78 results about "Correction algorithm" patented technology

To provide an ultra-precise optical measurement method. [Solution] The system comprises a mounting base 100, a laser system provided on the mounting base 100, a probe system, and a measurement table system. The probe system includes a probe 300 and a Z-direction movement mechanism for moving the probe 300 up and down. The measurement table system includes a stage and an XY movement mechanism for moving the stage along the X and Y directions. The laser system includes a laser transmitter, a set of reflective mirrors, multiple laser interferometers, and a deflection mirror. Inside the probe 300 is a floating rod that can levitate and a stylus sphere attached to the bottom end of the floating rod, and the stylus sphere contacts the workpiece to be measured during measurement. The steps of the roundness error correction algorithm are to place a reference sphere on the stage and measure it, remove the error parameter, solve the shape error of the reference sphere using an aspherical equation, and then correct the measurement data by the shape error in the subsequent measurement process.

This invention belongs to the field of positioning algorithm technology and discloses a method for motion bistation time-frequency difference (SDP) positioning. The algorithm of this invention provides a complete process for motion bistation positioning without requiring manual selection of an initial solution. The SDP algorithm used can handle the problem of motion bistation SDP positioning. When noise is high, SDP gradually deviates from the CRLB bound. The accuracy of the corrected result can be guaranteed by using the Refine algorithm or maximum likelihood estimation based on Gauss-Newton. With low measurement error, the direct correction algorithm slightly deviates from the CRLB bound, mainly due to errors introduced by linearization.

This invention discloses a method and system for dynamically determining the impact of construction projects on hydrological monitoring, relating to the field of hydrological monitoring technology. The specific steps are as follows: constructing an evaluation index system that couples static and dynamic indicators; assigning static weights to static indicators using the analytic hierarchy process (AHP) and dynamic weights to dynamic indicators using the entropy weight method; calculating the total weight based on the static and dynamic weights; constructing and training a machine learning model; inputting the static, dynamic, and total weight data into the trained machine learning model; and outputting the impact level; automatically matching response measures based on the impact level and trend prediction results. This invention proposes a dynamic weight correction algorithm based on project stage and hydrological conditions, applying machine learning algorithms to determine the impact level of construction projects on hydrological monitoring, achieving a closed-loop linkage from level determination to measure matching, and solving the problems of singular and disconnected evaluation in existing technologies.

The application discloses a kind of electric vehicle charging pile order exception clearing settlement method and device, comprising: obtaining the real-time order of vehicle networking platform;Based on the inference engine of preset detection real-time order whether it is abnormal order;Response to real-time order is normal order, then directly upload real-time order to vehicle networking platform;Response to real-time order is abnormal order, then based on correction algorithm or preset prediction model carries out numerical correction or data prediction to real-time order, obtains revised abnormal order and uploads to vehicle networking platform.One aspect, according to the mass historical abnormal data obtained by vehicle networking platform, mining clearing screening rule, combined with the experience rule of power grid expert custom clearing screening rule, the inference engine obtained can accurately detect abnormal order, on the other hand, it can be to electric vehicle charging pile abnormal order numerical correction or data prediction, reduce the economic loss caused by order exception.

This application discloses a 3D imaging method and system based on structured light phase measurement, relating to the field of 3D imaging technology. The method includes: calibrating a structured light measurement system to obtain intrinsic and extrinsic parameters, and determining the effective measurement depth range and the corresponding effective absolute phase interval; controlling a projector to project a preset sinusoidal fringe pattern onto the measured scene, acquiring a deformed fringe image modulated by the surface of the measured object, and obtaining a wrapping phase map; calculating the initial fringe order of each pixel based on the effective measurement depth range using a frequency domain order-based fringe order no-neighborhood solution algorithm; performing no-neighborhood verification and error correction on the initial fringe order based on the effective absolute phase interval using an order self-verification and error correction algorithm to obtain the final fringe order; and calculating the absolute phase map of the entire field of view based on the wrapping phase map and the final fringe order, and converting the point cloud data. This application aims to solve the technical problem of existing spatial phase unfolding techniques relying on the continuity of adjacent pixels.

