17results about How to "Efficient automatic detection" patented technology

The invention discloses a PCB (Printed Circuit Board) back drilling defect detection process, which relates to the technical field of defect detection, and comprises the following steps: placing a PCB to be detected on a detection table; wherein the PCB to be detected is subjected to back drilling processing; obtaining distribution of through holes of the PCB to be detected and positions and directions of back drilling holes; according to the scanning direction, the scanning visual angle and the scanning base point of the laser scanner, point cloud data of the back drilling face of the PCB to be detected and point cloud data of the through hole face of the PCB to be detected are collected; performing depth map conversion on the point cloud data of the back drilling surface of the PCB to be detected and the point cloud data of the through hole surface of the PCB to be detected to obtain a back drilling depth image of the back drilling surface and a through hole depth image of the through hole surface; and according to the direction of the back drilling hole, the back drilling depth image of the back drilling surface and the through hole depth image of the through hole surface, identifying the defect of the back drilling hole of the PCB to be detected. According to the method and the device, the defect detection efficiency of the back drill of the PCB is improved.

The invention belongs to the technical field of seam welding detection, and particularly discloses and provides a roof waterproof roll seam welding detection method which comprises the following steps: constructing a three-dimensional model of a to-be-constructed welding area, and marking the type of a welding detection point; welding characteristic analysis is conducted on the welding area, and all welding characteristic indexes are obtained; the number of welding detection points is determined, and the welding detection points are marked; confirming a standard passing threshold value of each welding detection point corresponding to each welding detection index; building a welding quality inspection model; sequentially carrying out quality inspection according to a set welding quality inspection plan, and recording quality inspection values; and the welding quality score value is output, and a welding quality inspection report of the waterproof coiled material is constructed and fed back. According to the method, the defect that current welding detection points are arranged comprehensively is effectively overcome, the specific welding characteristics of the waterproof coiled material are fully combined, the adaptability of a seam welding detection scene of the roof waterproof coiled material is improved, and meanwhile the representativeness and rationality of a welding detection result are guaranteed.

The invention discloses a polyester fabric defect detection method and system based on a visual image, and relates to the field of fabric detection.The method comprises the steps that a multi-scale feature map of a polyester fabric is obtained; generating change track characteristics of each key process; extracting integrated features from the multi-scale feature map of the polyester fabric by using a convolutional neural network, and constructing a multi-granularity feature matrix in combination with the change trajectory features of each key process; based on federated learning and a random forest technology, performing importance scoring on each feature in the multi-granularity feature matrix, and performing feature screening according to importance scores to obtain polyester fabric defect identification input features; and performing score prediction on the polyester fabric defect identification input features through a neural network, and identifying a potential polyester fabric defect area. According to the method, the accuracy and robustness of defect detection of the polyester fabric are improved, and the method has the advantages of data privacy protection and multi-source information integration.

The utility model provides a mortar fluidity detection device. The mortar fluidity detection device comprises a support frame, a mixing assembly and a measuring assembly, the supporting frame is provided with a table board extending in the horizontal plane. The mixing assembly is movably mounted on the supporting frame and is suitable for stirring raw materials to obtain mortar; and the measuring assembly is mounted on the supporting frame and is suitable for receiving the mortar from the mixing assembly and uniformly discharging the mortar to the table board so as to obtain the expansion degree of the mortar which is completely spread and is in a static state, and the fluidity of the mortar is evaluated according to the expansion degree.

This utility model discloses a surface defect detection device for rubber roller production, comprising a feeding assembly, a rotary drive assembly, a discharging assembly, and a vision inspection assembly. The feeding assembly includes a feed plate for the rubber rollers to be inspected, a feed lifting ramp, and a lifting assembly for orderly conveying the rubber rollers to be inspected. The rotary drive assembly includes an active drive shaft for roller rotation, a passive drive shaft for roller rotation, a roller rotation drive motor, and a drive shaft mounting bracket to ensure stable rotation of the rubber rollers. The discharging assembly includes a discharge lifting ramp and a collection trough for collecting the inspected rubber rollers. The vision inspection assembly includes a translational drive rail and a surface defect detection camera to achieve omnidirectional scanning of surface defects on the rubber rollers. This equipment has a high degree of automation, accurate detection, effectively improves the quality control level of rubber roller production, and ensures the surface quality of the rubber rollers.

The invention provides an electric automobile power battery EIS detection device and method in the technical field of electric automobile power battery detection. The device comprises a main control module, a charging module, a battery module, a switching power supply module, an EIS detection module, an insulation detection module, a switch K1 and a switch K2. The charging module, the battery module, the switching power supply module, the main control module and the EIS detection module are connected in sequence; the detection end positive electrode of the insulation detection module is connected with one end of the switch K1 and the detection end positive electrode of the EIS detection module, the detection end negative electrode is connected with one end of the switch K2 and the detection end negative electrode of the EIS detection module, and the control end is connected with the main control module. The method has the advantages that the detection convenience, the field applicability and the equipment integration degree are greatly improved.

