estimating a target fuzzy speed, which method is applied to a radar sensor. The method comprises: alternately transmitting a first waveform signal and a second waveform signal respectively at a first center frequency and a second center frequency; processing intermediate frequency signals of the first waveform signal and the second waveform signal, so as to respectively generate a first range-Doppler matrix and a second range-Doppler matrix; acquiring the number of phase wraps according to a phase difference between the first range-Doppler matrix and the second range-Doppler matrix, and a beat frequency of the second waveform signal; and estimating a target speed and a target distance by means of the number of phase wraps. The beneficial effects of the method lie in further improving the estimation of an aliased area and a speed by using information from a Doppler frequency shift difference, such that the estimation of a fuzzy speed is more reliable.

A wire-breakage position estimation device (58) comprising: a torque acquisition unit (70) which acquires a torque (Tq) of a take-up motor (52); a determination unit (72) which determines whether or not a rear end (12a) of a wire electrode (12) has passed a take-up roller (48); a rotation angle acquisition unit (74) which acquires a rotation angle (ARO) of the take-up motor (52); and a wire-breakage position estimation unit (76) which estimates a wire-breakage position (PBR) in the wire electrode (12) on the basis of the rotation angle (ARO) acquired from when wire-breakage has occurred in the wire electrode (12) to when the rear end (12a) has been determined to have passed the take-up roller (48).

A shape sensor is provided for acquiring a shape profile along an extension direction of an existing weld bead, and a control unit includes a welding information acquisition unit for acquiring welding information during formation of an adjacent weld bead when forming the adjacent weld bead at a position adjacent to the existing weld bead, and a defect candidate extraction unit for determining an angle characteristic portion having a base angle equal to or greater than a threshold in the existing weld bead based on the shape profile, determining a welding characteristic portion of the welding information based on the welding information, and extracting the welding characteristic portion corresponding to the angle characteristic portion as a defect candidate by associating the welding characteristic portion with the angle characteristic portion.

This invention discloses a method for simulating the underwater topography of natural lakes based on shoreline topographic features, belonging to the field of earth science technology. This invention focuses on "simulating the natural process of lake level drop," fully utilizing the lakeside topographic information and morphological parameters extracted from DEM data to achieve reliable estimation of water depth and water storage in natural lakes without actual measured data. The main advantages are as follows: 1) This method can automatically adjust the calculation formula for underwater topography based on lake morphological parameters, thereby achieving autonomous adjustment for water depth prediction of different types of lakes, effectively improving the accuracy and reliability of the simulation results; 2) In the underwater topography simulation process, the reshaping effect of lake sediments on the underwater topography is considered, and a correction formula is introduced into the slope calculation module, making the slope calculation results closer to the actual lakebed morphology, further improving the accuracy of the simulation process.

The application provides a point cloud passable domain and cost map generation method, device and electronic equipment. The method comprises: acquiring structure point cloud data collected by a mobile platform and preset grid layering parameters, constructing a point cloud column set according to the structure point cloud data and the preset grid layering parameters, extracting a lower envelope ground belt according to the lowest point cloud of each point cloud column in the point cloud column set, determining a support surface for the movement of the mobile platform according to the lower envelope ground belt, and determining a clearance according to the support surface and the point cloud column set; determining obstacle point cloud data according to the support surface and the clearance, determining a passable domain and a passing cost of the mobile platform according to the support surface, the clearance, the obstacle point cloud data and a slope step constraint of the mobile platform, and generating a passing map for the movement of the mobile platform according to the passable domain and the passing cost. Thus, the problem that the existing map generation scheme is prone to misjudgment of the passable region in a complex three-dimensional structure point cloud environment and has poor accuracy of the generated path planning map is solved.

The present invention belongs to the technical field of lithium-ion batteries, and provides a battery health state estimation method and system based on a pre-trained large language model. The technical solution is to fuse multi-cycle charging information to perform candidate voltage combinations to efficiently obtain candidate features. By establishing a voltage-charge capacity curve in a constant current charging stage, effective candidate features can be extracted without the need for complete charging and discharging data or the need to establish a complex mathematical model or electrochemical model. At the same time, with the help of a pre-trained large language model and model fine-tuning technology, continuous, reliable and accurate estimation of the battery health state is achieved.