This invention proposes a method for multi-target recognition, tracking, and vibration extraction of bridge cable-stayed bridge videos based on unmanned aerial vehicles (UAVs). The method includes: Step 1: Constructing a refined tilted and slender target detection model for bridge cable-stayed bridges based on the YOLOv11 model; Step 2: Proposing a multi-target tracking algorithm that integrates the tilted and slender target detection model and the StrongSORT algorithm; Step 3: Improving the displacement extraction method by combining SIFT / ORB feature point matching and sub-pixel refinement techniques; Step 4: Designing a UAV motion correction algorithm based on variational mode decomposition and time-frequency domain joint screening; Step 5: Constructing a joint working mode analysis algorithm that combines natural excitation technology and random subspace recognition algorithm. This method achieves high-precision extraction of cable-stayed bridge vibration signals and identification of cable-stayed bridge modal parameters, providing technical support for health monitoring of long-span cable-stayed bridges.

The application discloses a kind of based on space sampling consistency determination pipe robot multi-source perception full true simulation test system, belong to pipe detection simulation test technical field, it includes mechanical execution system, space state perception gate and physical trigger system, multi-sensor sampling unit, true value reconstruction system.Mechanical execution system provides the motion reference along the axial direction of pipeline, and allow to introduce controlled nonlinear disturbance, space state perception gate and physical trigger system are used for the arbitration of sampling opportunity when FPGA motion control card, step modulation and physical trigger;Multi-sensor sampling unit is used to execute sampling instruction and generate original data with position label;True value reconstruction system is used to construct the standardized pipeline true value containing position, texture and geometric information;The application realizes high-fidelity three-dimensional digital reconstruction to the inner wall of pipeline by introducing IMU posture latch, micro time delay elastic capture, binocular vision forward variable frequency modulation and reverse geometry correction algorithm.

The application discloses a kind of tool butt joint method and system, including end setting with laser range finder, positioning tool interface is provided with measured piece;When reaching the position to be corrected, the laser measurement height value is read by laser range finder;The correlation analysis of the installation offset of laser range finder and the projection point on measured piece is carried out, and the coordinate relationship equation is established;Offset is calculated according to coordinate relationship equation, whether offset meets the requirement is judged, if it meets the requirement, then butt joint is completed, if it does not meet the requirement, then translation adjustment is carried out.The application is tested in laboratory, can control robot end absolute positioning accuracy to be below ±0.25mm, satisfies the requirement that robot completes butt joint operation;Uniform processing standard and gauge standard batch processing measured target are used, and quick replacement can be realized;3-point correction algorithm is used, installation error is weakened, and calculation error caused by installation error is further reduced.

The application provides a tour route planning method and device, belonging to the technical field of path planning, the method comprises the following steps: step 1: constructing a GIS map of a recreation place, marking the entrance, intersection and play point as a point with a unique identifier; step 2: connecting each point to generate a directed path, the directed path includes a one-way path and a two-way path; step 3: calculating the shortest path between any two points by using the Floyd algorithm to generate a shortest route set RS; step 4: receiving the starting point, ending point and traversal point set input by the user, and generating a planned route through the optimal path point bridging and correction algorithm. The tour route planning method and device provided by the application can quickly generate a tour route covering all specified points, with the shortest path, the least repetition and dynamic requirements.

Systems, methods, and computer-readable media provide a graph processing system that incorporates a graph neural network (GNN) based recommender system (RS), as well as a method for training a GNN based RS to address feature leakage that leads to overfitting of the trained GNN based RS. A message correction algorithm is used to modify a user node embedding and a positive item node embedding generated by the graph neural network when generating mini batches of training triples used to train the GNN based RS. The GNN message passing operations are performed on one graph only, in contrast to existing approaches which typically run GNN message passing operations on multiple adjusted input graphs constructed for multiple training triples.

The application discloses a blockchain-based economic dispatching method, comprising the following steps: obtaining a distributed power supply; constructing an Ethereum private blockchain network based on the distributed power supply; obtaining distributed power supply output power based on the Ethereum private blockchain network; performing economic dispatching calculation through a gradient correction algorithm based on the distributed power supply output power; and obtaining an economic dispatching result. Through the above technical solution, the application can make the economic dispatching reach the actual global optimum in real time and safely.

