Small-diameter tube DR detection method

Abstract

The invention discloses a small-diameter tube DR detection method, and relates to the technical field of automatic nondestructive testing, and the method comprises the following steps: S1, an information management system judges whether DR image quality needs to be confirmed, if yes, the step S2 is entered, and if not, the step S3 is entered; s2, the information management system carries out DR image quality confirmation; s3, the conveyed small-diameter pipe is positioned, the small-diameter pipe is clamped after the small-diameter pipe is positioned in place, and grating opening and closing adjustment is conducted; s4, an image acquisition module acquires a DR image of the clamped small-diameter pipe welded junction and sends the DR image to an information management system, and the information management system automatically evaluates the DR image of the small-diameter pipe welded junction and judges whether defects exist or not; and S5, alarming and marking the defective small-diameter pipes, and sorting qualified small-diameter pipes and defective small-diameter pipes. Small-diameter tube clamping, small-diameter tube rotation, grating opening and closing, image quality indicator placement, image quality measurement and defect evaluation are automatically controlled, and full automation of small-diameter tube flaw detection operation is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of automated nondestructive testing, and more particularly to a DR testing method for small-diameter pipes. Background Art

[0002] Welding is a key process in the manufacturing of major power generation equipment, and its quality determines the safety and reliability of power generation equipment. According to external quality feedback over the years, more than 80% of the quality problems of power plant boilers are caused by weld quality. Therefore, effectively improving the welding quality of power plant boiler enterprises is very important to ensure production safety and help enterprises improve quality and efficiency.

[0003] In the petrochemical, energy and power, aerospace and other industries, small-diameter pipes (specifically pipes with a diameter of 100mm or less) are important parts of related equipment. The serpentine pipe is a small-diameter pipe and is a core component of power station boilers. The operating temperature is as high as 677℃ and the working pressure is 40MPa.

[0004] In the prior art, when X-ray imaging defect detection is performed on the serpentine and straight pipe welds of boiler high-temperature components, a DR imaging detection system (referred to as industrial television RTV in the industry) is required. Currently, the industry RTV system is a semi-automatic system that mainly performs detection through manual control, which has the following problems: 1. The semi-automatic system uses manual weld finding to find the weld of the small diameter pipe, and then performs DR inspection on the weld of the small diameter pipe. In the manual weld finding method, people's attention may be distracted, resulting in the omission of some welds with small differences from the parent material, thus causing quality problems.

[0005] 2. In the DR imaging detection system, when evaluating defects in DR images of small-diameter pipe welds, the signal-to-noise ratio, resolution and contrast of DR images are low, which is not conducive to AI algorithm evaluation and manual evaluation.

[0006] 3. Manual control of small-diameter tube clamping and rotation, manual control of grating opening and closing, manual control of image quality meter placement and image quality measurement, manual image review and defect marking, low detection efficiency. Summary of the invention

[0007] In order to overcome the defects in the prior art, the present invention discloses a small-diameter pipe DR detection method. The purpose of the present invention is to solve the problems existing in the manual control detection in the prior art.

[0008] In order to achieve the above objectives, the technical solution adopted by the present invention is: A small-diameter pipe DR detection method comprises the following steps: 1. Image quality confirmation and judgment S1, the information management system determines whether it is necessary to confirm the DR image quality, if so, it proceeds to step S2, if not, it proceeds to step S3; 2. Image Quality Confirmation S2, the information management system confirms the quality of the DR image, and enters step S3 after the quality confirmation is qualified; Preferably, step S2 includes: the information management system sets acquisition parameters, and performs single-wire, double-wire, and signal-to-noise ratio quality confirmation on the DR image according to the set acquisition parameters; if the quality is qualified, the image is stored and the process proceeds to step S3; if the quality is unqualified, the acquisition parameters are adjusted and the quality is confirmed again; Among them, the quality confirmation of single wire and double wire includes: S21, the information management system sends an image quality meter placement signal to the controller, including a dual-wire image quality meter placement signal and / or a single-wire image quality meter placement signal; S22, the controller controls the double-wire placement mechanism and / or the single-wire placement mechanism to move according to the received image quality meter placement signal, and drives the double-wire image quality meter and / or the single-wire image quality meter to move to between the small-diameter tube and the X-ray system for placement; S23, the image acquisition module acquires the single-wire image and the double-wire image of the small-diameter tube DR detection, and sends the acquired single-wire image and the double-wire image to the information management system; S24. The information management system confirms the sensitivity and resolution of the small-diameter tube DR image based on the single-wire image and the double-wire image.

[0009] 3. Small diameter tube positioning and grating opening and closing adjustment S3, positioning the small-diameter tube to be transported, clamping the small-diameter tube after positioning, and adjusting the grating opening and closing; Preferably, step S3 includes: When the small-diameter pipe is transported on the pipe conveying system, the visual identification of the outdoor weld of the lead room is carried out to reduce the speed once, and the small-diameter pipe is transported slowly after the speed reduction; Scan the QR code information of the small-diameter tube, and send the scanned QR code information to the information management system. The information management system extracts the small-diameter tube weld information according to the QR code information, and performs grating opening and closing adjustment according to the extracted small-diameter tube weld information; The small-diameter pipes that are transported slowly are visually identified at the welds in the lead room and then slowed down a second time. The small-diameter pipes are stopped and clamped in the area to be inspected.

[0010] 1. Small diameter pipe positioning The small diameter pipe positioning in step S3 includes the following steps: 1) Video acquisition A1. When the small-diameter pipe is transported on the pipe transport system, the outdoor surveillance camera and the indoor surveillance camera respectively collect the outdoor surveillance video and the indoor surveillance video of the transported small-diameter pipe; In the present invention, the pipe conveying system is used to convey the small-diameter pipes from outside the lead room to inside the lead room for DR testing.

[0011] 2) Welding joint detection A2. The information management system uses its weld detection model to detect the small-diameter pipe weld area in the outdoor surveillance video and the indoor surveillance video, and determines whether the weld area reaches the determination area; Preferably, in step A2, the weld detection model is trained based on the YOLOX target detection algorithm.

[0012] Preferably, in step A2, the determination area includes an outdoor determination area and an indoor determination area; For the weld area detected by the outdoor monitoring video, determine whether the weld area reaches the outdoor determination area, and if so, proceed to step A3; For the weld area detected by the indoor surveillance video, determine whether the weld area reaches the indoor determination area, and enter step A4 if it reaches the indoor determination area.