The invention relates to the technical field of door and window detection, and in particular to a combined door and window frame combination degree detection system and method, which improves the accuracy and efficiency of door and window combination degree detection; the system comprises: a door and window upper machine platform, which is used to install doors and windows to be detected, after the doors and windows to be detected are installed, adjustable environmental spaces are formed on both sides of the doors and windows to be detected, an environmental simulation unit is arranged on the door and window upper machine platform, and the environmental simulation unit is used to adjust the air pressure, temperature, humidity and concentration of set gas of two adjustable environmental spaces; a mechanical arm execution module, which is arranged in the adjustable environmental space on the side where the door and window handle is installed, and is used to perform multi-angle force application opening and closing actions on the doors and windows to be detected; a sensor integration module, which is used to collect the air pressure, temperature, humidity, concentration of set gas, noise decibel when the doors and windows are opened and closed, and the applied pulling force when the mechanical arm execution module performs the opening and closing operation of the two adjustable environmental spaces according to a set collection frequency.

The utility model discloses a full-size profiling detection device, which relates to the technical field of detection and comprises a support, an air cylinder is arranged above the support, a profiling jig is arranged at the head of the air cylinder, a proximity sensor is arranged at the front end of the profiling jig, a judgment sensor is arranged above the profiling jig, and the proximity sensor is connected with the judgment sensor. The profiling jig comprises a jig body and a through hole. According to the utility model, rapid clamping of the workpiece is realized through the profiling jig driven by the cylinder, high-efficiency automatic detection of the processing condition of the annular groove of the workpiece is realized in combination with the proximity sensor and the laser correlation judgment sensor, the production efficiency is improved, the error of manual detection is reduced, and the device has good flexibility and expandability and is suitable for popularization and application. The structure is exquisite, the misjudgment condition of a CCD visual system is avoided, and the total cost is greatly reduced.

The invention discloses an image-based sub-pixel-level high-precision two-dimensional size online measurement method and system, and the method comprises the steps: 1, collecting a part image, and carrying out the denoising and binarization processing of the image; 2, carrying out correction processing on the image; 3, performing edge detection on the image, and grouping line segments according to different slopes and intercept; 4, combining the line segments of each group into a straight line; 5, obtaining coordinates of intersection points of all the synthesized straight lines, corroding the binarized part image, screening out coordinates of points outside a black area of the corroded image to obtain new coordinates of the intersection points, taking the coordinates of the intersection points as two end points of an edge straight line, and connecting the straight line to obtain a straight line which is the contour edge straight line of the part; and 7, measuring the contour of the part to obtain measurement data. According to the invention, high-precision measurement of the two-dimensional size of the object is carried out by using the image, so that the measurement precision reaches the micron level, and efficient, accurate and automatic detection of the size of the part in the production process is realized.

The invention belongs to the field of target material production, particularly relates to a semiconductor target material detection device and a detection method thereof, and aims to solve the problems that only one type can be detected at one time, the detection efficiency is low, the target material is easy to damage due to frequent clamping operation and the use is not convenient enough in the conventional detection mode adopting detection tools such as a micrometer and a vernier caliper. According to the technical scheme, the device comprises a workbench and a target material, a rotating disc for bearing the target material is rotationally arranged at the top of the workbench, four telescopic rods are arranged on the outer wall of the rotating disc in a sliding mode, and a motor, a first electric push rod, a second electric push rod and other driving components and a first contact switch, a second contact switch and other detection elements are integrated; and efficient and automatic detection of the semiconductor target material is realized. Through unified control of the controller, multiple steps of positioning, rotating, outer wall detection, rectangular opening detection, through hole detection and the like of the target material can be automatically completed, and the detection efficiency and accuracy are greatly improved.

The invention discloses a docking system and method for a lightning arrester of a wind driven generator, and the method comprises the following steps: a controller obtains a picture shot by a visual detection device to control an unmanned mobile platform, and a mechanical arm drives a self-adaptive detection device to be docked with the lightning arrester, so that the ends of a plurality of conductive rods are in preliminary contact with the lightning arrester; the spring is compressed to provide passive pre-tightening force towards the lightning arrester for the conducting rod; the controller controls the linear motion mechanism to extend out of the target displacement to drive the conducting rod to continuously press the lightning arrester; the controller collects the actual displacement of the linear motion mechanism; the controller judges whether the error between the actual displacement and the target displacement is smaller than an error threshold value or not, if not, the controller controls the linear motion mechanism to retreat by the preset displacement, controls the linear motion mechanism to repeatedly execute multiple stretching and retreating operations, and then controls the linear motion mechanism to stretch out by the target displacement; and the end parts of the plurality of conducting rods are in stable contact with the lightning arrester. And safe and reliable automatic detection of the lightning arrester is realized.

