120 results about "Material defect" patented technology

The invention relates to the field of semiconductor packaging material defect detection, in particular to a semiconductor packaging material defect detection method based on deep learning, which comprises the following steps: acquiring a surface image, and extracting a two-dimensional contour and a feature point set; preprocessing the image, and separating a packaging material main body area; constructing a two-dimensional defect identification model based on Transform, and outputting a two-dimensional detection result; scanning suspected and unknown defect areas to obtain three-dimensional point cloud data, and extracting geometric and texture features; fusing two-dimensional and three-dimensional data through a space-time alignment model; utilizing the multi-modal fusion model to output defect positions and types; and evaluating the defect importance based on the material node connectivity and the stress distribution, and generating a visual detection report. According to the invention, high-precision detection of semiconductor packaging material defects is realized, the defect identification rate, the positioning precision and the detection efficiency are improved through multi-modal data fusion and a deep learning model, and a visual report can be generated based on material structure quantification defect importance.

The invention provides a packing material defect detection method and system based on machine vision, and relates to the technical field of machine vision, and the method comprises the steps: collecting a multi-angle image sequence to construct a depth map, and carrying out the geometric correction and illumination compensation of an image; generating a feature map sequence by using a multi-scale direction filter bank and a self-adaptive direction enhancement factor, and constructing a feature pyramid structure to realize hierarchical segmentation of a flaw region; extracting a multi-dimensional feature set containing local textures, gray statistics and shape description, distributing weight coefficients through a feature evaluation matrix, and fusing to generate a feature vector; a double-order cascade classifier is used for classification, a lightweight decision tree is used for rapid pre-classification in the first order, and features are extracted and fused through an attention-enhanced deep network in the second order. According to the invention, the accuracy and real-time performance of the defect detection of the packing material are improved, and the adaptability of the detection system to different types of defects is enhanced.

The invention discloses a nondestructive testing method for composite material defects, and relates to the technical field of nondestructive testing, and the method comprises the following steps: firstly, collecting a scanning waveform of a test piece A, determining a potential defect area based on an echo amplitude and a time difference, and outputting a sequence containing space coordinates, an original waveform and focusing parameters; an effective time window is intercepted after preprocessing, sub-bands are generated through wavelet packet decomposition, and total energy is calculated and normalized to obtain an energy vector; secondly, based on a known sample, evaluating the separability of sub-bands by using a Fisher criterion, sorting the sub-bands, determining an optimal energy dimension through cross validation, combining sub-band energy features with phase and time difference features into composite vectors, inputting the composite vectors into a dual-channel lightweight deep network, outputting defect categories and confidence coefficients, and mapping the defect categories and confidence coefficients to a C scanning frame image; and finally, backtracking the three-dimensional coordinates, calculating the defect volume and the residual wall thickness, and comparing with a material performance database to output a conclusion. The problem of misjudgment caused by echo waveform similarity is solved, and detection closed-loop optimization is achieved.

The invention relates to the field of material damage mechanics, in particular to a deterioration performance analysis method for characterizing material defect details through a ossification tree. The method comprises the following steps: acquiring three-dimensional shape data of internal defects of a material through microscopic CT scanning, extracting defect features in combination with an image processing algorithm, converting the defect features into an ossification tree structure, and constructing a defect heterogeneous tensor model; a single-defect sample is accurately reproduced by adopting a 3D printing technology, a rigidity degradation index equation is established through a mechanical test and symbolic regression analysis, and the influence of defects on the material performance is quantified. According to the method, on the basis of K-means clustering and an auto-encoder network, auto-encoding fingerprints of defects are generated through a feature weight matrix and an adjacent matrix, and clustering analysis of six types of defects such as annular defects and sickle-shaped defects is achieved; the 3D printing technology is adopted, the original shape of the defect is accurately re-engraved, and preparation of a single-defect material is achieved. And through symbolic regression, a one-dimensional bubble rigidity deterioration index equation is provided, and the influence of material defects on material deterioration is quantified.

