CN111213053A - Device and method for detecting inner wall of micro-fine tube based on coherent light - Google Patents
Device and method for detecting inner wall of micro-fine tube based on coherent light Download PDFInfo
- Publication number
- CN111213053A CN111213053A CN201880067108.9A CN201880067108A CN111213053A CN 111213053 A CN111213053 A CN 111213053A CN 201880067108 A CN201880067108 A CN 201880067108A CN 111213053 A CN111213053 A CN 111213053A
- Authority
- CN
- China
- Prior art keywords
- defect
- wall
- coherent light
- microtube
- calculation results
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 230000001427 coherent effect Effects 0.000 title claims abstract description 96
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000007547 defect Effects 0.000 claims abstract description 233
- 238000001514 detection method Methods 0.000 claims abstract description 102
- 239000000523 sample Substances 0.000 claims abstract description 66
- 239000013307 optical fiber Substances 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 174
- 230000004044 response Effects 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 15
- 238000007689 inspection Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 238000005286 illumination Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000004901 spalling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/954—Inspecting the inner surface of hollow bodies, e.g. bores
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
A device (100) and a method for detecting the inner wall of a microtube (101) based on coherent light, wherein the device (100) comprises: the coherent light emitter (108) is used for generating coherent light and transmitting the coherent light to the detection probe (102) through the first lens (105), the half-mirror (104) and the optical fiber (103); the detection probe (102) is used for projecting coherent light onto the inner wall of the microtube (101) and transmitting the reflected coherent light to a coherent light receiver (107) through an optical fiber (103), a half-mirror (104) and a second lens (106); the coherent light receiver (107) is used for obtaining a speckle image of the inner wall of the microtube (101) according to the reflected coherent light; and transmitting the speckle image of the inner wall of the microtube (101) to a graphic processor (109); and the image processor (109) is used for determining the defect type of the inner wall of the microtube (101) according to the speckle image of the inner wall of the microtube (101). The device solves the problem that the defects of the inner wall of the microtube can not be detected in the prior art.
Description
The application relates to the field of pipeline detection, in particular to a device and a method for detecting the inner wall of a micro-capillary based on coherent light.
The micro-fine tube and the inner hole with small size characteristics are widely applied in the fields of mechanical manufacturing industry, chemical industry, medical instruments and the like. Once explosion, leakage and other accidents happen to the critical inner hole structure, the whole machine cannot work, and even the life and property of people are seriously threatened. The detection of the defects on the inner wall of the microtube has important significance for manufacturing, quality control and safety guarantee.
In the conventional pipeline detection, a non-optical nondestructive detection method is mostly adopted in industry, and mainly utilizes the electromagnetic properties, ultrasonic waves and the like of pipeline materials to carry out detection, including a magnetic leakage method, an eddy current method, an ultrasonic wave method and the like. The other is contact measurement, which is a measurement method for obtaining measurement information mainly by direct contact between a sensing element of a measurement device and a measured surface. The disadvantage is that frequent contact of the probe with the pipe wall can cause wear of the probe, which needs to be calibrated frequently in order to maintain accuracy; the point-by-point measurement has slow measurement speed and low detection efficiency, and can not detect the inner hole of the micro-pipeline or the part with the diameter smaller than the diameter of the probe.
Aiming at the problems that the detection requirements of small-sized micro pipelines and inner holes of parts are increasingly large, the internal space of the micro pipelines is narrow, the requirement on system detection precision is high, the detection requirements of the pipelines cannot be met by the conventional detection methods, the effective detection method is basically based on optical visual detection and a wired laser 3D scanning method, and by adopting a charge-coupled device (CCD) camera, small lamps for illumination are arranged on the periphery and directly shoot the inner wall of the pipeline, and the obtained images are analyzed to identify the defect area, the defect size and the like. The two methods are suitable for pipelines with larger diameters, can realize measurement with higher precision, but the required imaging device is larger, so that the pipelines with relatively small structures cannot be operated. In addition, the image on the inner wall of the tube is influenced by uneven illumination, inaccurate imaging focusing and image distortion, so that the detection effect is reduced; in summary, the inner wall of the micro-tube cannot be detected based on the conventional illumination method and imaging technology.
Disclosure of Invention
The embodiment of the application provides a device and a method for detecting the inner wall of a micro-capillary based on coherent light, which solve the problem that the defects of the inner wall of the micro-capillary cannot be accurately detected in the prior art.
In a first aspect, an embodiment of the present application provides an apparatus for inspecting an inner wall of a microtube, comprising:
the detection probe comprises a semi-transparent semi-reflecting mirror, a first lens, a second lens, a coherent light emitter, a coherent light receiver and an image processor, wherein the semi-transparent semi-reflecting mirror, the first lens, the second lens, the coherent light emitter, the coherent light receiver and the image processor are connected with the detection probe through optical fibers; a conical reflector is arranged at the front end of the detection probe;
the coherent light emitter is used for generating incident coherent light and transmitting the incident coherent light to the detection probe through the first lens, the semi-transparent and semi-reflective mirror and the optical fiber;
the conical reflector of the detection probe is used for projecting the incident coherent light onto the inner wall of the microtube, reflecting the coherent light reflected by the inner wall of the microtube, and transmitting the coherent light to the coherent light receiver through the optical fiber, the semi-transparent semi-reflecting mirror and the second lens;
the coherent light receiver is used for obtaining a speckle image of the inner wall of the micro-tube according to the reflected coherent light; the speckle images of the inner wall of the micro-tube are transmitted to the image processor;
the image processor is used for determining the defect type of the inner wall of the microtube according to the speckle image of the inner wall of the microtube.