The invention discloses a railway hopper car remote state estimation method, device and equipment, and the method comprises the steps: modeling a railway hopper car sensor network into a discrete time random system comprising a plurality of nodes, and obtaining a state space model corresponding to the railway hopper car sensor network; establishing a packet loss and spoofing attack model of a sensor measurement signal under an amplification forwarding relay strategy; wherein a measurement signal of each sensor is transmitted to the remote estimator through the amplification forwarding relay; determining a remote estimation model according to the state space model and the packet loss and spoofing attack model; and calculating an estimator gain matrix by using the remote estimation model, and outputting a railway hopper car operation state estimation value according to the estimator gain matrix. According to the method, the running state of the railway hopper car is accurately and reliably estimated, and the safety and the operation efficiency of railway freight are improved.

The invention discloses a photovoltaic system dynamic state estimation method and a photovoltaic system dynamic state estimation system based on solar irradiance change, which are characterized in that the randomness of solar irradiance is regarded as unknown input of DSE, and the unknown input is merged into an unscented Kalman filtering algorithm in an unbiased minimum variance form to realize state estimation of a photovoltaic system. According to the method, the dynamic state of the photovoltaic system can be timely and accurately estimated, the problem that the estimation precision is influenced by illumination volatility is solved, and the operation state of the power system is better described.

The invention discloses a vehicle dynamics parameter estimation method based on machine learning, which mainly obtains important parameters of vehicle dynamics involved in simulation test software through analysis, provides a prediction method for unknown parameters in the important parameters, and provides a solution for the condition that some parameters are difficult to obtain in engineering. Specifically, a grouping orthogonal test method is adopted, the test of a simulation software platform is taken as the basis, the importance of vehicle dynamics parameters is judged, a full-connection neural network is adopted to predict important unknown parameters of vehicle dynamics, and a real vehicle test result is compared with a simulation test to verify the prediction accuracy. The method focuses on analyzing and predicting unknown parameters in the vehicle dynamic parameters according to the characteristics that the types of the vehicle dynamic parameters are various and the influence of each parameter on the vehicle dynamic response is different, effectively solves the problem of sensitivity of the vehicle dynamic parameters with the automatic driving function, and particularly reliably estimates the unknown vehicle dynamic sensitive parameters.

The invention relates to the technical field of anti-collision early warning, and discloses a transformer substation crane three-dimensional anti-collision early warning system and method based on a millimeter wave radar, and the system comprises a millimeter wave radar module which is used for obtaining point cloud observation data; the Beidou satellite positioning module is used for acquiring absolute geographic coordinates of the crane; the processing module is used for estimating the motion states of the crane jib and the hoisted object based on the point cloud observation data and the absolute geographic coordinates, quantifying the dynamic collision risk based on the estimated motion states of the crane jib and the hoisted object, and generating an early warning signal; and the early warning module is used for receiving the early warning signal and sending out early warning information. According to the method, the crane jib, the hoisted object and the point cloud observation data are modeled into the random finite set, the probability hypothesis density filter is adopted for processing, and meanwhile, the point cloud observation data are obtained through the millimeter wave radar, so that the motion states of the crane jib and the hoisted object can be stably and reliably estimated, and the view blind area is eliminated.

The present invention discloses a urea injection quality sensor, which belongs to the technical field of urea solution detection, and includes a float, an inner column, a Hall magnetic sensor, a quality sensing module and a signal processing unit. The inner column is provided with a Hall magnetic sensor connected to the signal processing unit; the Hall magnetic sensor can interact with the magnet installed in the float to generate a liquid level sensing signal. When the float moves up and down, the liquid level sensing signal changes to form a pulse sequence. The signal processing unit can obtain continuous urea liquid level according to the pulse sequence and the position of the Hall magnetic sensor; the quality sensing module is connected to the signal processing unit to generate a urea quality sensing signal; the urea injection quality sensor detects urea nozzle failure according to the urea quality sensing signal and the continuous urea liquid level. The sensor can obtain accurate urea liquid level, and while providing multiple functions, the urea crystallization and ammonia storage amount calculation method based on high-precision liquid level information also makes its estimation more reliable.

