WO2022053001A1 - 焊缝内部缺陷智能检测装置、方法及介质 - Google Patents

焊缝内部缺陷智能检测装置、方法及介质 Download PDF

Info

Publication number
WO2022053001A1
WO2022053001A1 PCT/CN2021/117548 CN2021117548W WO2022053001A1 WO 2022053001 A1 WO2022053001 A1 WO 2022053001A1 CN 2021117548 W CN2021117548 W CN 2021117548W WO 2022053001 A1 WO2022053001 A1 WO 2022053001A1
Authority
WO
WIPO (PCT)
Prior art keywords
defect
image
neural network
network model
convolutional neural
Prior art date
Application number
PCT/CN2021/117548
Other languages
English (en)
French (fr)
Inventor
刘骁佳
戴铮
刘欢
周鹏飞
王飞
王英伟
洪海波
危荃
Original Assignee
上海航天精密机械研究所
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海航天精密机械研究所 filed Critical 上海航天精密机械研究所
Publication of WO2022053001A1 publication Critical patent/WO2022053001A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
    • G01N23/02—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material
    • G01N23/04—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by transmitting the radiation through the material and forming images of the material
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/03—Investigating materials by wave or particle radiation by transmission
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/10—Different kinds of radiation or particles
    • G01N2223/101—Different kinds of radiation or particles electromagnetic radiation
    • G01N2223/1016—X-ray
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/401—Imaging image processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/629—Specific applications or type of materials welds, bonds, sealing compounds
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/646—Specific applications or type of materials flaws, defects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10116—X-ray image

