485results about How to "Improve positioning accuracy" patented technology

The invention relates to the technical field of data processing, and discloses a double-end fault positioning method based on signal enhancement, which is used for improving the efficiency of double-end fault positioning based on signal enhancement. The method comprises the following steps: acquiring and preprocessing electrical signals at two ends of a power transmission line to obtain preprocessed synchronous electrical signals; performing adaptive enhancement processing on the preprocessed synchronous electrical signal to obtain an enhanced fault feature signal; performing time-frequency analysis and feature extraction on the enhanced fault feature signal to obtain a fault feature vector and a key parameter; performing machine learning analysis on the fault feature vectors and the key parameters to obtain a fault type identification result and initial fault position estimation; performing multi-algorithm fusion analysis on the preliminary fault position estimation to obtain an accurate fault position coordinate; and performing geographic information mapping and field verification on the accurate fault position coordinates to obtain a fault positioning result and system optimization data.

The invention provides an AI-based automatic identity card image cutting and OCR recognition method and system, and relates to the technical field of image processing, and the method comprises the steps: collecting a multi-angle depth image and a visible light image, reconstructing a three-dimensional model of a certificate through a three-dimensional point cloud registration network, and achieving the perspective correction of an image through the combination of attention posture estimation and projection matrix optimization; a double-flow memory neural network is adopted to carry out information area positioning, a feature extraction backbone network constructs a multi-scale feature pyramid, and a dynamic memory updating network carries out feature matching and dictionary updating based on a time sequence attention module and comparative learning; and performing character recognition on the segmented information sub-images through a multi-branch feature enhancement network, improving the recognition precision in combination with a self-attention enhancement unit and a context reasoning unit, and dynamically optimizing network parameters by using a reinforcement learning controller until a preset recognition credibility threshold value is reached.

The invention provides a catheter tip accurate positioning method and system based on electrocardiogram guidance. The method is applied to a control module of a catheter tip accurate positioning device. The method comprises the following steps: acquiring a standard electrocardiogram corresponding to a to-be-positioned patient, and constructing P-wave baseline features of the patient according to the standard electrocardiogram; when the catheter is inserted into a preset area of a patient, electrocardiogram detection information sent by an electrocardiogram sensing module of the device is obtained and analyzed, and waveform information of P waves is obtained; obtaining first change information and second change information according to the P-wave baseline characteristics and the waveform information so as to obtain first position information corresponding to the catheter; if it is confirmed that the P wave is obviously increased when the catheter is inserted according to the P wave variability information and it is confirmed that the distance between the catheter and the right atrium is smaller than the preset distance according to the first position information, pushing of the catheter is stopped, and accurate positioning of the catheter tip is completed. The accuracy of catheterization is improved through electrocardiogram guidance, and the safety and accuracy of overall operation are improved.

The invention provides a myocardial infarction positioning method based on cross-modal knowledge fusion. The method comprises the following steps: acquiring a target 1D-VCG signal and constructing a 2D-VCG image data set; extracting spatial features, time sequence features and pseudo tags from the 2D-VCG signals and the 1D-VCG signals through a teacher model and a student model; aligning and transforming the spatial features and the time sequence features through a cross-modal generator; and cross-modal knowledge fusion and MI positioning are realized through a cross-modal generator. According to the method, through knowledge enhancement and student enhancement strategies, the accuracy of myocardial infarction positioning is improved, and the overall framework of cross-modal learning is optimized through the adaptive weight method; the method is realized in a knowledge distillation form, spatial features of 2D-VCG are successfully fused into 1D-VCG time sequence analysis, and the positioning accuracy of myocardial infarction is remarkably improved by combining cooperative work of a teacher model, a student model and a cross-modal generator.

The invention provides an oil well casing corrosion monitoring method and device based on machine vision. The method comprises the steps that an image to be subjected to corrosion monitoring is acquired; the to-be-corroded monitoring image is an image of the oil well casing, which is acquired by utilizing preset machine vision equipment; according to a Harris operator positioning and prediction feature algorithm, positioning corrosion feature points in the image to be subjected to corrosion monitoring; based on the corrosion feature points, positioning corrosion geometric features in the image to be subjected to corrosion monitoring by adopting a slope template; the corrosion geometric characteristics are used for analyzing corrosion geometric parameters of oil well casing corrosion; and determining the monitoring result of the oil well casing corrosion according to the corrosion geometric parameters. According to the method, the positioning and prediction accuracy of corrosion characteristics can be improved in a complex environment, the monitoring result of oil well casing corrosion is more accurate and reliable, meanwhile, a large number of sensors do not need to be arranged in the process, and the workload and the cost are reduced.