The present application provides a kind of personnel identification and counting method and system based on single vision, comprising: using latitude correction algorithm to carry out equidistant cylindrical development to wide-angle image of single vision, eliminate edge human distortion;Personnel detection model is trained through data set, and the feature response of occluded target is adaptively enhanced;The virtual trajectory of the occluded target is maintained by establishing a "parent-child association" state machine;Trajectory matching algorithm is used to perform time sequence shape matching on the trajectories inside and outside the door, accurately retrieve the lost exit target due to occlusion and perform counting compensation.The present application realizes high-precision counting of complex occlusion behaviors such as side by side and close contact under the premise of using only single vision and without depth sensor, with a counting error rate of less than 2%, significantly reducing the deployment cost of the system.

This invention discloses a method and device for correcting eccentric wellbore in resistivity logging of ultra-deep fractured reservoirs. The method involves continuously moving a conventional dual-lateral logging tool downhole while simultaneously acquiring shallow and deep resistivity information of the reservoir, obtaining continuous shallow and deep resistivity response curves at different reservoir depths. Combining wellbore size and mud resistivity curves with a pre-established dual-lateral shallow and deep resistivity eccentric wellbore correction chart, the eccentric wellbore correction chart is discretized and digitized into an eccentric wellbore database. Based on the shallow and deep resistivity data at different depths, a resistivity eccentric wellbore correction algorithm is used to correct the actually measured dual-lateral shallow and deep resistivity data, obtaining shallow and deep resistivity curves that eliminate the influence of wellbore size, mud resistivity, and instrument eccentricity. This provides logging data interpreters with more realistic dual-lateral resistivity curve data reflecting the characteristics of fractures in ultra-deep reservoirs, ensuring the effective evaluation of fracture characteristics in ultra-deep reservoirs.

A method of correcting an image includes: inputting an input image and a correction parameter to a first neural network model; and obtaining an inference image from the first neural network model, the inference image corresponding to the correction parameter. The first neural network model is a model trained to minimize a difference between the inference image that is output after the input image and the correction parameter are input and a label image corresponding to the correction parameter. The label image is an image obtained by, when the correction parameter is applied to at least one image correction algorithm, correcting the input image by using the at least one image correction algorithm.

The application provides a semi-supervised image segmentation method based on uncertain pseudo label correction. The method comprises the following steps: training an initialized semantic segmentation model using a labeled data set to obtain a teacher model; generating pseudo labels for an unlabeled data set using the teacher model to form an unlabeled data set with pseudo labels, and mixing the unlabeled data set with an original labeled data set to obtain a mixed labeled training set; training a student model using the mixed labeled training set and the labeled data set through an uncertainty pseudo label correction algorithm; inputting an original image to be classified into the trained student model, and generating a mask segmentation result by the student model; and classifying the original image according to the mask segmentation result. The method of the application introduces labeled images and reliable labeling information to effectively eliminate noise in the pseudo labels, and realizes the generation of unlabeled image training samples with different scale effects, thereby suppressing noise and errors in the pseudo labels from different regional scales.

The application provides a regional crop yield estimation method, system, device and storage medium, adopts a random forest model to simulate the yield of crops in a region, calibrates the model error based on a rotation correction algorithm, and predicts the yield of crops in the region through the random forest model after correction. The rotation correction algorithm can effectively calibrate the general error of the existing crop yield estimation model in the high / low yield area. Compared with the existing error regression correction algorithm and machine learning correction algorithm, the rotation correction algorithm further corrects the error regression model of linear fitting to improve the correction effect in the low / high value area. Compared with superimposing a machine learning error correction model, the rotation correction algorithm has stronger generalization ability, avoids overfitting phenomenon caused by using a too complex machine learning model during training, and has better correction effect and wider applicability.

