576 results about "Vision inspection" patented technology

The present invention relates to a system (101) and method (401) for performing vision inspection on at least one photovoltaic cell or module; said system (101) is capable to detect defects (102) in said photovoltaic cell or module (103) by detecting shadow representation on image captured by at least one detector (119) when said defect (102) obstructs transflected light in said photovoltaic cell or module (103); said light emitted from at least one first light source (115); wherein said system (101) further comprises of at least one second light source (118) to perform photoluminescence inspection on said photovoltaic cell or module (103).

The invention relates to the field of industrial visual inspection, and provides an automatic test performance benchmark construction method which comprises the following steps: dynamically generating ROI (Region of Interest) parameters; performing pixel cutting on the target area of the production line according to the dynamically generated ROI parameters to generate a high-speed image data stream, and aligning the image acquisition moment with the mechanical motion phase of the production line; selecting a matched visual detection model based on target features in the high-speed image data stream, and outputting a defect detection result by the matched visual detection model; according to defect distribution parameters of a preset test scene, the simulation defect features are embedded into the high-speed image data stream, and a mixed test data stream is generated; performing multi-device time sequence alignment on the mixed test data stream and the defect detection result, and packaging into a standardized data set containing a unified time reference; and analyzing the standardized data set, comparing the simulated defect truth value label with a defect detection result, calculating a multi-dimensional performance index of the visual inspection system, and generating a test report containing parameter optimization suggestions.

The invention provides a detection, grinding and sand blasting integrated platform for a small complex workpiece. The detection, grinding and sand blasting integrated platform comprises a platform body, a grabbing robot is installed on the table body, and a feeding conveying line, a first visual detection mechanism, a grinding station and a sand blasting station are arranged on the periphery of the grabbing robot. A second visual inspection mechanism is arranged on one side of the polishing station; the grinding station comprises a movable seat used for carrying workpieces, and the movable seat is connected with a translation mechanism. A cleaning assembly is slidably mounted in the polishing station, the cleaning assembly is connected with a locking mechanism, a supporting frame is fixed to the movable seat, and a connecting mechanism is mounted on the supporting frame and used for being connected with the locking mechanism; an unlocking part is arranged on the connecting mechanism; the cleaning assembly is connected with a reset part. The equipment integrates the functions of detection, grinding and sand blasting, one-stop machining of workpieces is achieved, and manual circulation among multiple pieces of equipment is not needed. And meanwhile, based on a visual detection result, self-adaptive polishing path planning is carried out, and a polishing track can be dynamically generated according to the defect type and position.

The invention relates to dispensing detection integrated equipment, and belongs to the technical field of IGBT packaging, and the dispensing detection integrated equipment comprises a feeding and discharging conveying line which extends in the X-axis direction; the transplanting conveying line is arranged on one side of the feeding and discharging conveying line and extends in the Y-axis direction; the NG conveying line is arranged on one side of the transplanting conveying line and extends in the Y-axis direction; the dispensing mechanism is erected above the transplanting conveying line and is far away from the loading and unloading conveying line; the AOI visual inspection mechanism is erected above the transplanting conveying line and located between the feeding and discharging conveying line and the dispensing mechanism; the carrying mechanism is erected above the area where the feeding and discharging conveying line, the transplanting conveying line and the NG conveying line are located. By reasonably arranging the positions of the conveying line and the mechanism, the movable line of product production is optimized, the physical path of the production process is shortened, a complete quality closed loop is constructed, and the automation efficiency of the dispensing procedure and the product yield are effectively improved.

The invention provides a generation and discrimination collaborative optimization industrial visual detection system and method, and relates to the field of computer vision and artificial intelligence. The decoder comprises a unified encoder, a reconstruction decoder, a condition generation decoder and a discrimination head; the unified encoder is used for extracting general visual features based on the to-be-detected image; the reconstruction decoder is used for obtaining a reconstruction image without defects; the condition generation decoder is used for generating a defect image containing a specified defect; the discrimination head is used for identifying the reconstructed image and outputting confidence based on an identification result; training is carried out based on a defect image generated by a condition generation decoder, and a defect category and a category probability are generated; and the collaborative optimization module is used for constructing a collaborative loss function, a task loss function and a total loss function, reversely updating a discrimination head parameter based on a gradient generated by the total loss function, and generating a decoder parameter and a unified encoder parameter. The joint evolution of the generative model and the discrimination model is realized, and the performance of industrial visual inspection can be effectively improved.