In a possible embodiment, the speckle images of the inner wall of the microtube include a plurality of panoramic sub-speckle images of the inner wall of the microtube, and the image processor determines the defect type of the inner wall of the microtube according to the speckle images of the inner wall of the microtube, including:
the image processor splices the panoramic sub-speckle images of the inner walls of the micro-capillaries into panoramic speckle images of the inner walls of the micro-capillaries;
the image processor calculates the panoramic speckle image of the inner wall of the micro-tube according to the defect identification model to obtain a calculation result;
and the image processor acquires the defect type corresponding to the calculation result from the corresponding relation table of the calculation result and the defect type so as to determine the defect type of the inner wall of the microtube.
In a possible embodiment, the image processor is further configured to:
before determining the defect type of the inner wall of the micro-capillary according to the calculation result, acquiring a plurality of groups of speckle images, wherein each speckle image in each group of speckle images of the plurality of groups of speckle images corresponds to one defect type;
performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;
respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
In a possible embodiment, the image processor is further configured to:
before determining the defect type of the inner wall of the micro-capillary according to the calculation result, sending a request message to a third-party server, wherein the request message is used for requesting to acquire the defect identification model and the corresponding relation table of the calculation result and the defect type, which are stored by the third-party server;
and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
In a possible embodiment, the image processor is further configured to:
after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;
according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;
inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
In a possible embodiment, the apparatus further comprises: the movement mechanism is connected with the detection probe;
the motion mechanism is used for dragging the detection probe to move in the microtube, and the distance of each movement is less than or equal to the length of the microtube detected by the detection probe each time.
In a possible embodiment, when the detection probe is of a curved shape, the detection probe further comprises:
and the rotating device is used for rotating the detection probe, and the rotating angle is the angle input by the user.
In one possible embodiment, the coherent light is a laser of any frequency from ultraviolet light to near-infrared light.
In a second aspect, an embodiment of the present application further provides a method for detecting an inner wall of a microtube based on coherent light, including:
acquiring a panoramic speckle image of the inner wall of the microtube according to coherent light reflected by the inner wall of the microtube;
the image processor calculates the panoramic speckle image of the inner wall of the micro-tube according to the defect identification model to obtain a calculation result;
and the image processor acquires the defect type corresponding to the calculation result from the corresponding relation table of the calculation result and the defect type so as to determine the defect type of the inner wall of the microtube.
In one possible embodiment, acquiring a panoramic speckle image of the inner wall of the microtube according to the coherent light reflected by the inner wall of the microtube includes:
acquiring panoramic sub-speckle images of the inner walls of the micro-fine tubes according to the coherent light reflected by the inner walls of the micro-fine tubes;
and splicing the panoramic sub-speckle images of the inner walls of the multiple micro-tubes into a panoramic speckle image of the inner wall of the micro-tube.
In a possible embodiment, the method further comprises:
before determining the defect type of the inner wall of the micro-tube according to the calculation result, acquiring a plurality of groups of speckle images, wherein each speckle image in each group of speckle images corresponds to one defect type;
performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;
respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
In a possible embodiment, the method further comprises:
before determining the defect type of the inner wall of the micro-capillary according to the calculation result, sending a request message to a third-party server, wherein the request message is used for requesting to acquire the defect identification model and the corresponding relation table of the calculation result and the defect type, which are stored by the third-party server;
and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
In a possible embodiment, the method further comprises:
after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;
according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;
inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
In one possible embodiment, the coherent light is a laser of any frequency from ultraviolet light to near-infrared light.
In a third aspect, the present embodiments also provide a computer storage medium storing a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute all or part of the method according to the second aspect.
It can be seen that, in the scheme of the embodiment of the present application, the conical reflector disposed at the front end of the detection probe irradiates the incident coherent light onto the inner wall of the microtube, and transmits the coherent light reflected by the inner wall of the microtube to the coherent light receiver; the coherent light receiver obtains a speckle image of the inner wall of the micro-tube according to the reflected coherent light; and transmitting the speckle images of the inner wall of the micro-tube to a graphic processor; and the image processor determines the defect type of the inner wall of the micro-tube according to the speckle image of the inner wall of the micro-tube. The method and the device solve the problem that the defects of the inner wall of the micro-fine tube cannot be detected in the prior art.
These and other aspects of the present application will be more readily apparent from the following description of the embodiments.
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an apparatus for inspecting an inner wall of a microtube according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of another apparatus for detecting an inner wall of a capillary according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of coherent light imaging;
FIG. 4 is a schematic diagram illustrating a principle of detecting an inner wall of a microtube according to an embodiment of the present application;
FIG. 5 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 7 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 8 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 9 is a schematic diagram of a defect identification model provided in an embodiment of the present application;
FIG. 10 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 11 is a schematic diagram illustrating another principle of coherent light-based detection of the inner wall of a microtube according to an embodiment of the present application;
FIG. 12 is a flowchart illustrating a method for detecting an inner wall of a microtube using coherent light according to an embodiment of the present application.
Embodiments of the present application are described below with reference to the drawings.
