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

A failure detection method and device are used for detecting defects on a conductor. The method comprises the following steps: arranging at least two output ends with equal electric potentials on the conductor to be detected; inputting constant detection current to the detection points arranged on the conductor to be detected along the preset path in sequence; detecting the output current of each output end; establishing the correspondence between the output current of the output ends and the positions of the detection points based on the position information of each detection point and the output current information of each output end; and judging whether the detection points have defects according to the correspondence. The method can accurately locate the defects and use charged particle beams as the detection current sources to avoid dimension limit of the irradiation points, thus meeting the requirement of small-dimension failure analysis.

The present invention relates to the field of inner detection on oil gas pipelines, and discloses a mileage and geospatial coordinates fitting method for pipeline body data so as to solve the technical problem that pipeline direction can not be accurately calibrated and defects can not be accurately positioned in the prior art. The method comprises: establishing an alignment database of a pipeline; after establishing the alignment database, separately adding a detection result with an inner detection mileage and an aligned data object into the alignment database; performing hard spot alignment on data objects contained in the alignment database; performing data segmentation and tension calibration; and after the hard spot alignment, implementing defect alignment of weld joints of the pipeline. The technical effect of not only accurately calibrating the pipeline direction, but also accurately positioning the defect can be achieved.

The invention relates to software quality defect detection method and system based on static analysis, belonging to the technical field of computer information safety. The detection method comprises the concrete steps as follows: firstly, inputting detected source codes, and selecting a defect mode according to the detected source codes; secondly, pre-processing the detected source codes; thirdly, carrying out control flow graph compression on merged source codes; fourthly, determining whether defects exist in the mode of an original detected program; fifthly, treating results, i.e., converting the position information of a termination status of detected source program codes to the position information of the original source codes; and sixthly, outputting, i.e., showing final determined result to users. The detection method and system can find software defects in advance, shorten software development cycle, save development cost and improve software quality, directly positions the detected program source codes, accurately positions the defects, and can improve the test efficiency and reduce false alarm rate.

The present invention is a detection method for insulator string drop defects based on sparse representation. Firstly, the image segmentation algorithm is used to segment the captured original image containing insulator strings, and background interference such as snow accumulation and power lines is eliminated, and the image is segmented into multiple Then, perform ASIFT matching between these disconnected areas and the insulators in the insulator string library, and the insulator string area is the number of matching points higher than the set threshold; then, the identified insulators Segment the insulator single disk in the string area to obtain multiple insulator small disks; finally, use the sparse representation classifier to classify and mark each insulator small disk, identify whether a single small disk has a string drop defect, and display it in the original image in the location identification. Compared with other methods, it has higher recognition accuracy and accurate defect location.

The invention discloses a method for monitoring defects of a high-temperature steam injection pipeline. An embedded probe is connected with a probe interface of a coupler; an exciting circuit is connected with an excitation source interface of the coupler; an input end of a signal conditioning circuit is connected with a signal conditioning interface of the coupler, and an output end of the signal conditioning circuit is connected with a data acquisition card interface of a computer acquisition and processing system; the excitation source inputs a pulsed excitation signal to the embedded probe through the coupler, excites ultrasonic guided-waves in the pipeline, and generates ultrasonic echoes when encountering the defects, the ultrasonic echoes are transmitted to the embedded probe and are converted into voltage signals through the embedded probe; the voltage signals are transmitted to the signal conditioning circuit to be processed through the coupler and are output to the computer acquisition and processing system which acquires, processes and displays the ultrasonic echo signals containing defect information. The embedded probe can be embedded in an insulating layer of the pipeline, and the insulating layer of the high-temperature steam injection pipeline does not need to be damaged basically, but online detection and long-term monitoring for the defects of the pipeline can be realized, and the defects of the pipeline can be simply and accurately positioned.

The invention discloses a method for detecting weld seams and weld seam defects based on deep learning. The YOLOV3 network is used to realize the detection of weld seams and / or weld seam defects; the training steps of the network: the workpiece image is frame-selected by the positioning frame for the weld seam , marking, as a training data set; use the positioning frame to frame the weld defect and mark the defect type as the training data set I; obtain the coordinate x of the positioning frame p 、y p , and the width and height dimensions w p 、h p ; Initialize the network; randomly call the input tensor a j Carry out training calculations and output the detection results; use the detection results to calculate the error function loss of the prediction results; combine the gradient descent method to adjust the weight W and the bias value b, and cycle like this to obtain a trained network; this method, for multiple welds, Simultaneous detection of various defect types, one-time measurement can realize welding seam identification and positioning and defect detection, effectively improving measurement efficiency and accuracy.

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 relates to a method for detecting inclusions in bearing steel by dual-frequency ultrasonic waves. A cylindrical bearing steel sample that has undergone quenching, tempering heat treatment and gold processing is installed on a water immersion high-frequency ultrasonic flaw detector, and a 10 MHz flat probe and The 25MHz focusing probe jointly detects the sample, and analyzes the A and C scanning images formed synchronously to determine the size, quantity and distribution of inclusions in the medium carbon bearing steel. In meeting the international high standard bearing steel testing requirements Based on this, a unique standard for judging the purity level of steel has been formed. In addition, this experimental method can accurately locate the detected inclusions, and can accurately locate the location of the inclusions, which is convenient for further research and analysis of the characteristics of the inclusions, and guides metallurgical production.

