CN113793338A - Method, system and device for detecting defects of metal piece with hole and storage medium - Google Patents

Method, system and device for detecting defects of metal piece with hole and storage medium Download PDF

Info

Publication number
CN113793338A
CN113793338A CN202111365981.6A CN202111365981A CN113793338A CN 113793338 A CN113793338 A CN 113793338A CN 202111365981 A CN202111365981 A CN 202111365981A CN 113793338 A CN113793338 A CN 113793338A
Authority
CN
China
Prior art keywords
detection
detection module
piece
detected
image
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.)
Granted
Application number
CN202111365981.6A
Other languages
Chinese (zh)
Other versions
CN113793338B (en
Inventor
不公告发明人
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Shulian Cloud Computing Technology Co ltd
Original Assignee
Chengdu Shulian Cloud Computing Technology Co ltd
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 Chengdu Shulian Cloud Computing Technology Co ltd filed Critical Chengdu Shulian Cloud Computing Technology Co ltd
Priority to CN202111365981.6A priority Critical patent/CN113793338B/en
Publication of CN113793338A publication Critical patent/CN113793338A/en
Application granted granted Critical
Publication of CN113793338B publication Critical patent/CN113793338B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/95Computational photography systems, e.g. light-field imaging systems
    • H04N23/951Computational photography systems, e.g. light-field imaging systems by using two or more images to influence resolution, frame rate or aspect ratio
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30108Industrial image inspection
    • G06T2207/30136Metal

Abstract

The embodiment of the application provides a method, a system and a device for detecting defects of a metal piece with a hole and a storage medium, wherein the transparent detection turntable is controlled to rotate; when the piece to be detected passes through a first detection module of the plurality of detection modules, controlling the first detection module to acquire a first image of the piece to be detected, and determining whether a defect exists on a first surface of the piece to be detected based on the first image; if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; and if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images. The technical problem of large resource consumption in the defect detection of the metal piece with the hole is solved.

Description

Method, system and device for detecting defects of metal piece with hole and storage medium
Technical Field
The invention relates to the technical field of perforated metal part product control, in particular to a method, a system and a device for detecting defects of a perforated metal part and a storage medium.
Background
The perforated metal piece is a common part in a mechanical product, and the quality of the finished product is directly influenced by the product quality of the perforated metal piece, so that the defect detection of the perforated metal piece is an important link of quality control.
In the prior art, the resource consumption is large when the defects of the metal piece with the hole are detected.
Disclosure of Invention
The application mainly aims to provide a method, a system and a device for detecting defects of a perforated metal part and a storage medium, and solves the technical problem of high resource consumption in defect detection of the existing perforated metal part.
In order to achieve the above object, an embodiment of the present application provides a method for detecting defects of a metal piece with a hole, which is used for a device for detecting defects of a metal piece with a hole, and the device for detecting defects of a metal piece with a hole further includes a detection turntable and a plurality of detection modules; the detection turntable is provided with a plurality of detection stations;
the method comprises the following steps:
controlling the detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition regions of the plurality of detection modules when rotating along with the detection turntable;
when the piece to be detected passes through a first detection module of the plurality of detection modules, controlling the first detection module to acquire a first image of the piece to be detected, and determining whether a defect exists on a first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface;
if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
and if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images.
Optionally, the detection turntable is a transparent detection turntable; the plurality of detection modules comprise an inner wall detection module, an upper surface detection module, a lower surface detection module and a side detection module; the first detection module is any one of an inner wall detection module, an upper surface detection module, a lower surface detection module and a side detection module.
Optionally, the plurality of detection modules are sequentially arranged along the rotation direction of the transparent detection turntable according to the defect severity or the defect occurrence probability; and the defect severity is the defect severity of the detection surface corresponding to the detection module.
Optionally, the inner wall detection module, the upper surface detection module, the lower surface detection module and the side detection module are sequentially arranged along the rotation direction of the transparent detection turntable.
Optionally, after the step of controlling the rotation of the transparent detection turntable, the method further includes:
when the to-be-detected piece is detected to be placed in the detection station, generating a virtual tracing code of the to-be-detected piece; the virtual tracing code comprises an identifier of the to-be-detected piece and an initialized defect detection result;
if the first surface has defects, the step of controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition any more, comprises the following steps:
and if the first surface has defects, updating the defect detection result in the virtual tracing code, and controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition.
Optionally, the mark of the to-be-detected piece is the generation time of the tracing code, and the initialized defect detection result comprises the detection defect-free state of the to-be-detected piece and the defect-free state of each detection surface;
if the first surface has defects, the step of updating the defect detection result in the virtual traceback code includes:
and if the first surface has defects, updating the initialization defect detection result to obtain a defect detection result, wherein the defect detection result comprises that the first surface has defects and the piece to be detected has defects.
Optionally, the device for detecting the defects of the perforated metal piece further comprises a sensor;
after the step of controlling the rotation of the transparent detection turntable, the method further comprises the following steps:
when station information acquired by the sensor is received, controlling the first detection module to acquire a first image of the piece to be detected; and the station information is information that the detection station passes through the first detection module.
