303 results about "Position shift" patented technology

The invention discloses an industrial image anomaly detection method and device, equipment and a storage medium, and relates to the field of image recognition. Obtaining a defect-free product graph, making a comparison data set based on the defect-free product graph, and performing pre-storage processing; performing feature point shape matching on the comparison data set based on the received to-be-detected image and the extracted feature point data, and determining a comparison image of the to-be-detected image; taking the to-be-detected image as a target object, correcting a product image area in the image, and aligning the product image area with the product image area of the to-be-detected image according to a pixel shift operation; and comparing the aligned product image areas, and identifying abnormal defects in the to-be-detected image. According to the scheme, the comparison data set of the defect-free product image is constructed, the feature point matching and pixel-level alignment technologies are combined, the problem of false detection caused by product position deviation or form change in a traditional method is effectively solved, the adaptability to illumination change is improved through brightness adjustment and difference matrix analysis, and the detection accuracy is improved. The method has the advantages of high detection precision, high environmental adaptability and high processing efficiency.

The invention discloses a primary and secondary mirror combined detection system and method for a beam shrinking system, and belongs to the technical field of optical detection.The method comprises the steps that a first micro-spherical mirror and a second micro-spherical mirror are arranged, reflection light spots are captured through an interferometer, the position offset is calculated, and a first control instruction for adjusting the pose of a secondary mirror is generated; a dual-band light source is integrated in a detection light path, wavefront data and alignment monitoring data are collected, and temperature drift is corrected to obtain effective combined wavefront; an error separation model is constructed based on the primary mirror compensator parameter and the Zernike aberration coefficient, and a primary mirror surface shape error component and a secondary mirror offset error component are decoupled and separated by using a preset aberration coupling coefficient; feeding the error component back to a polishing process and a displacement table for closed-loop iterative correction until the RMS value and the PV value of the effective combined wavefront meet a preset imaging quality index; through precise positioning, error correction and decoupling separation, the precision and efficiency of primary and secondary mirror combination detection are improved, and targeted correction is realized.

The invention discloses a cutter state real-time monitoring and compensating method, system and equipment and a medium, and relates to numerical control precision machining. In the method, a cutting edge optical image, an acoustic emission signal time domain waveform, a vibration acceleration parameter and real-time temperature data of a cutting area of a cutter in the machining process are collected; measuring the maximum width and depth of a wear belt through an image to form a wear characteristic quantized value, and judging a wear over-limit state; judging the damage state based on the continuous ultralimit time of the instantaneous mutation rate of the acoustic emission signal; judging the abnormal vibration grade and state through vibration spectrum analysis; and inputting the vibration spectrum and the temperature data into a prediction model to obtain a position offset prediction quantity. And calculating a size deviation value according to a wear / damage state, calculating a coordinate offset according to vibration abnormity, generating a cutter geometric compensation instruction or a motion trail compensation instruction, and completing real-time compensation operation. According to the scheme, the fine abnormal change of the cutter in the machining process can be captured in time, and compensation is conducted according to the fine abnormal change.

The invention relates to the technical field of surface mounting, and discloses an SMT (Surface Mount Technology)-based patch vision correction method, which comprises the following steps: S1, a calibration stage: constructing a double-coordinate system mapping model based on a PCB (Printed Circuit Board) plane, and establishing a nonlinear distortion compensation matrix according to the patch thickness; s2, a pickup stage: a CCD shooting camera is arranged at the top of the suction nozzle, a top CCD is triggered to shoot when the suction nozzle picks up an element, and pin coplanarity data is extracted; s3, a positioning stage: setting a reference point at the top of the PCB, scanning the PCB reference point through a CCD, and calculating a deviation between an actual position and a theoretical coordinate by using an algorithm processor; and S4, compensation execution: the motion shaft system dynamically adjusts the mounting path according to the deviation vector. The visual correction method based on SMT pasting has the advantages of accurate pasting and the like, and solves the problems of pasting position offset, low efficiency and unstable precision caused by factors such as vibration of an element feeder, mechanical transmission errors and thermal deformation of a PCB (Printed Circuit Board) due to dependence on manual calibration in the existing SMT pasting process.