The utility model discloses an air flotation test device for solid-liquid separation of biogas slurry, which relates to the technical field of anaerobic fermentation product treatment and comprises an air flotation tank, a water collecting tank, a residue collecting tank, a residue scraping mechanism, a reflux pump, a bubble machine and a bubble water releaser, the water collecting tank is communicated with the air flotation tank, and the water collecting tank can receive residue-removed biogas slurry in the air flotation tank; the bubble water releaser is fixedly arranged in the treated biogas slurry in the air flotation tank and can fill bubble water into the treated biogas slurry, a liquid inlet of the reflux pump is communicated with the water collecting tank, a liquid outlet of the reflux pump is communicated with a liquid inlet of the bubble machine, a liquid outlet of the bubble machine is communicated with the bubble water releaser, and the bubble water releaser is communicated with the water collecting tank. The slag collecting tank is fixedly arranged at the top of the inner side wall of the air floatation tank, the slag scraping mechanism is arranged above the air floatation tank, and the slag scraping mechanism can scrape biogas residues on the liquid level of treated biogas slurry in the air floatation tank into the slag collecting tank; according to the utility model, reliable evaluation and pre-estimation can be provided for the actual removal effect of the biogas residue in the biogas slurry doped with the biogas residue by the air flotation equipment.

The present invention discloses a method for constructing a 3D posture estimation model for joint static and dynamic joint relationships. The method comprises the following steps: grouping and grading 15 recognized human joints; designing a cascade estimation and multi-branch feature sharing network to construct a human static joint relationship model; designing a multi-branch attention mechanism and a single-branch attention mechanism to construct a human dynamic joint relationship model; fusing the human static joint relationship model and the human dynamic joint relationship model to obtain a 3D posture estimation model for joint static and dynamic joint relationships, that is, a second-stage model of two-stage 3D posture estimation; designing a posture population equilibrium and an error metric algorithm to expand the diversity of posture data of the Human3.6M training set, and training the second-stage model of the two-stage 3D posture estimation to obtain the model parameters. The present invention can effectively alleviate the depth ambiguity problem faced by single-image 3D posture estimation and improve the robustness of the 3D posture estimation model.

The application discloses a method for correcting and predicting radial section sound pressure of underwater focused ultrasonic sound field, which comprises the following steps: obtaining an axial scanning signal of the underwater focused ultrasonic sound field and extracting a signal envelope; constructing a proportional correction coefficient based on the ratio of the signal envelope to a theoretical axial sound pressure; modeling the change of the proportional correction coefficient with the axial position by using Gaussian process regression to obtain the corrected axial sound pressure; predicting the radial section beam width of the underwater focused ultrasonic sound field at any axial position; decomposing the existing measured radial section into modes, extracting a spatial mode function and a mode weight coefficient, establishing a prediction model of the change of the mode weight coefficient with the axial position by using Gaussian process regression, reconstructing the preliminary radial section sound pressure distribution at any axial position, and correcting the preliminary radial section by using the corrected axial sound pressure and the predicted beam width. The application can realize the prediction of the radial section sound pressure of the underwater focused ultrasonic sound field at any axial position.

The present application belongs to the technical field of bicycle power meter, and specifically discloses a zero point automatic calibration method for a bicycle power meter, which comprises the following steps: recording the current time as the initial time, collecting strain gauge data and acceleration data and storing them in a data buffer; judging whether the bicycle enters a stable state; performing initial calibration of the zero point in the stable state; judging whether to enter a first mode or a second mode according to a user zero point calibration instruction; periodically calculating a refined zero point at a first time interval in the first mode, and performing calibration according to the refined zero point; updating a temporary zero point in the second mode, and performing calibration based on the updated temporary zero point when the time difference is not less than a second time interval. The present application effectively filters out interference factors such as wind vibration, slight collision and misoperation, so that the zero point estimation is more stable and reliable. The present application can automatically judge the zero point estimation opportunity, and significantly reduces the risk of zero point error caused by misoperation.

The present application belongs to the technical field of hydrogeological parameter measurement, and discloses a kind of spatio-temporal quantitative expression method of hydrogeological parameter based on non-contact observation method, spatio-temporal quantitative expression method of hydrogeological parameter based on non-contact observation method includes: using the NMR geophysical prospecting method of different field source form, GPR geophysical prospecting method, TEM geophysical prospecting method collects different types, different structure geophysical data;And based on the different types, different structure geophysical data inversion obtains hydrogeological parameter;Based on D-S evidence theory, the hydrogeological parameter obtained by inversion is merged with the collected hydrogeological data to obtain the best estimate of the hydrogeological parameter.The present application merges the measured different types, different structure geophysical data and the collected hydrogeological data to obtain the best estimate of the hydrogeological parameter, and quantifies the uncertainty factor.