Referring to FIG. 1, FIG. 1 is a schematic structural diagram of an apparatus for inspecting and repairing an inner wall of a microtube according to an embodiment of the present disclosure. As shown in fig. 1, the microtube inner wall detection apparatus 100 includes:
the detection probe 102, a half-mirror 104 connected with the detection probe 102 through an optical fiber 103, a first lens 105, a second lens 106, a coherent light emitter 108, a coherent light receiver 107 and an image processor 109.
The coherent light emitter 108 generates coherent light and irradiates the first lens 105, and the first lens 105 irradiates the coherent light onto the half mirror 104 located on the focal plane thereof, and transmits the coherent light to the detection probe 102 through the optical fiber 103 connected to the half mirror 104. The coherent light transmitted from the half mirror 104 through the optical fiber 103 may be referred to as incident coherent light for the detection probe 102.
As shown in fig. 2, when the thin tube inner wall detection apparatus 100 is used for detection, the detection probe 102 needs to be inserted into a micro-tube 101 to be detected, a conical reflector 1021 is provided at the front end of the detection probe 102, and the conical reflector 1021 reflects incident coherent light 10 onto the inner wall of the micro-tube 101 and reflects coherent light 11 reflected or scattered by the inner wall of the micro-tube 101.
The coherent light 11 reflected or scattered by the inner wall of the microtube 101 is transmitted to the coherent light receiver 107 through the half mirror 104 and the second lens 106, and the coherent light receiver 107 converts the received coherent light into a speckle image. Wherein the coherent light receiver 107 is located on a focal plane of the second lens 106. The design combines the illumination light path and the imaging light path, and realizes the simultaneous completion of illumination and imaging in a narrow microtube space.
The incident coherent light is laser light with any frequency from ultraviolet light to near infrared light.
Alternatively, the coherent light emitter may be a charge-coupled device (CCD) sensor or a Complementary Metal Oxide Semiconductor (CMOS) sensor.
It should be noted here that, the inner wall of the microtube has a fixed structure or a smooth surface, defects are mainly distributed on the inner wall of the member, the size of the defects is generally between 50um and 1mm, and for coherent laser with a wavelength of 650nm, the precision of the defects on the inner wall of the microtube which can be detected can reach 1 um. The microscopic deformation of the inner wall of the microtube can cause the change of diffraction spots. When light is introduced to a rough surface, scattered light is present at every point on the surface, and the scattered light is coherent light, which has different amplitudes and phases and is randomly distributed. The scattered light is superposed to form granular structures with obvious contrast, which are speckles. As shown in fig. 3, after the incident coherent light irradiates the inner wall of the capillary, the inner wall of the capillary reflects or scatters the coherent light to the coherent light receiver, and the coherent light receiver converts the received light signal into an image, so as to obtain a speckle image of the inner wall of the capillary.
Since the detecting probe 102 detects the ring zone of the current position at a fixed measuring position in the microtube 101 each time, the detecting probe needs to be drawn by a moving mechanism to move along the inside of the microtube 101, and the coherent light receiver 107 can obtain panoramic sub-images of the inner wall of the microtube at different positions, as shown in fig. 4, the inner wall sub-image of the current position is a shadow of the ring zone.
Assuming that the length of the microtube which can be detected by the detection probe 102 is d and the total length of the microtube is L each time, the detection probe needs to perform detection L/d times, and the detection of the inner wall of the microtube can be completed. After each detection by the detection probe 102, a panoramic sub-speckle image of the inner wall is obtained by the coherent light receiver; then under the traction of the motion structure, the detection probe 102 moves for a distance d, and the detection process is repeated; after the microtube with the length of L is detected, L/d inner wall panoramic sub-speckle images can be obtained, as shown in FIG. 5.
After the coherent light receiver 107 acquires each inner wall panoramic sub-speckle image, transmitting the inner wall panoramic sub-speckle image to the image processor 109; after the image processor 109 receives one inner wall panoramic sub-speckle image, a time label is marked on the inner wall panoramic sub-speckle image, and the time label is the current system time. After receiving the L/d pieces of inner wall panoramic sub-speckle images, the image processor 109 splices the L/d pieces of inner wall panoramic sub-speckle images into the panoramic speckle image of the inner wall of the microtube according to the sequence of the time tags.
Briefly described herein, an image stitching technique includes the steps of:
1) image preprocessing: and carrying out basic operations of digital image processing such as histogram matching, smoothing filtering, enhancement transformation and the like on the original image, and preparing for the next step of image splicing.
2) Image registration: the image registration is the core of the whole image stitching process, and the accuracy of the registration determines the stitching quality of the images. The basic idea is as follows: firstly, finding the corresponding positions of templates or feature points of an image to be registered and a reference image, then establishing a conversion mathematical model between the reference image and the image to be registered according to the corresponding relation, converting the image to be registered into a coordinate system of the reference image, and determining the overlapping area between the two images. The key to accurate registration is to find a data model that can well describe the transformation relationship between two images.
3) Image synthesis: after a conversion relation model between two images is determined, namely an overlapping area is determined, images to be spliced need to be inlaid into a visually feasible panoramic image according to information of the overlapping area. Due to the difference in image gray scale (or brightness) caused by different shooting conditions, or a certain registration error still exists in the image registration result, in order to reduce the influence of the remaining deformation or the difference in brightness (or gray scale) between images on the mosaic result as much as possible, a suitable image synthesis strategy needs to be selected.