The invention relates to a logistics robot system capable of sorting steel body material defects, which builds a sorting-logistics-endurance integrated whole-course autonomous system architecture, and integrates a heterogeneous dual-core processor architecture with deep hardware. The two key technologies of a YOLOv11-SG lightweight defect detection model and a lightweight LCC-LCC topology wireless charging system are organically combined, a state machine driven full-process cooperative control logic is matched, a complete autonomous sorting logistics solution is formed, the lightweight defect detection model guarantees independent perception of a terminal, the endurance problem is solved through the wireless charging technology, and the system is simple in structure and convenient to operate. And by combining the multi-module collaborative hardware and process design, the robot can autonomously operate in narrow and small scenes such as a 400mm narrow channel, the dependence on cloud computing and manual intervention is thoroughly eliminated, and a low-cost intelligent upgrading path is provided for medium and small-scale logistics scenes.

The invention discloses a labeling quality intelligent detection method and system for multiple materials, and the method comprises the steps: S1, collecting original image data of paper, plastic and metal labels through an industrial camera, and carrying out the preprocessing, and obtaining standardized image data; s2, designing an improved edge detection network, extracting an initial edge feature of the label, generating a linear edge feature through curve fitting, calculating a label rotation angle, and executing rotation transformation to obtain image data after rotation correction; s3, constructing a double-branch network comprising material and defect branches, extracting material types, generating defect features in combination with the material types, and finally generating structured defect features; and S4, according to the structured defect features, generating material tolerance, and then calculating a quality score and a quality grade. According to the method, the problems of material misjudgment and defect detection omission caused by low rotation correction precision of the special-shaped label and staged processing of multi-material defect detection in a traditional method can be solved.

The invention provides a high-precision material defect detection method based on a nano sensor, and relates to the technical field of material defect detection.The method comprises the steps that S1, the nano sensor is provided and detects tiny defects on the surface or inside of a material, S2, the nano sensor is installed on the surface or inside of the material to be detected, and S3, the material to be detected is detected; and the material is monitored in real time through a sensor, and signals of potential defects in the material are obtained. According to the high-precision material defect detection method based on the nano sensor, the nano sensor and an advanced artificial intelligence algorithm are combined, so that high-precision identification of tiny defects in a material is realized. Defect type classification is carried out by using a random forest algorithm, and the image data and the signal feature data are subjected to conjoint analysis, so that accurate classification and positioning of multiple defect types are ensured.

The invention relates to the technical field of blank defect detection, in particular to a large-scale shaft forging blank defect identification method based on ultrasonic flaw detection data, and the method comprises the following steps: obtaining an ultrasonic A scanning signal of a large-scale shaft forging blank; extracting a back scattering signal from the ultrasonic A scanning signal; the back scattering signals are preprocessed; calculating the power spectrum density of the back scattering signal; obtaining characteristic parameters related to depth based on the power spectrum density; calculating to obtain a dynamic attenuation coefficient changing along with the depth based on the characteristic parameters; a compensation factor is obtained through exponential operation; compensating the original echo peak amplitude of the defect detected in the A scanning signal by using the compensation factor to obtain a defect signal amplitude; and comparing the amplitude of the defect signal with a threshold value of a standard DAC curve under a corresponding depth, and judging whether a defect exists or not. According to the invention, the accuracy and reliability of defect identification are improved.

The invention relates to the technical field of metal material detection, in particular to a metal material detection method and device based on a multi-mode excitation source. When multi-modal data is adopted for metal material detection, firstly, the defect type of the metal material is determined, then, different multi-modal data feature fusion methods are adopted, when the metal material to be detected is of a single-defect type, feature fusion is carried out by adopting multi-modal features of a convolutional neural network model based on an attention mechanism, and the defect type of the metal material to be detected is detected. When the to-be-detected metal material is of a multi-defect type, performing feature fusion on the multi-modal features by adopting a hierarchical weighted summation method; the feature fusion is more purposeful, the accuracy of the feature fusion is improved, and the accuracy of metal material defect detection is further improved.