The invention discloses an intelligent fusion navigation filtering method and system for complex environment transition. Navigation data and environment data are collected by a sensor arranged on ocean equipment, preliminary navigation state estimation is obtained after the navigation data passes through a strapdown inertial navigation module, and local error state estimation and filter health degree are obtained after the navigation data and the navigation data are input into a parallel sub-filter; combining the navigation data and the environment data with the health degree of the filter to serve as fusion data, inputting the fusion data into a reinforcement learning agent to obtain a dynamic fusion weight, performing weighted fusion on the plurality of local error state estimations by using the dynamic fusion weight, and superposing the fusion data on the initial navigation state estimation to generate a final navigation result. According to the method, the optimization mapping relation between the environment characteristics and the filtering weight is directly learned through the reinforcement learning agent, integrated self-adaptive adjustment from environment perception to fusion decision is achieved, and the estimation precision and robustness of a navigation system in dynamic complex environments such as a bay-ocean transition section are effectively improved.

A vehicle speed state estimation method based on a vehicle-mounted 4D millimeter-wave radar comprises: 1. real-time reading of target data collected by a 4D millimeter-wave radar; 2. conversion of the target data, target clustering to obtain a target cluster and its attributes, initialization if the data is the first frame, and termination of the current calculation; 3. matching degree calculation of the target cluster of the current frame using the estimation result of the previous frame, and obtaining the target cluster confidence by combining the target cluster height confidence; 4. establishing a speed state and target cluster observation equation, establishing an optimization equation using the vehicle speed state and the target cluster of the current frame and solving it; 5. evaluating the estimated vehicle speed state to determine whether an output condition is met, outputting estimated information of the vehicle speed state if the condition is met, and reducing the target cluster height confidence if the condition is not met and returning to step 4; a good speed estimation effect can be achieved even in a multi-dynamic target scenario.

The invention discloses a method and device for modeling hysteresis characteristics of a battery and a storage medium, and belongs to the field of battery modeling. The invention relates to a method for modeling a hysteresis characteristic of a battery, which comprises the following steps of: modeling the hysteresis characteristic of the battery to obtain an initial model, and discretizing the initial model to obtain a discrete hysteresis characteristic model of the battery; measuring the OCV and the SOC when the charging and discharging direction of the battery only changes once to obtain a first-order rotation curve of the battery; and performing parameter identification on the discrete battery hysteretic characteristic model based on the battery first-order rotation curve to obtain a target battery hysteretic characteristic model. The constructed target battery hysteretic characteristic model can distinguish the reversible component and the irreversible component of the OCV, the OCV reconstruction precision and the SOC estimation precision are improved, the accuracy when the OCV is used for battery sorting and matching is improved, and meanwhile the hardware cost is not increased.

This invention discloses a joint estimation method for power system state and parameters based on Newton-Raphson guided machine learning, relating to the fields of smart grid optimization and power system analysis. The method includes: addressing the problems of low iteration efficiency and machine learning physical mapping distortion in traditional state estimation and parameter identification, embedding the fixed-step Newton-Raphson method as a differentiable module into the machine learning training framework to construct an end-to-end model for parameter and state co-optimization; establishing a PV / PQ node hybrid input-output mapping mechanism that conforms to actual measurement scenarios, using the admittance matrix as an optimizable parameter, and achieving gradient backpropagation under physical constraints through automatic differentiation; designing a node-level state estimation loss function, combined with physical regularization methods for conductance / susceptance, to ensure the feasibility and stability of parameter estimation; and balancing computational efficiency and accuracy by dynamically adjusting the number of Newton iteration steps, ultimately achieving high-precision state prediction and grid parameter reconstruction. Verified on the IEEE-118 node system, this method converges within three Newton iterations, with a state estimation error below 1.2e⁻³, an admittance reconstruction error reduced by 41% compared to the baseline, and strong generalization ability under multiple operating conditions. This invention can be applied to the construction of digital twins for power grids, online security assessment, and fault diagnosis, significantly improving the efficiency and accuracy of power system analysis.

The invention discloses a lithium battery health state prediction method combining BWO optimization and GPR, and belongs to the field of battery health monitoring. According to the method, through combination of optimization of a whale optimization algorithm and a Gaussian process regression model, the accuracy and robustness of prediction are further improved, input noise and complex data can be effectively processed, the generalization ability and prediction precision of the model are remarkably improved through a multi-model integration and secondary learning mode, and the method is suitable for various application scenes and has wide application prospects. The invention particularly relates to a lithium battery management system in a mobile energy storage power supply.