In one possible embodiment, in order to improve the detection accuracy, during the detection of the inner wall of the microtube 101, the detection probe 102 moves by a distance d1 each time under the traction of the motion mechanism, where d1 is smaller than d, and after M times of detection, the detection probe 102 completes the detection of the inner wall of the microtube 101 with the length L, and obtains M panoramic sub-speckle images of the inner wall of the microtube, where M is L/d 1; since the length of the microtube that can be detected by the detection probe 102 is d each time, there are overlapping detection areas in two adjacent detection processes, and thus there are the same portions for two inner wall panoramic sub-speckle images obtained by two adjacent detections, as shown in fig. 6.
After the image processor 109 obtains the M panoramic sub-images of the inner wall of the microtube, the M panoramic sub-images of the inner wall of the microtube are spliced according to an image splicing technology to obtain a panoramic speckle image of the inner wall of the microtube.
In a possible embodiment, as shown in a diagram a of fig. 7, in order to adapt to micro-tubes with different calibers, the detection probe 102 is curved, and the detection probe 102 is provided with a rotating device 1022, which can receive the angle input by the user in a wired or wireless manner, so as to detect defects at different positions and different angles on the inner wall of the micro-tube 101, and further perform directional detection on the defects on the inner wall of the micro-tube 101.
Specifically, the length of the inspection probe 102 for inspecting the inner wall of the microtube 101 is s, as shown in a diagram of fig. 7 a; the angle of each detection is θ, as shown in the b-diagram of fig. 7, after each detection by the detection probe 102, the coherent light receiver 107 obtains an inner wall panoramic speckle pattern block and transmits the inner wall panoramic speckle pattern block to the image processor 109, and after the image processor 109 obtains the inner wall panoramic speckle pattern block, a first time stamp is marked on the inner wall panoramic speckle pattern block, where the first time stamp is the current system time; the detecting probe 102 rotates an angle θ 1 in a preset direction each time under the control of the rotating device 1022, where θ 1 is θ; the detection probe 102 finishes the detection of the inner wall of the micro-capillary at the current position after rotating 360/theta 1 times, at this time, the image processor 109 acquires 360/theta 1 pieces of inner wall panoramic speckle image blocks, the image processor 109 splices the 360/theta 1 pieces of inner wall panoramic speckle image blocks into one inner wall panoramic sub-speckle image according to the sequence of the first time tags of the inner wall panoramic speckle image blocks and according to the image splicing technology, and simultaneously, a second time tag is marked on the inner wall panoramic sub-speckle image, and the second time tag is the current system time.
Alternatively, the preset direction may be a clockwise direction or a counterclockwise direction.
After the defect detection of the inner wall of the ring belt at the current position is completed, the detection probe 102 is moved by a distance s1 along the detection direction under the traction of the motion mechanism, and s1 is s; and then, the detection probe finishes the acquisition of the inner wall panoramic sub-speckle image of the current position according to the method, and a second time label is marked on the inner wall panoramic sub-speckle image. According to the method, under the traction of the moving structure, the detection probe finishes the detection of the inner wall of the micro-tube through the detection process for L/s1 times, and the image processor acquires L/s1 inner wall panoramic sub-speckle images.
After the image processor 109 acquires the L/s1 internal wall panoramic sub-speckle images, the L/s1 internal wall panoramic sub-speckle images are spliced into an internal wall panoramic speckle image according to the sequence of the second time tags of each internal wall panoramic sub-speckle image and the image splicing technology.
Alternatively, under the control of the rotation device 1022 of the detection probe, when the detection probe 102 rotates in the preset direction by an angle θ 1 < θ, since the angle detected by the detection probe 102 at each time is θ, the areas of the inner wall of the micro-tube detected twice consecutively by the detection probe 102 overlap, and the overlapping area is as shown in fig. 8, where there is an overlapping portion between two inner wall panoramic speckle images obtained by the connector of the coherent light receiver 107. According to the method, the detection probe 102 rotates 360/theta 1 times under the control of the rotating device 1022 thereof to complete the defect detection of the inner wall of the ring zone at the current position, and the image processor 109 acquires 360/theta 1 pieces of inner wall panoramic speckle image blocks; and the image processor 109 splices the 360/theta 1 pieces of inner wall panoramic speckle image blocks into inner wall panoramic sub-speckle images at the current position according to an image splicing technology. Then, according to the method, under the traction of the moving structure, the detection probe 102 finishes the detection of the inner wall of the micro-tube through the detection process for L/s1 times, and the image processor 109 acquires L/s1 inner wall panoramic sub-speckle images.
After the image processor 109 acquires the L/s1 internal wall panoramic sub-speckle images, the L/s1 internal wall panoramic sub-speckle images are spliced into an internal wall panoramic speckle image according to the sequence of the second time tags of each internal wall panoramic sub-speckle image and the image splicing technology.
In a possible embodiment, after the image processor 109 obtains the panoramic speckle image of the inner wall of the microtube, the image processor 109 inputs the panoramic speckle image of the inner wall of the microtube into a defect identification model, the defect identification model is a neural network model, and the neural network operation is performed on the panoramic speckle image of the inner wall of the microtube through the defect identification model to obtain at least one calculation result, each calculation result corresponds to a defect type, and the image processor 109 can determine the defect type existing in the inner wall of the microtube according to the calculation result. As shown in fig. 9, the defect identification model includes an input layer, an intermediate layer, and an output layer; after the panoramic speckle images of the inner wall of the microtube are input from the input layer and are subjected to intermediate layer operation, the output layer can output four calculation results, including a first calculation result, a second calculation result, a third calculation result and a fourth calculation result, which respectively correspond to no defect, dirt, crack and deformation.