The invention relates to the technical field of logistics navigation, and discloses a logistics park navigation method, device and equipment and a storage medium, and the method comprises the steps: obtaining logistics order information when it is detected that a vehicle enters a preset range of a logistics park, and generating path information according to the logistics order information; selecting navigation equipment in a navigation transceiving cabin according to the navigation equipment selection strategy to obtain target navigation equipment; importing the path information into the target navigation equipment to obtain started navigation equipment; and distributing the started navigation equipment to the vehicle so as to realize navigation control of the logistics park. According to the invention, accurate navigation of the logistics vehicle can be realized, and the operation efficiency of a logistics park is effectively improved.

A laser cutting machine for metal plate cutting relates to the technical field of laser cutting machines and comprises a horizontally-arranged cutting table, a receding groove and a sliding U-shaped plate are sequentially arranged at the top of the cutting table in the length direction of the cutting table in a penetrating mode, the sliding U-shaped plate is horizontally arranged in a sliding mode, and a three-axis module is arranged at the position, above the receding groove, of the top of the cutting table. The laser cutting gun is installed on the three-axis module, a plurality of supporting rollers are horizontally arranged in the sliding U-shaped plate side by side, the two ends of each supporting roller are correspondingly and rotationally connected with the opposite inner walls of the sliding U-shaped plate, a horizontally-arranged partition plate is fixedly arranged on the inner wall of the avoiding groove, and a transferring assembly is arranged at the bottom of the partition plate. A discharging assembly and a fixing box are arranged on the left side and the right side of the partition plate correspondingly. The problem that cut finished products in kerfs of an existing laser cutting machine are difficult to take out is solved. And when cutting scraps are cleaned, shutdown disassembly operation is needed. And the positioning accuracy of the cutting area is low. And the post-treatment process of the cutting excess materials is tedious.

The invention provides a composite material acoustic emission source positioning system and method, and the method comprises the steps: respectively extracting the arrival time of an acoustic wave signal reaching each acoustic emission sensor, and calculating the arrival time difference between every two acoustic emission sensors; taking the time difference of arrival as a known condition, taking an acoustic emission source coordinate as an optimization variable, and combining with a pre-calibrated sound velocity characteristic of the composite material to establish an optimization model taking a root-mean-square error of a theoretical time difference of arrival and an actual time difference of arrival as a target function; and improving an original whale optimization algorithm by using a nonlinear convergence factor and a random initialization strategy, carrying out iterative solution on the optimization model by using the improved whale optimization algorithm, and when a preset iteration termination condition is met, taking an optimal solution output by the optimization model as a positioning result. The positioning accuracy of the composite material generation source is improved, and the positioning difficulty is reduced.

The invention discloses an infrared target detection method and model based on convolution attention. The model comprises a backbone network, a neck network and a detection layer. Generating feature maps of multiple scales through repeated feature extraction and attention adjustment of the backbone network; performing multi-scale feature fusion on the multi-layer feature map through a neck network module to generate a final feature map suitable for detection; and converting the final feature map into a final target detection result through a detection layer. According to the method, small targets in the image can be more effectively concerned by introducing an attention mechanism, so that the detection precision is improved, detail information and context information of the image can be captured at the same time by utilizing a multi-scale feature fusion technology, the feature expression ability is enhanced, and the content of the image can be more carefully understood.

The invention belongs to the technical field of device detection and positioning, particularly relates to a method and a system for detecting and positioning defects of a stacked package semiconductor device, and aims to solve the problem that the defects of the stacked package semiconductor device are difficult to position. The method comprises the following steps: obtaining structural parameters and material parameters of a failed stacked package semiconductor device; if the laminated packaging semiconductor device is a ceramic packaging device, sample grinding is carried out after sample preparation, then an excitation signal is taken out in a lossless mode and applied, and if the laminated packaging semiconductor device is a plastic packaging device, the excitation signal is directly applied; collecting the temperature of the side surface of the laminated packaging semiconductor device, and determining the position of a defect in an X-axis-Z-axis plane; constructing a temperature-time sequence, and calculating a phase angle after Fourier transform to obtain a defect phase difference-frequency relationship; and establishing a Y-axis depth defect solving model by using a heat conduction algorithm, and determining the position of the defect in combination with a defect phase difference-frequency relationship. According to the invention, the defect detection and positioning accuracy is improved.