[0013] Preferably, step A2 comprises: A21. In each frame of the outdoor surveillance video and the indoor surveillance video, an outdoor determination area and an indoor determination area are defined respectively, and trip wires are set at equal distances in the outdoor determination area and the indoor determination area; A22, detecting each frame of the outdoor surveillance video and the indoor surveillance video, and identifying the weld area in each frame of the surveillance video; A23, select the midpoint of the weld area as the trajectory point, and track the trajectory points of the latest N frames of the outdoor surveillance video or the indoor surveillance video; Preferably, in step A23, the deepAort algorithm is used to track the trajectory points of the latest 15 frames.

[0014] A24, determining whether the trajectory points of the latest N frames are all located in the outdoor determination area or the indoor determination area; If not, it means the weld has not reached the position; If so, take the trajectory points of the current frame and the trajectory points of the Nth frame before, and determine whether the weld area reaches the outdoor determination area or the indoor determination area based on the trajectory points of the current frame and the trajectory points of the Nth frame before.

[0015] Preferably, step A24 further comprises: For the outdoor judgment area, if the current frame trajectory point is above the trip wire, and the previous N frame trajectory point is below the trip wire, it means that the weld has reached the outdoor judgment area, the small-diameter pipe needs to be transmitted at a reduced speed, and enter step A3; For the outdoor judgment area, if the trajectory point of the current frame is below the trip wire, and the trajectory point of the previous N frames is above the trip wire, it means that the small-diameter pipe is being repaired and is being transported in the opposite direction. The transmission speed of the small-diameter pipe will not be reduced; For the indoor judgment area, if the current frame trajectory point is on the right side of the trip wire, and the previous N-th frame trajectory point is on the left side of the trip wire, it means that the weld has reached the indoor judgment area, and the small-diameter pipe needs to stop transmission and start clamping, and enter step A4; For the indoor judgment area, if the trajectory point of the current frame is on the left side of the trip wire, and the trajectory point of the previous N frames is on the right side of the trip wire, it means that the small-diameter pipe is being repaired and is being transmitted in the opposite direction, and the transmission speed of the small-diameter pipe is not reduced.

[0016] 3) One-time identification and speed reduction A3. When it is determined that the weld area in the outdoor monitoring video reaches the outdoor determination area, the information management system sends a speed reduction instruction to the controller, and the controller controls the pipe transmission drive component of the pipe conveying system to reduce speed according to the speed reduction instruction; 4) Secondary identification and positioning stop A4. When it is determined that the weld area in the indoor monitoring video reaches the indoor judgment area, the information management system sends a stop pipe feeding and start pipe clamping instruction to the controller. The controller controls the pipe transmission drive of the pipe conveying system to stop pipe feeding and controls the pipe clamping drive of the pipe clamping system to clamp the small-diameter pipe according to the stop pipe feeding and start pipe clamping instructions, and then stops pipe feeding and clamps the pipe to position the weld.

[0017] In the present invention, outdoor refers to the outside of the flaw detection room. Indoor refers to the inside of the flaw detection room, where an X-ray machine, a X-ray machine motion mechanism, a flat panel detector, a grating, a small-diameter tube clamping and rotating mechanical structure and other mechanisms are installed to perform DR detection on the small-diameter tube.

[0018] In the present invention, outdoor monitoring video is collected, and it is determined whether the weld area in the outdoor monitoring video reaches the outdoor judgment area. After reaching the outdoor judgment area, the pipe transmission drive component of the pipe conveying system is controlled to slow down. This arrangement is because: the transmission speed of small-diameter pipes on the transmission roller is faster, and a motor speed reduction instruction is required before the motor stop instruction arrives, otherwise the weld positioning error will be large.

[0019] In the present invention, indoor monitoring video is collected, and it is determined whether the weld area in the indoor monitoring video reaches the indoor judgment area. After reaching the indoor judgment area, the pipe transmission driving component of the pipe conveying system is controlled to stop feeding the pipe, and the pipe clamping driving component of the pipe clamping system is controlled to clamp the small-diameter pipe. This arrangement is because: after the small-diameter pipe is in place, the small-diameter pipe weld flaw detection needs to clamp the small-diameter pipe and rotate it 4 times. One image is taken for each rotation, and a total of 5 images are taken for defect detection.

[0020] 2. Grating opening and closing adjustment Preferably, in step S3, the grating opening and closing adjustment includes the following steps: 1) Grating point pre-adjustment B1. When detecting a small-diameter pipe of a certain diameter, the information management system sends the pre-adjustment instruction of the grating closing amount of the pipe of the corresponding diameter to the controller. The controller controls the action of the grating opening and closing motor according to the pre-adjustment instruction of the grating closing amount of the pipe, and adjusts the grating to the preset grating point; Preferably, in step B1, before the preset position of the grating is adjusted, the grating is placed at the origin and is in a fully open state.

[0021] Preferably, in step B1, the tube grating closure amount is 2 cm larger than the corresponding standard grating closure amount.

[0022] Preferably, in step B1, grating closure information of pipes with different specifications and diameters is set in the information management system.

[0023] 2) DR image acquisition B2. After the grating is adjusted to the preset grating position, the image acquisition module acquires the DR image of the small-diameter tube; 3) Gray value calculation B3, the image acquisition module sends the acquired small-diameter tube DR image to the information management system, and the information management system processes the small-diameter tube DR image to obtain the grayscale value of each pixel in the small-diameter tube DR image; Preferably, step B3 comprises the following steps: B31, the image acquisition module receives the X-ray signal transmitted through the weld, and performs photoelectric conversion and A / D conversion to generate a digital image; B32, the information management system obtains 16-bit single-channel digital images by calling the BDK of the image acquisition module; B33. The information management system reads the digital image and generates 16-bit grayscale data for each pixel, that is, the grayscale value of each pixel.

[0024] 4) Threshold comparison B4, the information management system counts the number of pixels whose grayscale values ​​are greater than the grayscale threshold in the pixel points of the small-diameter tube DR image, and compares the number of pixels with the pixel number threshold. When the number of pixels is greater than the pixel number threshold, it proceeds to step B5 to perform grating closure fine-tuning, otherwise the grating is at an appropriate point and no adjustment is performed; Preferably, in step B4, the grayscale threshold is 50,000, and the pixel quantity threshold is 70.

[0025] 5) Grating closure fine-tuning B5. The information management system sends a grating fine-tuning instruction to the controller. The controller controls the grating opening and closing motor according to the grating fine-tuning instruction to fine-tune the grating.