The invention discloses an insulating material defect identification method and device based on a terahertz spectrum, terminal equipment and a storage medium, and belongs to the field of insulating material detection.The method comprises the steps that the matching weight of a target terahertz spectrum is determined according to the terahertz spectrum of each known defect in a defect type library; calculating the matching cost between the target terahertz spectrum and the terahertz spectrum sample according to the matching weight; if the matching cost is smaller than a first threshold value, according to the signal intensity and the frequency range of the target terahertz spectrum, calculating a time-varying index of the target terahertz spectrum, judging a difference value between the time-varying index and a sample time-varying index corresponding to the terahertz spectrum sample, and when it is determined that the difference value is smaller than a second threshold value, judging that the to-be-identified area has defects; and if the matching cost is not less than the first threshold value, determining that the to-be-identified area does not have defects. According to the invention, the problem of low detection accuracy caused by manual detection of the defects of the insulating material in the prior art can be solved.

The invention discloses a composite material defect detection method and system fusing infrared imaging and deep learning, and the method comprises the steps: preparing a defect-containing composite material plate, obtaining an original infrared thermal image data set of the defect-containing composite material plate, carrying out the preprocessing, training the defect-containing data set through the processed data set, and carrying out the recognition of the defect-containing data set. Obtaining a neural network containing defect characteristics of the composite material; and establishing a multi-index evaluation system, obtaining a defect contour, and marking a defect type and a defect area. By combining infrared nondestructive testing with an artificial intelligence method, batch detection of internal defects of the composite material is realized, errors caused by manual detection are reduced, and the accuracy and efficiency of damage detection are improved.

The invention relates to the technical field of image processing, in particular to an optical module packaging material defect detection method. Segmenting the image based on the segmentation threshold to form a plurality of segmentation regions; for each segmented region, based on the gray features of the pixel points in each segmented region, calculating the regional rationality of the current segmented region, and taking the product of the regional rationality as the segmented interval rationality; in response to the condition that the reasonability of the segmentation interval is greater than a preset reasonable threshold value, taking the segmented image as a segmented image for defect detection; and in response to the condition that the reasonable degree of the segmentation interval is smaller than or equal to a preset reasonable threshold value, optimizing the segmentation threshold value, obtaining an optimal segmentation boundary, taking an image segmented based on the optimal segmentation boundary as a segmented image, and performing defect detection based on the segmented image. The method has the effect of improving the recognition and extraction accuracy of the corrosion area on the surface of the optical module packaging material.

The invention relates to the technical field of thermal interface material defect detection, in particular to a nondestructive detection method and system for thermal interface material application defects, and the system comprises an electric displacement table, heating laser, detection laser, a photoelectric detector, an acoustic optical modulator, a lock-in amplifier, an optical element and a data processing unit; the electric displacement table is used for fixing a sample and accurately controlling the position of the sample; the sample is of a silicon-thermal interface material-substrate sandwich structure; the upper-layer silicon wafer of the sample is plated with a metal film as a transduction layer; the heating laser is used for heating the sample; the acoustic optical modulator is used for modulating the heating laser, so that the heating laser heats the sample in a sine wave form; the detection laser is used for detecting sample temperature fluctuation; the photoelectric detector is used for collecting and detecting laser reflection signals; the lock-in amplifier is used for extracting and detecting laser phase and amplitude signals. According to the invention, non-destructive rapid detection of the defects of the thermal interface material in an application scene can be realized.

The invention provides a fan blade state detection method. According to the method, ultrasonic detection data of a to-be-detected area of the fan blade is obtained, and when it is determined that the risk level of the to-be-detected area is higher than a preset risk level according to waveform features in waveform data in the ultrasonic detection data, the ultrasonic detection thickness of each to-be-confirmed position in the to-be-detected area is obtained; according to the method, the ultrasonic detection thickness is detected, and the detection result of each to-be-confirmed position is determined according to the ultrasonic detection thickness, so that the area possibly having defects can be quickly screened out, the detection efficiency is improved, and the material defect type in the blade can be detected.

The application discloses a heat-shrinkable tube detection method based on image recognition and relates to the technical field of power material defect detection, and is used for solving the problems of defect profile distortion, positioning deviation and insufficient classification accuracy caused by optical ghost interference in heat-shrinkable tube detection; the mapping relationship of light refraction paths is established based on the brightness gradient difference and the refractive index difference, the theoretical ghost interference fringes are generated by dynamically adjusting the optical path difference of the interferometer, and the abnormal areas deviating from the theoretical distribution are screened; meanwhile, the residual ghost interference is eliminated by combining light source incidence angle optimization and defect displacement amount calculation, and finally, the precise classification and positioning of defects are realized through multi-dimensional matching of geometric parameters and historical defect data, the detection accuracy is improved, the dependence on complex algorithms is reduced, and the real-time detection demand of industrial production lines is adapted.

This invention relates to the field of materials evaluation technology, specifically proposing a material defect detection method and system based on multi-dimensional feature fusion. The method involves synchronously acquiring thermal response data through pulse and phase-locked loop dual-modal thermal excitation, extracting four-dimensional features in the time and frequency domains, and constructing a unified pixel-level feature vector through standardized preprocessing. Then, a response map is generated through weighted fusion, and candidate abnormal regions are screened. Finally, defect determination is completed by combining dual-branch classification and decision-level fusion. This approach addresses both shallow and deep defect detection in the tested flat plate material component, effectively distinguishing between various defects such as interlayer debonding, microcracks, and porosity, solving the problems of poor accuracy and easy confusion in single thermal excitation detection. Furthermore, the standardized preprocessing process improves feature stability, enabling accurate determination of defect location and type, thus enhancing the accuracy and comprehensiveness of defect detection in the tested flat plate material component.

The invention relates to the technical field of computer vision, in particular to a material defect detection method for keyboard and keycap production, and the method comprises the steps: obtaining an initial image and a grayscale image of a keyboard and a keycap to be detected; obtaining a suspected defect area in the gray level image according to the gray level difference of pixel points in the gray level image; for any suspected defect area, acquiring a defect coefficient of each pixel point in the any suspected defect area according to color features of pixel points of a corresponding area in the initial image and distribution features and texture features of the pixel points of the any suspected defect area; obtaining a self-adaptive small-scale weight and a self-adaptive large-scale weight of each pixel point by using a defect coefficient of each pixel point in the gray level image; according to the self-adaptive small-scale weight and the self-adaptive large-scale weight of each pixel point, an enhanced image is obtained by using a Retinex algorithm, and the accuracy of material defect detection of keyboard and keycap production is improved.

The application discloses a kind of microwave thermal imaging detection method and its detection device, belong to non-metal material defect detection technical field, it includes heating box, the bottom of heating box is provided with rotating table, rotating table is provided with gripper, the top of heating box is provided with microwave heating device, spray pipeline, infrared camera and CCD camera, microwave heating device is connected with signal generator, infrared camera and CCD camera are electrically connected with image processing module.This scheme uses fluorescent penetrant to penetrate non-metal workpiece to be measured, uses the high sensitivity response of penetrant to microwave pulse to generate heat signal, uses heat signal to carry out microwave thermal sensing imaging, can fully detect the internal condition of defect;At the same time, fluorescent penetrant is used for fluorescent imaging, the visualization of defect position can be realized, so as to detect the distribution of defect surface;Two kinds of imaging are fused and analyzed, realize the comprehensive detection of surface shape and internal structure for non-metal workpiece defect.

According to the analysis method for the steam pipeline welding seam cracking reason, through combination of staged gradient corrosion and an image analysis technology, material defects are quantified, layered stripping energy spectrum detection and fractal dimension calculation are adopted, the interaction between oxidation corrosion and instantaneous cracking is distinguished, a grain size matching index and five-dimensional scoring system is provided, and the analysis result of the steam pipeline welding seam cracking reason is obtained. And carrying out dynamic coupling analysis on multiple parameters such as material structure difference, insufficient welding heat input and abnormal component gradient. According to the method, quantitative judgment of the failure mode is achieved through multi-dimensional data fusion, the problems that a traditional method is high in one-sidedness and large in error rate are effectively solved, stress corrosion and other cracking reasons can be rapidly positioned, unplanned shutdown and economic losses caused by weld joint failure are remarkably reduced, and the method is suitable for systematic safety evaluation of the high-temperature and high-pressure steam pipeline.

The application provides a spinning rib body folding and meat defect control method and system for a cross inner rib cylinder, comprising the following steps: S1, adopting multi-roller collaborative spinning; S2, establishing a finite element simulation model based on an actual core mold, a blank and a spinning roller; S3, adjusting the corner angle distribution and radial offset distribution of the spinning rollers in the spinning roller group in a power reduction mode to reduce the folding and meat defect in the finite element simulation; S4, if the folding and meat defect is not eliminated, further eliminating the folding and meat defect by increasing the attack angle of the spinning roller group; and S5, performing a process test based on the spinning parameters used in the simulation. The spinning rib body defect control method provided by the application can effectively inhibit the generation of the folding and meat defect of the cylinder spinning inner rib, and improve the size accuracy of the cylinder.

The invention discloses an alternating-current electromagnetic field detection method for subsurface defects of a metal material. The method comprises the following steps: performing model analysis on electromagnetic field distribution of the subsurface defects; designing and optimizing a subsurface defect detection probe; building a subsurface defect detection system; and making artificial defects to carry out experimental verification on a simulation result. Aiming at the problem that the detection defect depth of ACFM is insufficient, compared with existing equipment, the detection depth is improved, the efficiency and accuracy of metal material defect detection are further improved, and a reference is provided for guaranteeing industrial safety and prolonging the service life of the equipment.

The present invention belongs to the field of semiconductor technology and relates to a patterned controllable droplet epitaxy method for semiconductor molecular beam epitaxy. The method comprises the following steps: maintaining the temperature of the substrate below the melting point of the target droplet material; depositing the target droplet material on the surface of the substrate to form a metal coating layer, the deposition thickness of which is higher than the critical thickness of the target droplet material when normally forming droplets; in-situ introducing laser interference pulse irradiation to act on the metal coating layer to achieve the patterned orderly construction of the target droplets. The method of the present invention can realize the patterned preparation of group III element droplets. The principle and implementation process of the method are fully compatible with the traditional droplet epitaxy process, there is no risk of introducing any material defects, and there is no selection of substrate types, thereby solving the problems commonly existing in the current existing patterning technology, including potential damage to the quality of the material crystal, poor consistency of the droplet composition, and the type of droplets being directly limited by the selected substrate.

The present invention addresses the problem of providing a long-strip-shaped copper alloy which has high hardness, is capable of suppressing material defects over a long period of time, and has excellent yield during mass production. The present invention is a long copper alloy having an equivalent line diameter of 0.5-5.0 mm, containing, in mass%, 9.00% < = Ni < = 15.00%, 0.30% < = Si < = 0.90%, 0.50% < = Al < = 2.00%, 2.00% < Sn < = 4.50%, and 0% < B < 0.010%, the remainder being Cu and unavoidable impurities, and having a Vickers hardness of 350 HV or more and an electrical conductivity of 8% IACS or more, the relationship ratio of Si, Al, Sn, and B satisfying 120 < = (1.7 Si + 1.2 Al + Sn) / 3.9 B < = 300.

The utility model discloses a winged part mould relates to mould technical field, including upper mould, the inside fixedly connected with forming assembly of upper mould, the bottom fixedly connected with lower mould of forming assembly, the inside of lower mould is provided with resilience subassembly, the top of upper mould is provided with injection moulding hole, and forming assembly includes male die. This winged part mould is driven male die to go down by upper mould, makes the precise clamping of male block and recess, positioning column and positioning groove, can rapidly and stably fixed cavity, effectively prevents cavity displacement in the injection moulding process, ensures the size accuracy of forming part, through the cooperation of injection moulding hole and glue hole, and the molten plastic can even, quick filling cavity, reduces bubble and material defect such as lack, promotes part quality, and this kind of structure design is reasonable, and the operation is simple, improves production efficiency, and reduces the scrap rate, is helpful to the realization of efficient, high -quality injection moulding production of enterprise, strengthens market competitiveness.

The application discloses a prestressed middle plate production line mold for a subway station, which comprises a fixed bottom plate, a prestressed middle plate mold fixedly connected to the upper surface of the fixed bottom plate and used for pouring concrete, a tensioning assembly and a control assembly. In order to solve the problem that common steel bar tensioning equipment may be broken due to stress mutation or material defects when stress is applied, and the mold or equipment is easily damaged by instant energy release, the tensioning assembly is designed, the inside of the tensioning assembly is provided with a buffer assembly, the buffer assembly can play a buffering role when stress is applied, can absorb impact energy when overload occurs, and the control assembly is further designed, sliding friction is triggered under over-limit tension through the control assembly, the maximum transmission force is limited, and equipment damage caused by sudden breakage is avoided.

Aspects of the present application relate to the automated characterization of material defects in paved surfaces. More specifically, in accordance with one or more aspects of the present application, a location processing service may be utilized to utilized machine-learned algorithms in the characterization of material defects in paved surfaces. The characterizations are illustratively associated with a hierarchical set of categories. The location processing service can further utilize machine learned algorithms to identify one or more remediation recommendations corresponding to the associated characterization of the paved surface.

The utility model relates to a pulse type material defect detection device, in particular to a lens focal length detector for the pulse type material defect detection device, which comprises a support seat, a movable seat, a lens main body, a diaphragm, a collimator and an observation whiteboard, the top of the support seat is connected with the movable seat in a sliding manner, and the top of the movable seat is provided with the lens main body; a diaphragm is arranged on the outer side of the lens body. When the lens body moves, the connecting block is driven to move, so that the clamping block is driven to move, the inserting block is not prone to shaking through the rubber block, meanwhile, the placing stability of the supporting base can be enhanced through the balance weight base and the anti-skid pad at the bottom of the balance weight base, and in the focal length measuring process, the inserting plate can be inserted into the U-shaped block at the top of the lens body, so that the focal length is measured. The top of the U-shaped block and the top of the observation whiteboard are located at the same height, so that a vernier caliper can be conveniently used for measuring focal length.

The invention provides a metal material defect detection method. The method comprises the following steps: acquiring a 2D grey-scale map and a 3D depth map of a to-be-detected metal material; analyzing the 2D grey-scale map by using a preset dichotomy model, and determining whether the metal material to be detected has surface defects or not; responding to the condition that the metal material to be detected has the surface defect, analyzing the 2D grey-scale map by using a preset multi-classification model, and determining the type of the surface defect of the metal material to be detected; and under the condition that a preset condition is met, analyzing the 2D grey-scale map and the 3D depth map by using a preset fusion model, and determining whether the to-be-detected metal material has a deformation defect or not. The invention further provides metal material defect detection equipment, a computer readable medium and a computer program product.

The utility model relates to a medicine packing material defect detecting, sorting and material collecting device, and relates to the field of medical equipment, the medicine packing material defect detecting, sorting and material collecting device comprises a first conveyor belt and a second conveyor belt, the first conveyor belt and the second conveyor belt are provided with separation blades at intervals, and medicine boxes are placed between the adjacent separation blades; infrared sensors used for detecting whether box tongues stretch out of the conveying belts are arranged on the two sides of the first conveying belt in the width direction, the first conveying belt and the second conveying belt are each provided with a plane detection assembly used for detecting the large end faces of medicine boxes, a box turning assembly is arranged between the first conveying belt and the second conveying belt, and a discharging assembly is arranged at the tail end of the second conveying belt; the discharging assembly is provided with a waste removing assembly used for removing damaged box bodies. The detection device has the effects of improving the detection accuracy and the detection efficiency of the defects of the medicinal materials packed in the box, and further removing the defective box.

1. Name of the product in this design: Intelligent Detection Equipment for Roll Material Defects. 2. Purpose of this design: For use in intelligent detection equipment for defects in rolled materials. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model.