The invention discloses a positioning method, device and system for a surgical cart and a storage medium. The method comprises the following steps: acquiring a first view image, corresponding to a registration device, of a first surgical cart acquired by an image acquisition device, and determining a first relative pose of the first surgical cart relative to the registration device based on the first view image; acquiring a second visual field image, corresponding to the registration device, of a second surgical cart acquired by an image acquisition device, and determining a second relative pose of the registration device relative to the second surgical cart based on the second visual field image; and determining a relative positioning pose of the first surgical trolley relative to the second surgical trolley based on the first relative pose and the second relative pose. According to the embodiment of the invention, the problem of data interference of a plurality of sensor devices in a traditional positioning method is solved, and the positioning accuracy of the surgical trolley is improved while the positioning complexity is reduced.

The invention discloses a pig health assessment method based on a rail-mounted inspection robot, and the method comprises the following steps: S1, collecting an RGB image, an infrared image and a depth image of a pig through the rail-mounted inspection robot, and recording the health condition of the pig; s2, extracting physiological and behavior characteristics of the pig through a deep learning model according to the RGB image, the infrared image and the depth image; s3, obtaining health indexes of the pigs according to the physiological and behavior characteristics of the pigs; s4, standardizing the health indexes of the pigs through z-score to obtain scores of the health indexes of the pigs; and S5, constructing a random forest model according to the health condition of the pig, taking the score of the health index of the pig as an independent variable, training through the random forest model to obtain the weight of the health index, establishing a pig health scoring model according to the weight of the health index, and calculating the health score of the pig, thereby realizing automatic pig health assessment.

The invention relates to the technical field of instrument calibration, in particular to an automatic leveling and plumbing system which comprises a laser transmitting module, a laser receiving module, a transmitting verification module, an anomaly analysis module, a plumbing correction module and a result output module, the laser transmitting module transmits laser, the laser receiving module obtains light spot information and transmits the light spot information to the transmitting verification module, and the plumbing correction module outputs the result. The laser emission quantity and parameters are controlled, the abnormity analysis module is used for determining the clear and stable state of laser emission and judging whether the laser emission accords with the plummet detection condition, the plummet correction module is used for judging whether laser verification is carried out or not according to the analysis result and sending a control instruction to the emission verification module, and the result output module is used for outputting the plummet detection result. According to the invention, the automation level and the measurement precision of the plummet detection are improved, the personal error is reduced, and the stability and the reliability of the system are enhanced.

The invention relates to the technical field of image processing, in particular to a vacuum printed PCB precise feeding method and system guided by machine vision, and the method comprises the steps: obtaining the feature points of a to-be-positioned PCB image and the feature points of a real PCB image; calculating the credibility of each feature point of the real PCB image, screening out a target feature point according to the credibility, and matching the target feature point with the feature points of the to-be-positioned PCB image to complete positioning and feeding of the real PCB image; wherein the calculation of the credibility of the feature points comprises the step of clustering the feature points of the real PCB image to obtain a plurality of clusters. According to the invention, by screening the feature points of the real PCB image, it is ensured that the feature points are more accurate and stable, mismatching is reduced, and the accuracy of image matching is improved; and some redundant or unimportant feature points can be removed, so that the workload of subsequent matching and calculation is reduced.

The invention relates to an offshore wind power fault analysis and positioning method based on residual correction, and the method comprises the following steps: building a digital twinborn model of an offshore wind power grid based on the offshore wind power grid; fusing the measurement value of the measurement system of the offshore wind power grid and the digital twinborn model, and establishing a state estimation model; predicted power of each node of an offshore wind power grid is predicted through a state estimation model, a fault section is determined by collecting actual power of each node of a measurement system, calculating weighted residual errors of the predicted power and the actual power, virtual nodes are arranged in the fault section, and weighted residual errors of adjacent virtual node sections are compared. And an adjacent virtual node section with the maximum weighted residual error is obtained, so that the accurate position of the fault is determined. Compared with the prior art, the method has the advantages of high positioning precision, wide applicability and the like.