Definitions

  • the invention relates to the technical field of intelligent detection, in particular, to an intelligent detection device, method and medium for internal defects of welds.
  • the inspection personnel formulate the inspection process to realize the welding seam inspection.
  • the layout of the inspection optical path depends heavily on the inspection personnel's knowledge reserve and experience, and the inspection image evaluation depends on the inspector. not tall.
  • Patent document CN107748200B (application number: CN201710712559.0) discloses a piezoelectric array flexible sensor and a detection method for detecting weld seam defects based on characteristic guided waves.
  • the sensor is composed of a plurality of piezoelectric units, which are arranged on a flexible substrate; each piezoelectric unit is covered with a damping block, surrounded by sound-absorbing materials, and the sensor shell is packaged with a flexible protective film; all piezoelectric units are connected in series with a logic After switch and delay, connect in parallel to the positive bus.
  • Piezoelectric units are divided into three categories, which excite three different modes of guided waves respectively, and have different degrees of sensitivity to different types of defects to achieve complementarity.
  • the sensor selects different piezoelectric array detection methods through logic switches, and adapts to the welding seam detection requirements of different curvature surfaces and structures; the delay device adjusts the excitation time difference to realize the synthesis and focusing of the sound beam.
  • the purpose of the present invention is to provide an intelligent detection device, method and medium for internal defects of welds.
  • An intelligent detection device for welding internal defects includes: an X-ray tube, an imaging board, an optical path simulation and control unit, and a cloud platform server;
  • the optical path simulation and control unit selects the transillumination optical path according to the shape of the weld, and adjusts the positions of the X-ray tube and the imaging plate according to the selected transillumination optical path, so that the weld is located at the preset position between the X-ray tube and the imaging plate; X After the ray transmits the weld, it is imaged on the imaging plate to obtain the X-ray image, that is, the original grayscale image of the weld, and the image is pushed to the cloud platform server.
  • the preset position refers to:
  • the imaging plate is located in the focal plane where the focal point of the radiation emitted by the X-ray tube is located.
  • the optical path simulation and control unit selects the optimal transillumination optical path according to the shape of the weld, and according to the optimal penetration Illuminate the light path, adjust the position of the X-ray tube and the imaging plate, so that the welding seam is at the preset position between the X-ray tube and the imaging plate; stitch the original grayscale image, and push the image to the cloud platform server;
  • the cloud platform server preprocesses the original grayscale image of the weld, so that the contrast of the original grayscale image meets the requirements, and the preprocessed image is obtained; the preprocessed image is input into the convolutional neural network model CNN for defect screening, Determine whether the preprocessed image contains defects;
  • Extract the image in the minimum block diagram after defect location input the deep learning neural network model DNN, classify the defect, and get the type of defect.
  • the original grayscale image of the weld is preprocessed, and the preprocessing method includes: image enhancement, non-linear image change, filtering and noise reduction, and image sharpening;
  • the convolutional neural network model CNN is pre-trained, and the specific training method is as follows:
  • the training image is the preprocessed image of the original grayscale image of the weld, and the image is pre-marked with or without defects to form a label; the labels are divided into defective and non-defective labels;
  • the convolutional neural network model CNN is trained to obtain a trained convolutional neural network model CNN, that is, the parameters in the convolutional neural network model CNN have been optimized.
  • the trained convolutional neural network model CNN can output a label, and judge whether the weld is defective according to the label, so as to realize defect screening.
  • the minimum block diagram of the location of the defect refers to: a rectangular frame composed of a set of parallel lines tangent to the longest diameter of the defect and a set of parallel lines perpendicular to it.
  • the convolutional neural network model RCNN with the region of interest needs to be pre-trained, and the training method is as follows:
  • the optimization method is to train the convolutional neural network model RCNN with the region of interest, and obtain the trained RCNN model with the region of interest, that is, the parameters in the convolutional neural network model RCNN with the region of interest have been processed. optimization.
  • the trained convolutional neural network model RCNN with a region of interest can output the minimum block diagram of the location of the defect, and realize the defect location according to the minimum block diagram of the location of the defect.
  • the deep learning neural network model DNN needs to be pre-trained, and the training method is as follows:
  • the steps of any one of the above-mentioned methods for intelligently detecting internal defects of a weld seam are implemented.
  • the present invention has the following beneficial effects:
  • the present invention realizes the confirmation of the optimal detection optical path by adopting the optical path simulation and control module, instead of the optical path arrangement determined by the testing personnel relying on experience, to obtain the optimal image and improve the image accuracy and sensitivity.
  • the present invention uses the cloud platform server to perform intelligent analysis of digital ray images, and through cloud services, can effectively collect and summarize the gradual quality information and internal defects of different products in the inspection process, and improve data support for design and production process optimization. , and ultimately improve the quality of the product
  • the present invention analyzes digital ray images and intelligently interprets the results through the computer deep learning method, partially or completely replaces the manual film evaluation process, effectively reduces the manual detection time, and avoids human errors under the premise of ensuring the accuracy of defect recognition. , to improve the work efficiency of weld quality inspection.
  • the present invention uses the convolutional neural network model CNN to screen digital ray image defects.
  • This method can effectively identify the macroscopic information and microscopic information in the image, and can upgrade and optimize the model with the accumulation of data, so as to iterate for the defect screening algorithm. Provide support.
  • the present invention uses the convolutional neural network model RCNN with the region of interest to locate defects in digital ray images. This method can effectively identify the minimum block diagram of defects and provide support for subsequent defect size measurement for defect rating.
  • Fig. 1 is the schematic block diagram of the intelligent defect detection method of welding seam digital radiographic image according to the present invention
  • Fig. 2 is a schematic diagram of an intelligent detection device for internal defects of welds according to the present invention
  • FIG. 3 is a schematic diagram of a welding seam digital radiographic image defect screening algorithm according to the present invention.
  • FIG. 4 is a schematic diagram of the defect location algorithm of the digital radiographic image of the weld according to the present invention.
  • the invention is mainly applied to the welding seam inspection of complex structural parts, effectively improves inspection quality and inspection consistency, improves the accuracy and efficiency of inspection image evaluation, and finally improves the welding seam quality. It provides the basis for the digitalization and intelligent application of production processes.
  • Fig. 1 is a schematic block diagram of the intelligent defect detection method for welding seam digital radiographic image according to the present invention. Defect 1, 7 - Defect 2, 8 - Defect 3, 9 - Qualified, 10 - Rework Repair, 11 - Concession Acceptance, 12 - Scrap.
  • Fig. 2 is a schematic diagram of the intelligent detection device for welding internal defects of the present invention. In Fig. 2, 1-optical path simulation and control unit, 2-X-ray tube, 3-imaging board, and 4-cloud platform.
  • Fig. 3 is a schematic diagram of the defect screening algorithm of the digital radiographic image of the weld according to the present invention. In Fig.
  • Fig. 4 is a schematic diagram of the welding seam digital radiographic image defect location algorithm of the present invention.
  • An intelligent detection device for welding internal defects of the present invention includes: an X-ray tube, an imaging board, an optical path simulation and control unit, and a cloud platform server; as shown in FIG. 2 ;
  • the optical path simulation and control unit can optimize the optimal transillumination optical path through the built-in simulation module according to the topographical features of the weld or the 3D model, that is, the X-rays are emitted from the ray tube, perpendicular to the surface of the weld or its sectional plane to transmit the weld to the imaging
  • the X-rays are emitted from the ray tube, perpendicular to the surface of the weld or its sectional plane to transmit the weld to the imaging
  • the cloud platform server preprocesses the original grayscale image of the weld, so that the contrast of the original grayscale image meets the requirements, and the preprocessed image is obtained; the preprocessed image is input into the convolutional neural network model CNN for defect screening, Determine whether the preprocessed image contains defects.
  • the cloud platform server can package and integrate defect intelligent detection methods, and can also be deployed on the Internet to output cloud services; it can effectively collect and summarize different products in the inspection process, and form weld digital ray image data sets of different products, which is the basis for defect intelligence. The development of detection methods provides the basis.
  • the image judged to contain defects is input into the convolutional neural network model RCNN with the region of interest, the defects in the defective images are located, and the minimum block diagram of the location of the defect is marked to realize the defect localization.
  • Extract the image in the minimum block diagram after defect location input the deep learning neural network model DNN, classify the defect, and get the type of defect.
  • the imaging plate is located at the focal point of the X-ray tube radiation.
  • the preprocessing methods include but are not limited to: image enhancement, image nonlinear change, filter noise reduction, image sharpening, and the like.
  • the preprocessing methods include but are not limited to: image enhancement, filtering and noise reduction, and image smoothing.
  • the preprocessing methods include but are not limited to: image enhancement, non-linear image change, filtering and noise reduction, wavelet transform, and the like.
  • the contrast requirement of the original grayscale image is preferably as follows: the grayscale difference of four adjacent pixel points of one pixel point meets the minimum discrimination threshold requirement of the detection threshold.
  • Defects preferably include porosity, slag inclusion, and incomplete penetration.
  • the convolutional neural network model CNN is pre-trained, and the preferred training method is as follows:
  • the training image is the preprocessed image of the original grayscale image of the weld, and mark the image with or without defects in advance to form a label; the label is divided into defective and non-defective labels;
  • the trained convolutional neural network model CNN is obtained, that is, the parameters in the convolutional neural network model CNN have been optimized.
  • the structure, objective function, and model parameters of the convolutional neural network model CNN can be optimized in various combinations for training and testing.
  • the structure of CNN can also choose network structures such as AlexNet and ResNet; the objective function
  • parameters such as learning rate and regular term can also be added to form a relatively complex objective function;
  • model parameter optimization can also choose stochastic gradient descent, momentum gradient descent, and mini-batch gradient descent.
  • the trained convolutional neural network model CNN can output the label, judge whether the weld is defective according to the label, and realize defect screening.
  • the convolutional neural network model RCNN with regions of interest needs to be pre-trained.
  • the preferred training method is as follows:
  • the convolutional neural network model RCNN is trained, as shown in Figure 4, the candidate frame is extracted from the input image, the candidate frame is mapped to the feature map ROI by the method of extracting the feature map by CNN, and then the ROI is adjusted to a fixed size by ROI pooling, Classification and regression are performed after obtaining ROI features.
  • the trained convolutional neural network model RCNN with the region of interest is obtained, that is, the parameters in the convolutional neural network model RCNN with the region of interest have been optimized.
  • the structure, objective function, and model parameters of the convolutional neural network model RCNN can be combined for training and testing.
  • the structure of RCNN can also choose SDD and other network structures;
  • parameters such as learning rate and regular term can also be added to form a relatively complex objective function; in addition to the gradient descent method for model parameter optimization, stochastic gradient descent, momentum gradient descent, and mini-batch gradient descent can also be selected.
  • stochastic gradient descent, momentum gradient descent, and mini-batch gradient descent can also be selected.
  • you can choose various methods to combine, and choose a combination with good effect, such as high accuracy, low false detection rate, fast training speed, etc., as parameters to train the convolutional neural network model RCNN.
  • the trained convolutional neural network model RCNN with a region of interest is preferably able to output the smallest block diagram of the location of the defect, and realize the defect location according to the smallest block diagram of the location of the defect.