The application discloses a client perception and quantification method for power utilization information collection data transmission, comprising the following steps: collecting multi-dimensional parameters such as link bandwidth occupation, transmission delay and packet loss rate through an edge end electric collection perception calculation and analysis platform, performing feature mapping and enhancement through an electric collection transmission abnormality perception identification network, calling a transmission link perception diagnosis prediction model to predict abnormal trends, dynamically correcting load deviation by using a client load balancing error correction algorithm, constructing a quantification evaluation system by integrating various data through the platform, and finally outputting results such as client perception quantification values, while performing operations such as calibration feature screening, time sequence decomposition, correction amount calculation and parameter integration. Through multi-technology cooperation and full-process closed-loop design, the application realizes comprehensive perception and accurate quantification of the transmission state of the client, and adapts to the complex scene requirements of power utilization information collection data transmission.

The application provides a kind of insulator contamination hyperspectral feature extraction detection method and system, belong to power equipment detection technical field, including: to insulator sample is scanned to multiple wave bands, obtain the original hyperspectral image of preset wave band, and original hyperspectral image is corrected using black and white correction algorithm, based on the spectral response characteristics of insulator sample contamination component, according to the signal-to-noise ratio and spectral difference degree of each wave band of corrected hyperspectral image, filter out characteristic wave band data;Using first derivative transformation to pre-process characteristic wave band data;From the pre-processed characteristic wave band data, extract multi-dimensional feature parameters;Construct the fusion prediction model based on support vector machine and partial least squares regression, input multi-dimensional feature parameters into fusion prediction model, output the contamination grade and equivalent salt density value of insulator sample.The application improves the accuracy of insulator sample contamination hyperspectral detection through data quality optimization, efficient feature screening, integrated model construction and other designs.

This invention discloses a dynamic automatic correction system for the nozzle area of ​​a steam turbine regulating stage, comprising: a detection module for real-time acquisition of operating parameters of the steam turbine regulating stage, including the pressure difference across the regulating valve, main steam flow rate, reheat steam temperature, unit power, and speed; and a control module, which is communicatively connected to the detection module and incorporates a load rate calculation model, a dynamic correction algorithm, and secondary correction logic. This invention ensures that the regulating valve opening remains within the high-efficiency range by dynamically correcting the nozzle area, combined with secondary correction logic. This verifies that throttling losses are reduced under low load conditions, directly reducing energy consumption and improving the unit's operational economy. Simultaneously, through high-frequency data acquisition, dynamic coefficient optimization, and flexible correction cycles, it achieves a "second-level" correction response. The specification clearly states that it can quickly meet the peak-shaving needs of the power grid and solve the problem of nozzle area decoupling from operating conditions under load fluctuations.

This invention discloses a power-decreasing, slow-start control method for electric cookers to prevent temperature overshoot. It relates to the field of intelligent control for electric cookers and aims to solve the problems of temperature overshoot and thermal inertia hysteresis during heating, thereby improving heating accuracy and safety. The core technical solution involves applying a low-amplitude rectangular pulse power excitation during initialization or the start of a new cooking cycle. This collects multi-dimensional time-series signals of heating element temperature, pot bottom temperature, and steam pressure, generating a data fingerprint reflecting the dynamic characteristics of the thermal response. Multi-scale feature extraction, noise suppression, and baseline correction algorithms are used to establish an individual thermal behavior model for the cooker. Combined with real-time operating conditions and prediction algorithms, the power output is dynamically adjusted to achieve smooth, gradual power reduction control without overshoot risk. The system can adaptively optimize the thermal response model, improving temperature control accuracy and effectively reducing energy consumption and temperature fluctuations.

The present application belongs to the field of assembly of a simulator dome structure, and relates to a simulator dome assembly tool and method. The tool comprises a top cover assembly tool and a main body assembly tool. The use of a special dome assembly tool can ensure that the assembled dome and projector support meet the use requirements. On the one hand, the assembly precision of the dome is improved, and the step difference between the dome segments is eliminated. The formation of a perfect circle between the dome segments is conducive to the generation of a projection image correction algorithm, thereby improving the projection effect and quality. On the other hand, the assembly quality of the dome is improved. The projector has a large mass and a long force arm, and generates a large force and torque during the movement of the simulator. The improvement of the assembly quality helps to ensure the connection quality between the dome segments, so that the stress on the dome is uniform, the deformation of the dome during the movement of the simulator is small, and the service life of the dome and the imaging stability of the projection are improved. The method can also be applied to the splicing and forming of other large-size segmented spheres with high assembly quality requirements.