[0026] Preferably, step B5 comprises the following steps: B51, after the grating reaches the preset point, the controller communicates with the information management system through TCP, and the controller sends a start fine-tuning signal to the information management system; B52. After receiving the fine-tuning signal, the information management system returns a successful reception signal to the controller, and the controller starts to control the grating opening and closing motor to rotate slowly to fine-tune the grating closing. The information management system continuously repeats steps B2-B5 in real time; B53. When the number of pixels whose grayscale values ​​are greater than the grayscale threshold in step B4 is less than or equal to the pixel number threshold, the information management system sends an end adjustment signal to the controller. After receiving the signal, the controller controls the grating opening and closing motor to stop rotating, and returns a successful reception signal to the information management system, indicating that the grating has reached the appropriate position.

[0027] IV. Image Acquisition and Evaluation S4, the image acquisition module acquires the DR image of the clamped small-diameter pipe weld and sends it to the information management system, which automatically evaluates the DR image of the small-diameter pipe weld to determine whether there are defects; Preferably, step S4 comprises the following steps: S41, the image acquisition module acquires a DR image of the small-diameter pipe weld, and sends the acquired DR image of the small-diameter pipe weld to the information management system; when acquiring the DR image of the small-diameter pipe weld, the clamped small-diameter pipe is rotated N times to capture the DR image of the small-diameter pipe weld; S42. The information management system performs defect detection on the DR image of the small-diameter pipe weld to obtain a defect detection result; wherein, when performing defect detection, the DR image of the small-diameter pipe weld is first subjected to image enhancement preprocessing, and then the DR image of the small-diameter pipe weld after the image enhancement preprocessing is detected to detect the defect type and defect location of the DR image of the small-diameter pipe weld.

[0028] Preferably, the image enhancement preprocessing in step S42 comprises the following steps: S421, when no inspection workpiece is placed at the small-diameter pipe weld inspection station, collecting a plurality of DR images at the inspection station, and processing the plurality of DR images to obtain a dark field image and a correction curve; Preferably, step S421 includes: when no inspection workpiece is placed at the small-diameter pipe weld inspection station, opening the grating to the maximum position to expose the flat-panel detector, adjusting the movement of the X-ray machine head so that the X-ray machine is vertically aligned with the flat-panel detector to emit X-rays, and the flat-panel detector collects several DR images.

[0029] Preferably, step S421 includes the following steps: S4211. When no inspection workpiece is placed at the small-diameter pipe weld inspection station, a plurality of DR images with different grayscale values ​​at the inspection station are collected, and the DR image with the lowest grayscale value is used as a dark field image; Preferably, step S4211 includes: when no inspection workpiece is placed at the small-diameter pipe weld inspection station, first turn off the X-ray machine, use 10 frames of superposition and averaging to collect an image with a grayscale value of 0 as a dark field image, then turn on the X-ray machine, adjust the voltage, and use 10 frames of superposition and averaging to collect 4 DR images as bright field images when the image grayscale values ​​are 10000, 20000, 30000, and 40000, respectively.

[0030] S4212, using a plurality of DR images with different gray values, respectively, and subtracting the dark field image, to obtain a plurality of calibration reference images; S4213, calculating the image grayscale mean of each correction reference image as the standard correction value of each pixel response in the correction reference image, and obtaining a correction curve of the correction output changing with the grayscale response in different grayscale intervals.

[0031] Preferably, step S4213 includes: for each correction reference image, averaging the image grayscale as the standard correction value of each pixel response, and based on the linear relationship between grayscale response and correction output, obtaining four correction curves of correction output changing with grayscale response in the grayscale ranges of 0-10000, 10000-20000, 20000-30000, and 30000-40000, respectively.

[0032] S422, when the inspection workpiece is placed at the small-diameter pipe weld inspection station, a DR image of the small-diameter pipe weld at the inspection station is collected, and the DR image of the small-diameter pipe weld is corrected using a dark field image and a correction curve; Preferably, step S422 includes: when the inspection workpiece is placed at the small-diameter pipe weld inspection station, the DR image of the small-diameter pipe weld on the inspection station is collected as the original image, and the dark field image is subtracted from the original image to obtain a bias error elimination image, and then each pixel in the bias error elimination image is corrected using the correction curve.

[0033] Preferably, in step S422, 10 frames are superimposed and averaged to collect the DR image of the small-diameter pipe weld at the inspection station.

[0034] Preferably, in step S422, using the correction curve to correct each pixel in the bias error elimination image includes: first determining in which grayscale interval the pixel grayscale value is located, then calculating the pixel correction value based on the correction curve corresponding to the pixel grayscale value and the grayscale interval, and correcting the pixel using the correction value.

[0035] S423, performing image enhancement processing on the corrected DR image of the small-diameter pipe weld to obtain a DR evaluation image of the small-diameter pipe weld.

[0036] Preferably, step S423 includes: The guided filtering method is used to perform guided filtering and smoothing on the corrected DR image M of the small-diameter pipe weld to obtain a smoothed image N. The guided filtering filter is an Edge-preS2erving filter. Use the corrected small-diameter pipe weld DR image M to subtract the smoothed image N to obtain a detailed contour image; Multiply the detail contour image by the magnification factor a to magnify the detail contour image; The enlarged image is added to the smoothed image N to obtain the enhanced image I.

[0037] Preferably, in step S42, the defect types of the DR image of the small-diameter pipe weld include: pores, lack of fusion, lack of penetration, weld bumps, poor forming, undercuts, concave, cracks, burn-throughs, and tool marks.

[0038] 5. Marking and sorting S5. Alarm and mark defective small-diameter tubes, and sort qualified and defective small-diameter tubes.

[0039] Step S5 includes: S51. According to the review results, for the defective small-diameter pipes, alarm and mark them, and conduct manual review before transporting them to the storage rack; S52. According to the review results, the qualified small-diameter pipes are directly transported to the storage rack; S53, sorting the defective small-diameter tubes and qualified small-diameter tubes on the storage rack into qualified racks and repair racks respectively; S54. For the small-diameter tubes on the qualified material rack, upload their data; S55. The small diameter tubes on the repair rack are repaired and then transported to the tube transport system for secondary DR inspection.

[0040] Beneficial effects of the present invention: The small-diameter tube DR detection method provided by the present invention can efficiently and quickly realize the weld positioning of the transmitted workpiece to avoid the problem of missed detection. After positioning, the workpiece transportation is stopped and the small-diameter tube is clamped to realize subsequent small-diameter tube DR detection; at the same time, the frequency of manual operation by personnel is effectively reduced to prevent the occurrence of missed detection of welds.