The invention relates to a method for detecting irregular workpieces based on machine vision. By acquiring images of irregular workpieces and performing edge detection, the edges of the workpiece images are converted into polar coordinates, and the polar coordinates are set in different positions by Hough transform. θ The intersection of the connecting lines in the horizontal direction is used as a new two-dimensional plane, and the missing points are obtained by judging the intersection points according to the information gain of all connecting points in the two-dimensional plane. If there are no bubbles in the inspected area, there is no defect in the workpiece. If there are bubbles in the missed inspection area, the edge area of ​​the bubbles in the missed inspection area is obtained, and the volume and sum of all bubbles in adjacent frames and single-frame images are analyzed according to the edge area of ​​the bubbles. Position change, determine the exact position of the missed detection defect, based on machine vision, comprehensive analysis, more accurate positioning of the defect position of the irregular detection workpiece, high detection accuracy and strong practicability.

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 aims at providing a post insulator flaw inspection device and a usage method thereof. The post insulator inspection device is mainly used for reducing the possibility of post insulator damage in inspection, can improve the inspection efficiency and also can be used by being mutually matched with equipment in the prior art. For achieving the purposes, the post insulator inspection device comprises three functional parts including a bearing structure, a lifting structure and a rotating structure; the bearing structure adopts a framework enclosed by two underframe transverse guards and underframe vertical guards; the lifting structure is installed on the underframe transverse guards and comprises screw rods which penetrate through the underframe transverse guards and are in threaded connection with the underframe transverse guards, the bottoms of the screw rods are fixed on supporting strips, and the tops of the screw rods are provided with rotating hand wheels; the rotating structure comprises a rotating structure body and a guiding structure body. Through the arrangement, the post insulator inspection device has the advantages of being capable of being mutually matched with the various inspection equipment in the prior art and achieving inspection under various severe environments.

The invention relates to a synchronous control system for digital rays of a circular welding seam on a pipe. In the system provided by the invention, a crawling track is fixed on the pipe from one side of the welding seam; a scanner with a ray detector is driven by a servo motor to scan along the welding seam; a magnetic induction synchronous control device is arranged outside the pipe; a magnetic induction receiver and a constant potential X ray machine which are installed on a crawler are arranged in the pipe; an industrial personnel computer is connected with a magnetic induction emitter through RS232; the magnetic induction emitter is connected with the magnetic induction receiver by emitting electromagnetic field signals and sends an exposure starting and exposure stopping command toa ray source controller PLC (Programmable Logic Controller) in the pipe; the industrial personnel computer is connected with a servo driver through an RS232 communication line; the servo driver connected with an encoder is connected with a direct current servo motor; a direct current power supply is connected with the servo driver, the direct current servo motor and the encoder and supplies electricity to the servo driver, the direct current servo motor and the encoder; one output of the PLC is connected with the input of a power supply controller; the output of the power supply controller isconnected with a ray pipe; and simultaneously, the output of the PLC is connected with the ray pipe.

The invention discloses a method for positioning defects of a T-type stringer on the basis of ultrasonic guided waves. The method comprises the following specific steps of: (S1) analyzing by the semi-analytical finite element method theory to obtain a guided-wave characteristic propagating on the T-type stringer; (S2) selecting all frequencies and modes for detection by frequency dispersion curvesand wave structures; (S3) carrying out excitation and reception of guided waves on the ends of the T-type stringer along guided-wave sensors arranged along the circumferential direction, wherein thesensors are fixed by clamps and are coupled with the surface of the stringer; (S4) using signal excitation equipment to generate guided-wave signals with the selected frequencies; (S5) determining longitudinal positions of the damages by time difference between peak values of echo signals and excitation signals according to the excitation frequency and the mode wave velocity selected every time, and determining positions of horizontal defects according to detection results of all frequencies and modes with different horizontal-defect sensitivity.

The invention aims at providing a post insulator flaw inspection device and a usage method thereof. The post insulator inspection device is mainly used for reducing the possibility of post insulator damage in inspection, can improve the inspection efficiency and also can be used by being mutually matched with equipment in the prior art. For achieving the purposes, the post insulator inspection device comprises three functional parts including a bearing structure, a lifting structure and a rotating structure; the bearing structure adopts a framework enclosed by two underframe transverse guards and underframe vertical guards; the lifting structure is installed on the underframe transverse guards and comprises screw rods which penetrate through the underframe transverse guards and are in threaded connection with the underframe transverse guards, the bottoms of the screw rods are fixed on supporting strips, and the tops of the screw rods are provided with rotating hand wheels; the rotating structure comprises a rotating structure body and a guiding structure body. Through the arrangement, the post insulator inspection device has the advantages of being capable of being mutually matched with the various inspection equipment in the prior art and achieving inspection under various severe environments.