The invention discloses a motor insertion piece positioning detection method using optical recognition, and particularly relates to the technical field of motor manufacturing and detection. Collecting a high-resolution image containing the insert structure; carrying out image gray level enhancement and reflection interference suppression; extracting insert edge gradient information, and constructing an insert boundary point set; fitting the profile of the insert according to the boundary point set, and correcting the profile through a shape prior model; extracting barycentric coordinates and center positioning features of the inserts, calculating offsets delta X and delta Y and an angular deviation theta, and constructing a position offset vector V; the V is compared with a set tolerance model T, and whether the insertion piece is qualified or not is judged; an error distribution thermodynamic diagram is generated based on the offset data of the multiple punching sheets, and trend evaluation of the mold state and the material stability is achieved; according to the method, high-precision, full-automatic and visual detection of the sheet inserting position can be realized, and the sheet punching quality control level is improved.

The invention relates to the technical field of laser centering, in particular to a centering device special for laser cutting light beams and a using method. And in combination with vision and a special adjusting device, coaxial adjustment of a laser beam and the center of the nozzle can be rapidly completed through a self-adaptive algorithm, the intelligent level of the laser cutting machine is improved, and an important link of laser cutting full-automatic machining is complemented. The centering device comprises a motor module connected with the laser cutting head, an imaging device, a visual acquisition device and a control unit; according to the method, a visual collection device and an imaging device are matched to collect the center position of a nozzle and the center position of red light of a laser, the center position is converted into the movement distance of a motor module in a centering device in real time through a self-adaptive algorithm, and position offset is conducted on a focusing lens in a laser cutting head; by calculating the position deviation value of the nozzle center and the red light center of the laser, centering is ensured to meet the requirement, so that coaxial adjustment of the laser beam and the nozzle center is realized.

The invention provides a camera-based AI visual recognition and prediction control method and related equipment, and the method comprises the steps: obtaining continuous image frames of a moving object, and recognizing the skeleton key point coordinates and appearance feature information of the moving object; inputting the skeleton key point coordinates and the appearance feature information into a preset time sequence neural network model to obtain a motion prediction track; performing space mapping on the centroid coordinates of the moving object according to the motion prediction trajectory, and determining focal length control parameters of the camera; meanwhile, angle mapping is carried out on the position offset of the moving object, and pan-tilt control parameters are determined; and tracking and shooting the moving object according to the focal length control parameter and the holder control parameter. Through the mode, the camera can complete the pre-adjustment of the focusing mechanism and the composition direction before the target motion trend occurs, thereby effectively reducing the delay error in the focal length switching process, and improving the clear imaging rate and composition stability of a high-speed motion main body.

The invention relates to the technical field of mechanical engineering and intelligent control, and particularly discloses a dynamic leveling method and system for a damping profiling icebreaking snow remover. The method comprises the steps that high-strength alloy impact toughness parameters and staggered rolling path parameters are collected, an icebreaking wheel set rigidity matching matrix is generated through optimization, and adjustable rigidity assignment is completed; acquiring road surface fluctuation data within a profiling distance based on a laser ranging device, and fusing multispectral and millimeter wave radar data to generate a three-dimensional dynamic terrain map; inputting the rigidity matching matrix and the dynamic terrain map into an LSTM mechanical simulation engine, calculating five-wheel-set dynamic pressure distribution and outputting real-time wheel set pressure parameters; the real-time pressure parameter is compared with the measured value of the sensor, and an oil cylinder stroke compensation instruction is generated to drive hydraulic leveling control; analyzing the three-dimensional position offset of the snow shovel and the ice breaking wheel, converting the three-dimensional position offset into a side row inclination angle parameter, and generating a multi-shaft torque cooperative control instruction; and generating a material wear characteristic spectrum through federal learning training, and dynamically correcting a path inclination angle and a rigidity compensation parameter. The ice breaking and snow removing device has the beneficial effects of improving ice breaking and snow removing efficiency, enhancing equipment stability and reducing material abrasion.