[0041] The small-diameter tube DR detection method provided by the present invention can make the defect details of the DR image more clearly visible, can avoid a large amount of manual adjustment of the image contrast to find defects, and improve the accuracy of the computer using the AI ​​algorithm to evaluate the image. By correcting the DR image of the small-diameter tube weld, the image signal-to-noise ratio and resolution can be greatly improved; by enhancing the DR image of the small-diameter tube weld, the defect contrast can be increased, providing conditions for AI evaluation and manual determination of defects, and ensuring the quality of small-diameter tube defect detection. Compared with the image processing of the existing RTV system, the correction and enhancement post-processing results of this method can obtain a higher signal-to-noise ratio, resolution and contrast, which is more conducive to AI algorithm evaluation and manual evaluation.

[0042] The small-diameter tube DR detection method provided by the present invention automatically controls the clamping of small-diameter tubes, the rotation of small-diameter tubes, the opening and closing of gratings, the placement of image quality meters, the measurement of image quality, and the defect evaluation, thereby realizing full automation of small-diameter tube flaw detection operations and intelligent evaluation, greatly reducing the workload of workers and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flow chart of the small diameter pipe DR detection method of the present invention; Figure 2 It is a schematic diagram of outdoor weld detection of the present invention; Figure 3 A schematic diagram of indoor weld positioning of the present invention; Figure 4 Schematic diagram of hardware used in the small-diameter pipe DR detection method of the present invention; Figure 5 This is a schematic diagram of the internal hardware used in the small-diameter pipe DR detection method of the present invention. DETAILED DESCRIPTION

[0044] The concept, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and drawings to fully understand the purpose, characteristics and effects of the present invention.

[0045] Example 1 A small diameter pipe DR detection method, such as Figure 1 , Figure 4 and Figure 5 As shown, the following steps are included: S1, the information management system determines whether it is necessary to confirm the DR image quality, if so, it proceeds to step S2, if not, it proceeds to step S3; S2, the information management system confirms the quality of the DR image, and enters step S3 after the quality confirmation is qualified; S3, positioning the small-diameter tube to be transported, clamping the small-diameter tube after positioning, and adjusting the grating opening and closing; S4, the image acquisition module acquires the DR image of the clamped small-diameter pipe weld and sends it to the information management system, which automatically evaluates the DR image of the small-diameter pipe weld to determine whether there are defects; S5. Alarm and mark defective small-diameter tubes, and sort qualified and defective small-diameter tubes. Example 2 This embodiment further elaborates on step S1 based on embodiment 1. In the present invention, when performing DR inspection on small-diameter tubes, when welds with different wall thicknesses are first transilluminated, that is, when each weld joint of the small-diameter tube is first transilluminated, it is necessary to confirm the quality of the acquired image, such as sensitivity and resolution. This requires the use of an image quality meter to measure the image quality. Therefore, the present invention first determines whether image quality measurement is required.

[0046] Example 3 This embodiment further describes step S2 based on embodiment 2. Figure 1 As shown, step S2 includes: the information management system sets acquisition parameters, and confirms the quality of single-wire, double-wire, and signal-to-noise ratio of DR images based on the set acquisition parameters. If the quality is qualified, the image is stored and the process proceeds to step S3. If the quality is unqualified, the acquisition parameters are adjusted and the quality is confirmed again.

[0047] Among them, the quality confirmation of single wire and double wire includes: S21, the information management system sends an image quality meter placement signal to the controller, including a dual-wire image quality meter placement signal and / or a single-wire image quality meter placement signal; S22, the controller controls the double-wire placement mechanism and / or the single-wire placement mechanism to move according to the received image quality meter placement signal, and drives the double-wire image quality meter and / or the single-wire image quality meter to move to between the small-diameter tube and the X-ray system for placement; S23, the image acquisition module acquires the single-wire image and the double-wire image of the small-diameter tube DR detection, and sends the acquired single-wire image and the double-wire image to the information management system; S24. The information management system confirms the sensitivity and resolution of the small-diameter tube DR image based on the single-wire image and the double-wire image.

[0048] Example 4 This embodiment further describes step S3 based on embodiment 3. Figure 1 As shown, step S3 includes: When the small-diameter pipe is transported on the pipe conveying system, the visual identification of the outdoor weld of the lead room is carried out to reduce the speed once, and the small-diameter pipe is transported slowly after the speed reduction; Scan the QR code information of the small-diameter tube, and send the scanned QR code information to the information management system. The information management system extracts the small-diameter tube weld information according to the QR code information, and performs grating opening and closing adjustment according to the extracted small-diameter tube weld information; The small-diameter pipes that are transported slowly are visually identified at the welds in the lead room and then slowed down a second time. The small-diameter pipes are stopped and clamped in the area to be inspected.

[0049] Example 5 This embodiment further describes step S3 based on embodiment 4. The small-diameter pipe positioning in step S3 includes the following steps: A1. When the small-diameter pipe is transported on the pipe transport system, the outdoor surveillance camera and the indoor surveillance camera respectively collect the outdoor surveillance video and the indoor surveillance video of the transported small-diameter pipe; A2. The information management system uses its weld detection model to detect the small-diameter pipe weld area in the outdoor surveillance video and the indoor surveillance video, and determines whether the weld area reaches the determination area; A3. When it is determined that the weld area in the outdoor monitoring video reaches the outdoor determination area, the information management system sends a speed reduction instruction to the controller, and the controller controls the pipe transmission drive component of the pipe conveying system to reduce speed according to the speed reduction instruction; A4. When it is determined that the weld area in the indoor monitoring video reaches the indoor judgment area, the information management system sends a stop pipe feeding and start pipe clamping instruction to the controller. The controller controls the pipe transmission drive of the pipe conveying system to stop pipe feeding and controls the pipe clamping drive of the pipe clamping system to clamp the small-diameter pipe according to the stop pipe feeding and start pipe clamping instructions, and then stops pipe feeding and clamps the pipe to position the weld.

[0050] In this embodiment, the controller is a PLC. The main purpose of weld positioning is to achieve accurate positioning of the weld area. The technology used is to build a first recognition speed reduction and second recognition positioning stop system based on the frequency domain / image recognition algorithm to ensure the effectiveness of flaw detection area positioning. The main technology is to install cameras to monitor and identify the target area outdoors and indoors, and use deep learning technology to train the weld detection model (YOLOX target detection algorithm). When a weld is identified in the outdoor monitoring area, the information management system sends a command to the PLC through TCP / IP communication, and the PLC controls the motor to slow down once, and then identifies the weld in the indoor monitoring area. The information management system sends a command to the PLC through TCP / IP communication, and the PLC controls the motor to stop feeding and start clamping the pipe. It can efficiently and quickly realize the weld positioning of the workpiece to avoid missed detection problems. After positioning, the workpiece conveying is stopped to realize subsequent small-diameter pipe DR detection; at the same time, it effectively reduces the frequency of manual operation by personnel to prevent missed detection of welds.

[0051] In step A2, the determination area includes an outdoor determination area and an indoor determination area; For the weld area detected by the outdoor monitoring video, determine whether the weld area reaches the outdoor determination area, and if so, proceed to step A3; For the weld area detected by the indoor surveillance video, determine whether the weld area reaches the indoor determination area, and enter step A4 if it reaches the indoor determination area.

[0052] Step A2 includes: A21. In each frame of the outdoor surveillance video and the indoor surveillance video, an outdoor determination area and an indoor determination area are defined respectively, and trip wires are set at equal distances in the outdoor determination area and the indoor determination area; A22, detecting each frame of the outdoor surveillance video and the indoor surveillance video, and identifying the weld area in each frame of the surveillance video; A23, select the midpoint of the weld area as the trajectory point, and track the trajectory points of the latest N frames of the outdoor surveillance video or the indoor surveillance video; A24, determining whether the trajectory points of the latest N frames are all located in the outdoor determination area or the indoor determination area; If not, it means the weld has not reached the position; If yes, take the track points of the current frame and the track points of the Nth frame before, and judge whether the weld area reaches the outdoor judgment area or the indoor judgment area according to the track points of the current frame and the track points of the Nth frame before. For the outdoor judgment area, if the current frame trajectory point is above the trip wire, and the previous N frame trajectory point is below the trip wire, it means that the weld has reached the outdoor judgment area, the small-diameter pipe needs to be transmitted at a reduced speed, and enter step A3; For the outdoor judgment area, if the trajectory point of the current frame is below the trip wire, and the trajectory point of the previous N frames is above the trip wire, it means that the small-diameter pipe is being repaired and is being transported in the opposite direction. The transmission speed of the small-diameter pipe will not be reduced; For the indoor judgment area, if the current frame trajectory point is on the right side of the trip wire, and the previous N-th frame trajectory point is on the left side of the trip wire, it means that the weld has reached the indoor judgment area, and the small-diameter pipe needs to stop transmission and start clamping, and enter step A4; For the indoor judgment area, if the trajectory point of the current frame is on the left side of the trip wire, and the trajectory point of the previous N frames is on the right side of the trip wire, it means that the small-diameter pipe is being repaired and is being transmitted in the opposite direction, and the transmission speed of the small-diameter pipe is not reduced.

[0053] In this embodiment, the specific technology is as follows: For outdoor and indoor recognition cameras, the determination area is demarcated in their respective monitoring areas, such as Figure 2 and Figure 3 As shown in the yellow box, set a trip wire at equal distances in the yellow box, such as Figure 2 and Figure 3As shown by the blue line in the middle, the weld detection model is trained using the YOLOX algorithm. The indoor and outdoor cameras process each frame of the video stream respectively and detect the weld when the pipe is transported. Figure 2 and Figure 3 In the red detection frame, select the midpoint of the detection frame as the trajectory point, such as Figure 2 and Figure 3 The green track point in the middle uses the deepsort algorithm to track the track points of the latest 15 frames. For each frame of the video stream, it is calculated whether the track point is in the judgment area. If the track point is not in the judgment area, it means that the weld has not reached the position. If it is in the judgment area, take the track point of the current frame and the track point of the 15th frame before. For the outdoor judgment area, if the track point of the current frame is above the trip wire and the track point of the 15th frame before is below the trip wire, it means that the weld has reached the outdoor judgment area. The information management system sends a command to the PLC to slow down through TCP / IP communication. If the track point of the current frame is below the trip wire and the track point of the previous 15 frames is above it, it means that the pipe is transported in the opposite direction, which is a rework operation and the pipe does not slow down. For the indoor judgment area, if the current frame trajectory point is on the right side of the trip wire, and the previous 15 frames are on the left side of the trip wire, it means that the weld has reached the indoor judgment area. The information management system sends a command to the PLC through TCP / IP communication to stop transmission and locate the weld. If the current frame trajectory point is on the left side of the trip wire, and the previous 15 frames are on the right side, it means that the pipe is transmitted in the opposite direction, that is, it is a repair operation, and the pipe does not slow down. This realizes the detection of weld positioning.

[0054] Example 6 This embodiment further describes step S3 based on embodiment 5. In step S3, the grating opening and closing adjustment includes the following steps: B1. When detecting a small-diameter pipe of a certain diameter, the information management system sends the pre-adjustment instruction of the grating closing amount of the pipe of the corresponding diameter to the controller. The controller controls the action of the grating opening and closing motor according to the pre-adjustment instruction of the grating closing amount of the pipe, and adjusts the grating to the preset grating point; B2. After the grating is adjusted to the preset grating position, the image acquisition module acquires the DR image of the small-diameter tube; B3, the image acquisition module sends the acquired small-diameter tube DR image to the information management system, and the information management system processes the small-diameter tube DR image to obtain the grayscale value of each pixel in the small-diameter tube DR image; B4, the information management system counts the number of pixels whose grayscale values ​​are greater than the grayscale threshold in the pixel points of the small-diameter tube DR image, and compares the number of pixels with the pixel number threshold. When the number of pixels is greater than the pixel number threshold, it proceeds to step B5 to perform grating closure fine-tuning, otherwise the grating is at an appropriate point and no adjustment is performed; B5. The information management system sends a grating fine-tuning instruction to the controller. The controller controls the grating opening and closing motor according to the grating fine-tuning instruction to fine-tune the grating.

[0055] During the DR flaw detection of small-diameter tubes, it is necessary to adjust the grating opening and closing for tubes of different diameters to shield the light, so as to avoid overexposure of the edge of the captured DR image due to large X-ray transmission at the edge. This embodiment uses the above grating adjustment method to automatically adjust the grating opening and closing of tubes of different diameters to obtain a DR image with a normal transmission dose.

[0056] In step B1, before the image acquisition module acquires the DR image of the small-diameter tube, the grating is placed in a fully open state at the origin. The grating closure is mainly to block useless X-rays, and its closure amount is mainly determined by the tube diameter. Different small-diameter tube diameter specifications and corresponding grating closure amounts are recorded in the information management system. The grating closure amounts of small-diameter tubes with different tube diameter specifications recorded in this information management system are 2 cm larger than the corresponding standard grating closure amounts. This is to enable the grating to reach the standard point position from the preset point position through subsequent fine-tuning closure, so as to achieve a more accurate final grating point position. When detecting a small-diameter tube of a certain diameter, the information management system sends the grating closure amount of the tube diameter specification to the controller, and the controller controls the grating opening and closing motor to make the grating close by the corresponding amount, thereby achieving grating point pre-adjustment.

[0057] In this embodiment, the information management system is specifically R-PCE software in a computer, and the controller is a programmable logic controller PLC. R-PCE software sets the grating closure information of pipes with different pipe diameters. For example, the pipe diameters are 38.1mm, 45mm, 51mm, 54mm, 57mm, and 60mm, and the corresponding grating closures are 5cm, 7.6cm, 10cm, 11.6cm, 13.3cm, and 15cm.

[0058] In this embodiment, before the DR image is taken, the R-PCE communicates with the PLC, and the R-PCE sends a pre-adjustment instruction to the PLC. The PLC controls the rotation of the grating opening and closing motor to control the grating closing according to the pre-adjustment instruction. In this way, for a pipe of a certain diameter, the opening and closing of the grating is pre-adjusted to a relatively reasonable amount, thereby reducing the time for subsequent adjustment of the grating through dynamic image acquisition analysis and improving the adjustment efficiency.

[0059] In this embodiment, the image acquisition module is specifically a flat panel detector, which is installed under the grating and is used to receive X-rays and perform A / D conversion. The R-PCE software acquires the acquired DR image through the SDK call of the flat panel detector, wherein the flat panel detector and the computer are connected to the same local area network through a switch. The image acquisition module is controlled by the information management system.

[0060] Step B3 includes the following steps: B31, the flat panel detector receives the X-ray signal transmitted through the weld, and performs photoelectric conversion and A / D conversion to generate a digital image; B32, R-PCE software communicates with the flat panel detector and obtains 16-bit single-channel digital images (DR images) by calling the SDK of the flat panel detector. The image format is tif; B33, R-PCE software processes digital images, directly reads images, and generates 16-bit grayscale data for each pixel, that is, the grayscale value of each pixel (the grayscale value is generated by directly reading the digital image, 16-bit data, and the size range is 0-65535).

[0061] In this embodiment, the image is a single-channel 16-bit grayscale image. The built-in algorithm of the R-PCE software counts the grayscale value of each pixel according to the image data, and sets two thresholds, a grayscale threshold and a pixel number threshold. The grayscale threshold used in this system is 50,000, and the pixel number threshold is 70. When the R-PCE software recognizes that the number of pixels with a grayscale value greater than 50,000 is greater than 70, the R-PCE software communicates with the PLC, and the PLC controls the motor through the I / O to start closing the grating. During the closing process of the grating, the R-PCE software dynamically calculates the number of pixels with a grayscale value greater than 50,000. As the grating closes, the number of pixels with a grayscale value greater than 50,000 will gradually decrease.

[0062] In this embodiment, when the grayscale value of a pixel is greater than the grayscale threshold (50000), it indicates that the X-ray dose received by the pixel is too large, that is, the pixel is overexposed.

[0063] When the number of pixels with grayscale values ​​greater than the grayscale threshold (50000) is greater than the pixel number threshold (70), it indicates that more pixels are overexposed. Under normal X-ray dose conditions, this condition generally indicates that the grating is opened too much and needs to be closed.

[0064] Step B5 includes the following steps: B51, after the grating reaches the preset point, the controller communicates with the information management system through TCP, and the controller sends a start fine-tuning signal to the information management system; B52. After receiving the fine-tuning signal, the information management system returns a successful reception signal to the controller, and the controller starts to control the grating opening and closing motor to rotate slowly to fine-tune the grating closing. The information management system continuously repeats steps B2-B5 in real time; B53. When the number of pixels whose grayscale values ​​are greater than the grayscale threshold in step B4 is less than or equal to the pixel number threshold, the information management system sends an end adjustment signal to the controller. After receiving the signal, the controller controls the grating opening and closing motor to stop rotating, and returns a successful reception signal to the information management system, indicating that the grating has reached the appropriate position.

[0065] Example 7 This embodiment further describes step S4 based on embodiment 6. Step S4 includes the following steps: S41, the image acquisition module acquires a DR image of the small-diameter pipe weld, and sends the acquired DR image of the small-diameter pipe weld to the information management system; when acquiring the DR image of the small-diameter pipe weld, the clamped small-diameter pipe is rotated N times to capture the DR image of the small-diameter pipe weld; S42. The information management system performs defect detection on the DR image of the small-diameter pipe weld to obtain a defect detection result; wherein, when performing defect detection, the DR image of the small-diameter pipe weld is first subjected to image enhancement preprocessing, and then the DR image of the small-diameter pipe weld after the image enhancement preprocessing is detected to detect the defect type and defect location of the DR image of the small-diameter pipe weld.

[0066] The image enhancement preprocessing in step S42 includes the following steps: S421, when no inspection workpiece is placed at the small-diameter pipe weld inspection station, collecting a plurality of DR images at the inspection station, and processing the plurality of DR images to obtain a dark field image and a correction curve; S422, when the inspection workpiece is placed at the small-diameter pipe weld inspection station, a DR image of the small-diameter pipe weld at the inspection station is collected, and the DR image of the small-diameter pipe weld is corrected using a dark field image and a correction curve; S423, performing image enhancement processing on the corrected DR image of the small-diameter pipe weld to obtain a DR evaluation image of the small-diameter pipe weld.

[0067] Step S421 includes: when no inspection workpiece is placed at the small-diameter pipe weld inspection station, the grating is opened to the maximum position to expose the flat-panel detector, the movement of the X-ray machine head is adjusted so that the X-ray machine is vertically aligned with the flat-panel detector to emit X-rays, and the flat-panel detector collects several DR images.

[0068] In this embodiment, the collected DR image needs to be corrected first. Without placing the inspection workpiece, 5 DR images with grayscale values ​​of approximately 0, 10000, 20000, 30000, and 40000 are collected by 10-frame superposition and averaging. The image with a grayscale value of 0 is a dark field image.

[0069] Specifically, when no inspection workpiece is placed at the small-diameter pipe weld inspection station, the X-ray machine is turned off first, and an image with a grayscale value of 0 is collected as a dark field image by using 10-frame superposition and averaging. Then the X-ray machine is turned on, the voltage is adjusted, and 4 DR images are collected as bright field images by using 10-frame superposition and averaging when the image grayscale values ​​are 10000, 20000, 30000, and 40000. Five DR images with grayscale values ​​of 0, 10000, 20000, 30000, and 40000 are obtained.

[0070] Secondly, the dark field image was subtracted from the five DR images to eliminate the bias error and obtain five calibration reference images.

[0071] Finally, for each reference image, the image grayscale average is used as the standard correction value of each pixel response. For each pixel, since the grayscale response and the correction output are in a linear relationship, four correction curves showing the change of correction output with grayscale response can be obtained in the intervals of 0-10000, 10000-20000, 20000-30000, and 30000-40000 respectively.

[0072] Step S422 includes: placing the workpiece, collecting the weld DR image as the original image by superimposing and averaging 10 frames, subtracting the dark field image from the original image to eliminate the bias error, and correcting each pixel of the image after the error is eliminated. First, determine the interval of the pixel grayscale value, and then calculate the pixel correction value based on the grayscale value and the obtained correction curve.

[0073] In step S422, the signal-to-noise ratio and resolution of the corrected image are improved, and step S423 performs image enhancement to maintain the edge information of the image while increasing the contrast. The specific method is to use guided filtering, set the corrected DR image as M, and use M as the guide image. At this time, the guided filter becomes an edge-preserving filter. After filtering, the smoothed image N is obtained. In order to enhance the details and suppress the noise at the same time, the smoothed image N is subtracted from the corrected DR image itself to obtain the details and contour information of the image. The details and contours are enlarged and multiplied by the enlargement coefficient a. Finally, the smoothed image N is added to obtain the final image I after image enhancement. The specific formula is: After actual processing, the actual enhancement effect is best when a is 3. The enhanced image I is the DR evaluation image of the small-diameter pipe weld. The DR evaluation image of the small-diameter pipe weld is then used to evaluate the defects in the image. Specifically, AI algorithm evaluation and manual evaluation can be used.

[0074] In step S42, the enhanced DR image is used to detect the defect types and defect locations of the DR image. The current algorithm can detect a total of 10 types of defects, including porosity, lack of fusion, incomplete penetration, weld bead, poor forming, undercut, concave, crack, burn-through, and tool marks.

[0075] Example 8 This embodiment further describes step S5 on the basis of embodiment 7. Figure 1 As shown, step S5 includes: S51. According to the review results, for the defective small-diameter pipes, alarm and mark them, and conduct manual review before transporting them to the storage rack; S52. According to the review results, the qualified small-diameter pipes are directly transported to the storage rack; S53, sorting the defective small-diameter tubes and qualified small-diameter tubes on the storage rack into qualified racks and repair racks respectively; S54. For the small-diameter tubes on the qualified material rack, upload their data; S55. The small diameter tubes on the repair rack are repaired and then transported to the tube transport system for secondary DR inspection.

[0076] The above is a specific description of the implementation mode of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention, and these equivalents or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A small diameter pipe DR detection method, characterized in that: The following steps are involved: S1, the information management system determines whether it is necessary to confirm the DR image quality, if so, it proceeds to step S2, if not, it proceeds to step S3; S2, the information management system confirms the quality of the DR image, and enters step S3 after the quality confirmation is qualified; S3, positioning the small-diameter tube to be transported, clamping the small-diameter tube after positioning, and adjusting the grating opening and closing; S4, the image acquisition module acquires the DR image of the clamped small-diameter pipe weld and sends it to the information management system, which automatically evaluates the DR image of the small-diameter pipe weld to determine whether there are defects; S5. Alarm and mark defective small-diameter tubes, and sort qualified and defective small-diameter tubes.

2. The small diameter pipe DR detection method according to claim 1, characterized in that: Step S2 includes: the information management system sets acquisition parameters, and confirms the quality of the DR image in terms of single-wire, double-wire, and signal-to-noise ratio according to the set acquisition parameters. If the quality is acceptable, the image is stored and the process proceeds to step S3. If the quality is unacceptable, the acquisition parameters are adjusted and the quality is confirmed again. Among them, the quality confirmation of single wire and double wire includes: S21, the information management system sends an image quality meter placement signal to the controller, including a dual-wire image quality meter placement signal and / or a single-wire image quality meter placement signal; S22, the controller controls the double-wire placement mechanism and / or the single-wire placement mechanism to move according to the received image quality meter placement signal, and drives the double-wire image quality meter and / or the single-wire image quality meter to move to between the small-diameter tube and the X-ray system for placement; S23, the image acquisition module acquires the single-wire image and the double-wire image of the small-diameter tube DR detection, and sends the acquired single-wire image and the double-wire image to the information management system; S24. The information management system confirms the sensitivity and resolution of the small-diameter tube DR image based on the single-wire image and the double-wire image.

3. The small diameter pipe DR detection method according to claim 1, characterized in that: The S3 steps include: When the small-diameter pipe is transported on the pipe conveying system, the visual identification of the outdoor weld of the lead room is carried out to reduce the speed once, and the small-diameter pipe is transported slowly after the speed reduction; Scan the QR code information of the small-diameter tube, and send the scanned QR code information to the information management system. The information management system extracts the small-diameter tube weld information according to the QR code information, and performs grating opening and closing adjustment according to the extracted small-diameter tube weld information; The small-diameter pipes that are transported slowly are visually identified at the welds in the lead room and then slowed down a second time. The small-diameter pipes are stopped and clamped in the area to be inspected.

4. The small diameter pipe DR detection method according to claim 1, characterized in that: The small diameter pipe positioning in step S3 includes the following steps: A1. When the small-diameter pipe is transported on the pipe transport system, the outdoor surveillance camera and the indoor surveillance camera respectively collect the outdoor surveillance video and the indoor surveillance video of the transported small-diameter pipe; A2. The information management system uses its weld detection model to detect the small-diameter pipe weld area in the outdoor surveillance video and the indoor surveillance video, and determines whether the weld area reaches the determination area; A3. When it is determined that the weld area in the outdoor monitoring video reaches the outdoor determination area, the information management system sends a speed reduction instruction to the controller, and the controller controls the pipe transmission drive component of the pipe conveying system to reduce speed according to the speed reduction instruction; A4. When it is determined that the weld area in the indoor monitoring video reaches the indoor judgment area, the information management system sends a stop pipe feeding and start pipe clamping instruction to the controller. The controller controls the pipe transmission drive of the pipe conveying system to stop pipe feeding and controls the pipe clamping drive of the pipe clamping system to clamp the small-diameter pipe according to the stop pipe feeding and start pipe clamping instructions, and then stops pipe feeding and clamps the pipe to position the weld.

5. The small diameter pipe DR detection method according to claim 4, characterized in that: Step A2 includes: A21. In each frame of the outdoor surveillance video and the indoor surveillance video, an outdoor determination area and an indoor determination area are defined respectively, and trip wires are set at equal distances in the outdoor determination area and the indoor determination area; A22, detecting each frame of the outdoor surveillance video and the indoor surveillance video, and identifying the weld area in each frame of the surveillance video; A23, select the midpoint of the weld area as the trajectory point, and track the trajectory points of the latest N frames of the outdoor surveillance video or the indoor surveillance video; A24, determining whether the trajectory points of the latest N frames are all located in the outdoor determination area or the indoor determination area; If not, it means the weld has not reached the position; If yes, take the trajectory points of the current frame and the trajectory points of the Nth frame before, and judge whether the weld area reaches the outdoor judgment area or the indoor judgment area according to the trajectory points of the current frame and the trajectory points of the Nth frame before, including: For the outdoor judgment area, if the current frame trajectory point is above the trip wire, and the previous N frame trajectory point is below the trip wire, it means that the weld has reached the outdoor judgment area, the small-diameter pipe needs to be transmitted at a reduced speed, and enter step A3; For the outdoor judgment area, if the trajectory point of the current frame is below the trip wire, and the trajectory point of the previous N frames is above the trip wire, it means that the small-diameter pipe is being repaired and is being transported in the opposite direction. The transmission speed of the small-diameter pipe will not be reduced; For the indoor judgment area, if the current frame trajectory point is on the right side of the trip wire, and the previous N-th frame trajectory point is on the left side of the trip wire, it means that the weld has reached the indoor judgment area, and the small-diameter pipe needs to stop transmission and start clamping, and enter step A4; For the indoor judgment area, if the trajectory point of the current frame is on the left side of the trip wire, and the trajectory point of the previous N frames is on the right side of the trip wire, it means that the small-diameter pipe is being repaired and is being transmitted in the opposite direction, and the transmission speed of the small-diameter pipe is not reduced.

6. The small diameter pipe DR detection method according to claim 1, characterized in that: In step S3, the grating opening and closing adjustment includes the following steps: B1. When detecting a small-diameter pipe of a certain diameter, the information management system sends the pre-adjustment instruction of the grating closing amount of the pipe of the corresponding diameter to the controller. The controller controls the action of the grating opening and closing motor according to the pre-adjustment instruction of the grating closing amount of the pipe, and adjusts the grating to the preset grating point; B2. After the grating is adjusted to the preset grating position, the image acquisition module acquires the DR image of the small-diameter tube; B3, the image acquisition module sends the acquired small-diameter tube DR image to the information management system, and the information management system processes the small-diameter tube DR image to obtain the grayscale value of each pixel in the small-diameter tube DR image; B4, the information management system counts the number of pixels whose grayscale values ​​are greater than the grayscale threshold in the pixel points of the small-diameter tube DR image, and compares the number of pixels with the pixel number threshold. When the number of pixels is greater than the pixel number threshold, it proceeds to step B5 to perform grating closure fine-tuning, otherwise the grating is at an appropriate point and no adjustment is performed; B5. The information management system sends a grating fine-tuning instruction to the controller. The controller controls the grating opening and closing motor according to the grating fine-tuning instruction to fine-tune the grating.

7. The small diameter pipe DR detection method according to claim 1, characterized in that: The S4 step includes the following steps: S41, the image acquisition module acquires a DR image of the small-diameter pipe weld, and sends the acquired DR image of the small-diameter pipe weld to the information management system; when acquiring the DR image of the small-diameter pipe weld, the clamped small-diameter pipe is rotated N times to capture the DR image of the small-diameter pipe weld; S42. The information management system performs defect detection on the DR image of the small-diameter pipe weld to obtain a defect detection result; wherein, when performing defect detection, the DR image of the small-diameter pipe weld is first subjected to image enhancement preprocessing, and then the DR image of the small-diameter pipe weld after the image enhancement preprocessing is detected to detect the defect type and defect location of the DR image of the small-diameter pipe weld.

8. The small diameter pipe DR detection method according to claim 7, characterized in that: The image enhancement preprocessing in step S42 includes the following steps: S421, when no inspection workpiece is placed at the small-diameter pipe weld inspection station, collecting a plurality of DR images at the inspection station, and processing the plurality of DR images to obtain a dark field image and a correction curve; S422, when the inspection workpiece is placed at the small-diameter pipe weld inspection station, a DR image of the small-diameter pipe weld at the inspection station is collected, and the DR image of the small-diameter pipe weld is corrected using a dark field image and a correction curve; S423, performing image enhancement processing on the corrected DR image of the small-diameter pipe weld to obtain a DR evaluation image of the small-diameter pipe weld.

9. The small diameter pipe DR detection method according to claim 8, characterized in that: Step S423 includes: The guided filtering method is used to perform guided filtering and smoothing on the corrected DR image M of the small-diameter pipe weld to obtain a smoothed image N. The guided filtering filter is an Edge-preS2erving filter. Use the corrected small-diameter pipe weld DR image M to subtract the smoothed image N to obtain a detailed contour image; Multiply the detail contour image by the magnification factor a to magnify the detail contour image; The enlarged image is added to the smoothed image N to obtain the enhanced image I.

10. The small diameter pipe DR detection method according to claim 1, characterized in that: Step S5 includes: S51. According to the review results, for the defective small-diameter pipes, alarm and mark them, and conduct manual review before transporting them to the storage rack; S52. According to the review results, the qualified small-diameter pipes are directly transported to the storage rack; S53, sorting the defective small-diameter tubes and qualified small-diameter tubes on the storage rack into qualified racks and repair racks respectively; S54. For the small-diameter tubes on the qualified material rack, upload their data; S55. The small diameter tubes on the repair rack are repaired and then transported to the tube transport system for secondary DR inspection.

Images