The invention discloses a partial discharge intelligent wireless sensor based on edge calculation and a detection method, and the sensor employs a piezoelectric crystal to sense an ultrasonic signal excited by partial discharge, and obtains the ultrasonic signal through at least four partial discharge wireless sensors attached to a housing of a detected device. Partial discharge diagnosis is carried out according to the ultrasonic signal peak value and the discharge frequency, and when the ultrasonic signal received by any sensor meets the partial discharge diagnosis criterion, it is considered that the detected equipment has a partial discharge fault; and on the basis of all sensor coordinates and the arrival time of the main peak of the ultrasonic signal, simultaneous equations are established, and partial discharge positioning is realized by solving the equations. The device can be directly attached to a shell of electrical equipment such as a transformer for use, wiring and subsequent battery replacement maintenance are not needed, automatic networking can be achieved, on-line monitoring and positioning of internal partial discharge of the electrical equipment are achieved, and the safe operation level of the electrical equipment is improved.

The invention relates to a wall-climbing robot positioning system and method based on a space structure circular descriptor. A depth image sensor (RGB-D) camera outputs a depth image; collecting three-dimensional point cloud data of three-dimensional space wall surface points; and conformally mapping the contour of the wall-climbing robot to a minimum bounding ball (MBS). A space structure circular descriptor (SSCD) algorithm module maps the three-dimensional point cloud data to a two-dimensional positioning navigation plane, and an SSCD image is formed on the two-dimensional positioning navigation plane; and point cloud features of the SSCD images from the k-1 moment to the k moment are matched, and positioning of the wall-climbing robot on the three-dimensional space wall surface at the current moment is completed. An airborne inertial measurement unit (IMU) measurement module acquires the angular velocity and acceleration of the wall-climbing robot; the attitude information of the wall-climbing robot at the current moment is obtained by carrying out pre-integration on the collected angular velocity and acceleration. Therefore, three-dimensional data are mapped to a two-dimensional plane through a space structure circular descriptor (SSCD) algorithm, and the wall-climbing robot is accurately positioned and navigated.

The present invention is applicable to the field of image processing technology, and in particular to an image processing system based on computer vision, the system comprising: a cutting device, a sorting device, a pushing device and a pop-up device; the cutting device is used to obtain the image to be processed, and use a preset edge detection algorithm to locate the edge pixels, mark the center position of the image to be processed as the origin, and construct a cutting coordinate system; the image to be processed is cut into four first-generation quadrants, and the number of edge pixels in each first-generation quadrant is calculated. If the number is greater than a preset threshold, the first-generation quadrants are continued to be cut; the sorting device is used according to the pre-constructed definition rules. By constructing a data stack and a cutoff block, the present invention can dynamically adjust the number of blocks in the cloud according to the operation of the cloud, and by cooperating with two groups of processing nodes, it can fully optimize resource utilization and ensure image processing efficiency.

The invention provides a robot 3D visual positioning error correction method and system based on deep learning, and relates to the technical field of robot visual positioning, and the method comprises the steps: obtaining the initial position information of a robot in a three-dimensional space, extracting image features through a deep learning model, calculating a displacement error, comparing the displacement error with a distance threshold value, and executing the correction step. Through multi-sensor data fusion and dynamic target position adjustment, the positioning precision and reliability of the robot in a complex environment are optimized. The invention aims to improve the positioning accuracy of the robot in a three-dimensional space through deep learning and a multi-sensor fusion technology and reduce the positioning deviation caused by environment change and sensor errors, so that the more intelligent and autonomous robot navigation capability is realized.

The invention relates to a cable positioning method and system based on partial discharge signal arrival time identification, and the method comprises the steps: employing a high-frequency current sensor with a time service function, and sensing a high-frequency partial discharge signal of the partial discharge of a cable grounding lower lead in a single-end or double-end connection mode; the high-frequency partial discharge signals are conditioned and collected; identifying the arrival time of the partial discharge signal from the collected high-frequency partial discharge signal based on a signal energy criterion; and positioning a cable defect position according to the cable length and the signal arrival time difference. Compared with the prior art, power failure of the cable is not needed, fault point positioning is achieved under the condition that normal operation of the cable is not affected, automatic implementation can be achieved, manual intervention errors are reduced, and the accuracy and efficiency of power cable fault point positioning are greatly improved.