The invention is applied to the technical field of flatness detection, and discloses a flatness detection mechanism which comprises a workbench, a switching linear module is fixedly arranged on the upper surface of the workbench, a switching seat is mounted on the surface of the switching linear module, and a laser detector is fixedly mounted at the upper end of the switching seat. And a feeding mechanism is arranged on the upper surface of the workbench, and efficient detection of the flatness of the surface of the material through a laser detector is achieved by positioning and conveying the material. According to the flatness detection mechanism, the combination of the feeding linear module and the feeding seat is matched with the guiding of the limiting plate to the plate, so that the bearing plate and the plate placed on the bearing plate can be accurately conveyed to a designated position, the problem of plate position deviation in the traditional feeding process is solved, the plate can accurately enter a detection area of a laser detector, and the detection efficiency is improved. It is guaranteed that the laser detector can comprehensively and accurately scan the surface of the plate according to the preset path, and the high-precision advantage of laser detection is brought into full play.

The invention belongs to the field of additive manufacturing, and relates to a flight printing position compensation method which comprises the following steps: 1) judging whether a to-be-processed point has position offset during flight printing or not, and if so, performing a step 2); if not, exiting; and 2) performing position offset compensation on the galvanometer according to the movement speed of the moving device. The invention provides the flight printing position compensation method capable of effectively avoiding position deviation of the processing point and improving the printing precision at the same time.

The invention provides a moving ship detection method based on spatial-temporal characteristics, which comprises the following steps: firstly, eliminating land and thick cloud regions through dual-threshold segmentation preprocessing, and adaptively extracting weak ship candidate targets in a water area by combining top-hat transform with sequential statistical filtering; combining detection results of each wave band, expanding the area of a ship candidate target, realizing signal enhancement and eliminating static false alarms, combining multiple frames of candidate targets, and carrying out filtering processing by utilizing a multi-direction rotation linear kernel by utilizing position offset characteristics of a moving target in five wave bands of a Gaofen-4 satellite due to imaging time difference; according to the method, real ships in smooth track distribution are reserved, isolated and randomly distributed false alarms or non-coherent track false alarms are eliminated, and stable and high-precision ship detection is effectively guaranteed while the low false alarm rate is kept.

The invention relates to the technical field of dental image shooting, and discloses a label-based intelligent positioning method and device, a positioner and a ray machine, and the method comprises the steps: collecting response signals of a plurality of induction labels of an imaging sensor aiming at a signal transmitted by a label positioner arranged on the ray machine, and receiving signal intensity and carrier phase information; the method comprises the following steps: estimating an estimated distance for any induction tag by fusing a linear relationship between an attenuation model of received signal strength and a carrier phase, and eliminating a single tag error by utilizing multi-point sampling in combination with the estimated distance and position information of all the induction tags and a position offset generated by a positioning imaging sensor relative to a ray machine, so as to realize submillimeter-level accurate positioning. The alignment accuracy and efficiency of the two are improved, so that the position is accurate when the dental X image is shot, and the imaging sensor is ensured to completely fall into the range of the projection area; the device is flexible in installation, low in cost, small in angle dependence, and suitable for low-power-consumption scenes where the size of the sensor in the oral cavity is limited and no independent power supply exists.

The utility model relates to the technical field of optical part machining, and discloses a sapphire special-shaped part concave-convex surface arc light chamfering machine which comprises an operation table, and a lifting seat, a servo motor, an adjusting arm and other components are arranged on the operation table. And switching of the machining angle and position of the sapphire special-shaped part can be achieved through the lifting base, the servo motor and the adjusting arm. The positioning piece is matched with the limiting piece, the special-shaped piece can be accurately positioned and fixed, the clamping wing and the correcting plate of the limiting piece clamp and fix the special-shaped piece under the action of the gear, and position deviation is prevented. The operation table is correspondingly provided with a concave grinding tool, a convex grinding tool and a rotating motor. According to the utility model, the problems that the stress is non-uniform when a handheld workpiece is chamfered, the manual repeated debugging operation is tedious, and the position deviation is easy to occur when a special-shaped workpiece is clamped in a one-way manner are solved, and the machining precision and efficiency are improved.