Further, the output layer of the defect identification model may output any one of the four calculation results, or output any combination of the second calculation result, the third calculation result and the fourth calculation result, that is, the defect type output by the defect identification model may be any one of defect-free, dirty, cracked and deformed; or the output defect type is any combination of dirt, crack and deformation. The method can directly determine the type of the defect in the inner wall of the microtube according to the input panoramic speckle image of the inner wall of the microtube.
In a possible embodiment, after the image processor 109 obtains the panoramic speckle image of the inner wall of the micro-pipe, the image processor 109 inputs the panoramic speckle image of the inner wall of the micro-pipe into the defect identification model. And calculating the panoramic speckle image of the inner wall of the micro-tube by using the defect identification model to obtain a calculation result, and determining the defect type corresponding to the settlement result according to the corresponding relation table of the calculation result and the defect type.
The table of the correspondence between the calculation result and the defect type is shown in table 1.
Range of calculation results | Type of defect |
(a1,a2] | Defect free |
(a2,a3] | Smudge |
(a3,a4] | Spalling of the rock |
(a4,a5) | Deformation of |
TABLE 1
Specifically, the correspondence table between the calculation result and the defect type lists 4 defect types, which are respectively defect-free, dirty, cracked and deformed. When the calculated result is greater than a1 and less than or equal to a2, the image processor 109 determines that the inner wall of the microtube is defect-free; when the settlement result is greater than a2 and less than or equal to a3, the image processor 109 determines that the defect type of the inner wall of the micro-capillary is dirty; when the settlement result is greater than a3 and less than or equal to a4, the image processor 109 determines the defect type of the inner wall of the micro-capillary as a crack; when the settlement result is more than a4 and less than a5, the image processor 109 determines the defect type of the inner wall of the micro-tube as deformation.
It should be noted that the defect types of the inner wall of the micro-tube include, but are not limited to, defect-free, smudging, chipping, and deformation.
Optionally, before the image processor 109 inputs the panoramic speckle image of the inner wall of the capillary into the defect identification model, before the image processor 109 determines the defect type of the inner wall of the capillary according to the calculation result, a plurality of groups of speckle images are obtained, where each speckle image in each group of speckle images corresponds to one defect type;
performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;
respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
As shown in table 1, the image processor 109 inputs a group of speckle images without defects into the defect recognition model to obtain a plurality of calculation results, where a1 of the calculation result range corresponding to a defect is the minimum value of the calculation results, and a2 is the maximum value of the calculation results.
In a possible embodiment, before inputting the panoramic speckle image of the inner wall of the capillary into the defect identification model, the image processor 109 sends a request message to a third-party server before determining the defect type of the inner wall of the capillary according to the calculation result, where the request message is used to request to obtain the defect identification model and the correspondence table between the calculation result and the defect type stored in the third-party server;
and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
Further, the image processor 109 is further configured to retrain the defect identification model, and update the correspondence table between the calculation result and the defect type to ensure the accuracy of defect identification, which is specifically as follows:
after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;
according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;
inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
It should be noted that, the retraining of the defect identification model and the updating of the correspondence table between the calculation result and the defect type may be performed by the third-party server, and the image processor 109 retransmits a request message to the third-party server for requesting to acquire the retrained defect identification model and the updated correspondence table between the calculation result and the defect type every time the defect type identification is performed N times by using the defect identification model and the correspondence table between the calculation result and the defect type
In a possible embodiment, the inner wall inspection device may perform defect inspection of the inner wall of the microtube at a fixed point.
Specifically, as shown in fig. 10, the detection probe 102 is provided with a conical mirror; the microtube inner wall detection device receives position information to be detected, which indicates a distance between the position to be detected and the microtube detection inlet, which is a position corresponding to the origin O as shown in fig. 10. The detection probe 102 is drawn by the moving mechanism to move to the position to be detected indicated by the information of the position to be detected, and defect detection is performed on the annular inner wall of the position to be detected. The specific process of the inspection probe 102 for detecting defects at the position to be inspected can be referred to the related description of the above embodiments, and will not be described herein.
The coherent light receiver 109 obtains a speckle image of the annular inner wall of the position to be detected according to the reflected or scattered coherent light transmitted by the optical fiber 103, and transmits the speckle image to the image processor 109, and the image processor 109 inputs the speckle image into the defect identification model for calculation to obtain a calculation result. The image processor 109 determines the defect type corresponding to the calculation result according to the correspondence table between the calculation result and the defect type, thereby determining whether the position to be detected has a defect and a defect type.
As shown in fig. 11, a rotating device is disposed in the inspection probe 102, the inspection device for the inner wall of the capillary receives information of a point to be inspected (L1, α), wherein L1 represents a distance between the point to be inspected and an inspection inlet of the capillary 101, and α represents an included angle between a straight line passing through a center point of a cross section of the point to be inspected and a straight line L2 passing through the center point, the inspection probe 102 moves to a cross section of the point to be inspected, which is located at the inspection inlet L1 of the capillary 101, under the traction of a moving mechanism, and then the inspection probe 102 rotates counterclockwise by an angle α under the control of the rotating device, with the straight line L2 as a reference line, so that the point to be inspected is located within the inspection range of the inspection probe 102, and then the inspection probe 102 inspects the point to be inspected by using coherent light, wherein a specific process of the inspection probe 102 for inspecting the point to be inspected for defects can be referred to the description of the above embodiment, and will not be described.