  • the deep learning neural network model DNN needs to be pre-trained.
  • the preferred training method is as follows:
  • the structure, objective function, and model parameters of the convolutional neural network model DNN can be combined for training and testing.
  • the structure of the DNN can also choose VGG, ResNet and other network structures;
  • parameters such as learning rate and regular term can also be added to form a relatively complex objective function;
  • model parameter optimization can also choose stochastic gradient descent, momentum gradient descent, and mini-batch gradient descent.
  • the deep learning neural network model DNN can output the label with the defect type, and realize the defect classification according to the label with the defect type.
  • the classified defects can also be graded to determine whether their defect grades meet the pre-input patterns of different grades of the same type of defects, and output the detection results;
  • the present invention performs preprocessing to achieve a further solution for improving defect contrast as follows: introducing an optimization algorithm to find a preprocessing combination that maximizes defect contrast.
  • the present invention sets the contrast requirement of the original grayscale image, and a further solution for realizing the improvement of the image contrast is: adjusting the X-ray irradiation intensity according to the size and material of the weld to be inspected.
  • the convolutional neural network model CNN is trained, and the further scheme for realizing the improvement of defect screening is: selecting the structure of the residual network ResNet as the structure of the volume and the neural network model CNN for training.
  • the convolutional neural network model RCNN with the region of interest is trained, and the further scheme for realizing the improvement of defect location is: selecting the structure of the Faster R-CNN model as the structure of the volume with the region of interest and the neural network model RCNN to carry out the training. Training.
  • the deep learning neural network model DNN of the present invention is trained, and the further scheme for realizing the improvement of defect classification is: optimizing the learning rate and the regular term part in the objective function of the deep learning neural network model DNN
  • the present invention can also carry out defect ratings for the classified defects, judge whether the defect grades meet the inspection standards, and output the inspection results.
  • the preferred solution is:
  • the DNN network is used to classify the classified defects, and the defects are rated. Specifically, the images to be rated are input into the trained network, and the labels representing the defect levels are output. The judgment is based on evaluating whether it meets the previous DNN network. Patterns of different levels of the same defect entered by the trainer.
  • a further scheme for realizing the improvement of the device index by the present invention is: a further scheme for realizing the reduction of the missed judgment rate of intelligent film evaluation is to write the missed judgment rate into the objective function for optimization.
  • the present invention overcomes the problem of filming the internal information of the welding seam by the commonly used radiographic imaging technology, and then interpreting the internal defects of the welding seam by experienced workers according to the film. Moreover, during the quality inspection period, the labor cost is high, the experienced workers are scarce, and the training cycle of skilled workers with inspection qualifications is long. With the increase of inspection work intensity, manual inspection is often accompanied by low inspection efficiency, misjudgment and leakage of inspection results. Judgment and other human errors, which seriously affect the product quality inspection work.
  • the key process of the intelligent detection device and method for weld defects proposed by the present invention is as follows: (1) As for the ray source inside the cylindrical cabin, the X-rays are emitted from the ray source and are perpendicular to the weld cabin. The cut surface of the body surface is injected to form the best transillumination light path, which is received by the imaging plate placed outside the cabin and located on the ray focal plane to form the original grayscale image of the digital ray of the girth weld of the cabin, which is pushed to the cloud platform server.
  • the cloud platform server preprocesses the original grayscale image of the digital ray of the cabin girth weld, so that the contrast of the original grayscale image meets the requirements, and the preprocessed image is obtained; (3) The preprocessed image is input into the volume
  • the integrated neural network model CNN is used to screen defects and determine whether the preprocessed images contain defects.
  • the convolutional neural network model CNN needs to be pre-trained.
  • the model parameters are initialized with random functions to obtain an untrained convolutional neural network model CNN.
  • the error between the model output and input is defined as the objective function, and the error is used.
  • the method of backpropagation updates the model parameters, and the method of gradient descent is used to find the parameter update and drop to obtain the minimum value of the objective function, and complete the training of the convolutional neural network model CNN.
  • the trained convolutional neural network model CNN has the ability to screen defects and can screen the input images for defects. (4) Input the images judged to contain defects into the convolutional neural network model RCNN with the region of interest, locate the defects in the defective images, and mark the minimum block diagram of the location of the defects, so as to realize the defect localization.
  • the convolutional neural network model RCNN with a region of interest needs to be pre-trained.
  • a random function is used to initialize the model parameters to obtain an untrained convolutional neural network model RCNN with a region of interest.
  • the error between the output and the input is defined as the objective function
  • the model parameters are updated by the method of error back propagation
  • the gradient descent method is used to find the parameter update and drop to obtain the minimum value of the objective function, and complete the convolutional neural network with the region of interest. Training of the model RCNN.
  • the trained convolutional neural network model RCNN with regions of interest has the capability of defect localization, and can mark the smallest block diagram of the location of the defect to realize defect localization.
  • the deep learning neural network model DNN needs to be pre-trained. On the basis of the AlexNet network model structure, a random function is used to initialize the model parameters to obtain an untrained deep learning neural network model DNN. The error between the model output and the input is defined as the objective function, using the error The method of back propagation is used to update the model parameters, and the method of gradient descent is used to find the parameter update and lower to obtain the minimum value of the objective function, and complete the training of the deep learning neural network model DNN.
  • the trained deep learning neural network model DNN has the ability to classify defects, and can classify the specific categories of defect images (porosity, slag inclusion, and incomplete penetration) in the input minimum block diagram.
  • the evaluation efficiency test is carried out, 500 images are randomly selected from the digital radiographic images of the welding seam, and 500 images are handed over to experienced film critics for evaluation and the intelligent defect detection device and method mentioned in the present invention.
  • the total time for manual and machine evaluation is calculated, and the evaluation time for each image is calculated.
  • the test results are that the manual filming time is 28.6 seconds per sheet, and the machine filming time is 14.3 seconds per sheet.
  • the defect intelligent detection device and method mentioned in the present invention improves the efficiency by about 100% compared with the traditional manual evaluation method.
  • the traditional manual detection method is replaced by the detection method of computer combined with deep learning neural network artificial intelligence algorithm, and the detection knowledge of experienced inspection technicians is converted into machine language that can be quantified by computer.
  • the digital image collected by the inspection equipment is analyzed by new artificial intelligence technology, and the defects in the image are located, identified, rated, and automatically and intelligently interpret the output results. , to avoid human error, improve work efficiency and reduce labor costs. And when the amount of detection data continues to accumulate, the detection accuracy rate will also increase.
  • the technical problem solved by the present invention is: to overcome the deficiencies of the prior art, to provide an intelligent detection device and method for internal defects of the weld, which is applied to the quality inspection task of the weld.
  • X-ray image analysis intelligent interpretation of the results, effectively reduce the time of manual inspection, avoid errors caused by human operation under the premise of ensuring the accuracy of defect identification, and improve the efficiency of weld quality inspection.
  • an intelligent detection device and method for welding internal defects comprising: an X-ray tube, an imaging board, an optical path simulation and control unit, and a cloud platform server;
  • the optical path simulation and control unit can select the optimal transillumination optical path according to the shape or 3D model of the weld, and can adjust the position of the X-ray tube and the imaging plate according to the optimal transillumination optical path, so that the weld is located between the X-ray tube and the imaging plate.
  • the optimal position between the imaging plates; the optical path simulation and control unit controls the X-ray tube to emit X-rays, and after the X-rays transmit the welding seam, they are imaged on the imaging plate to obtain the X-ray image, that is, the original grayscale image of the welding seam;
  • the original grayscale image of the seam is pushed to the cloud platform server;
  • the cloud platform server preprocesses the original grayscale image of the weld so that the contrast of the original grayscale image meets the requirements, that is, the preprocessed image is obtained; the preprocessed image is input into the convolutional neural network model CNN for defect screening , to determine whether the preprocessed image contains defects.
  • the image judged to contain defects is input into the convolutional neural network model RCNN with the region of interest, the defects in the defective images are located, and the minimum block diagram of the location of the defect is marked to realize the defect localization.
  • Extract the image in the minimum block diagram after defect location input the deep learning neural network model DNN, classify the defect, and get the type of defect.
  • the imaging plate is to be located at the focal point of the X-ray tube radiation.
  • the original grayscale image of the weld is preprocessed, as follows:
  • the preprocessing methods include but are not limited to: image enhancement, image nonlinear change, filter noise reduction, and image sharpening.
  • the preprocessing methods include but are not limited to: image enhancement, filtering and noise reduction, and image smoothing.
  • the preprocessing methods include but are not limited to: image enhancement, non-linear image change, filtering and noise reduction, and wavelet transform.
  • the contrast requirement of the original grayscale image is specifically: the grayscale difference of four adjacent pixels of one pixel meets the minimum discrimination requirement of the detection threshold.
  • the defects include porosity, slag inclusion, and incomplete penetration.
  • the convolutional neural network model CNN is pre-trained, and the specific training method is as follows:
  • the training image is the preprocessed image of the original grayscale image of the weld, and the image is pre-marked with or without defects to form a label; the labels are divided into defective and non-defective labels;
  • the trained convolutional neural network model CNN can output a label, and judge whether the weld is defective according to the label, so as to realize defect screening.
  • the minimum block diagram of the location of the defect refers to: a rectangular frame composed of a group of parallel lines tangent to the longest diameter of the defect and a group of parallel lines perpendicular to it (the part that can be tangent to the outermost edge of the defect).
  • the convolutional neural network model RCNN with the region of interest needs to be pre-trained, and the training method is as follows:
  • the trained convolutional neural network model RCNN with a region of interest can output the minimum block diagram of the location of the defect, and realize the defect location according to the minimum block diagram of the location of the defect.
  • the deep learning neural network model DNN needs to be pre-trained, and the training method is as follows:
  • the deep learning neural network model DNN is trained to obtain a trained deep learning neural network model DNN, that is, the parameters in the deep learning neural network model DNN have been optimized.
  • the deep learning neural network model DNN can output labels with defect types, and realize defect classification according to the labels with defect types.
  • a defect rating can be performed on the classified defects to determine whether the defect grades satisfy the different level patterns of the same type of defects input by the pre-DNN network training, and output the detection results.
  • the system, device and each module provided by the present invention can be completely implemented by logically programming the method steps.
  • the same program is implemented in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, and embedded microcontrollers, among others. Therefore, the system, device and each module provided by the present invention can be regarded as a kind of hardware component, and the modules used for realizing various programs included in it can also be regarded as the structure in the hardware component;
  • a module for realizing various functions can be regarded as either a software program for realizing a method or a structure within a hardware component.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)