According to the position deviation detection method and device and the sensor provided by the invention, the image information of the to-be-detected object detected by the sensor is acquired, and the target edge is screened based on the image information; performing light intensity information sampling of pixel points on the target edge along the normal direction of the target edge to obtain light intensity information of sampling points; constructing a forward discrete gradient sequence based on the light intensity information of the sampling points; calculating a discrete centroid weight sequence based on the gradient sequence, and determining a continuous centroid based on the discrete centroid weight sequence; determining a displacement offset of the target edge based on the continuous centroid; obtaining a distance between a receiver of the sensor and the object to be measured, and calculating a compensation value based on the distance and a diffraction compensation model; and compensating the displacement offset based on the compensation value to determine the position offset of the object to be measured, so that the measurement precision of the position offset can be improved, and the measurement stability can be improved.

The invention discloses a bridge expansion joint displacement real-time laser monitoring device, and relates to the technical field of bridge displacement monitoring, the bridge expansion joint displacement real-time laser monitoring device comprises rubber mats and a self-adjusting assembly, the rubber mats are arranged on the two sides of an expansion joint, a housing is connected to the rubber mat on one side of the expansion joint, the self-adjusting assembly is arranged on the inner side of the housing, and the self-adjusting assembly comprises a limiting frame. When the expansion joint displacement detection device is used, the position of the detection head can be automatically adjusted according to the external temperature change so as to adapt to the position deviation of the target caused by thermal expansion and cold contraction of the structural member, the detection error can be avoided, the displacement of the expansion joint can be amplified when displacement detection is carried out on the expansion joint, then the amplified data are measured, and the detection accuracy is improved. Therefore, the detection accuracy is improved, difficulty in detection or detection errors caused by infinitesimal displacement of the expansion joint is avoided, the detection head can be automatically cleaned while the expansion joint moves, detection errors caused by stain adhesion are avoided, and other power sources do not need to be designed.

The utility model discloses a parallelism adjusting structure for a scientific-grade CMOS camera, and the structure comprises a parallelism adjusting assembly which comprises a camera body and an adjustable plate. The stable moving assembly comprises a fixing groove, a connecting groove, a vertical rod, a clamping groove and a sliding block; the fixing grooves are formed in the two sides of the adjustable plate respectively, the connecting grooves are formed in the two sides of the camera body respectively, the vertical rods are clamped between the inner sides of the vertically adjacent fixing grooves and the connecting grooves, the clamping grooves are formed in the inner side faces of the vertical rods, and the sliding blocks are slidably connected to the inner sides of the clamping grooves. By arranging the stable moving assembly, when the supporting parts are rotated one by one, moving force pushes the sliding block through the camera body, so that the sliding block moves in the clamping groove, the camera body is promoted to move in the direction of the vertical rod through the sliding block, and therefore the situation that the camera body is driven by rotation of the supporting parts to deviate is prevented; and the influence of position offset of the camera main body on parallelism adjustment is avoided.

To provide an optical sensor capable of performing highly accurate optical sensing of a scene.SOLUTION: The optical sensor includes a unit D1 including x blocks 11, for example, three (x = 3) blocks a, b, and c, each having a plurality of pixels 12 arranged in a first direction 11A in a plan view. The pixels 12 are arranged at a pixel pitch D1 in the first direction P1. The three blocks a, b, and c are arranged side by side in a second direction D1 orthogonal to the first direction D2, and are arranged to be shifted from each other by P1 / 3 in the first direction D1. For example, the light receiving elements 11A and 10b each including the units 10a corresponding to the number of stages of the TDI are arranged so as to partially overlap each other in the D1 in the first direction, and the optical sensing is performed using the blocks a and b in which the positional deviation of the pixels 12 is minimized. In addition, by increasing the size of each of the light receiving elements 10a and 10b in the second direction D2, inclination at the time of mounting, poor connection, and the like are suppressed.SELECTED DRAWING: Figure 10

The invention provides a position measurement device, a measurement method, a workpiece stage position compensation method, an exposure method and exposure equipment, and the measurement device comprises a first reflector, a second reflector, a first interferometer reference axis, a second interferometer reference axis and a data processing module. The first reflecting mirror and the second reflecting mirror are arranged at the bottom of the objective lens; the first interferometer reference axis is configured to measure a first horizontal displacement of the objective lens; a second interferometer reference axis configured to measure a second horizontal displacement of the objective lens; the data processing module is configured to determine the deflection angle of the objective lens according to the first horizontal displacement and the second horizontal displacement of the objective lens and the height difference between the first interferometer reference axis and the second interferometer reference axis. According to the invention, the deflection angle of the objective lens can be measured, so that errors caused by deflection of the objective lens can be compensated to the position of the workpiece table, and the influence of the position offset of the objective lens on the overlay precision can be reduced.