The utility model discloses an automatic visual inspection device for a finished product gum tape, which relates to the technical field of inspection devices, and comprises a support leg, the top of the support leg is fixedly connected with a plurality of support plates. During detection, sliding blocks on a plurality of illumination plates are aligned to sliding grooves in a trapezoidal supporting frame and slide into the sliding grooves, then limiting pieces are rotated to enable fixing shafts to integrally fix the sliding blocks and the trapezoidal supporting frame, a good illumination effect is achieved during detection, and then a mounting column is rotated to integrally combine a fixing plate and a fixing column; then a plurality of fixed shafts II are rotated to loosen the detector from an adjusting block, and then the overall angle of the detector can be adjusted, so that the detection camera can have a better visual detection effect, and the purposes of quickly adjusting the light during observation and the overall observation angle of the detection camera, preventing a poor detection effect and improving the detection efficiency are achieved. And subsequent personnel need to check again with naked eyes.

The invention relates to the technical field of vertical shaft guide detection, in particular to an industrial intelligent visual detection and diagnosis system for a vertical shaft guide. The coal dust shadow quantization unit extracts a coal dust region by adopting a double-peak self-adaptive threshold segmentation combined region growing algorithm, and introduces a space weight factor to calculate an average gray value and a coverage area proportion, and the dynamic coupling calibration unit depends on a three-dimensional lookup table calibrated by multiple working conditions and nonlinear interpolation; the optimal deviation compensation coefficient of the jitter and coal dust combination is matched, a dynamic gray segmentation threshold value is generated, and a defect diagnosis decision unit accurately calculates the abrasion depth through partition self-adaptive segmentation, multi-scale morphological filtering and denoising and gradient amplitude and curvature double-constrained sub-pixel edge detection. A hierarchical control instruction is output according to the real-time depth and the historical trend, coupling interference is eliminated, the cage guide abrasion detection accuracy is improved, and a reliable basis is provided for safe operation and maintenance.

The auxiliary device comprises a bottom plate, a detection device is fixedly installed at the upper end of the bottom plate, a bearing assembly is installed on the side, located on the detection device, of the bottom plate, and a supporting block is installed on the surface of the end, away from the detection device, of the bottom plate in a sliding mode. A sliding platform of an electric sliding table moves to drive a supporting block installed at the upper end of the sliding platform to move, then the distance between a seat at the upper end of the supporting block and a bracket in a bearing assembly is adjusted, and the practicability of the device is improved; the sliding groove and the sliding block limit lifting of the lifting pipe, a mounting plate at the top of the lifting pipe adjusts the height of the seat along with lifting of the lifting pipe, meanwhile, a steel ball sleeve embedded in the top of the supporting block provides auxiliary supporting for lifting of the lifting pipe, the lifting pipe is prevented from shaking during lifting, and then the stability of the seat is improved.

The invention concerns a device designed for eyesight examination, which can be applied in medicine, in particular in ophthalmology The device can be used for perimetry / visual field testing and also other parameters where tests are conducted by means of light stimuli displayed in front of the patient's eyes.

The invention discloses a full-automatic segmentation disc type X-ray industrial visual inspection machine which comprises a feeding assembly, a detection assembly, a pressing assembly and an indexing suction nozzle assembly which are integrated through a mounting platform to form a closed detection system, the feeding assembly comprises a machine box, the inner wall of the machine box is fixedly connected with the mounting platform, and the inner wall of the machine box is fixedly connected with the detection assembly; the disc face of the installation platform is parallel to the bottom face of the machine box, a material supplementing device, a vibration disc and an ion fan are sequentially arranged on the installation platform, and a discharging port of the vibration disc is connected with a product conveying groove fixed to the installation platform. A series of complex operations such as loading, precise positioning, efficient scanning, deep analysis and rapid unloading of the disc can be automatically completed, the detection efficiency and accuracy are remarkably improved, and the detection efficiency and accuracy are greatly improved through precise detection and efficient treatment and through the modular integrated design of the feeding assembly, the detection assembly, the pressing assembly and the indexing suction nozzle assembly. Industrial visual inspection seamless connection of electric detection and X-ray detection is realized, and the production period is greatly shortened.