The utility model discloses a circuit board soft board splicing assembly, and relates to the circuit board splicing technology field, the circuit board soft board splicing assembly comprises a positioning seat, and also comprises a positioning mechanism, the positioning mechanism comprises a movable seat arranged on the left side of the positioning seat, the top of the movable seat is fixedly provided with an upper pressing plate, and the top of the upper pressing plate is fixedly provided with a lower pressing plate; an upper pressing wheel used for pressing a soft plate downwards is movably connected into a wheel groove formed in the bottom of the upper pressing plate, a handle is fixed to the upper pressing plate, a connecting assembly is arranged between the positioning base and the movable base, a guide groove is formed in the left side of the positioning base, and a guide rail transversely moving along the inner wall of the guide groove is fixed to the right side of the movable base. According to the utility model, through the arrangement of the upper pressing plate and the upper pressing wheel, the soft board is inserted between the upper pressing plate and the movable seat and is pressed by the upper pressing wheel, and then the movable seat is moved to the position of the positioning seat, so that the positioning between the soft board and the hard board can be realized, the accuracy of each splicing position is ensured, errors are prevented, and the consistency of splicing quality is ensured.

The invention provides a YOLO-based ox horn capacitor bushing polarity detection method and system, and the method comprises the following steps: a data set construction step: carrying out the preprocessing of an ox horn capacitor detection video, and obtaining a data set; a model optimization step: optimizing the YOLO detection model, and constructing a target detection model; a training iteration step: performing training iteration on the target detection model through the data set; and a detection and judgment step: detecting the ox horn capacitor detection video through the target detection model after training iteration, and judging whether the printing of the ox horn capacitor is wrong or not. By adopting the improved YOLOv8 structure, the problem of low horn capacitance detection recognition rate is solved, so that the effect of accurate horn capacitance detection is achieved.

The invention discloses a robot moving method and a robot moving device, and belongs to the technical field of robots. The robot moving method comprises the steps of determining first position information of a target object based on a target signal intensity vector set received by the target object and a plurality of reference signal intensity vector sets; based on the first position information and first information of a plurality of candidate robots in the target area, controlling a target robot in the plurality of candidate robots to move into the first area where the target object is located; and in the first area, the target robot is controlled to move to a core area where the target object is located based on the UWB signal. According to the robot moving method, the problems that Bluetooth is large in positioning error and prone to being interfered by obstacles in a complex environment are solved, meanwhile, the problem that UWB signals cannot be covered in multiple intervals with wall signal shielding is solved, a UWB base station does not need to be fixedly arranged at high cost, and the positioning precision and accuracy are high.

The invention provides a vertical furnace front conveying device, a wafer box conveying method of a vertical furnace and a vertical furnace system.The vertical furnace front conveying device comprises a front shell, a cache fixing device, a translation mechanical arm, a lifting module and a translation conveying module, a butt joint opening is formed in the front shell and correspondingly connected with an inlet of the vertical furnace, and the translation mechanical arm is arranged in the front shell; the cache fixing device and the translation transmission module are both arranged in the front shell, the lifting module is connected with the translation manipulator and the translation transmission module, and the translation manipulator and the translation transmission module move in the first direction and the second direction respectively. According to the front conveying device for the vertical furnace, automatic production is achieved, then the production efficiency is effectively improved, transfer motion is divided into two independent motions in the first direction and the second direction, the overall positioning precision and motion accuracy are effectively improved, the adaptability of the device is also effectively improved, and the production cost is reduced. And therefore, the reliability and the practicability of the device are improved, and the final quality of products is guaranteed.

The invention discloses a vehicle positioning method, device and equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining the relative position parameters of a vehicle and a plurality of target ground markers, and calculating the distance between the target ground markers according to the cosine theorem; according to the distance between the target ground markers and the corresponding relation table of the distance codes and the identification numbers, obtaining the identification numbers of the target ground markers; on the basis of the marker coordinate corresponding table, obtaining absolute coordinate values of the target ground markers; and determining the absolute coordinate of the vehicle according to the absolute coordinate value and the relative position parameter of each target ground marker. Compared with the prior art, the absolute coordinates of the vehicle are determined based on the corresponding relation table of the distance codes and the identification numbers and the marker coordinate corresponding table, and the positioning efficiency and accuracy of the automatic driving vehicle in the port container yard are effectively improved.