The present invention relates to the field of fan control algorithms, and in particular to a blade tracking algorithm and system for non-stop inspection of fan blades, comprising step S1, tracking the fan in the fan image in subsequent frames through a long video object segmentation model XMem, performing semantic segmentation to generate a mask image; step S2, calculating and screening the longest intersection segment of the perpendicular line and the contour of adjacent points in the boundary point set and the corresponding perpendicular line equation, determining two perpendicular lines that meet preset conditions and determining the intersection point, which is the center point of the fan; step S3, performing position offset and change analysis on each blade key point to achieve accurate tracking of the blade key point. The present invention can accurately segment and track fan blades, achieve fine positioning of the blades by accurately extracting the edges, key points and morphological information of the blades, improve the accuracy and stability of tracking, avoid shutdown and manual intervention, reduce the workload and maintenance cost of manual inspections, and reduce the misjudgment and risks caused by human factors.

A kind of projector auto-focusing method based on spectral sensor and related equipment, in the method, the wavelength decomposition is carried out to reflected light signal, and light intensity value is obtained;The initial distance value between projector and projection surface is calculated;Acceleration data and angular velocity data are integrated to obtain position offset and attitude angle offset;Compensation distance is determined, and actual projection distance is calculated;Control stepper motor to drive lens assembly to move to the focusing position corresponding to target focal length value;Control stepper motor to drive lens assembly to reciprocate;New reflected light signal is reacquired after each reciprocation;Based on the preset mapping model, new reflected light signal is processed to obtain current measurement distance;When the deviation value between current measurement distance and preset best imaging distance is less than the preset threshold value for the first time, the focusing position corresponding to final measurement distance is determined as final focusing position. The precision of projector auto-focusing is improved, and then the definition of projection picture is improved.

The embodiment of the invention provides a light path adjusting device and a spectrum detector, the light path adjusting device comprises a first adjusting piece, a connecting shaft, a second adjusting piece and an optical lens, the connecting shaft is arranged on the first adjusting piece and is used for connecting the first adjusting piece and a base station of the spectrum detector; the second adjusting piece comprises a first connecting end and a second connecting end which are connected with each other, and the first connecting end penetrates through the first adjusting piece; the optical lens is fixed on one side of the second connecting end along the first direction and is provided with a light emitting end surface; the intersection point of the central axis of the connecting shaft and the central axis of the first connecting end coincides with the center of the light emitting end face, the first adjusting piece and the second adjusting piece can rotate around the connecting shaft relative to the base table, and the second adjusting piece can rotate relative to the first adjusting piece through the first connecting end. According to the optical path adjusting device, the light position deviation caused by mechanical adjustment is effectively avoided, the adjustment of the optical piece lens is rapidly and accurately carried out, the actual optical path is made to accord with the designed optical path, and the optical path deviation is reduced.

A forming apparatus is provided. An application module performs detection of an end portion of a substrate and detection of a pattern region of the substrate, and applies a formable material to an application region of the substrate decided based on the detected pattern region. A planarization module performs detection of the end portion of the substrate and detection of an end portion of a member, and performs the planarization using the substrate and the member. A controller performs alignment between the substrate and the member based on the end portion of the substrate, the end portion of the member, and a positional shift amount between the pattern region and an outer shape of the substrate specified based on the end portion of the substrate detected in the application module.

This application provides a motion mechanism control method, device, electronic device, and storage medium, relating to the field of robotics. The specific solution is as follows: Obtain the current image pose in the target object image; determine the rotation angle difference between the angle in the current image pose and the angle in the reference image pose; based on the position in the current image pose, the position in the reference image pose, the rotation angle difference, the center position of the motion mechanism's rotation axis, and the center fitting deviation of the rotation axis, obtain the position offset of the motion mechanism moving towards the target object. The center fitting deviation is obtained based on the reference image pose, the angles included in the running image pose of the auxiliary object after rotation relative to the reference position in the image acquisition device, and the re-examination image position of the auxiliary object; control the motion mechanism to move the position offset towards the target object's location. Applying the solution provided in this application can improve the accuracy of controlling the movement of the motion mechanism.

The present embodiment provides a multi-charged particle beam drawing apparatus that suppresses a beam position shift on a sample surface. The charged particle beam drawing apparatus of the present embodiment is a multi-charged particle beam drawing apparatus including: a blanking aperture array substrate provided with a plurality of blankers that perform blanking deflection of a plurality of charged particle beams that constitute a plurality of beams; and a first shielding member disposed on a downstream side of the blanking aperture array substrate in a traveling direction of the plurality of beams, having a cylindrical portion through which the plurality of beams pass inside, and being composed of a high magnetic permeability material.

A charged particle beam device acquires an image by scanning a specimen with a probe formed from a charged particle beam and detects a signal emitted from the specimen. The charged particle beam device includes an optical system that forms the probe; a control unit that repeatedly performs correction processing and image acquisition processing for acquiring a frame image; and an image processing unit that generates an image of the specimen based on a plurality of the frame images. In the correction processing, the control unit acquires a reference image, and corrects the shifting of the irradiation position of the probe. The image processing unit acquires position shift information, corrects a position shift between the frame images based on the position shift information, and generates an image of the specimen based on the plurality of corrected frame images.

The utility model discloses a disc part detection device, relates to the disc detection technology field, and comprises a work bench and a workpiece, the top end of the work bench is fixedly connected with a control assembly, the front end of the control assembly is fixedly connected with an insertion disc, the insertion disc is provided with a group of symmetrical insertion grooves, the insertion grooves are matched with the workpiece, and the insertion disc is fixedly connected with the work bench. Two sets of symmetrical correcting assemblies are arranged on the front side of the inserting disc, the correcting assemblies are movably connected with the outer side of the workpiece, and a support is fixedly connected to the top end of the workbench. According to the utility model, through the arranged correction assembly, when the controller drives the detection unit to move downwards, the axis of the detection head can coincide with the axis of the workpiece, so that the position of the workpiece is corrected and fixed at the same time, the position deviation of the workpiece in the detection process is avoided, and the rotation of the workpiece can be controlled at the same time; therefore, when the disc surface detector detects the disc surface, the disc surface can be accurately detected at each position, and the detection accuracy is improved.

The utility model relates to the technical field of welding detection, and discloses an X-ray detection device based on weld defects, which comprises a fixed base and a lifting detection mechanism, the top of the fixed base is fixedly connected with a sealing cover, the inner wall of the sealing cover is fixedly connected with a detection guider, the outer wall of the sealing cover is fixedly connected with a driving motor, and the driving motor is fixedly connected with the lifting detection mechanism. And the outer wall of the driving motor is fixedly connected with a sliding limiting column. According to the X-ray detection device based on the weld defects, paired side wall limiting mechanisms are arranged on the outer wall of the detection table, square limiting grooves are formed in the outer walls of the side wall limiting mechanisms, and limiting sliding blocks can be limited, so that when the device works, position deviation of the detection table can be effectively avoided, and then the detection result of an X-ray flaw detector can be improved; and the hydraulic rod can drive the detection table to ascend and descend, so that the equipment can adjust the detection focal length, and the practicability of the equipment is further improved.

A binocular vision calibration method and device relates to the field of camera calibration. The method comprises: capturing multiple sets of left and right eye images in a first space using a binocular camera, inputting these images into a first processing model, and outputting two sets of light source position information, wherein the two sets of light source position information correspond to multiple left and right eye images, respectively; determining two light source motion paths based on the two sets of light source position information; matching the two light source motion paths to determine a first matching result; and calibrating the binocular camera based on the first matching result. Based on this solution, the left and right camera position offset can be detected during the use of the binocular camera after it leaves the factory, and the binocular camera can be calibrated based on the detection results, effectively suppressing error accumulation in the binocular camera to avoid failure of the depth of field modeling system. Furthermore, the method does not require additional auxiliary equipment and can be deployed on drones, resulting in low implementation costs.