The coherent light receiver 107 obtains a speckle image of the annular inner wall of the point to be detected according to the reflected or scattered coherent light transmitted by the optical fiber 103, transmits the speckle image to the image processor, and the image processor 109 inputs the speckle image into the defect identification model for calculation to obtain a calculation result. The image processor 109 determines the defect type corresponding to the calculation result according to the correspondence table between the calculation result and the defect type, thereby determining whether the point to be detected has a defect and a defect type.
It can be seen that, in the scheme of the embodiment of the application, whether the inner wall of the micro-tube has a defect is determined by acquiring the speckle image of the inner wall of the micro-tube and according to the speckle image; when it is determined that the defect exists, determining the type of the defect; the defect is repaired according to the type of the defect. By adopting the method and the device, the problem that the defects of the inner wall of the microtube cannot be accurately detected in the prior art is solved, and the defects of the inner wall of the microtube are repaired.
Referring to FIG. 12, FIG. 12 is a schematic flow chart illustrating a method for inspecting an inner wall of a microtube according to an embodiment of the present disclosure. As shown in fig. 12, the method includes:
s1201, the micro-tube inner wall detection device obtains a panoramic speckle image of the micro-tube inner wall according to the coherent light reflected by the micro-tube inner wall.
In one possible embodiment, acquiring a panoramic speckle image of the inner wall of the microtube according to the coherent light reflected by the inner wall of the microtube includes:
acquiring panoramic sub-speckle images of the inner walls of the micro-fine tubes according to the coherent light reflected by the inner walls of the micro-fine tubes;
and splicing the panoramic sub-speckle images of the inner walls of the multiple micro-tubes into a panoramic speckle image of the inner wall of the micro-tube.
S1202, the micro-pipe inner wall detection device calculates the panoramic speckle image of the micro-pipe inner wall according to the defect identification model to obtain a calculation result.
S1203, the inner wall detection device of the micro-tube obtains the defect type corresponding to the calculation result from the corresponding relation table of the calculation result and the defect type, so as to determine the defect type of the inner wall of the micro-tube.
In a possible embodiment, the method further comprises:
before determining the defect type of the inner wall of the micro-tube according to the calculation result, acquiring a plurality of groups of speckle images, wherein each speckle image in each group of speckle images corresponds to one defect type;
performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;
respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
In a possible embodiment, the method further comprises:
before determining the defect type of the inner wall of the micro-capillary according to the calculation result, sending a request message to a third-party server, wherein the request message is used for requesting to acquire the defect identification model and the corresponding relation table of the calculation result and the defect type, which are stored by the third-party server;
and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
In a possible embodiment, the method further comprises:
after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;
according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;
inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;
and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
In one possible embodiment, the coherent light is a laser of any frequency from ultraviolet light to near-infrared light.
It should be noted that, specific implementation manners of the above steps S1201-S1203 can refer to the related descriptions of the embodiments shown in fig. 1-fig. 11, and are not described herein again.
Embodiments of the present application also provide a computer storage medium storing a computer program, where the computer program includes program instructions, and the program instructions, when executed by a processor, cause the computer to execute all or part of the method of the embodiment shown in fig. 12.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in view of the above, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
- A device for detecting the inner wall of a microtube based on coherent light, comprising:the detection probe comprises a semi-transparent semi-reflecting mirror, a first lens, a second lens, a coherent light emitter, a coherent light receiver and an image processor, wherein the semi-transparent semi-reflecting mirror, the first lens and the second lens are connected with the detection probe through optical fibers; a conical reflector is arranged at the front end of the detection probe;the coherent light emitter is used for generating incident coherent light and transmitting the incident coherent light to the detection probe through the first lens, the semi-transparent and semi-reflective mirror and the optical fiber;the conical reflector of the detection probe is used for projecting the incident coherent light onto the inner wall of the microtube, reflecting the coherent light reflected by the inner wall of the microtube, and transmitting the coherent light to the coherent light receiver through the optical fiber, the semi-transparent semi-reflecting mirror and the second lens;the coherent light receiver is used for obtaining a speckle image of the inner wall of the micro-tube according to the reflected coherent light; the speckle images of the inner wall of the micro-tube are transmitted to the image processor;the image processor is used for determining the defect type of the inner wall of the microtube according to the speckle image of the inner wall of the microtube.
- The apparatus of claim 1, wherein the speckle images of the inner wall of the microtube comprise a plurality of panoramic sub-speckle images of the inner wall of the microtube, and wherein the image processor determines the type of defect in the inner wall of the microtube based on the speckle images of the inner wall of the microtube, comprising:the image processor splices the panoramic sub-speckle images of the inner walls of the micro-capillaries into panoramic speckle images of the inner walls of the micro-capillaries;the image processor calculates the panoramic speckle image of the inner wall of the micro-tube according to the defect identification model to obtain a calculation result;and the image processor acquires the defect type corresponding to the calculation result from the corresponding relation table of the calculation result and the defect type so as to determine the defect type of the inner wall of the microtube.