The invention discloses a single-phase earth fault positioning method and system based on zero-sequence current integration, and the method comprises the steps: recording fault transient zero-sequence current data within 0.04 s after a fault occurs at each detection point on a line after the single-phase earth occurs on the line; the method comprises the following steps: firstly, filtering fault transient zero-sequence current data acquired by each detection point within a set period to obtain transient data, then calculating an amplitude within a set time period after a fault, and generating a transient zero-sequence current amplitude sequence of each detection point; the main station calculates a transient zero-sequence current amplitude integral coefficient and an amplitude comprehensive difference coefficient of the detection points at the two ends of each section on the fault line by using the uploaded transient zero-sequence current amplitude sequence data; and the master station carries out positioning according to the calculated transient zero-sequence current amplitude integral coefficient and amplitude comprehensive difference coefficient of each section. The system comprises a data acquisition module, a data processing module, a calculation module and a positioning module. The method can judge the fault section according to the amplitude integral coefficient.

The invention provides an urban gas pipeline leakage detection method and system, and relates to the technical field of pipeline leakage localization, and the method comprises the steps: building a gas pipeline mathematical model between adjacent pressure regulating stations; discretizing the gas pipeline inlet and the gas pipeline outlet to obtain a discretized data model for describing the gas pipeline inlet and the gas pipeline outlet; actual signals are collected; de-noising correction is carried out on the actual signal; inputting the corrected actual flow into the discretization data model according to the position of the discrete node to which the actual flow belongs, and outputting model prediction pressure; calculating a pressure difference value between the model prediction pressure of the gas pipeline outlet and the corrected actual pressure; calculating an average pressure difference value by combining a dynamic time window determined based on the Bayesian theorem under the condition that the pressure difference value is greater than a preset difference value, entering the next step under the condition that the average pressure difference value is greater than the preset difference value, and otherwise, returning to collect the actual signal again; and determining the leakage position of the gas pipeline. And the gas pipeline monitoring efficiency and the leakage position positioning accuracy are improved.

The invention relates to a material bundle surface defect identification system based on improved YOLOv10. The image acquisition system is used for capturing and processing a high-resolution material beam image on the surface of the material beam; the data analysis system is used for carrying out identification and defect classification processing on the preprocessed high-resolution material beam image; the dynamic model improvement system adopts an improved YOLOv10 network model; and the data visualization presentation system is used for displaying statistical information of the high-resolution material beam image in real time. The invention also discloses a material bundle surface defect identification method based on the improved YOLOv10. According to the method, the fusion capability of multi-scale features is enhanced, so that the YOLOv10 can still effectively perform defect detection and classification in a complex noise interference environment, and particularly, the detection of tiny defects on the surface of a material bundle is more accurate; the method has stronger adaptability and robustness, and can improve the detection precision and reduce the omission ratio.

The invention provides a weeding point positioning method, device and equipment. The method comprises the following steps: acquiring an original image formed by collecting weeds to be removed; preprocessing the original image to obtain a to-be-processed image; the to-be-processed image is identified, the image area where the to-be-removed weeds are located and the type of the to-be-removed weeds are determined, and the type of the to-be-removed weeds is related to the structure and shape of the weeds; processing the image area, and determining a skeleton of the weeds to be removed; and determining a weeding point position of the to-be-removed weed based on the type of the to-be-removed weed and the skeleton of the to-be-removed weed, wherein the weeding point position is a stem base center of the to-be-removed weed in the original image. The weeding point positioning method is used for positioning the weeding points in the area shown in the image more accurately and more efficiently according to the shot image.

The utility model discloses an adjustable glass straight line double-edge straightening machine, which relates to the technical field of glass processing and comprises a base, a fixed frame is fixedly mounted on the left side of the upper end of the base, a movable frame is arranged on the right side of the upper end of the base, and displacement sliding rails are arranged on the front side and the rear side of the upper end of the base. Protective boxes are fixedly mounted at the front end and the rear end of the base correspondingly, and polishing structures are mounted on the inner sides of the upper ends of the fixed frame and the movable frame correspondingly. According to the adjustable glass linear double-edge straightening machine, the supporting plate is arranged between the movable frame and the fixed frame, supporting wheels are utilized to make contact with the bottom of glass, supporting is achieved, the supporting effect on the glass is guaranteed, the positioning accuracy of the glass is improved, damage to the glass during machining is avoided, and when the movable frame moves, the glass is not prone to being damaged. The supporting plate on the right side can be driven to move, the distance between the multiple supporting plates is kept equal through connection of the connecting rod assemblies, and the supporting device can be conveniently matched with supporting of glass of different sizes.