The embodiment of the application provides a driving risk assessment method and device, electronic equipment and storage medium, target vehicle corresponding mobile signaling data is acquired, the mobile signaling data is generated in the interaction process of a terminal device and a base station; the mobile signaling data is corrected based on a preset trajectory correction algorithm, and corresponding vehicle driving data is obtained; driving behavior characteristics are extracted in the vehicle driving data based on a plurality of preset dimensions; driving risk indicators are determined based on the driving behavior characteristics and the vehicle basic information corresponding to the target vehicle, and the driving risk indicators are used for vehicle insurance pricing of the target vehicle. The application introduces mobile signaling data as a unified data source, and uses trajectory correction algorithm and multi-dimensional feature analysis, which effectively improves the accuracy, comprehensiveness and reliability of driving risk assessment, thereby providing accurate data support for fine and differentiated vehicle insurance pricing.

This invention discloses a data acquisition method based on DSM and DOM, simultaneously loading DSM data, DOM data, flight path data, and boundary line data, performing coordinate transformation and processing; acquiring feature outline vector data based on DOM data, and collecting feature elevation information based on the OSGB format model generated from DSM data; and performing projection correction through a correction algorithm, translating features with projection discrepancies perpendicular to the flight path direction to obtain the true outline position of the features. This invention breaks the constraints of traditional acquisition methods, designing a projection correction algorithm based on inherent mathematical principles to achieve projection correction, solving the drawbacks of inconsistencies between acquired feature outlines and reality, and significant inversion phenomena, thus improving the spatial position accuracy of the acquired data. It not only realizes basic scale topographic mapping functions and new basic surveying and mapping geographic entity acquisition and editing functions, but also realizes modeling data acquisition and editing functions.

This invention relates to the field of industrial pump monitoring technology, and discloses a method and system for estimating the flow rate of a centrifugal pump based on curve fitting. The method acquires the head-flow characteristic curve and historical operating data provided by the centrifugal pump at the time of manufacture, and fits the characteristic curve into a mathematical model; it collects the pressure signal at the centrifugal pump outlet and the ambient temperature signal of the centrifugal pump, obtains the current density of the medium being pumped by the centrifugal pump, and converts the pressure signal into a head value that takes density and altitude correction into account; it substitutes the head value into the fitted mathematical model, solves the inverse function using Newton's iteration method, and obtains the estimated flow rate; it adaptively corrects the estimated flow rate according to a preset correction algorithm to obtain the final flow rate value; it determines the operating range of the centrifugal pump based on the estimated flow rate and head value; it calculates the operating efficiency of the centrifugal pump based on the estimated flow rate and head value, and provides energy efficiency optimization suggestions based on the efficiency value.

This invention provides a method and system for detecting defects in industrial products. It acquires defect-free images and generates defect samples by fusing a stable diffusion model, low-rank adaptive technology, and a control network. These defect samples are then merged with real defect samples from the industrial production process to construct a comprehensive sample library, providing high-quality data support for training the detection model. An improved YOLOv8 model is constructed and trained based on the comprehensive sample library. A closed-loop adaptive illumination adjustment system, an improved global adaptive gamma correction algorithm, and a Gaussian filtering fusion scheme are employed to respond to illumination fluctuations in real time. Images of the products to be inspected are acquired and input into the trained improved YOLOv8 model, which outputs defect information. Specifically, the above method significantly improves detection accuracy, stability, and efficiency.

The application provides a point defect feature restoration method based on deep learning, which captures the morphology of the same type of point defects in different areas of the screen through optical shooting and camera imaging, obtains a plurality of defect small pictures through cutting, establishes an image pair dataset of the same type of point defects in the central area and the non-central area according to the defect small pictures, obtains a network model with a restoration function through a deep learning network training, maps the point defects in the non-central area into the morphology and gray scale features of the defects in the central area based on the network model, and then classifies the restored images. The method solves the classification difficulty problem caused by the large difference in defect morphology, makes up for the deficiency of the conventional correction algorithm, improves the reliability of defect morphology restoration, and thus improves the accuracy and efficiency of defect classification.