- The apparatus of claim 2, wherein the image processor is further configured to:before determining the defect type of the inner wall of the micro-capillary according to the calculation result, acquiring a plurality of groups of speckle images, wherein each speckle image in each group of speckle images of the plurality of groups of speckle images corresponds to one defect type;performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
- The apparatus of claim 2, wherein the image processor is further configured to:before determining the defect type of the inner wall of the micro-capillary according to the calculation result, sending a request message to a third-party server, wherein the request message is used for requesting to acquire the defect identification model and the corresponding relation table of the calculation result and the defect type, which are stored by the third-party server;and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
- The apparatus of claim 3 or 4, wherein the image processor is further configured to:after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
- The apparatus of any of claims 1-5, further comprising: the movement mechanism is connected with the detection probe;the motion mechanism is used for dragging the detection probe to move in the microtube, and the distance of each movement is less than or equal to the length of the microtube detected by the detection probe each time;the detection probe also comprises a rotating device which is used for rotating the detection probe, and the rotating angle is the angle input by the user.
- A method for detecting the inner wall of a microtube based on coherent light, comprising:acquiring panoramic sub-speckle images of the inner walls of the micro-fine tubes according to the coherent light reflected by the inner walls of the micro-fine tubes; splicing the panoramic sub-speckle images of the inner walls of the multiple micro-capillary tubes into panoramic speckle images of the inner walls of the micro-capillary tubes;calculating the panoramic speckle image of the inner wall of the micro-tube according to the defect identification model to obtain a calculation result;and obtaining the defect type corresponding to the calculation result from the corresponding relation table of the calculation result and the defect type so as to determine the defect type of the inner wall of the microtube.
- The method of claim 7, further comprising:before determining the defect type of the inner wall of the micro-capillary according to the calculation result, acquiring a plurality of groups of speckle images, wherein each speckle image in each group of speckle images in the plurality of groups of speckle images corresponds to one defect type;performing neural network training according to the plurality of groups of speckle images to obtain the defect identification model;respectively inputting the multiple groups of speckle images into the defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;and acquiring a corresponding relation table of the calculation results and the defect types according to the plurality of groups of calculation results, wherein the corresponding relation table of the calculation results and the defect types comprises a calculation result range and corresponding defect types, and the upper limit and the lower limit of the calculation result range are respectively the maximum value and the minimum value of a group of calculation results corresponding to the defect types.
- The method of claim 7, further comprising:before determining the defect type of the inner wall of the micro-capillary according to the calculation result, sending a request message to a third-party server, wherein the request message is used for requesting to acquire the defect identification model and the corresponding relation table of the calculation result and the defect type, which are stored by the third-party server;and receiving a response message sent by the third-party server to respond to the request message, wherein the response message carries the defect identification model and the corresponding relation table of the calculation result and the defect type.
- The method according to any one of claims 7-9, further comprising:after the defect type identification is carried out for N times by using the defect identification model and the corresponding relation table of the calculation result and the defect type, a plurality of groups of speckle images are obtained again, wherein N is an integer larger than 1;according to the multiple groups of speckle images obtained again, retraining the defect identification model to obtain a retrained defect identification model;inputting the reacquired multiple groups of speckle images into the trained defect identification model for calculation to obtain multiple groups of calculation results, wherein each group of calculation results in the multiple groups of calculation results corresponds to one defect type;and according to the multiple groups of calculation results, re-acquiring the corresponding relation table of the calculation results and the defect types.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2018/097662 WO2020019348A1 (en) | 2018-07-27 | 2018-07-27 | Device and method for detecting inner wall of microcapillary on basis of coherent light |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111213053A true CN111213053A (en) | 2020-05-29 |
Family
ID=69180725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201880067108.9A Pending CN111213053A (en) | 2018-07-27 | 2018-07-27 | Device and method for detecting inner wall of micro-fine tube based on coherent light |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111213053A (en) |
WO (1) | WO2020019348A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113702400A (en) * | 2021-08-09 | 2021-11-26 | 复旦大学 | Panoramic technology-based pipeline inner wall defect detection system and detection method thereof |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115389538B (en) * | 2022-08-09 | 2023-12-29 | 深圳市埃芯半导体科技有限公司 | X-ray analysis device and method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2631697A1 (en) * | 1988-05-17 | 1989-11-24 | Hispano Suiza Sa | APPARATUS FOR OPTICALLY CONTROLLING THE INTERNAL PROFILE OF A TUBE OR BORING |