The invention relates to the technical field of computer vision detection, and discloses a PCB defect detection method based on improved YOLOv8. According to the invention, by introducing the C2f module fused with the coordinate attention mechanism, the adaptive weighted bidirectional feature pyramid structure and the lightweight decoupling detection head, the feature extraction capability and the spatial positioning precision of the model for PCB micro defects are improved, and the problem of small target missing detection is solved; meanwhile, in combination with defect area specific enhancement training and a dynamic receptive field optimization strategy, the anti-interference capability of the model to a complex background is enhanced, and the false detection rate is greatly reduced; besides, by adopting a structure re-parameterization technology, the model reasoning speed is improved while the detection precision is ensured, so that the method can be efficiently deployed on industrial detection equipment with limited resources, the balance of high precision and high efficiency is realized, and the comprehensive performance of PCB defect detection is comprehensively improved.

According to the blowing detection equipment and the detection method, the structure is simple, the accurate positions of the materials can be observed through a displayer, the overlapped and side-by-side materials can be distinguished through image processing, and the mistaken blowing or missing blowing process of the blowing nozzle can be directly observed through cached images. The device comprises a feeding module, a rotating disc module, a visual detection module and a material receiving module, the material receiving module comprises a material receiving support, an OK blowing module and an NG blowing module, and the visual detection module is arranged between the feeding module and the material receiving module and matched with a product at the loading disc end of the rotating disc module; the measuring method comprises the following steps: A, feeding and straightening a product; B, acquiring images of the product at different detection positions; C, comparing and controlling the state switching of the material receiving assembly according to image acquisition results; and D, synchronously detecting false blowing and missing blowing through the monitoring camera. The method is applied to the technical field of product sorting.

The invention discloses a workpiece visual inspection equipment control system, and relates to the technical field of visual inspection, the workpiece visual inspection equipment control system comprises a main body mechanism, the main body mechanism comprises a workbench, and the top of the workbench is provided with a turnover mechanism. A workpiece is fixed twice through a first clamping plate and a second clamping plate, the number of times of fixing the workpiece again is reduced, the comprehensiveness of workpiece detection is further improved, repeated positioning errors are avoided, meanwhile, the clamping direction can be automatically switched through rotation of a gear, the detection efficiency and flexibility are remarkably improved, and through the arrangement of a lifting unit, the detection precision is improved. Temporary support is provided in the workpiece reversing process, the workpiece is lifted before fixing to ensure full attachment to the rotating block, a contact gap is eliminated to improve the rotating stability, the workpiece retracts in time after being clamped to avoid interference to multi-axis movement, and the workpiece is lifted again before reversing to prevent the workpiece from being separated from the rotating block due to gravity.

The invention provides a visual inspection system which is used for detecting the appearance of a workpiece, and the outer surface of the workpiece comprises a first end face and a side surface which are connected. The visual detection system comprises a positioning unit and a first detection unit; the positioning unit is used for positioning a workpiece; the first detection unit comprises a reflector device and a visual detection device. The reflecting mirror device is used for being arranged in the circumferential direction of the workpiece so as to image a part of the side surface of the workpiece. The light incidence face of the visual detection device is used for being arranged opposite to the first end face of the workpiece so as to shoot an image of the first end face for appearance detection and shoot an imaging image in the reflector device for appearance detection. The visual detection device is adopted to perform appearance detection on the first end face and the side surface of the workpiece, so that the detection precision and the detection efficiency of the appearance of the workpiece are greatly improved.

The invention relates to the technical field of flywheel detection, and discloses an AI visual detection device for flywheel defect detection, comprising a station for bearing a flywheel, the station being capable of reciprocating along a first preset path, a first driving assembly for driving the station to reciprocate along the first preset path, and a detection mechanism for detecting different defect information of the flywheel, according to the flywheel defect detection device, the station reciprocates on the first preset path and passes through the multiple detection mechanisms, detection of different kinds of defect information of the flywheel is carried out at the different detection mechanisms, detection of multiple types of defects and specific parameters of the flywheel can be achieved, multi-mechanism cooperative calibration is achieved, the detection precision is improved, and in addition, the detection efficiency is improved. The whole detection process is completed on the same moving path, the flywheel does not need to be manually moved, the turnover time consumption is reduced, continuous circulation of detection, discharging and feeding can be achieved through reciprocating movement of the stations, and the detection efficiency is improved.

The utility model discloses a mistake-proofing visual inspection device with an automatic sheet arranging function, which belongs to the field of mistake-proofing visual inspection devices and comprises a conveying frame, a driving roller is movably mounted on one side in the conveying frame, a driven roller is movably mounted on the other side in the conveying frame, and a conveying belt is movably mounted on the driving roller and the driven roller. The conveying frame is movably connected with an automatic sheet arranging assembly, after the automatic sheet arranging assembly and the PLC are arranged, the conveying belt moves, an industrial camera detects an image, the image is transmitted to the PLC, whether a finished product is qualified or not is judged, and when the finished product is not qualified, the push plate moves towards the side face, so that the push plate pushes the defective product out of a moving-out opening and enters the position above the movable carrying plate; and the PLC movably controls the height of the movable carrier plate, so that when the defective products fall off, the defective products cannot be damaged due to the fact that the height is too high, and follow-up reworking of the defective products is facilitated.

The invention relates to the technical field of visual inspection, in particular to an automatic visual inspection device for automobile parts, which comprises a conveying mechanism and an inspection mechanism, and is characterized in that the inspection mechanism comprises a frame, an electric cylinder is mounted at the top of the frame, an elastic mounting plate assembly is mounted at the telescopic end of the electric cylinder, and equipment boxes are symmetrically mounted on two opposite side walls of the frame; when the wire harness isolation plate is detected, the wire harness isolation plate is conveyed to the position below the detection lens assembly through the conveying mechanism, then the elastic mounting plate assembly and the detection lens assembly are driven to descend through the electric air cylinder, and the detection lens assembly is driven to move downwards through the driving mechanism. Wherein the elastic mounting plate assembly firstly drives the two shading positioning pieces to descend and abut against the conveying belt through the driving piece, so that a closed shading environment can be formed among the two shading positioning pieces, the conveying belt and the equipment box, no external light source enters the equipment box, and interference of the external light source on detection is avoided.

The utility model discloses lithium battery automatic visual inspection equipment which comprises a base frame, a distribution box arranged on one side of the top end of the base frame, a detection box arranged on the other side of the top end of the base frame, two bearing tables arranged at the lower end in the detection box, limiting pieces arranged at the bottom of the detection box on one sides of the bearing tables, and two guide rails arranged at the bottom of the detection box below the bearing tables. A top plate is arranged at the top of the detection box through a support, a belt transmission mechanism is arranged at the bottom end of the top plate, a linkage seat is installed on the outer wall of one side of the belt transmission mechanism, and a bearing plate is arranged at the bottom end of the linkage seat; a worm and gear mechanism is arranged at the bottom end of the bearing plate, and a piece containing plate is arranged at the bottom end of the worm and gear mechanism. According to the utility model, the detection precision of the lithium battery product when the detection equipment is used is guaranteed, the convenience of the detection equipment when the detection equipment is used is improved, and the detection efficiency of the lithium battery product when the detection equipment is used is improved.

The invention belongs to the technical field of three-dimensional modeling, and particularly relates to a three-dimensional visual detection method for motorcycle tires. According to the method, a tire is fixed, multi-view point cloud scanning is carried out, and an improved SAC-IA algorithm is adopted for registration and fusion to construct a three-dimensional point cloud model; the method comprises the following steps: designing adaptive voxel grid filtering and denoising based on tire geometric prior, and after improved bilateral filtering smoothing, fitting and unifying a coordinate system through principal component analysis and least square to obtain a standardized point cloud model; and extracting four core parameters of thickness uniformity and sidewall contour curvature, inputting the four core parameters into the hybrid dynamic weight scoring network to output quality scores, and meeting the requirements of high-precision and high-efficiency quality inspection of motorcycle tires in an industrial environment.

The invention discloses a vision tester, and relates to the field of visual function measurement. The vision tester comprises a display, a computer and a selector, every two of the display, the computer and the selector are in communication connection; during vision examination, a testee is positioned right opposite to the display; the display is used for displaying sighting marks with different sizes and shapes; the selector is worn by a testee and is used for collecting a sighting mark identification result of the testee; and the computer is used for determining the vision examination result of the testee according to the identification result of the testee on the sighting mark. According to the visual acuity tester, visual acuity screening is not limited by scenes, and convenience and accuracy of visual acuity screening can be improved.

Clinical-quality eye examinations are provided at locations remote from the physician and outside of a clinical setting. A portable optical device and corresponding software are delivered to the patient's location. The portable optical device is configured for patient use in self-conducting an eye or vision exam and taking optical measurements. As a function of type of optical measurement data or health consideration of the patient, the corresponding software provides uploading and live streaming of the optical measurement data to the physician. The corresponding software is executed during the patient conducting the eye (vision) exam and enables the remotely located physician, to participate in the same via video conference. Alternatively, an artificial intelligence resource operating remotely or locally can provide physician-type guidance and eye health assessments. Alignment of device and patient eyes can be facilitated for remote exams.

An electronic device according to an embodiment of the present invention may comprise a processor that constructs an image generation model by applying, to a base model trained to generate a defective product image, a feature model generated on the basis of a normal product inspection image and a defective product inspection image, inputs defect information in the form of at least one of text and an image to the image generation model, and obtains a defective product image including a defect corresponding to the defect information through the image generation model.

The invention discloses an automatic welding process combining laser scanning with visual inspection. The process specifically comprises four working procedures of laser scanning before welding, automatic wire feeding, automatic welding and online tracking detection in welding. The specific implementation effects of each process are as follows: the pre-welding laser line scanner scans a weldment by emitting a laser beam to extract three-dimensional information of the weldment, so that a welding route is conveniently planned, and a walking route is fed back to the control cabinet; the control system can receive an instruction to control the driving system to carry out an automatic welding process, so that the welding gun reaches a specified position to carry out automatic welding; in the welding process, the infrared laser tracker dynamically tracks the welding gun, corrects the walking route and guides the compound eye camera to conduct visual inspection so as to judge the welding quality, and the machining targets that components at the welding seam connecting position are uniform, and the welding seam surface is high in quality and low in defect are achieved.

The present invention discloses a method for wafer bonding, belonging to the field of integrated circuit chip manufacturing. This method successively performs a cleaning process and a baking process in an integrated circuit chip manufacturing factory; the following bonding process is carried out through a wafer bonding device: the manipulator transfer area takes out the wafer from the wafer access area; the wafer ID reader and the wafer pre-aligner read the wafer ID and pre-align the wafer; the alignment and pre-bonding unit aligns and pre-bonds the wafer; the vision inspection area inspects whether there are bonding defects in the wafer pair after pre-bonding. If there are, the debonding unit debonds the wafer pair and then places the wafer in the wafer access area; otherwise, the wafer pair is directly placed in the wafer access area. In the bonding process, the wafer and the wafer pair are transferred through the manipulator transfer area and / or the post manipulator. The present invention optimizes the wafer bonding method, improves the productivity of the bonding process, and the wafer bonding device has a compact structure, a small floor area, and low costs.

The embodiment of the application discloses a kind of visual detection system, detection method and related device, visual detection system includes stage assembly, robot assembly and visual component, stage assembly includes driving part and stage body.The visual detection system provided by the application, stage assembly also has the ability of movement, stage assembly can be driven by driving piece and move and rotate along the first direction, at least for driving visual component to move in second direction and third direction by robot assembly, on the one hand, stage assembly and robot assembly can coordinate motion, can improve detection efficiency, can be carried on multiple stage bodies on stage assembly, that is, multiple pieces to be detected can be detected simultaneously;On the other hand, robot assembly can not move in the first direction, stage body moves in the first direction, reduces the probability that error is generated by the combination of stage body motion trajectory and robot assembly motion trajectory, to make visual detection more accurate.

The invention relates to the technical field of insulation rope detection, and discloses a high-precision measurement and surface defect identification insulation rope full-automatic detection system, which comprises a take-up and pay-off module, a laser measurement module, an AI visual detection module, a tension control module, a data transmission module and a data processing module, and is characterized in that the take-up and pay-off module comprises an active take-up and pay-off mechanism; the laser measuring module comprises a high-precision laser diameter measuring instrument; the AI visual detection module comprises a YOLOv8 visual detection system; the tension control module comprises a pneumatic tension controller; the data transmission module comprises an industrial Ethernet, and the data processing module comprises an industrial computer and professional data processing software. According to the full-automatic insulation rope detection system with high-precision measurement and surface defect identification, full-process automation of insulation rope detection is realized, and the problems of low efficiency, poor precision and high false alarm rate of traditional manual detection are solved.

This invention relates to a trimming end effector. The device includes a trimming module, a vision inspection module, an expansion module, and electrical and pneumatic control modules. This device replaces existing manual trimming methods with automated equipment, improving efficiency and reducing operator injury. Compared to existing end effectors, this device can adapt to both offline and real-time online compensation, and can select appropriate algorithm strategies based on factors such as the characteristics of the workpiece. The same trimming end effector can be used to adapt to different product configurations, significantly improving product adaptability. The device features a detachable expansion module at the front end, enabling automatic tool changing, chip removal, and clamping functions. The trimming end effector achieves stable connection with a robot via a quick-change mechanism. The quick-change module allows for high-precision, repeatable connections, enabling different processing functions to be performed at the same workstation according to process requirements. This device has broad application prospects in the aircraft assembly industry.

This application relates to the field of home appliance manufacturing technology, and provides a smart manufacturing production line and method for refrigerator bodies. The smart manufacturing production line for refrigerator bodies includes an outer shell forming line, an inner liner assembly line, and an assembly station. The inner liner assembly line includes a first positioning device, a second positioning device, a vision inspection device, a pushing device, and an automatic screw-locking device. The first and second positioning mechanisms are used to position the first and second inner liners respectively, and drive the first and second inner liners to move towards each other in a horizontal direction, so that the first mating part of the first inner liner and the second mating part of the second inner liner are aligned and engaged. The vision inspection device is used to perform alignment detection on the first and second mating parts from the side. The pushing device is used to apply an upward pushing force to the aligned mating parts. The automatic screw-locking device is used to downwardly fasten screws to the aligned mating parts, so that the screws pass through the aligned mating parts and are locked into the threaded holes of the metal parts, realizing the automated assembly of the refrigerator inner liners.

This application discloses an industrial inspection method, apparatus, equipment, product, and storage medium, relating to the field of industrial vision inspection technology. The method includes: responding to an industrial inspection command, acquiring an image to be inspected for membrane defects; processing the image using a preset defect detection model to obtain a defect detection result. The preset defect detection model is obtained by quantizing a target defect detection model, which is obtained by structural pruning and lightweight reconstruction of an initial defect detection model. The structural pruning and lightweight reconstruction are used to reduce the number of model parameters and computational load. This application reduces the number of model parameters and computational load through structured pruning and lightweight reconstruction, and then quantizes the model, enabling the quantized model to be deployed on edge devices while improving the model's inference efficiency, achieving efficient model compression and real-time inference.

The invention provides substrate visual inspection equipment, which comprises a horizontal conveying mechanism, a positioning carrying table mechanism, a visual inspection mechanism and an NG marking mechanism, and is characterized in that the horizontal conveying mechanism is used for conveying a substrate to the positioning carrying table mechanism for positioning; the positioning platform deck mechanism forms a detection platform for substrate detection above the horizontal conveying mechanism; the visual detection mechanism is used for carrying out visual detection on the substrate on the positioning carrying table mechanism and comprises at least two cameras which are arranged left and right, a light source, a first moving assembly for respectively driving the two cameras to move left and right and a second moving assembly for respectively driving the two cameras to move up and down; the NG marking mechanism is used for marking the substrate with the detection result being NG, and the NG marking mechanism is located between the two cameras in the horizontal direction and located above the positioning carrying table mechanism in the vertical direction.