The invention relates to the technical field of agricultural product detection, in particular to a detection device capable of efficiently and continuously detecting the internal quality of agricultural products, which comprises a feeding unit, a detection unit, a shifting unit and a discharging unit. Wherein the detection unit comprises a detection table arranged at the discharging end of the feeding unit, a top light detection assembly arranged on the detection table, a side light detection assembly arranged on the detection table, a bottom light detection assembly arranged on the detection table, and a limiting air cylinder arranged between the detection table and the feeding unit, and the detection direction of the side light detection assembly is perpendicular to the top light detection assembly. By arranging the detection unit, the effect of comprehensively, efficiently and automatically detecting agricultural products of different specifications can be achieved, and by arranging the top light detection assembly, the bottom light detection assembly and the photometric detection assembly, all-directional rapid detection of samples is achieved within the limited unit sample detection time; the rapid and efficient detection requirements of an agricultural product production line are met.

The invention discloses an automatic flattened bamboo defect detection method and system based on a convolutional neural network, and relates to the field of image recognition and material detection, and the method comprises the steps: carrying out the high-resolution image collection of the surface of a flattened bamboo through a high-definition camera; the collected flattened bamboo wood image is preprocessed; the preprocessed image is input into a trained convolutional neural network, the convolutional neural network is based on an improved ResNet-50 architecture, and the improved ResNet-50 architecture comprises a multi-scale feature extraction module, a feature fusion layer and a classification layer; the surface defects of the flattened bamboo wood are automatically identified through a convolutional neural network; and positioning and classifying the identified defects, and outputting a result to an automatic detection system. Compared with the prior art, various defects on the surface of the flattened bamboo wood are automatically detected through the convolutional neural network, manual intervention is not needed, and the detection efficiency and accuracy are greatly improved.

The utility model relates to the technical field of steel drum leak detection, in particular to a pressure test leak detection device suitable for a steel drum. According to the technical scheme, the device comprises a test frame, a detection groove is formed in the front side of the test frame, a rear side groove is formed in the rear side of the test frame, an air storage tank is installed in the rear side groove, a rotating bottom plate is rotationally connected to the bottom of the detection groove, a loading groove is formed in the rotating bottom plate, and a transverse plate is installed at the upper end of the detection groove through a telescopic cylinder; the two sides of the transverse plate are provided with an ejector rod and an inflation head respectively, and the ejector rod and the inflation head are symmetrically distributed on the transverse plate. In the inflation detection process, the opening in the upper end of the steel drum can be aligned with the ejector rod through the rotation of the steel drum, then the inflation head can be ensured to be aligned with the opening in the upper end of the steel drum through the rotation of the transverse plate, the purpose of automatically aligning inflation detection is achieved, and automatic inflation detection can be more efficiently carried out.

This application relates to the field of underwater robot technology and discloses a multimodal fusion intelligent detection method for bridge defects using underwater robots. The method includes: acquiring a set of underwater environmental parameters; dynamically adjusting imaging parameters by optimizing the light propagation path to overcome problems such as light attenuation and scattering in the underwater environment; utilizing multi-sensor data fusion technology, combining sonar and optical imaging data to generate a high-quality sequence of bridge surface images; extracting, classifying, and weighting defects in the images to generate an intermediate image set containing defect features; and performing multi-dimensional verification and local correction to ensure the accuracy of the defect features; finally, by evaluating the quality of the intermediate image set, standardized image data is generated to provide reliable input for defect extraction. This application can provide efficient and accurate technical support for bridge maintenance and safety assessment.

The utility model discloses a universal wheel hub threaded hole go-no go gauge five-six-seven hole detection mechanism, and relates to the wheel hub threaded hole detection technology field, the universal wheel hub threaded hole go-no go gauge five-six-seven hole detection mechanism comprises a rack and a slide rail, the slide rail is arranged on one side of the rack, one side of the slide rail far away from the rack is slidably provided with a movable frame, and the middle lower position of the movable frame is fixedly provided with a separator plate. A round hole is formed in the middle of the partition plate, a telescopic air cylinder is fixedly arranged at the upper end of the rack, the tail end of a piston rod of the telescopic air cylinder extends to the inner side of the rack and is fixedly connected with a movable frame, and a plurality of rotating rods are rotationally arranged on the inner side of the upper end of the movable frame; a transmission mechanism for driving the rotating rods to rotate is arranged at the top of the movable frame, first universal joints are arranged at the lower ends of the rotating rods, and connecting rods are arranged on the lower sides of the first universal joints. The hub threaded hole detection device can replace manual work, can efficiently and automatically detect the hub threaded hole, and can greatly improve the working efficiency.