JPH08286120A (en) * | 1995-04-13 | 1996-11-01 | Kubota Corp | In-tube inspection device |
CN101701922A (en) * | 2009-11-19 | 2010-05-05 | 西北工业大学 | Device for carrying out optical non-destructive testing on surface of annular inner wall |
CN102608124A (en) * | 2012-04-06 | 2012-07-25 | 天津大学 | Micro-pipe internal flaw and appearance measurement device and method |
JP2013066559A (en) * | 2011-09-21 | 2013-04-18 | Fujifilm Corp | Optical coherent tomographic image processing method and device for the same |
CN103063684A (en) * | 2012-12-20 | 2013-04-24 | 西安石油大学 | Pipeline inner wall panorama display and defect location method |
CN103673880A (en) * | 2013-12-06 | 2014-03-26 | 上海新跃仪表厂 | Micro-hole inner wall vision inspection system based on composite reflector and inspection method of system |
CN104568983A (en) * | 2015-01-06 | 2015-04-29 | 浙江工业大学 | Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040189987A1 (en) * | 2000-11-15 | 2004-09-30 | Quest Integrated Inc. | A method for reformer tube in situ inspection radius calculation |
DE102004045808A1 (en) * | 2004-09-22 | 2006-04-06 | Robert Bosch Gmbh | Optical measuring device for measuring a plurality of surfaces of a measurement object |
DE102014118753A1 (en) * | 2014-10-01 | 2016-04-07 | Jenoptik Industrial Metrology Germany Gmbh | Tester |
US9955088B2 (en) * | 2016-06-10 | 2018-04-24 | The Boeing Company | Hyperspectral borescope system |
CN108037190A (en) * | 2017-11-03 | 2018-05-15 | 大连理工大学 | A kind of high temperature furnace pipe damage rank intelligence assessment method based on neutral net |
-
2018
- 2018-07-27 CN CN201880067108.9A patent/CN111213053A/en active Pending
- 2018-07-27 WO PCT/CN2018/097662 patent/WO2020019348A1/en active Application Filing
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2631697A1 (en) * | 1988-05-17 | 1989-11-24 | Hispano Suiza Sa | APPARATUS FOR OPTICALLY CONTROLLING THE INTERNAL PROFILE OF A TUBE OR BORING |
US4967092A (en) * | 1988-05-17 | 1990-10-30 | Societe Anonyme Dite Hispano-Suiza | Apparatus for optically checking the inner profile of a tube or bore |
JPH08286120A (en) * | 1995-04-13 | 1996-11-01 | Kubota Corp | In-tube inspection device |
CN101701922A (en) * | 2009-11-19 | 2010-05-05 | 西北工业大学 | Device for carrying out optical non-destructive testing on surface of annular inner wall |
JP2013066559A (en) * | 2011-09-21 | 2013-04-18 | Fujifilm Corp | Optical coherent tomographic image processing method and device for the same |
CN102608124A (en) * | 2012-04-06 | 2012-07-25 | 天津大学 | Micro-pipe internal flaw and appearance measurement device and method |
CN103063684A (en) * | 2012-12-20 | 2013-04-24 | 西安石油大学 | Pipeline inner wall panorama display and defect location method |
CN103673880A (en) * | 2013-12-06 | 2014-03-26 | 上海新跃仪表厂 | Micro-hole inner wall vision inspection system based on composite reflector and inspection method of system |
CN104568983A (en) * | 2015-01-06 | 2015-04-29 | 浙江工业大学 | Active-omni-directional-vision-based pipeline inside functional defect detection device and detection method |
Non-Patent Citations (3)
Title |
---|
孙立根,朱立光著, 中国地质大学出版社, pages: 134 - 138 * |
李晓舟: "微小尺寸零件表面缺陷光学检测方法", 《兵工学报》, 31 July 2011 (2011-07-31) * |
陆文俊: "小孔径工件的内外壁视觉检测***研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 June 2015 (2015-06-15) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113702400A (en) * | 2021-08-09 | 2021-11-26 | 复旦大学 | Panoramic technology-based pipeline inner wall defect detection system and detection method thereof |
Also Published As
Publication number | Publication date |
---|---|
WO2020019348A1 (en) | 2020-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101109715B (en) | Optical method for detecting defect on inner wall of holes | |
US20190318469A1 (en) | Defect detection using coherent light illumination and artificial neural network analysis of speckle patterns | |
JP6562051B2 (en) | Inspection system | |
KR20160090359A (en) | Surface defect detection method and surface defect detection device | |
Rodríguez-Martín et al. | Procedure for quality inspection of welds based on macro-photogrammetric three-dimensional reconstruction | |
CN101109716A (en) | Optical detecting method for internal surface of hole | |
US11410298B2 (en) | System and method for determining part damage | |
JPWO2016208622A1 (en) | Surface defect detection device and surface defect detection method | |
CN111213053A (en) | Device and method for detecting inner wall of micro-fine tube based on coherent light | |
CN114280075B (en) | Online visual detection system and detection method for surface defects of pipe parts | |
CN108827186A (en) | A kind of interior thorax contour measuring method of long and narrow cavity | |
Zhang et al. | Research on surface defect detection of ceramic ball based on fringe reflection | |
JP2005283440A (en) | Vibration measuring device and measuring method thereof | |
CN106796159A (en) | Method and apparatus for determining the geometric properties of fibre-optical preform | |
Guan et al. | Defect detection method for specular surfaces based on deflectometry and deep learning | |
Yuan et al. | High dynamic online detection method for surface defects of small diameter reflective inner wall | |
JP2006170684A (en) | Method and device for inspecting press failure | |
Yoshizawa et al. | Development of an inner profile measurement instrument using a ring beam device | |
CN204630951U (en) | Pipeline on-line measuring device | |
JP2006519990A (en) | A method to measure three-dimensional objects by back-light shadowgraphy | |
JP6064942B2 (en) | Surface defect detection method and surface defect detection apparatus | |
JP4791338B2 (en) | Optical measuring device | |
GB2624002A (en) | Method and system for characterizing perforations in a tubular | |
Frangione et al. | Multi-step approach for automated scaling of photogrammetric micro-measurements | |
CN110345866B (en) | Measuring device and method for hole measurement of handheld scanner |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |