31results about How to "Accurate defect location" patented technology

The invention relates to a device and a method for detecting carbon fiber composite material truss bonding defects by an ultrasonic phased array. The device comprises an ultrasonic phased array detector, a control computer, an ultrasonic phased array probe, a coupling wedge block, a displacement encoder, a coupling agent and a comparison specimen, wherein the ultrasonic phased array detector is connected with the control computer; the ultrasonic phased array probe is connected with the ultrasonic phased array detector; the probe end of the ultrasonic phased array probe is fixedly arranged on the coupling wedge block; the displacement encoder is connected with the ultrasonic phased array detector; the displacement encoder is fixedly connected with the coupling wedge block. The detection method comprises the following steps of connecting the detection device; setting the detection parameters; calibrating the ultrasonic phased array detector; adjusting scanning sensitivity; implementing detection; obtaining and recording the detection data. The device and the method have the advantages that the carbon fiber composite material truss bonding part with complicated space structure is detected, the better flexibility in use is realized, and the detection efficiency and the visual degree of detection results are improved.

The invention discloses a corrected full-focus imaging method for anisotropy weld seam defect array detection and belongs to the field of nondestructive testing. The method comprises the steps of processing full-matrix data received by a one-dimensional linear array sensor of a phased array, taking material anisotropy into consideration, calculating out group velocity of ultrasonic waves in an anisotropy medium, then utilizing a ray tracing algorithm based on a Fermat principle to calculate out propagation time of the ultrasonic waves in the anisotropy medium and finally achieving full-focus imaging of anisotropy weld seams. The method has the advantages that weld seam anisotropy is taken into consideration, the high-operation-efficiency ray tracing method based on the Fermat principle and the full-focus imaging method are combined, the problem that general full-focus imaging has inaccuracy in locating defects in the anisotropy medium is solved, and meanwhile, detection precision of the phased array in the anisotropy medium is improved.

The invention relates to an irregular workpiece detection method based on machine vision, and the method comprises the steps: obtaining an irregular workpiece image, carrying out the edge detection, converting the edge of the workpiece image into a polar coordinate system, employing the intersection of the polar coordinate system in the horizontal direction of different theta connecting lines as a new two-dimensional plane through Hough transformation, according to the information gain of all connecting line intersection points in the two-dimensional plane, judging the intersection points to obtain missing detection points, obtaining a missing detection area according to the missing detection points, performing bubble detection on the workpiece, if the missing detection area does not have bubbles, determining that the workpiece does not have defects, and if the missing detection area has bubbles, obtaining an edge area of the bubbles in the missing detection area; and according to the volume and position changes of all bubbles in the adjacent frames and the single-frame image are analyzed according to the marginal areas of the bubbles, determining the accurate position of the missing detection defect, so the defect position of the irregular detection workpiece is more accurately positioned based on machine vision and comprehensive analysis, the detection precision is high, and the practicability is high.

An embodiment of the invention provides a glass detection device used for solving the technical problem of absence of an effective detection method for inside of an original glass substrate. The glass detection device comprises a microwave-transparent carrier, a microwave transmitting antenna and a microwave receiving antenna, wherein the microwave transmitting antenna and the microwave receiving antenna are located on two sides of the microwave-transparent carrier respectively, and opening surfaces of the microwave transmitting antenna and the microwave receiving antenna are opposite. A detection structure for glass inside is formed by the glass detection device, and a defect position of the original glass substrate can be detected accurately through combination with a scanning position of microwave beams. The glass detection device provided by the embodiment of the invention is high in detection speed and has certain detect type distinguishing performance, and a defect in the glass is positioned accurately. The embodiment of the invention further provides a glass detection method.

The invention discloses a new energy lithium battery surface defect detection method based on adaptive deep learning. The method comprises the following steps: carrying out nonlinear mapping on a lithium battery surface grayscale image; transforming the decoupled irradiation component and reflection component to a frequency domain; performing filtering, inverse Fourier transform and exponential transform on the frequency domain data to obtain a reconstructed lithium battery image; based on morphological processing and background differencing, enhancing gray scale response at the defect; carrying out image segmentation and connected domain analysis and screening processing, and taking a result as a labeled image; designing an operator to simulate illumination details, and carrying out sample enhancement operation on the surface grayscale image of the lithium battery; training a deep convolutional neural network based on the enhanced sample image set and the labeled image; and achievinglithium battery surface defect detection based on the trained network. By utilizing the method, the detection efficiency can be improved and the false detection rate can be reduced in a lithium battery surface defect detection scene.

The invention provides a reference block for alloy steel bar ultrasonic flaw detection and a using method of the reference block. The reference block is a cylindrical matrix and comprises three comparison sections with the same diameter in the axial direction of the cylindrical matrix; a straight part is arranged on the circumferential wall of each comparison section; the circumferential wall of each comparison section is composed of the corresponding straight part and an arc part which are connected head to end in the circumferential direction of the circumferential wall; each straight part is a plane axially parallel to the cylindrical matrix; each arc part is a part of the circumferential surface sharing the axis with the matrix; flat bottom holes are formed in the planes of the straight parts; and the axes of the flat bottom holes are perpendicular to the planes of the straight parts, and intersect with the axis of the matrix. The reference block and a to-be-detected bar are similar in material and similar or the same in size, the structure is simple, the preparation cost is low, and flaw detection results are more accurate; and by arranging the three comparison sections for defect positioning, defect positioning is more accurate, the yield of steel is greatly increased, the detection cost is saved, and important significance for defect detection of the bar is achieved.

The invention discloses a method and a device for enhancing defect positioning based on program dependence. According to the method, statement data dependency relationships of a source code are analyzed, a statement defect suspicious degree table obtained by analyzing the source code through an existing software tool is combined with the statement data dependency relationships to form an eigenvalue vector composed of N + 1 suspicious degree values, and the eigenvalue vector serves as a sample of each statement of the source code and is input into a support vector machine for machine analysis, so that an optimized defect suspicious degree list is obtained. Therefore, a positioning result is enhanced, and defect positioning is more accurate.

The invention relates to the field of transportation equipment manufacturing, and particularly discloses a CMT welding defect identification method based on sound signal multi-feature fusion, and the method comprises the steps: taking a CMT welding defect as an analysis target in the analysis of a welding process signal, combining the existing data, and considering various conditions of faults and defects; adopting a plurality of mainstream signal analysis methods to carry out feature extraction such as wavelet transform, wavelet packet decomposition, Mel spectrum and short-time Fourier transform on sound signals; after feature extraction, fusing a plurality of signal features, and adopting a plurality of neural networks to carry out identification analysis on defect parts. Effective technical support is provided for analyzing welding acoustic signals so as to position defects, and the purpose of accurately positioning defect positions and defect types is achieved.