Abstract

一种焊缝内部缺陷的智能检测装置、检测方法及检测介质，由X射线管发出的X射线透照焊缝，通过光路仿真与控制单元实现最佳成像，然后在成像板上得到包含焊缝内部质量信息的数字图像，生成的图像被自动上传至云平台服务器，采用数字图像处理技术和深度学习神经网络算法对图像进行智能预处理、分析判别缺陷存在与否、缺陷定位、缺陷类型识别以及缺陷评级,从而实现图像表征的质量检测。在检测过程中实现了对复杂结构焊缝检测过程的精确控制；在图像评价过程中利用缺陷智能识别代替了人工评片过程，有效地缩减了人工检测时长，在保证缺陷识别准确率的前提下提高了焊缝质量检测的工作效率。

Description

焊缝内部缺陷智能检测装置、方法及介质 技术领域
本发明涉及智能化检测技术领域，具体地，涉及焊缝内部缺陷智能检测装置、方法及介质。
背景技术
目前在工业领域，焊缝内部缺陷检测是生产过程质量检测的重要一环，通常采用数字射线成像技术对焊缝内部信息拍片，之后由经验丰富的工人根据片子对焊缝内部缺陷判读。但是，数字射线图像的缺陷评判需要具有资质的技能工人才能完成，培养技能工人需要耗费大量的时间和金钱，而且，大量的评片工作易导致技能工人的疲劳，极易导致误判、漏判等人为误差。同时，伴随生产力的发展，产量的增加，对评片效率提出了更高要求。随着人工智能技术的发展，基于数字图像的深度学习神经网络算法在无损检测领域中承担起越来越重要的任务。
现有技术通过检测人员制定检测工艺实现焊缝检测，检测光路的布置严重依靠检测人员知识贮备与经验，检测图像评价靠检测人员，检测图像质量与评价受主观影响严重，检测效率和检测一致性不高。
专利文献CN107748200B(申请号：CN201710712559.0)公开了一种基于特征导波的焊缝缺陷检测压电阵列式柔性传感器及检测方法。传感器由多个压电单元构成矩阵，排列在柔性衬底上；每个压电单元上覆盖阻尼块，周围填充吸声材料，传感器外壳以柔性保护膜封装；所有压电单元正极引线串联一个逻辑开关和延时器后，并联至正极总线。压电单元分三种类别，分别激发三种不同模式导波，对不同类型的缺陷敏感程度不一，实现互补。该传感器通过逻辑开关选择不同的压电阵列检测方式，且适应不同曲率表面和结构的焊缝检测需求；延时器调节激励时间差，实现声束的合成与聚焦。
发明内容
针对现有技术中的缺陷，本发明的目的是提供一种焊缝内部缺陷智能检测装置、 方法及介质。
根据本发明提供的一种焊缝内部缺陷智能检测装置，包括：X射线管、成像板、光路仿真与控制单元、云平台服务器；
光路仿真与控制单元根据焊缝外形选择透照光路，并根据选择的透照光路，调整X射线管和成像板的位置，使焊缝位于X射线管与成像板之间的预设位置；X射线透射焊缝后，在成像板上成像，得到X射线图像，即焊缝原始灰度图像，将图像推送至云平台服务器。
优选地，所述预设位置指：
成像板位于X射线管发出射线的焦点所在的焦平面。
根据本发明提供的一种基于上述所述的焊缝内部缺陷智能检测装置的焊缝内部缺陷智能检测方法，光路仿真与控制单元根据焊缝外形，选择最佳透照光路，并根据最佳透照光路，调整X射线管和成像板的位置，使焊缝位于X射线管与成像板之间的预设位置；X射线透射焊缝后，在成像板上成像，得到X射线图像，即焊缝原始灰度图像，将图像推送至云平台服务器；
云平台服务器，对焊缝原始灰度图像进行预处理，使得原始灰度图像的对比度达到要求，得到预处理后的图像；将预处理后的图像输入卷积神经网络模型CNN，进行缺陷筛选，判断预处理后的图像中是否含有缺陷；
将判定为含有缺陷的图像，输入到带有感兴趣区域的卷积神经网络模型RCNN，对有缺陷的图像中的缺陷定位，并标注缺陷所在位置的最小框图，实现缺陷定位；
提取缺陷定位后最小框图内的图像，输入深度学习神经网络模型DNN，进行缺陷分类，得到缺陷的类型。
优选地，所述对焊缝原始灰度图像进行预处理，所述预处理方式包括：图像增强、图像非线性变化、滤波降噪以及图像锐化；
原始灰度图像的对比度要求，具体为：一个像素点相邻四个像素点的灰度差值满足检测阈值最低区分限度要求；
缺陷，包括气孔、夹渣、缩松、裂纹、偏析这几类缺陷。
优选地，所述卷积神经网络模型CNN经过预先训练，具体训练方式如下：
(1)建立带标签的训练图像集，训练图像为焊缝原始灰度图像经过预处理后的图像，预先将图像有无缺陷进行标记，形成标签；标签分为有缺陷和无缺陷标记；
(2)将训练图像集中的图像逐个输入至未经训练的卷积神经网络模型CNN，根据预 先设定卷积神经网络模型CNN的结构、目标函数、模型参数优化方法，对卷积神经网络模型CNN进行训练，得到训练好的卷积神经网络模型CNN，即已对卷积神经网络模型CNN中参数进行优化。
优选地，所述训练好的卷积神经网络模型CNN能够输出标签，根据标签判断焊缝是否有缺陷，实现缺陷筛选。
缺陷所在位置的最小框图，是指：与缺陷最长径相切的一组平行线和与其垂直的一组平行线组成的矩形框。
优选地，所述带有感兴趣区域的卷积神经网络模型RCNN，需要经过预先训练，训练方式如下：
(1)建立带有缺陷最小框图的训练图像集；
(2)将带有缺陷最小框图的训练图像集中的图像逐个输入至初始卷积神经网络模型RCNN，根据预先设定带有感兴趣区域的卷积神经网络模型RCNN的结构、目标函数、模型参数优化方法，对带有感兴趣区域的卷积神经网络模型RCNN进行训练，得到训练好的带有感兴趣区域的RCNN模型，即已对带有感兴趣区域的卷积神经网络模型RCNN中参数进行优化。
优选地，所述训练好的带有感兴趣区域的卷积神经网络模型RCNN能够输出缺陷所在位置的最小框图，根据缺陷所在位置的最小框图，实现缺陷定位。
优选地，所述深度学习神经网络模型DNN，需要经过预先训练，训练方式如下：
(1)建立带缺陷类型标签的带有缺陷最小框图的训练图像集；每个带有缺陷最小框图的训练图像的缺陷类型标签对应一种缺陷类型；
(2)将带缺陷类型标签的带有缺陷最小框图的训练图像集中的图像逐个输入初始深度学习神经网络模型DNN，根据预先设定深度学习神经网络模型DNN的结构、目标函数、模型参数优化方法，对深度学习神经网络模型DNN进行训练，得到训练好的深度学习神经网络模型DNN，即已对深度学习神经网络模型DNN中参数进行优化。
优选地，所述计算机程序被处理器执行时实现上述中任一项所述的焊缝内部缺陷智能检测方法的步骤。
与现有技术相比，本发明具有如下的有益效果：
(1)本发明通过采用光路仿真与控制模块实现最优检测光路确认，代替检测人员依靠经验制定的光路布置，得到最优图像，提高图像精度与灵敏度。
(2)本发明通过采用云平台服务器进行数字射线图像智能分析，通过云服务， 可以有效收集汇总检测过程中不同产品，不同时间的逐渐质量信息与内部缺陷，为设计与生产工艺优化提升数据支撑，最终提升产品的质量
(3)本发明通过计算机深度学习方法对数字射线图像分析，智能判读结果，部分或全部代替人工评片过程，有效地缩减人工检测时长，在保证缺陷识别准确率的前提下，避免人因误差，提高焊缝质量检测工作效率。
(4)本发明通过卷积神经网络模型CNN进行数字射线图像缺陷筛选，该方法可以有效识别图像中的宏观信息和微观信息，并且可以随着数据量积累进行模型升级优化，为缺陷筛选算法迭代提供支撑。
(5)本发明通过带有感兴趣区域的卷积神经网络模型RCNN进行数字射线图像缺陷定位，该方法可以有效识别缺陷最小框图，为后续缺陷尺寸测量进行缺陷评级提供支撑。
(6)通过云平台服务器实现检测数据实时上传与处理，为生产全流程数字化创造条件
附图说明
通过阅读参照以下附图对非限制性实施例所作的详细描述，本发明的其它特征、目的和优点将会变得更明显：
图1为本发明焊缝数字射线图像智能缺陷检测方法示意框图；
图2为本发明焊缝内部缺陷智能检测装置示意图；
图3为本发明焊缝数字射线图像缺陷筛选算法示意图；
图4为本发明焊缝数字射线图像缺陷定位算法示意图。
具体实施方式
下面结合具体实施例对本发明进行详细说明。以下实施例将有助于本领域的技术人员进一步理解本发明，但不以任何形式限制本发明。应当指出的是，对本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变化和改进。这些都属于本发明的保护范围。
下面通过实施例，对本发明进行更为具体地说明。
实施例1：
下面结合附图和具体实施例对本发明做进一步详细描述。
本发明主要应用于复杂结构件的焊缝检测中，有效提高检测质量与检测一致性，提高检测图像评价的准确度与效率，最终提升焊缝质量，同时检测数据实现云平台存储与推送，为生产流程的数字化与智能化应用提供基础。
图1为本发明焊缝数字射线图像智能缺陷检测方法示意框图，图1中，1-原始图像，2-图像预处理，3-缺陷筛选，4-缺陷定位，5-缺陷类型识别，6-缺陷1，7-缺陷2，8-缺陷3，9-合格，10-返工维修，11-让步接收，12-报废。图2为本发明焊缝内部缺陷智能检测装置示意图，图2中，①-光路仿真与控制单元，②-X射线管，③-成像板，④-云平台。图3为本发明焊缝数字射线图像缺陷筛选算法示意图，图3中，a-卷积层，b-降采样层，c-卷积层，d-降采样层，e-全连接层，f-输出层(全连接+Softmax激活)。图4为本发明焊缝数字射线图像缺陷定位算法示意图，图4中，A-提取候选框，B-CNN提取特征图，C-ROI pooling，D-分类，5-回归。
本发明的一种焊缝内部缺陷智能检测装置，包括：X射线管、成像板、光路仿真与控制单元、云平台服务器；如图2所示；
光路仿真与控制单元，能够根据焊缝的形貌特征或三维模型，通过内置仿真模块优选最佳透照光路，即X射线从射线管发出，垂直于焊缝表面或其切面透射焊缝至成像板，或因焊缝特殊结构无法从垂直表面射入时，保证射线透射焊缝的路径最短；根据最佳透照管路控制X射线管和成像板，调整其位置，使焊缝位于X射线管与成像板之间的最佳位置，即成像板位于X射线管发出射线的焦点所在的焦平面；光路仿真与控制单元控制X射线管发出X射线，X射线透射焊缝后，在成像板上成像，光路仿真与控制单元控制成像板获取X射线图像，即焊缝原始灰度图像；光路仿真与控制单元，将焊缝原始灰度图像推送至云平台服务器；
云平台服务器，对焊缝原始灰度图像进行预处理，使得原始灰度图像的对比度达到要求，得到预处理后的图像；将预处理后的图像输入卷积神经网络模型CNN，进行缺陷筛选，判断预处理后的图像中是否含有缺陷。云平台服务器可以将缺陷智能检测方法打包集成，同时还可以部署在互联网上，输出云服务；并可有效收集汇总检测过程中不同产品，形成不同产品的焊缝数字射线图像数据集，为缺陷智能检测方法的研发提供基础。
将判定为含有缺陷的图像，输入到带有感兴趣区域的卷积神经网络模型RCNN，对有缺陷的图像中的缺陷定位，并标注缺陷所在位置的最小框图，实现缺陷定位。
提取缺陷定位后最小框图内的图像，输入深度学习神经网络模型DNN，进行缺陷分类，得到缺陷的类型。
成像板位于X射线管辐射的焦点上。
对焊缝原始灰度图像进行预处理，具体如下：
针对厚度梯度变化剧烈的原始灰度图像，预处理方式包括但不限于：图像增强、图像非线性变化、滤波降噪、图像锐化等。
针对表面粗糙的原始灰度图像，预处理方式包括但不限于：图像增强、滤波降噪、图像平滑等。
针对焊缝边缘的原始灰度图像，预处理方式包括但不限于：图像增强、图像非线性变化、滤波降噪、小波变换等。
实际进行图像预处理时，会尝试不同的预处理方法组合、参数，并从中优选出效果较好的预处理方法组合、参数。
原始灰度图像的对比度要求，优选为：一个像素点相邻四个像素点的灰度差值满足检测阈值最低区分限度要求。
缺陷，优选包括气孔、夹渣、未焊透这几类缺陷。
卷积神经网络模型CNN经过预先训练，优选训练方式如下：
①建立带标签的训练图像集，训练图像为焊缝原始灰度图像经过预处理后的图像，预先将图像有无缺陷进行标记，形成标签；标签分为有缺陷和无缺陷标记；
②将训练图像集中的图像逐个输入至未经训练的卷积神经网络模型CNN，即在VGG网络模型结构的基础上利用随机函数初始化模型参数，之后将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新下求得目标函数极小值，采用上述流程对卷积神经网络模型CNN进行训练，如图3所示，图像输入后，经过卷积得到特征图，经过降采样得到特征图，再重复卷积、降采样过程，将最终得到的特征图输入全连接层，通过输出层输出筛选结果。训练后得到训练好的卷积神经网络模型CNN，即已对卷积神经网络模型CNN中参数进行优化。实际训练过程中，卷积神经网络模型CNN的结构、目标函数、模型参数优化可以进行多种组合进行训练测试，如CNN的结构除VGG网络外，还可以选择AlexNet、ResNet等网络结构；目标函数除了输出与输入的误差外，还可以增加学习率、正则项等参数，组成相对复杂的目标函数；模型参数优化除了梯度下降方法外，还可以选择随机梯度下降、动量梯度下降、小批量梯度下降等方法，训练时，可以选取各种方法进行组合，从中选取效果较好的组合，如准确率高、虚检率低、训练速度快等，作为参数进行卷积神经网络模型CNN训练。
训练好的卷积神经网络模型CNN能够输出标签，根据标签判断焊缝是否有缺陷，实现缺陷筛选。
带有感兴趣区域的卷积神经网络模型RCNN，需要经过预先训练，优选训练方式如下：
①建立带有缺陷最小框图的训练图像集；训练图像集中的训练图像，带有焊缝所有可能发生的缺陷，每个训练图像至少包含一个缺陷，所有可能发生的缺陷，包括：气孔、夹渣、未焊透。
②将带有缺陷最小框图的训练图像集中的图像逐个输入至未经训练的带有感兴趣区域的卷积神经网络模型RCNN，即在YOLO网络模型结构的基础上利用随机函数初始化模型参数，之后将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新放下求得目标函数极小值，采用上述流程对带有感兴趣区域的卷积神经网络模型RCNN进行训练，如图4所示，在输入图像上提取候选框，通过CNN提取特征图的方法将候选框映射到特征图ROI，再通过ROI pooling将ROI调整到固定尺寸，获取ROI特征后进行分类和回归。训练后得到训练好的带有感兴趣区域的卷积神经网络模型RCNN，即已对带有感兴趣区域的卷积神经网络模型RCNN中参数进行优化。实际训练过程中，卷积神经网络模型RCNN的结构、目标函数、模型参数可以进行多种组合进行训练测试，如RCNN的结构除YOLO网络外，还可以选择SDD等网络结构；目标函数除了输出与输入的误差外，还可以增加学习率、正则项等参数，组成相对复杂的目标函数；模型参数优化除了梯度下降方法外，还可以选择随机梯度下降、动量梯度下降、小批量梯度下降等方法，训练时，可以选取各种方法进行组合，从中选取效果好的组合，如准确率高、虚检率低、训练速度快等，作为参数进行卷积神经网络模型RCNN训练。
训练好的带有感兴趣区域的卷积神经网络模型RCNN优选能够输出缺陷所在位置的最小框图，根据缺陷所在位置的最小框图，实现缺陷定位。
深度学习神经网络模型DNN，需要经过预先训练，优选训练方式如下：
①建立带缺陷类型标签的带有缺陷最小框图的训练图像集；每个带有缺陷最小框图的训练图像的缺陷类型标签对应一种缺陷类型；
②将带缺陷类型标签的带有缺陷最小框图的训练图像集中的图像逐个输入至未经训练的深度学习神经网络模型DNN，即在AlexNet网络模型结构的基础上利用随机函数初始化模型参数，之后将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新放下求得目标函数极小值，采用上 述流程对深度学习神经网络模型DNN进行训练，得到训练好的深度学习神经网络模型DNN，即已对深度学习神经网络模型DNN中参数进行优化。实际训练过程中，卷积神经网络模型DNN的结构、目标函数、模型参数可以进行多种组合进行训练测试，如DNN的结构除AlexNet网络外，还可以选择VGG、ResNet等网络结构；目标函数除了输出与输入的误差外，还可以增加学习率、正则项等参数，组成相对复杂的目标函数；模型参数优化除了梯度下降方法外，还可以选择随机梯度下降、动量梯度下降、小批量梯度下降等方法，训练时，可以选取各种方法进行组合，从中选取效果好的组合，如准确率高、虚检率低、训练速度快等，作为参数进行卷积神经网络模型DNN训练。
深度学习神经网络模型DNN能够输出带缺陷类型标签，根据带缺陷类型标签，实现缺陷分类。
在缺陷分类后，还可以对经过分类后的缺陷，进行缺陷评级，判断其缺陷等级是否满足预先输入的同种缺陷的不同级别图样，并输出检测结果；
本发明进行预处理，实现缺陷对比度提高的进一步方案为：引入优化算法，寻找缺陷对比度最大化的预处理组合。
本发明设定原始灰度图像的对比度要求，实现图像对比度提高的进一步方案为：根据待检焊缝的尺寸、材料，调整X射线辐照强度。
本发明卷积神经网络模型CNN进行训练，实现缺陷筛选提高的进一步方案为：选择残差网络ResNet的结构作为卷及神经网络模型CNN的结构进行训练。
本发明带有感兴趣区域的卷积神经网络模型RCNN进行训练，实现缺陷定位提高的进一步方案为：选择Faster R-CNN模型的结构作为带有感兴趣区域的卷及神经网络模型RCNN的结构进行训练。
本发明深度学习神经网络模型DNN进行训练，实现缺陷分类提高的进一步方案为：在深度学习神经网络模型DNN的目标函数中优化学习率、正则项部分
本发明在缺陷分类后，还可以对经过分类后的缺陷，进行缺陷评级，判断其缺陷等级是否满足检验标准，并输出检测结果，优选方案为：
在缺陷分类后，应用DNN网络对经过分类后的缺陷，进行缺陷评级，具体是将待评级图像输入已经训练好的网络，并输出表征缺陷等级的标签，判断依据是评价其是否满足事先DNN网络训练人员输入的同种缺陷的不同级别图样。
本发明能够实现装置什么指标提高的进一步方案为：实现智能评片的漏判率降低的进一步方案为，将漏判率写入目标函数，进行优化
在焊缝检测过程中，本发明克服了通常采用的射线成像技术对焊缝内部信息拍片，之后由经验丰富的工人根据片子对焊缝内部缺陷判读的问题。并且解决了质量检测期间，用工成本高、经验丰富的工人稀缺、培养具备检测资质的技术工人周期长，且随着检测工作强度的增加，人工检测往往伴随着检测效率低、检测结果误判漏判等人为误差，严重影响产品质量检测工作的问题。
以舱体环焊缝为例，本发明提出的焊缝缺陷智能检测装置及方法关键流程如下：(1)射线源至于圆筒形舱体内部，X射线自射线源发出，垂直于焊缝舱体表面切面射入，形成最佳透照光路，由置于舱体外部且位于射线焦平面上的成像板接收，形成舱体环焊缝数字射线原始灰度图像，推送至云平台服务器。(2)云平台服务器对舱体环焊缝数字射线原始灰度图像进行预处理，使得原始灰度图像的对比度达到要求，得到预处理后的图像；(3)将预处理后的图像输入卷积神经网络模型CNN，进行缺陷筛选，判断预处理后的图像中是否含有缺陷。卷积神经网络模型CNN需要预先训练，在VGG网络模型结构的基础上利用随机函数初始化模型参数得到未经训练的卷积神经网络模型CNN，将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新放下求得目标函数极小值，完成对卷积神经网络模型CNN的训练。训练后的卷积神经网络模型CNN具备缺陷筛选能力，能够将输入图像进行有无缺陷的筛选。(4)将判定为含有缺陷的图像，输入到带有感兴趣区域的卷积神经网络模型RCNN，对有缺陷的图像中的缺陷定位，并标注缺陷所在位置的最小框图，实现缺陷定位。带有感兴趣区域的卷积神经网络模型RCNN需要预先训练，在YOLO网络模型结构的基础上利用随机函数初始化模型参数得到未经训练的带有感兴趣区域的卷积神经网络模型RCNN，将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新放下求得目标函数极小值，完成对带有感兴趣区域的卷积神经网络模型RCNN的训练。训练后的带有感兴趣区域的卷积神经网络模型RCNN具备缺陷定位能力，能够标注缺陷所在位置的最小框图，实现缺陷定位。(5)提取缺陷定位后最小框图内的图像，输入深度学习神经网络模型DNN，进行缺陷分类，得到缺陷的类型。深度学习神经网络模型DNN需要预先训练，在AlexNet网络模型结构的基础上利用随机函数初始化模型参数得到未经训练的深度学习神经网络模型DNN，将模型输出与输入的误差定义为目标函数，采用误差反向传播的方法更新模型参数，并用梯度下降的方法寻找参数更新放下求得目标函数极小值，完成对深度学习神经网络模型DNN的训练。训练后的深度学习神经网络模型DNN具备缺陷分类能力，能够将输入的最小框图内的缺 陷图像具体类别(气孔、夹渣、未焊透)进行分类。
本发明进行了评片效率测试，从焊缝数字射线图像中随机抽取500张图像，分别交给有经验的评片师评片和本发明所提及的缺陷智能检测装置及方法评片，记录人工评片和机器评片的总时间，计算每一张图像的评片时间。测试结果为，人工平片时间28.6秒每张，机器平片时间14.3秒每张。本发明提及的缺陷智能检测装置及方法比传统人工评片方式提升效率约100％。
通过对比可知，本发明中以计算机结合深度学习神经网络人工智能算法的检测方式代替传统人工检测方式，将经验丰富的检验技能人员的检测知识转换为可被计算机量化的机器语言，通过对X射线检测设备采集到的数字图像，采用人工智能新技术进行分析图像，对图像中的缺陷定位、识别、评级，自动化、智能化判读输出结果，在保证检测准确率的前提下，可以长时间稳定工作，避免人为误差，提高工作效率，缩减用工成本。且在检测数据量不断积累的情况下，检测正确率也将随之提高。
实施例2：
本发明解决的技术问题为：克服现有技术不足，提供一种焊缝内部缺陷智能检测装置及方法，应用于焊缝的质量检测任务，根据焊缝内部缺陷特征，运用计算机深度学习方法对数字射线图像分析，智能判读结果，有效地缩减人工检测时长，在保证缺陷识别准确率的前提下，避免人为操作引起的误差，提高焊缝质量检测工作效率。
本发明解决的技术方案为：一种焊缝内部缺陷智能检测装置及方法，包括：X射线管、成像板、光路仿真与控制单元、云平台服务器；
光路仿真与控制单元，能够根据焊缝的外形或三维模型，选择最佳透照光路，并能够根据最佳透照光路，调整X射线管和成像板的位置，使焊缝位于X射线管与成像板之间的最佳位置；光路仿真与控制单元控制X射线管发出X射线，X射线透射焊缝后，在成像板上成像，得到X射线图像，即焊缝原始灰度图像；将焊缝原始灰度图像推送至云平台服务器；
云平台服务器，对焊缝原始灰度图像进行预处理，使得原始灰度图像的对比度达到要求，即得到预处理后的图像；将预处理后的图像输入卷积神经网络模型CNN，进行缺陷筛选，判断预处理后的图像中是否含有缺陷。
将判定为含有缺陷的图像，输入到带有感兴趣区域的卷积神经网络模型RCNN，对有缺陷的图像中的缺陷定位，并标注缺陷所在位置的最小框图，实现缺陷定位。
提取缺陷定位后最小框图内的图像，输入深度学习神经网络模型DNN，进行缺陷分类，得到缺陷的类型。
优选的，成像板要位于X射线管辐射的焦点上。
优选的，对焊缝原始灰度图像进行预处理，具体如下：
针对厚度梯度变化剧烈的原始灰度图像，预处理方式包括但不限于：图像增强、图像非线性变化、滤波降噪、图像锐化。
针对表面粗糙的原始灰度图像，预处理方式包括但不限于：图像增强、滤波降噪、图像平滑。
针对焊缝边缘的原始灰度图像，预处理方式包括但不限于：图像增强、图像非线性变化、滤波降噪、小波变换。
优选的，原始灰度图像的对比度要求，具体为：一个像素点相邻四个像素点的灰度差值满足检测阈值最低区分限度要求。
优选的，缺陷，包括气孔、夹渣、未焊透这几类缺陷。
优选的，卷积神经网络模型CNN经过预先训练，具体训练方式如下：
(1)建立带标签的训练图像集，训练图像为焊缝原始灰度图像经过预处理后的图像，预先将图像有无缺陷进行标记，形成标签；标签分为有缺陷和无缺陷标记；
(2)将训练图像集中的的图像逐个输入至未经训练的卷积神经网络模型CNN，根据预先设定卷积神经网络模型CNN的结构、目标函数、模型参数优化方法，对卷积神经网络模型CNN进行训练，得到训练好的卷积神经网络模型CNN，即已对卷积神经网络模型CNN中参数进行优化。
优选的，训练好的卷积神经网络模型CNN能够输出标签，根据标签判断焊缝是否有缺陷，实现缺陷筛选。
优选的，缺陷所在位置的最小框图，是指：与缺陷最长径相切的一组平行线和与其垂直的一组平行线(与缺陷边缘最外侧可相切部位)组成的矩形框。
优选的，带有感兴趣区域的卷积神经网络模型RCNN，需要经过预先训练，训练方式如下：
(1)建立带有缺陷最小框图的训练图像集；
(2)将带有缺陷最小框图的训练图像集中的图像逐个输入至未经训练的带有感兴趣区域的卷积神经网络模型RCNN，根据预先设定带有感兴趣区域的卷积神经网络模型RCNN的结构、目标函数、模型参数优化方法，对带有感兴趣区域的卷积神经网 络模型RCNN进行训练，得到训练好的带有感兴趣区域的卷积神经网络模型RCNN，即已对带有感兴趣区域的卷积神经网络模型RCNN中参数进行优化。
优选的，训练好的带有感兴趣区域的卷积神经网络模型RCNN能够输出缺陷所在位置的最小框图，根据缺陷所在位置的最小框图，实现缺陷定位。
优选的，深度学习神经网络模型DNN，需要经过预先训练，训练方式如下：
(1)建立带缺陷类型标签的带有缺陷最小框图的训练图像集；每个带有缺陷最小框图的训练图像的缺陷类型标签对应一种缺陷类型；
(2)将带缺陷类型标签的带有缺陷最小框图的训练图像集中的图像逐个输入至未经训练的深度学习神经网络模型DNN，根据预先设定深度学习神经网络模型DNN的结构、目标函数、模型参数优化方法，对深度学习神经网络模型DNN进行训练，得到训练好的深度学习神经网络模型DNN，即已对深度学习神经网络模型DNN中参数进行优化。
优选的，深度学习神经网络模型DNN能够输出带缺陷类型标签，根据带缺陷类型标签，实现缺陷分类。
优选的，在缺陷分类后，还可以对经过分类后的缺陷，进行缺陷评级，判断其缺陷等级是否满足预先DNN网络训练输入的同种缺陷的不同级别图样，并输出检测结果。
在本申请的描述中，需要理解的是，术语“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。
本领域技术人员知道，除了以纯计算机可读程序代码方式实现本发明提供的系统、装置及其各个模块以外，完全可以通过将方法步骤进行逻辑编程来使得本发明提供的系统、装置及其各个模块以逻辑门、开关、专用集成电路、可编程逻辑控制器以及嵌入式微控制器等的形式来实现相同程序。所以，本发明提供的系统、装置及其各个模块可以被认为是一种硬件部件，而对其内包括的用于实现各种程序的模块也可以视为硬件部件内的结构；也可以将用于实现各种功能的模块视为既可以是实现方法的软件程序又可以是硬件部件内的结构。
以上对本发明的具体实施例进行了描述。需要理解的是，本发明并不局限于上 述特定实施方式，本领域技术人员可以在权利要求的范围内做出各种变化或修改，这并不影响本发明的实质内容。在不冲突的情况下，本申请的实施例和实施例中的特征可以任意相互组合。

Claims (10)

  1. 一种焊缝内部缺陷智能检测装置，其特征在于，包括：X射线管、成像板、光路仿真与控制单元、云平台服务器；
    光路仿真与控制单元根据焊缝外形选择透照光路，并根据选择的透照光路，调整X射线管和成像板的位置，使焊缝位于X射线管与成像板之间的预设位置；X射线透射焊缝后，在成像板上成像，得到X射线图像，即焊缝原始灰度图像，将图像推送至云平台服务器。
  2. 根据权利要求1所述的一种焊缝内部缺陷智能检测装置及方法，其特征在于，所述预设位置指：
    成像板位于X射线管发出射线的焦点所在的焦平面。
  3. 一种基于权利要求1所述的焊缝内部缺陷智能检测装置的焊缝内部缺陷智能检测方法，其特征在于，光路仿真与控制单元根据焊缝外形，选择最佳透照光路，并根据最佳透照光路，调整X射线管和成像板的位置，使焊缝位于X射线管与成像板之间的预设位置；X射线透射焊缝后，在成像板上成像，得到X射线图像，即焊缝原始灰度图像，将图像推送至云平台服务器；
    云平台服务器，对焊缝原始灰度图像进行预处理，使得原始灰度图像的对比度达到要求，得到预处理后的图像；将预处理后的图像输入卷积神经网络模型CNN，进行缺陷筛选，判断预处理后的图像中是否含有缺陷；
    将判定为含有缺陷的图像，输入到带有感兴趣区域的卷积神经网络模型RCNN，对有缺陷的图像中的缺陷定位，并标注缺陷所在位置的最小框图，实现缺陷定位；
    提取缺陷定位后最小框图内的图像，输入深度学习神经网络模型DNN，进行缺陷分类，得到缺陷的类型。
  4. 基于权利要求3所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述对焊缝原始灰度图像进行预处理，所述预处理方式包括：图像增强、图像非线性变化、滤波降噪以及图像锐化；
    原始灰度图像的对比度要求，具体为：一个像素点相邻四个像素点的灰度差值满足检测阈值最低区分限度要求；
    缺陷，包括气孔、夹渣、缩松、裂纹、偏析这几类缺陷。
  5. 根据权利要求3所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述卷积 神经网络模型CNN经过预先训练，具体训练方式如下：
    (1)建立带标签的训练图像集，训练图像为焊缝原始灰度图像经过预处理后的图像，预先将图像有无缺陷进行标记，形成标签；标签分为有缺陷和无缺陷标记；
    (2)将训练图像集中的图像逐个输入至未经训练的卷积神经网络模型CNN，根据预先设定卷积神经网络模型CNN的结构、目标函数、模型参数优化方法，对卷积神经网络模型CNN进行训练，得到训练好的卷积神经网络模型CNN，即已对卷积神经网络模型CNN中参数进行优化。
  6. 根据权利要求5所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述训练好的卷积神经网络模型CNN能够输出标签，根据标签判断焊缝是否有缺陷，实现缺陷筛选。
    缺陷所在位置的最小框图，是指：与缺陷最长径相切的一组平行线和与其垂直的一组平行线组成的矩形框。
  7. 根据权利要求3所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述带有感兴趣区域的卷积神经网络模型RCNN，需要经过预先训练，训练方式如下：
    (1)建立带有缺陷最小框图的训练图像集；
    (2)将带有缺陷最小框图的训练图像集中的图像逐个输入至初始卷积神经网络模型RCNN，根据预先设定带有感兴趣区域的卷积神经网络模型RCNN的结构、目标函数、模型参数优化方法，对带有感兴趣区域的卷积神经网络模型RCNN进行训练，得到训练好的带有感兴趣区域的RCNN模型，即已对带有感兴趣区域的卷积神经网络模型RCNN中参数进行优化。
  8. 根据权利要求7所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述训练好的带有感兴趣区域的卷积神经网络模型RCNN能够输出缺陷所在位置的最小框图，根据缺陷所在位置的最小框图，实现缺陷定位。
  9. 根据权利要求3所述的一种焊缝内部缺陷智能检测方法，其特征在于，所述深度学习神经网络模型DNN，需要经过预先训练，训练方式如下：
    (1)建立带缺陷类型标签的带有缺陷最小框图的训练图像集；每个带有缺陷最小框图的训练图像的缺陷类型标签对应一种缺陷类型；
    (2)将带缺陷类型标签的带有缺陷最小框图的训练图像集中的图像逐个输入初始深度学习神经网络模型DNN，根据预先设定深度学习神经网络模型DNN的结构、目标函数、模型参数优化方法，对深度学习神经网络模型DNN进行训练，得到训练好的深度学习神 经网络模型DNN，即已对深度学习神经网络模型DNN中参数进行优化。
  10. 一种存储有计算机程序的计算机可读存储介质，其特征在于，所述计算机程序被处理器执行时实现权利要求3至9中任一项所述的焊缝内部缺陷智能检测方法的步骤。
PCT/CN2021/117548 2020-09-10 2021-09-10 焊缝内部缺陷智能检测装置、方法及介质 WO2022053001A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010949152.1A CN112083017A (zh) 2020-09-10 2020-09-10 焊缝内部缺陷智能检测装置、方法及介质
CN202010949152.1 2020-09-10

Publications (1)

Publication Number Publication Date
WO2022053001A1 true WO2022053001A1 (zh) 2022-03-17

Family

ID=73736378

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/117548 WO2022053001A1 (zh) 2020-09-10 2021-09-10 焊缝内部缺陷智能检测装置、方法及介质

Country Status (2)

Country Link
CN (1) CN112083017A (zh)
WO (1) WO2022053001A1 (zh)

Cited By (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114742811A (zh) * 2022-04-27 2022-07-12 桂林电子科技大学 一种基于改进Yolox的SMT产线焊点缺陷快速检测方法及系统
CN115482227A (zh) * 2022-09-26 2022-12-16 中机生产力促进中心有限公司 机器视觉自适应成像环境调整方法
CN115546137A (zh) * 2022-09-29 2022-12-30 浙江新宝汽车电器有限公司 一种柔性线束的x光自动检测方法
CN115797314A (zh) * 2022-12-16 2023-03-14 哈尔滨耐是智能科技有限公司 零件表面缺陷检测方法、系统、设备及存储介质
CN116051542A (zh) * 2023-03-06 2023-05-02 深圳市深视智能科技有限公司 缺陷检测方法及缺陷检测装置
CN116188475A (zh) * 2023-05-05 2023-05-30 德中(深圳)激光智能科技有限公司 一种外观缺陷自动光学检测的智慧控制方法、系统及介质
CN116258718A (zh) * 2023-05-15 2023-06-13 超音速人工智能科技股份有限公司 基于3d相机的焊接质量检测方法、系统、设备及介质
CN116433659A (zh) * 2023-06-09 2023-07-14 山东高速工程检测有限公司 一种三段式道路缺陷图像处理方法
CN116596891A (zh) * 2023-05-22 2023-08-15 南京林业大学 基于半监督多任务检测的木地板颜色分类及缺陷检测方法
CN116612120A (zh) * 2023-07-20 2023-08-18 山东高速工程检测有限公司 一种针对数据不平衡的两阶段式道路缺陷检测方法
CN116765635A (zh) * 2023-08-18 2023-09-19 济南邦德激光股份有限公司 一种用于激光切割机的焊缝识别方法及识别系统
CN116883400A (zh) * 2023-09-07 2023-10-13 山东大学 一种激光选区熔化过程中的铺粉孔隙率预测方法及系统
CN116930194A (zh) * 2023-09-14 2023-10-24 张家港思复安全科技有限公司 一种搅拌摩擦焊的缺陷检测系统、方法、电子设备和介质
CN116958086A (zh) * 2023-07-21 2023-10-27 盐城工学院 具有增强特征融合能力的金属表面缺陷检测方法及系统
CN117036348A (zh) * 2023-10-08 2023-11-10 中国石油大学(华东) 基于图像处理和裂纹识别模型的金属疲劳裂纹检测方法
CN117066690A (zh) * 2023-09-28 2023-11-17 苏师大半导体材料与设备研究院(邳州)有限公司 一种半导体加工用对准焊接装置
CN117079100A (zh) * 2023-08-14 2023-11-17 北京大学 一种基于深度学习的焊缝缺陷识别系统
CN117095245A (zh) * 2023-10-19 2023-11-21 阿法龙(山东)科技有限公司 一种基于深度学习的无缝钢管小样本学习方法
CN117115162A (zh) * 2023-10-24 2023-11-24 中安芯界控股集团有限公司 基于视觉分析对电池进行检测的芯片生产控制系统
CN117299596A (zh) * 2023-08-14 2023-12-29 江苏秦郡机械科技有限公司 一种自动检测的物料筛选系统及其筛选方法
CN117314916A (zh) * 2023-11-29 2023-12-29 宝鸡市钛程金属复合材料有限公司 一种基于人工智能的金属复合板爆炸焊接检测方法
CN117381261A (zh) * 2023-12-13 2024-01-12 德阳市华建机械设备有限公司 一种自动化焊接机的故障识别装置及方法
CN117437188A (zh) * 2023-10-17 2024-01-23 广东电力交易中心有限责任公司 一种用于智慧电网的绝缘子缺陷检测系统
CN117438330A (zh) * 2023-12-19 2024-01-23 武创芯研科技(武汉)有限公司 一种基于平面压痕的晶圆封装级rdl再布线层缺陷检测方法
CN117607155A (zh) * 2024-01-24 2024-02-27 山东大学 一种应变片外观缺陷检测方法及系统
WO2024040951A1 (zh) * 2022-08-26 2024-02-29 宁德时代新能源科技股份有限公司 定位目标区域的方法、装置及计算机可读存储介质
CN117745718A (zh) * 2024-02-19 2024-03-22 工业云制造(四川)创新中心有限公司 一种基于云制造的信息交互方法
CN117853493A (zh) * 2024-03-08 2024-04-09 山东天意机械股份有限公司 一种基于图像处理的墙板生产质量检测方法
CN118169547A (zh) * 2024-05-13 2024-06-11 常州忆隆信息科技有限公司 一种电动吻合器单次使用电路检测方法及系统

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112083017A (zh) * 2020-09-10 2020-12-15 上海航天精密机械研究所 焊缝内部缺陷智能检测装置、方法及介质
CN113409245B (zh) * 2021-04-06 2024-04-02 中国电子技术标准化研究院 一种电子元器件x射线检查缺陷自动识别方法
WO2022221803A1 (en) * 2021-04-12 2022-10-20 Exxonmobil Upstream Research Company Method and system for evaluating radiograph testing inspection of pipe welding
CN113222938A (zh) * 2021-05-14 2021-08-06 珠海埃克斯智能科技有限公司 芯片缺陷检测方法及系统与计算机可读存储介质
CN113231715A (zh) * 2021-05-31 2021-08-10 华南理工大学 一种大型叶片超低热输入快频焊接修复方法
CN113421304B (zh) * 2021-06-21 2024-05-28 沈阳派得林科技有限责任公司 一种工业射线底片图像焊道区域智能定位方法
CN113418940B (zh) * 2021-06-24 2023-03-14 电子科技大学 一种基于x射线示踪颗粒的检测方法及检测装置
CN113379721B (zh) * 2021-06-29 2022-05-06 广东科学技术职业学院 一种基于云平台的电子元器件质量检测装置
CN113298738A (zh) * 2021-07-13 2021-08-24 上海航天精密机械研究所 X射线焊缝图像自动增强装置及方法
CN113866189A (zh) * 2021-08-24 2021-12-31 上海航天精密机械研究所 基于多机械手协同的射线数字成像检测装置及其检测方法
CN113781415B (zh) * 2021-08-30 2024-06-07 广州大学 一种x射线图像的缺陷检测方法、装置、设备及介质
CN114076775B (zh) * 2021-11-15 2024-04-23 国核示范电站有限责任公司 一种管道焊缝射线检测几何不清晰度控制工艺
CN114354623A (zh) * 2021-12-30 2022-04-15 苏州凌云视界智能设备有限责任公司 弱印痕提取算法、装置、设备和介质
CN114559177B (zh) * 2022-03-07 2023-12-05 北京洞微科技发展有限公司 基于影像数据分析的焊接评估方法、装置及存储介质
CN115121895A (zh) * 2022-04-28 2022-09-30 广东省威汇智能科技有限公司 基于深度学习的选择波峰焊预警方法、装置及存储介质
CN115229374B (zh) * 2022-07-07 2024-04-26 武汉理工大学 一种基于深度学习的汽车白车身焊缝质量检测方法、装置
CN115266774B (zh) * 2022-07-29 2024-02-13 中国特种设备检测研究院 基于人工智能的焊缝射线检测评片方法
CN115100195B (zh) * 2022-08-24 2022-11-22 浙江双元科技股份有限公司 一种用于片材检测的一体化工业相机
CN115564766B (zh) * 2022-11-09 2023-06-13 浙江振兴阿祥集团有限公司 水轮机蜗壳座环的制备方法及其系统
CN117710369B (zh) * 2024-02-05 2024-04-30 山东省科院易达信息科技有限公司 基于计算机视觉技术的金属铝磷化膜缺陷检测方法及系统

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4694479A (en) * 1983-12-05 1987-09-15 Kohaszati Cyaropito Vallalat Gepipari Technologiai Intezet Video-radiographic process and equipment for a quality controlled weld seam
JPH0896136A (ja) * 1994-09-26 1996-04-12 Kawasaki Heavy Ind Ltd 溶接欠陥の評価システム
DE102008062866A1 (de) * 2008-11-13 2010-05-20 Daimler Ag Verfahren zur Qualitätsüberwachung einer Verbindungsnaht sowie Vorrichtung zum Laserschweißen oder Laserlöten
CN105938620A (zh) * 2016-04-14 2016-09-14 北京工业大学 一种小口径管内焊缝表面缺陷识别装置
CN110779937A (zh) * 2019-10-11 2020-02-11 上海航天精密机械研究所 一种铸件产品内部缺陷智能检测装置
WO2020048119A1 (en) * 2018-09-04 2020-03-12 Boe Technology Group Co., Ltd. Method and apparatus for training a convolutional neural network to detect defects
CN112083017A (zh) * 2020-09-10 2020-12-15 上海航天精密机械研究所 焊缝内部缺陷智能检测装置、方法及介质
CN112184693A (zh) * 2020-10-13 2021-01-05 东北大学 一种射线工业底片焊缝缺陷智能检测方法
CN113298738A (zh) * 2021-07-13 2021-08-24 上海航天精密机械研究所 X射线焊缝图像自动增强装置及方法

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1148333A1 (de) * 2000-02-05 2001-10-24 YXLON International X-Ray GmbH Verfahren zur automatischen Gussfehlererkennung in einem Prüfling
GB201704373D0 (en) * 2017-03-20 2017-05-03 Rolls-Royce Ltd Surface defect detection
TWI653605B (zh) * 2017-12-25 2019-03-11 由田新技股份有限公司 利用深度學習的自動光學檢測方法、設備、電腦程式、電腦可讀取之記錄媒體及其深度學習系統
CN110570410B (zh) * 2019-09-05 2022-03-22 河北工业大学 一种自动识别检测焊缝缺陷的检测方法
CN111539923B (zh) * 2020-04-17 2023-06-02 西安数合信息科技有限公司 一种焊缝缺陷的数字射线检测方法、系统及服务器

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4694479A (en) * 1983-12-05 1987-09-15 Kohaszati Cyaropito Vallalat Gepipari Technologiai Intezet Video-radiographic process and equipment for a quality controlled weld seam
JPH0896136A (ja) * 1994-09-26 1996-04-12 Kawasaki Heavy Ind Ltd 溶接欠陥の評価システム
DE102008062866A1 (de) * 2008-11-13 2010-05-20 Daimler Ag Verfahren zur Qualitätsüberwachung einer Verbindungsnaht sowie Vorrichtung zum Laserschweißen oder Laserlöten
CN105938620A (zh) * 2016-04-14 2016-09-14 北京工业大学 一种小口径管内焊缝表面缺陷识别装置
WO2020048119A1 (en) * 2018-09-04 2020-03-12 Boe Technology Group Co., Ltd. Method and apparatus for training a convolutional neural network to detect defects
CN110779937A (zh) * 2019-10-11 2020-02-11 上海航天精密机械研究所 一种铸件产品内部缺陷智能检测装置
CN112083017A (zh) * 2020-09-10 2020-12-15 上海航天精密机械研究所 焊缝内部缺陷智能检测装置、方法及介质
CN112184693A (zh) * 2020-10-13 2021-01-05 东北大学 一种射线工业底片焊缝缺陷智能检测方法
CN113298738A (zh) * 2021-07-13 2021-08-24 上海航天精密机械研究所 X射线焊缝图像自动增强装置及方法

Cited By (51)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114742811A (zh) * 2022-04-27 2022-07-12 桂林电子科技大学 一种基于改进Yolox的SMT产线焊点缺陷快速检测方法及系统
CN114742811B (zh) * 2022-04-27 2024-03-29 桂林电子科技大学 一种基于改进Yolox的SMT产线焊点缺陷快速检测方法及系统
WO2024040951A1 (zh) * 2022-08-26 2024-02-29 宁德时代新能源科技股份有限公司 定位目标区域的方法、装置及计算机可读存储介质
CN115482227A (zh) * 2022-09-26 2022-12-16 中机生产力促进中心有限公司 机器视觉自适应成像环境调整方法
CN115482227B (zh) * 2022-09-26 2023-09-12 中机生产力促进中心有限公司 机器视觉自适应成像环境调整方法
CN115546137A (zh) * 2022-09-29 2022-12-30 浙江新宝汽车电器有限公司 一种柔性线束的x光自动检测方法
CN115797314A (zh) * 2022-12-16 2023-03-14 哈尔滨耐是智能科技有限公司 零件表面缺陷检测方法、系统、设备及存储介质
CN115797314B (zh) * 2022-12-16 2024-04-12 哈尔滨耐是智能科技有限公司 零件表面缺陷检测方法、系统、设备及存储介质
CN116051542A (zh) * 2023-03-06 2023-05-02 深圳市深视智能科技有限公司 缺陷检测方法及缺陷检测装置
CN116051542B (zh) * 2023-03-06 2023-07-14 深圳市深视智能科技有限公司 缺陷检测方法及缺陷检测装置
CN116188475B (zh) * 2023-05-05 2023-07-25 德中(深圳)激光智能科技有限公司 一种外观缺陷自动光学检测的智慧控制方法、系统及介质
CN116188475A (zh) * 2023-05-05 2023-05-30 德中(深圳)激光智能科技有限公司 一种外观缺陷自动光学检测的智慧控制方法、系统及介质
CN116258718B (zh) * 2023-05-15 2023-10-31 超音速人工智能科技股份有限公司 基于3d相机的焊接质量检测方法、系统、设备及介质
CN116258718A (zh) * 2023-05-15 2023-06-13 超音速人工智能科技股份有限公司 基于3d相机的焊接质量检测方法、系统、设备及介质
CN116596891A (zh) * 2023-05-22 2023-08-15 南京林业大学 基于半监督多任务检测的木地板颜色分类及缺陷检测方法
CN116433659B (zh) * 2023-06-09 2023-08-29 山东高速工程检测有限公司 一种三段式道路缺陷图像处理方法
CN116433659A (zh) * 2023-06-09 2023-07-14 山东高速工程检测有限公司 一种三段式道路缺陷图像处理方法
CN116612120B (zh) * 2023-07-20 2023-10-10 山东高速工程检测有限公司 一种针对数据不平衡的两阶段式道路缺陷检测方法
CN116612120A (zh) * 2023-07-20 2023-08-18 山东高速工程检测有限公司 一种针对数据不平衡的两阶段式道路缺陷检测方法
CN116958086B (zh) * 2023-07-21 2024-04-19 盐城工学院 具有增强特征融合能力的金属表面缺陷检测方法及系统
CN116958086A (zh) * 2023-07-21 2023-10-27 盐城工学院 具有增强特征融合能力的金属表面缺陷检测方法及系统
CN117079100B (zh) * 2023-08-14 2024-02-09 北京大学 一种基于深度学习的焊缝缺陷识别系统
CN117299596B (zh) * 2023-08-14 2024-05-24 江苏秦郡机械科技有限公司 一种自动检测的物料筛选系统及其筛选方法
CN117299596A (zh) * 2023-08-14 2023-12-29 江苏秦郡机械科技有限公司 一种自动检测的物料筛选系统及其筛选方法
CN117079100A (zh) * 2023-08-14 2023-11-17 北京大学 一种基于深度学习的焊缝缺陷识别系统
CN116765635A (zh) * 2023-08-18 2023-09-19 济南邦德激光股份有限公司 一种用于激光切割机的焊缝识别方法及识别系统
CN116765635B (zh) * 2023-08-18 2024-04-12 济南邦德激光股份有限公司 一种用于激光切割机的焊缝识别方法及识别系统
CN116883400B (zh) * 2023-09-07 2023-11-21 山东大学 一种激光选区熔化过程中的铺粉孔隙率预测方法及系统
CN116883400A (zh) * 2023-09-07 2023-10-13 山东大学 一种激光选区熔化过程中的铺粉孔隙率预测方法及系统
CN116930194B (zh) * 2023-09-14 2023-12-08 张家港思复安全科技有限公司 一种搅拌摩擦焊的缺陷检测系统、方法、电子设备和介质
CN116930194A (zh) * 2023-09-14 2023-10-24 张家港思复安全科技有限公司 一种搅拌摩擦焊的缺陷检测系统、方法、电子设备和介质
CN117066690A (zh) * 2023-09-28 2023-11-17 苏师大半导体材料与设备研究院(邳州)有限公司 一种半导体加工用对准焊接装置
CN117066690B (zh) * 2023-09-28 2024-01-23 苏师大半导体材料与设备研究院(邳州)有限公司 一种半导体加工用对准焊接装置
CN117036348B (zh) * 2023-10-08 2024-01-09 中国石油大学(华东) 基于图像处理和裂纹识别模型的金属疲劳裂纹检测方法
CN117036348A (zh) * 2023-10-08 2023-11-10 中国石油大学(华东) 基于图像处理和裂纹识别模型的金属疲劳裂纹检测方法
CN117437188B (zh) * 2023-10-17 2024-05-28 广东电力交易中心有限责任公司 一种用于智慧电网的绝缘子缺陷检测系统
CN117437188A (zh) * 2023-10-17 2024-01-23 广东电力交易中心有限责任公司 一种用于智慧电网的绝缘子缺陷检测系统
CN117095245A (zh) * 2023-10-19 2023-11-21 阿法龙(山东)科技有限公司 一种基于深度学习的无缝钢管小样本学习方法
CN117115162A (zh) * 2023-10-24 2023-11-24 中安芯界控股集团有限公司 基于视觉分析对电池进行检测的芯片生产控制系统
CN117314916B (zh) * 2023-11-29 2024-01-30 宝鸡市钛程金属复合材料有限公司 一种基于人工智能的金属复合板爆炸焊接检测方法
CN117314916A (zh) * 2023-11-29 2023-12-29 宝鸡市钛程金属复合材料有限公司 一种基于人工智能的金属复合板爆炸焊接检测方法
CN117381261B (zh) * 2023-12-13 2024-03-08 德阳市华建机械设备有限公司 一种自动化焊接机的故障识别装置及方法
CN117381261A (zh) * 2023-12-13 2024-01-12 德阳市华建机械设备有限公司 一种自动化焊接机的故障识别装置及方法
CN117438330A (zh) * 2023-12-19 2024-01-23 武创芯研科技(武汉)有限公司 一种基于平面压痕的晶圆封装级rdl再布线层缺陷检测方法
CN117438330B (zh) * 2023-12-19 2024-04-02 武创芯研科技(武汉)有限公司 一种基于平面压痕的晶圆级封装rdl再布线层缺陷检测方法
CN117607155B (zh) * 2024-01-24 2024-04-19 山东大学 一种应变片外观缺陷检测方法及系统
CN117607155A (zh) * 2024-01-24 2024-02-27 山东大学 一种应变片外观缺陷检测方法及系统
CN117745718A (zh) * 2024-02-19 2024-03-22 工业云制造(四川)创新中心有限公司 一种基于云制造的信息交互方法
CN117853493A (zh) * 2024-03-08 2024-04-09 山东天意机械股份有限公司 一种基于图像处理的墙板生产质量检测方法
CN117853493B (zh) * 2024-03-08 2024-05-24 山东天意机械股份有限公司 一种基于图像处理的墙板生产质量检测方法
CN118169547A (zh) * 2024-05-13 2024-06-11 常州忆隆信息科技有限公司 一种电动吻合器单次使用电路检测方法及系统

Also Published As

Publication number Publication date
CN112083017A (zh) 2020-12-15

Similar Documents

Publication Publication Date Title
WO2022053001A1 (zh) 焊缝内部缺陷智能检测装置、方法及介质
CN110779937B (zh) 一种铸件产品内部缺陷智能检测装置
CN113034478B (zh) 一种基于深度学习网络的焊缝缺陷识别定位方法、系统
CN113469177B (zh) 基于深度学习的排水管道缺陷检测方法及系统
CN104977313A (zh) 一种焊缝x射线图像缺陷检测与识别方法和装置
CN109859163A (zh) 一种基于特征金字塔卷积神经网络的lcd缺陷检测方法
CN109285139A (zh) 一种基于深度学习的x射线成像焊缝检测方法
CN102175701B (zh) 工业x射线机在线探伤检测系统及方法
CN110047073A (zh) 一种x射线焊缝图像缺陷定级方法及系统
CN112700444B (zh) 基于自注意力与中心点回归模型的桥梁螺栓检测方法
CN109658396A (zh) 一种基于选择性搜索与cnn的铸件x光图像缺陷识别方法
CN112150410A (zh) 一种焊缝缺陷的自动检测方法及其系统
CN110097547B (zh) 一种基于深度学习的焊缝底片造假的自动检测方法
CN113421230B (zh) 基于目标检测网络的车载液晶屏导光板缺陷视觉检测方法
CN109142533A (zh) 一种铸件内部缺陷的快速检测方法及设备
CN113012123A (zh) 碳纤维复合材料缺陷损伤分类识别与定量分析方法及系统
CN111783616B (zh) 一种基于数据驱动自学习的无损检测方法
CN110660049A (zh) 一种基于深度学习的轮胎缺陷检测方法
Provencal et al. Identification of weld geometry from ultrasound scan data using deep learning
CN117173461A (zh) 一种多视觉任务的灌装容器缺陷检测方法、系统及介质
CN115760837A (zh) 一种基于深度神经网络的晶体质量评估方法及系统
CN115861170A (zh) 基于改进yolo v4算法的表面缺陷检测方法
CN115047015A (zh) 一种在线式x射线无损探伤检测方法及其系统
CN110335242A (zh) 一种基于多模型融合的轮胎x光病疵检测方法
CN117372402A (zh) 一种焊缝缺陷检测方法、装置、计算机设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21866053

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21866053

Country of ref document: EP

Kind code of ref document: A1