Optionally, when the first detection module is an upper surface detection module;
when detecting that it passes through first detection module in a plurality of detection modules to wait to detect the piece, control first detection module gather wait to detect the step of the first image of piece, include:
when the piece to be detected passes through a first detection module of the plurality of detection modules, acquiring a first image of the piece to be detected under the condition that the working distance WD of a lens of the first detection module is controlled to meet a first relational expression;
the first relation is:
Figure 478887DEST_PATH_IMAGE001
wherein d is the diameter of the first surface, and H is the horizontal field angle of the lens of the first detection module.
Optionally, the side detection module comprises N groups of area-array cameras, the N groups of area-array cameras are mounted around a target position in an encircling manner, the target position is a position through which the detection station passes in the rotation process of the transparent detection turntable, and N is an integer greater than or equal to 4;
when the first detection module is a side detection module, when detecting that the piece to be detected passes through a first detection module of the plurality of detection modules, the step of controlling the first detection module to acquire a first image of the piece to be detected comprises the following steps:
and when the piece to be detected passes through the side detection module, controlling N groups of area-array cameras to simultaneously acquire side images of the piece to be detected, wherein each group of area-array cameras acquires an image of 1/N area of the side of the piece to be detected.
Optionally, the to-be-detected piece comprises a first upper surface and a second upper surface; the upper surface detection module comprises a first upper surface detection module and a second upper surface detection module, the first upper surface detection module is used for collecting a first upper surface image, and the second upper surface detection module is used for collecting a second upper surface image; the first upper surface detection module and the second upper surface detection module are identical in structure;
the first upper surface detection module or the second upper surface detection module comprises a second support and a first camera movably connected to the second support, and a lens of the first camera faces the detection station from the upper part of the transparent detection turntable, so that the first camera is used for collecting a first upper surface image or a second upper surface image of the perforated metal part from the upper part of the transparent detection turntable;
the lower surface detection module comprises a third support and a second camera movably connected to the third support, and a lens of the second camera faces the detection station from the lower part of the transparent detection turntable, so that the second camera is used for collecting the lower surface image of the perforated metal piece from the lower part of the transparent detection turntable.
Optionally, the device for detecting the defect of the perforated metal piece further comprises a touch screen;
after determining that the to-be-detected piece has the defect, the method further comprises the following steps:
and sending the defect detection result to the touch screen so that the touch screen displays the defect detection result.
Optionally, the station spacing between adjacent detection stations on the detection turntable is equal.
Optionally, the station pitch is greater than or equal to the diameter of the piece to be detected, and the station pitch is less than or equal to the module pitch between the adjacent detection modules.
In addition, in order to achieve the above object, an embodiment of the present application further provides a defect detecting system for a perforated metal piece, which is used for the defect detecting device for the perforated metal piece, and the defect detecting device for the perforated metal piece further includes a transparent detecting turntable and a plurality of detecting modules; the transparent detection turntable is provided with a plurality of detection stations;
the system comprises:
the first control module is used for controlling the transparent detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition regions of the plurality of detection modules when rotating along with the transparent detection turntable;
the second control module is used for controlling the first detection module to collect a first image of the piece to be detected when the piece to be detected passes through a first detection module of the plurality of detection modules, and determining whether a defect exists on the first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface;
the third control module is used for controlling the second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules if the first surface has no defects, and determining whether the second surface of the piece to be detected has defects or not based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
and the fourth control module is used for controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition if the first surface has defects.
In addition, in order to achieve the above object, the present application further provides a device for detecting a defect of a perforated metal member, the device includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the foregoing method.
In addition, to achieve the above object, the present application further provides a computer readable storage medium, where a computer program is stored, and a processor executes the computer program to implement the foregoing method.
Furthermore, to achieve the above object, the present application also provides a computer program product, which when being processed, realizes the aforementioned method.
Compared with the prior art, the invention has the beneficial effects that:
the embodiment of the application provides a method, a system and a device for detecting the defects of a metal piece with a hole and a storage medium, which are used for a device for detecting the defects of the metal piece with the hole, wherein the device for detecting the defects of the metal piece with the hole further comprises a transparent detection turntable and a plurality of detection modules; the transparent detection turntable is provided with a plurality of detection stations; the method comprises the following steps: controlling the transparent detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition areas of the plurality of detection modules when rotating along with the transparent detection turntable; when the piece to be detected passes through a first detection module of the plurality of detection modules, controlling the first detection module to acquire a first image of the piece to be detected, and determining whether a defect exists on a first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface; if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module; and if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images.
That is, the embodiment of this application provides a substitute artificial automatic checkout device based on foraminiferous metalwork defect detecting device, on this basis, through in the testing process after there is the defect in certain one side detection of waiting to detect the piece, then follow-up module no longer gathers the image to this product and detects, directly skips, reduce image acquisition and software processing time, the waste of the computational resource to the resource has been reduced promptly, the big technical problem of resource consumption when having solved foraminiferous metalwork's defect detection, and because reduce image acquisition and software processing time, whole equipment work efficiency improves.
Drawings
Fig. 1 is a schematic structural diagram of a defect detection apparatus for a metal piece with a hole according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of another apparatus for detecting defects of a porous metal part according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an inner wall detection module or an upper surface detection module in the apparatus for detecting defects of a porous metal piece according to an embodiment of the present disclosure;
fig. 4 is a schematic view of a bearing structure provided in an embodiment of the present application
FIG. 5 is a schematic structural diagram of a lower surface detection module in the apparatus for detecting defects of a metal with via according to an embodiment of the present disclosure;
FIG. 6 is a schematic structural diagram of a side inspection module in the apparatus for detecting defects of a holey metal piece according to an embodiment of the present disclosure;
FIG. 7 is a schematic diagram of the side inspection module of FIG. 6;
fig. 8 is a schematic flowchart of a method for detecting defects of a metal part with holes according to an embodiment of the present disclosure;
fig. 9 is an explanatory diagram of a virtual traceback code provided in an embodiment of the present application;
FIG. 10 is an image of a bearing inner wall with a defect collected by the defect detecting device for a porous metal piece in the embodiment of the present application;
FIG. 11 is an image of a bearing inner wall having a burr defect collected by the apparatus for detecting a defect of a porous metal piece in an embodiment of the present application;
FIG. 12 is an image of a bearing inner wall having a blowhole defect collected by the apparatus for detecting a defect of a porous metal piece in the embodiment of the present application;
FIG. 13 is a bearing image taken with a conventional endoscope;
fig. 14 is a schematic structural diagram of a system for detecting defects of a metal piece with a hole according to an embodiment of the present application.
In the figure, 1, a pedestal, 2, a transparent detection turntable, 3, an inner wall detection module, 301, a first support, 302, an endoscope, 41, a first upper surface detection module, 42, a second upper surface detection module, 51, a third array camera, 52, a fourth array camera, 53, a first array camera, 54, a second array camera, 6, a lower surface detection module, 61, a third support, 62, a second camera, 7, a mechanical arm, 8, a discharge table, 9, a material pushing cylinder, 10, a cabinet body, 11, and a touch screen.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The main solution of the embodiment of the application is as follows: the defect detection device for the metal piece with the hole also comprises a transparent detection turntable and a plurality of detection modules; the transparent detection turntable is provided with a plurality of detection stations; the method comprises the following steps: controlling the transparent detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition areas of the plurality of detection modules when rotating along with the transparent detection turntable; when the piece to be detected passes through a first detection module of the plurality of detection modules, controlling the first detection module to acquire a first image of the piece to be detected, and determining whether a defect exists on a first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface; if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module; and if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images.
In the prior art, because the perforated metal part relates to a plurality of detection surfaces and different surface orientations, the prior detection technology is that all pictures shot by a camera are sent to an algorithm for processing, the priority is not available, and when all pictures are analyzed, whether the defects exist is judged, the processing load of a computer is large, each surface of each product needs to be shot, and the service life of the camera is reduced due to long-time work; the next product can be detected only after a certain product is specified to be detected, and for the product with the diameter within 100mm and 5 or 6 surfaces to be detected, the mode is not efficient, so that the resource consumption is high during the defect detection of the perforated metal piece.
The application provides a solution, provide a substitute artificial automatic checkout device based on foraminiferous metalwork defect detection device, on this basis, through after detecting certain face when waiting to detect the piece in the testing process and having the defect, then follow-up module no longer gathers the image and detects to this product, directly jump over, reduce image acquisition and software processing time, the waste to the computational resource of resource has been reduced promptly, the big technical problem of resource consumption when having solved the defect detection of foraminiferous metalwork, and because reduce image acquisition and software processing time, whole equipment work efficiency improves.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a device for detecting defects of a perforated metal piece in a hardware operating environment according to an embodiment of the present application.
As shown in fig. 1, the apparatus for detecting defects of a perforated metal member may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in figure 1 does not constitute a limitation of the apparatus for detecting defects in a perforated metal article and may include more or fewer components than those shown, or some combination of components, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and an electronic program.
In the defect detecting device for the perforated metal part shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the device for detecting the defects of the porous metal piece can be arranged in the device for detecting the defects of the porous metal piece, the device for detecting the defects of the porous metal piece calls a bad root cause positioning device in the production process of a product stored in the memory 1005 through the processor 1001, and the method for detecting the defects of the porous metal piece provided by the embodiment of the application is executed.
In an optional embodiment, the apparatus for detecting defects of a holed metal piece of the previous embodiment further includes a detection turntable and a plurality of detection modules; wherein, be provided with a plurality of detection stations on the detection carousel.
Specifically, referring to fig. 2, in the defect detecting device for a metal piece with a hole in the embodiment, the detection turntable is a transparent detection turntable 2, a plurality of detection stations are arranged on the transparent detection turntable 2, and the detection stations are used for placing a piece to be detected; the plurality of detection modules include:
the inner wall detection module 3 is used for acquiring an inner wall image of the piece to be detected;
the upper surface detection module is used for collecting an upper surface image of the piece to be detected from the upper part of the transparent detection turntable 2;
the lower surface detection module 6 is used for collecting the lower surface image of the piece to be detected from the lower part of the transparent detection turntable 2;
the side detection module is used for acquiring a side image of the piece to be detected; and the number of the first and second groups,
and the computer equipment is used for receiving the images acquired by the detection modules, and carrying out defect identification on the piece to be detected according to the images to obtain a defect detection result of the piece to be detected.
In this embodiment, the to-be-detected member is a metal member with holes, and may be a bearing or another metal member with holes.
Therefore, the inner wall detection module 3, the upper surface detection module, the lower surface detection module 6 and the side detection module are provided to detect the inner wall surface, the upper surface, the lower surface and the side of the through hole of the bearing respectively.
The following describes each structure of the apparatus of this embodiment in detail.
In this embodiment, the transparent detection turntable 2 may be an annular turntable, also referred to as a first ring in this embodiment. A plurality of detection stations are arranged on the transparent detection turntable 2; in operation, the transparent detection turntable 2 rotates at a certain speed. Specifically, the transparent detection turntable 2 adopts a hollow servo motor and a hollow speed reducer as driving, so that the speed control is convenient; the cable, the air pipe and the like are led out through the middle hole and do not interfere with each other in the rotation process; the servo motor and the speed reducer are electrically connected with computer equipment through cables so as to realize the control of the computer equipment on the transparent detection turntable 2; in addition, the glass rotary disc can be made of high-strength and high-transmittance explosion-proof glass, and the transmittance can reach 98 percent, so that the definition of a picture shot from the lower part through the transparent detection rotary disc 2 is high, and the accuracy of defect identification is ensured.
Referring to fig. 2, in this embodiment, each detection module is distributed along transparent detection carousel 2, and the piece that waits to detect on transparent detection carousel 2 when rotating along with transparent detection carousel 2, passes through each detection module in proper order to position setting through each detection module realizes respectively treating the image acquisition of each detection face of detecting the piece.
In a specific implementation process, the structure of the inner wall detection module 3 is the same as that of the upper surface detection module, referring to fig. 3, fig. 3 is a specific structure of the inner wall detection module 3, the inner wall detection module 3 includes a first bracket 302 and an endoscope 301 movably connected to the first bracket 302, and the endoscope 301 is used for collecting an inner wall image of the bearing. The endoscope 301 head is applied based on the principle of nondestructive testing, the inner wall of the bearing can be unfolded to be similar to a plane image, the defects such as impurities, burrs, sand holes and the like can be identified, and the accuracy of the defect detection of the inner wall is improved.
Referring to fig. 4, in one embodiment, the bearing of the present embodiment includes a first upper surface (surface S2) and a second upper surface (surface S3) in addition to the through-hole; in fig. 4, the surface S1 is an inner wall surface of the through hole of the bearing, the surface S4 is a side surface of the bearing, and the surface S5 is a lower surface of the bearing.
Correspondingly, the upper surface detection module comprises a first upper surface detection module 41 and a second upper surface detection module 42, the first upper surface detection module 41 is used for acquiring a first upper surface image, and the second upper surface detection module 42 is used for acquiring a second upper surface image; the first upper surface detection module 41 and the second upper surface detection module 42 have the same structure, specifically refer to fig. 2;
specifically, the first upper surface detection module 41 or the second upper surface detection module 42 includes a second bracket and a first camera movably connected to the second bracket, and a lens of the first camera faces the detection station from above the transparent detection turntable 2, so that the first camera is used for acquiring a first upper surface image or a second upper surface image of the bearing from above the transparent detection turntable 2;
referring to fig. 5, the lower surface inspection module 6 includes a third bracket 61 and a second camera 62 movably connected to the third bracket 61, and a lens of the second camera 62 faces the inspection station from below the transparent inspection turntable 2, so that the second camera 62 is used for acquiring an image of the lower surface of the bearing from below the transparent inspection turntable 2.
In the specific implementation process, the inner wall detection module 3, the first upper surface detection module 41, the second upper surface detection module 42 and the image acquisition device of the lower surface detection module 6 are movably arranged on the bracket, so that the adjustment can be performed as required. In a specific application, in order to achieve the purpose of real-time detection processing, the shooting surfaces of the image acquisition devices are required to be within the depth of field range of the lens (that is, when the piece to be detected passes through the detection module, the detection surface is within the depth of field range of the lens of the image acquisition devices), and one picture is respectively shot each time and stored and sent to the computer device for real-time detection processing, so that the detection efficiency is improved, the purpose of timely judging defects is achieved, and the purpose of determining whether the subsequent detection module continues to perform image acquisition is achieved.
Specifically, the shooting surface of the lens of the image acquisition device is within the depth of field range of the lens, and the following relational expression needs to be satisfied;
Figure 321421DEST_PATH_IMAGE001
wherein, in the step (A),
Figure 707272DEST_PATH_IMAGE003
the working distance of the lens, d the diameter of the detection surface and H the horizontal field angle of the lens.
In an embodiment, the side detecting module includes N groups of area-array cameras, where the N groups of area-array cameras are installed around a target position in an encircling manner, the target position is a position where the detecting station passes through in a rotation process of the transparent detecting turntable 2, and N is an integer greater than or equal to 4. Wherein, the target position is the position of the acquired image of the piece to be detected.
Specifically, when the transparent detection turntable 2 is in a first ring shape, referring to fig. 2 and 6, the side detection module includes 4 sets of area-array cameras, wherein two sets of area-array cameras (a first area-array camera 53 and a second area-array camera 54) are installed in the inner circle of the transparent detection turntable 2, and the other two sets of area-array cameras (a third area-array camera 51 and a fourth area-array camera 52) are installed outside the outer circle of the transparent detection turntable 2, so that the 4 sets of area-array cameras are installed around the target position in an encircling manner.
In the specific implementation process, because the outer circumference (side face) of the bearing is too large, the defect display of the common endoscope is not obvious, and the cost for customizing the endoscope with a larger visual field is too high, 4 groups of area-array cameras are adopted to be matched with the common fixed-focus lens, and pictures are acquired simultaneously, so that the cost of the device is reduced on the basis of ensuring the defect detection accuracy. As shown in fig. 7, in the side detection module, 4 cameras are mounted around each other, and each camera photographs the area of the bearing side 1/4 at the time of photographing. Each camera starts shooting from the point A to the point B (A1-B1 in the figure) simultaneously in the process that the bearing rotates along with the transparent detection turntable 2; during the period, the camera continuously takes pictures after receiving the trigger signal, and the frame rate of the camera is set according to the quantity of pictures to be taken. Because the camera adopts a frame triggering mode to acquire images, the frame rate means the number of pictures acquired per second. The calculation formula is as follows, wherein X is the picture quantity, d is the bearing diameter, and fov is the view field size; the frame rate is X/s.
Figure 628348DEST_PATH_IMAGE004
In conclusion, the setting of lower surface detection module 6 and side detection module in this embodiment can guarantee that the bearing need not overturn or rotate the operation in whole testing process, only need follow transparent detection carousel 2 and rotate can. On the basis, the quality of image acquisition can be ensured, so that the accuracy of defect detection is ensured.
In this embodiment, the images collected by each detection module are sent to a computer device for image recognition, and therefore, the computer device needs to have the existing image recognition software, such as the image recognition software based on machine learning, built therein.
In an implementation manner, the apparatus of this embodiment further includes:
the sensor is used for acquiring station information, and the station information comprises whether a bearing exists in the detection station or not;
and the computer equipment is also used for controlling each detection module to collect images according to the station information sent by the sensor.
In the specific implementation process, the sensor can be photoelectric switch sensor, sets up a plurality ofly in this embodiment, installs one on every module for gather station information, the response is promptly waited to detect whether reach the position that can image acquisition, carries out image acquisition from triggering the camera through computer equipment. Therefore, the work of each detection module can be accurately controlled through the sensor and the computer equipment, and automatic acquisition is realized.
In an implementation manner, the apparatus of this embodiment further includes:
and the mechanical arm 7 is used for transferring the bearing to the detection station or transferring the bearing out of the detection station.
In the concrete implementation process, the device of this embodiment can be lastingly to a plurality of waiting to detect a piece detect, and at the during operation, transparent detection carousel 2 rotates with certain speed, waits to detect that a piece is placed on the detection station of transparent detection carousel 2 according to certain interval. This process can be done manually, but for efficiency it can also be done by a robotic arm 7. Specifically, the mechanical arm 7 places the bearing to be detected at the previous station on the transparent detection turntable 2, and places a bearing (determined according to the diameter (D) of the bearing) at a certain distance (D) at intervals, wherein D is larger than or equal to D but not larger than the distance between the detection modules, otherwise, the detection speed is reduced. The arm 7 is placed the bearing on the transparent glass carousel according to the orderly according to interval D with the procedure that sets up, can guarantee to last to detect a plurality of detection pieces, and detection efficiency is high, and the flow production process on the specially adapted industrial production line guarantees product production efficiency promptly, can guarantee the discernment rate of accuracy to the product again.
In an implementation manner, the apparatus of this embodiment further includes:
the discharging table 8 is used for conveying the bearing;
the mechanical arm 7 is further configured to transfer the bearing from the discharging table 8 to the detection station, or transfer the bearing from the detection station to the discharging table 8.
In the specific implementation process, in order to improve the flow degree of the whole product line, the device of the embodiment is further provided with a discharging table 8, and the mechanical arm 7 can transfer the bearing from the discharging table 8 to the detection station to realize detection, or transfer the bearing from the detection station to the discharging table 8 to sequentially transfer the detected bearing.
In another embodiment, the apparatus of this embodiment further includes: and a material pushing cylinder 9. Therefore, the blanking mode of the bearing comprises two modes: firstly, 7 snatchs the unloading of arm, the advantage: the pneumatic clamping jaw grabs the product for blanking, so that glass cannot be damaged; secondly, push away material cylinder 9 and push away the material, the advantage: the speed is high, and the requirement of beat time can be met.
In an implementation manner, the apparatus of this embodiment further includes:
the touch screen 11, the touch screen 11 with computer equipment electric connection, the touch screen 11 is used for showing defect detection result and receiving control operation. In the specific implementation process, the control operation of a user can be received through the touch screen 11, so that a signal is sent to the computer equipment, and the control of the device is realized. On the other hand, the touch screen 11 can display a defect detection result, so that an operator can be prompted about the defect detection condition.
In an implementation manner, the apparatus of this embodiment further includes:
the cabinet body 10, install base 1 in the cabinet body 10, transparent detection carousel 2 rotate connect in on the base 1, the inner wall detects the module 3 the upper surface detects the module the lower surface detects the module 6 with the side detects the module and all installs on the base 1.
Referring to fig. 7, the cabinet 10 has protection and pollution isolation functions and has protection effects on bearings. The touch screen 11 can be installed on the surface of the cabinet 10 for convenient operation.
It should be understood that the above is only an example, and the technical solution of the present application is not limited in any way, and those skilled in the art can make the setting based on the actual application, and the setting is not limited herein.
Through the above description, it can be easily found that a foraminous metalwork defect detecting device of this embodiment includes: the detection device comprises a transparent detection turntable 2, wherein a plurality of detection stations are arranged on the transparent detection turntable 2, and the detection stations are used for placing a piece to be detected; the inner wall detection module 3 is used for acquiring an inner wall image of the piece to be detected; the upper surface detection module is used for collecting an upper surface image of the piece to be detected from the upper part of the transparent detection turntable 2; the lower surface detection module 6 is used for collecting the lower surface image of the piece to be detected from the lower part of the transparent detection turntable 2; the side detection module is used for acquiring a side image of the piece to be detected; and the computer equipment is used for receiving the images acquired by the detection modules, and performing defect identification on the piece to be detected according to the images to obtain a defect detection result of the piece to be detected. That is, the device's a plurality of detection modules can treat a plurality of detection faces of detecting piece and carry out comprehensive detection, solve the technical problem that current artifical detection efficiency is low. In addition, because the upper surface detection module and the lower surface detection module 6 are respectively arranged above and below the transparent glass, the piece to be detected can be directly collected by the upper surface detection module and the lower surface detection module 6 respectively on the transparent detection turntable 2, the operation such as overturning the piece to be detected is not needed, and the detection efficiency is further improved.
Referring to fig. 8, based on the apparatus for detecting defects of a holed metal piece in the foregoing embodiment, an embodiment of the present application further provides a method for detecting defects of a holed metal piece, where the method is executed by the computer device in the foregoing embodiment, and the method includes:
s20, controlling the detection turntable to rotate so that the to-be-detected pieces in the detection station sequentially pass through the image acquisition areas of the plurality of detection modules when rotating along with the detection turntable;
in the specific implementation process, the detection turntable can be controlled to rotate by computer equipment. The rotational speed (v) of detecting the carousel can be set for according to actual conditions, and as an embodiment, rotational speed (v) can be invariable to a value to keep detecting the at the uniform velocity of carousel and rotate, conveniently treat the continuous stable detection of detecting the piece.
S40, when the piece to be detected passes through a first detection module of the detection modules, controlling the first detection module to collect a first image of the piece to be detected, and determining whether the first surface of the piece to be detected has defects or not based on the first image; wherein the first image is an image of the first surface;
in the specific implementation process, the first detection module is any one of the inner wall detection module 3, the upper surface detection module, the lower surface detection module 6 and the side detection module. That is to say, under normal conditions, when waiting to detect the piece and pass through the detection module, this detection module all can carry out image acquisition to send computer equipment and carry out image recognition, obtain the defect detection result. The difference in the detection results will cause the subsequent operations to be different. Next, see S60 and S80.
S60, if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through the second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
in a specific implementation process, if the first surface has no defect, the subsequent detection is continued until a certain detection surface has a defect.
S80, if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images.
In the specific implementation process, if the first surface has defects, the piece to be detected is directly judged to have defects, and subsequent detection is not performed.
It should be noted that each detection module operates according to the steps of steps S40-S80, and performs image acquisition
Therefore, the embodiment provides a substitute artificial automatic detection device based on the porous metal part defect detection device, on the basis, after a certain surface of a to-be-detected part is detected to have a defect in the detection process, the subsequent module does not acquire images of the product any more and directly skips the detection, the image acquisition and software processing time is reduced, namely, the waste of computing resources of resources is reduced, the technical problem of high resource consumption in the defect detection of the porous metal part is solved, and the working efficiency of the whole device is improved due to the reduction of the image acquisition and the software processing time. And the mode of the opposite shooting reduces the working time of the camera and prolongs the service life.
It can be understood that, in the specific implementation process, in order to realize that the piece to be detected passes through the image acquisition regions of the plurality of detection modules in sequence when the detection turntable rotates, the detection modules need to be distributed in sequence along the transparent detection turntable 2. The distribution sequence can be arranged according to the actual defect condition of the product, and the arrangement priority is as follows: the side with the high priority feature is detected first, and the rest sides are detected later. When a certain defect appears, the algorithm identifies, and the subsequent stations are directly discharged without detection.
As an implementation manner, the plurality of detection modules are sequentially arranged along the rotation direction of the transparent detection turntable 2 according to the defect severity or defect occurrence probability; and the defect severity is the defect severity of the detection surface corresponding to the detection module. Lay according to defect severity or defect emergence probability size, with the defect severity height or the defect emergence probability big the detection module that the detection face corresponds set up in front, can guarantee the defective bearing of discernment as early as possible, improve defect identification's efficiency, save check-out time at the actual testing process, promote whole equipment work efficiency. On the basis, the bearing with the defects is identified as early as possible, the subsequent image acquisition and algorithm calculation cost can be saved, and the resources are saved.
Specifically, according to the historical defect detection data, the defect priority of the bearing is the inner wall detection module 3, the upper surface detection module, the lower surface detection module 6 and the side detection module, and therefore, in this embodiment, the inner wall detection module 3, the upper surface detection module, the lower surface detection module 6 and the side detection module are sequentially arranged along the rotation direction of the transparent detection turntable 2, so that the bearing sequentially passes through the inner wall detection module 3, the upper surface detection module, the lower surface detection module 6 and the side detection module when rotating along with the detection turntable.
It should be noted that, according to the historical defect detection data, the inner wall of the through hole of the bearing generally has defects such as impurities, burrs, and sand holes, which are the defects that the frequency of occurrence of the bearing is the highest and the severity of the defects is the highest. Therefore, in this embodiment, set up inner wall detection module 3 to the priority highest, first carry out the defect detection to the through-hole inner wall of bearing promptly, the defective bearing of discernment that can be as early as possible like this improves the efficiency of defect discernment, saves check-out time at the actual testing in-process, promotes whole equipment work efficiency. On the basis, the bearing with the defects is identified as early as possible, the subsequent image acquisition and algorithm calculation cost can be saved, and the resources are saved. As shown in fig. 10 to 12, the arrows in the drawings are defect positions in images of the inner wall having defects such as impurities, burrs, and voids, which are acquired by the defect detection apparatus of the present embodiment. Therefore, the device of the embodiment can detect the bearing with the defects of impurities, burrs and sand holes on the inner wall in the first time, complete the overall detection of the bearing in time, improve the efficiency of identifying the defects of the bearing, save the detection time and reduce the resource waste.
As an embodiment, after the step of controlling the rotation of the transparent detection turntable 2, the method further includes:
when the to-be-detected piece is detected to be placed in the detection station, generating a virtual tracing code of the to-be-detected piece; the virtual tracing code comprises an identifier of the to-be-detected piece and an initialized defect detection result;
in the present embodiment, the virtual tracing code is also referred to as a product virtual code. The device is used for recording the detection result of the product (bearing) in the whole process. The identification of the piece to be detected is used as the unique identification of the piece to be detected. And initializing the defect detection result as that each detection surface has no defect.
Correspondingly, if there is a defect on the first surface, the step of controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition any more includes:
and if the first surface has defects, updating the defect detection result in the virtual tracing code, and controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition.
In a specific implementation process, a unique virtual tracing code is generated, and when a defect is detected, the defect condition of a corresponding detection surface in the virtual tracing code needs to be updated according to the defect condition so as to record the defect condition of the piece to be detected.
Further, the mark of the piece to be detected is the generation time of the tracing code, and the initialized defect detection result comprises the detection defect-free state of the piece to be detected and the defect-free state of each detection surface;
if the first surface has defects, the step of updating the defect detection result in the virtual traceback code includes: and if the first surface has defects, updating the initialization defect detection result to obtain a defect detection result, wherein the defect detection result comprises that the first surface has defects and the piece to be detected has defects.
Referring to fig. 9, fig. 9 is a specific implementation of the virtual tracing back code, which includes the generation time of the virtual tracing back code, the total defect judgment (letter O or N) of the product (bearing), and the defect judgment (1 or letters a \ B \ C \ D \ E) of each detection surface. When a product passes through the detection module, the virtual tracing code is updated according to the defect detection condition of the product (bearing), and the defect is always judged to be a letter O only when no defect exists on the overall detection surface; otherwise, after a defect occurs on a certain detection surface, no detection result exists behind the detection surface, and the defect is always judged to be a letter N. Table 1 shows the final virtual traceback codes of 5 pieces to be detected in this embodiment.
Table 1 virtual traceback code case
Figure 497078DEST_PATH_IMAGE005
For example, when the surface S3 of the 3 rd device under inspection in table 1 is defective, the inspection surface S4 and the inspection surface S5 are no longer inspected, and the final virtual traceback code condition is as shown by the serial number 3 in table 1.
It can be understood that the virtual tracing code is designed in consideration that many bearings do not have their own identity codes, and the extra laser coding opportunity is added to increase the cost, and the product information is updated on a fixed path to generate the EXCEL form. The defect detection condition can be visually displayed, and the production cost of the product is saved.
In addition, through the binding of the dynamic virtual tracing code and the actual bearing, the detection is not required to be carried out after each surface of the same product is shot. Because all of the information is in the virtual code, the system need only determine from the code whether it is necessary to continue inspecting the product. The storage of the picture amount is reduced, and the data transmission time is reduced. Can also realize that a plurality of modules shoot simultaneously and detect different products through this kind of mode.
In one embodiment, the device for detecting the defects of the perforated metal piece further comprises a sensor;
after the step of controlling the rotation of the transparent detection turntable 2, the method further comprises the following steps:
when station information acquired by the sensor is received, controlling the first detection module to acquire a first image of the piece to be detected; and the station information is information that the detection station passes through the first detection module.
In the specific implementation process, the sensor can be photoelectric switch sensor, sets up a plurality ofly in this embodiment, installs one on every module for gather station information, the response is promptly waited to detect whether reach the position that can image acquisition, carries out image acquisition from triggering the camera through computer equipment. Therefore, the work of each detection module can be accurately controlled through the sensor and the computer equipment, automatic collection is realized, and the accuracy of image collection is improved.
As an embodiment, when the first detection module is an upper surface detection module;
when detecting that it passes through first detection module in a plurality of detection modules to wait to detect the piece, control first detection module gather wait to detect the step of the first image of piece, include:
when the piece to be detected passes through a first detection module of the plurality of detection modules, acquiring a first image of the piece to be detected under the condition that the working distance WD of a lens of the first detection module is controlled to meet a first relational expression;
the first relation is:
Figure 500675DEST_PATH_IMAGE006
wherein d is the diameter of the first surface, and H is the horizontal field angle of the lens of the first detection module.
In specific application, a program can be preset in computer equipment to realize automatic adjustment. It can be understood that, in order to achieve the purpose of real-time detection processing, the shooting surfaces of the image acquisition devices are required to be within the range of the depth of field of the lens (that is, when the piece to be detected passes through the detection module, the detection surface is within the range of the depth of field of the lens of the image acquisition devices), and one picture is respectively shot each time and stored and sent to the computer device for real-time detection processing, so that the detection efficiency is improved, the purpose of timely judging defects is achieved, and whether the subsequent detection module continues to perform image acquisition is determined.
As an implementation manner, the side detection module includes N groups of area-array cameras, where the N groups of area-array cameras are installed around a target position in an encircling manner, the target position is a position through which the detection station passes in a rotation process of the transparent detection turntable 2, and N is an integer greater than or equal to 4;
when the first detection module is a side detection module, when detecting that the piece to be detected passes through a first detection module of the plurality of detection modules, the step of controlling the first detection module to acquire a first image of the piece to be detected comprises the following steps:
and when the piece to be detected passes through the side detection module, controlling N groups of area-array cameras to simultaneously acquire side images of the piece to be detected, wherein each group of area-array cameras acquires an image of 1/N area of the side of the piece to be detected.
In the specific implementation process, referring to fig. 13, fig. 13 is a bearing image shot by the existing endoscope, and the deep color part at the most edge pointed by an arrow in the figure is an image display of the side surface of the bearing, so that it can be seen that, because the outer circumference (side surface) of the bearing is too large, the defect display shot by the ordinary endoscope is only a narrow circle and is not obvious, and the cost for customizing the endoscope with a larger view field is too high, so that a mode of matching 4 groups of area array cameras with the ordinary fixed focus lens is adopted, and simultaneously, the images are collected, so that the device cost is reduced on the basis of ensuring the defect detection accuracy. As shown in fig. 7, in the side detection module, 4 cameras are mounted around each other, and each camera photographs the area of the bearing side 1/4 at the time of photographing. During the detection process, each camera starts shooting from the point A to the point B simultaneously during the rotation process of the bearing along with the transparent detection turntable 2 (A1-B1 in the figure); during the period, the camera continuously takes pictures after receiving the trigger signal, and the frame rate of the camera is set according to the quantity of pictures to be taken. Because the camera adopts a frame triggering mode to acquire images, the frame rate means the number of pictures acquired per second. The calculation formula is as follows, wherein X is the picture quantity, d is the bearing diameter, and fov is the view field size; the frame rate is X/s.
Figure 676835DEST_PATH_IMAGE007
It can be understood that, in this embodiment, the side images of the to-be-detected object are collected simultaneously in a manner of matching a plurality of area-array cameras with a common fixed-focus lens, so that the quality of image collection can be ensured, the accuracy of defect detection is ensured, and the detection cost is reduced.
As an embodiment, the device for detecting the defects of the perforated metal piece further comprises a touch screen 11;
after determining that the to-be-detected piece has the defect, the method further comprises the following steps:
and sending the defect detection result to the touch screen 11, so that the touch screen 11 displays the defect detection result.
In the specific implementation process, the touch screen 11 can display a defect detection result (in the form of a virtual tracing code), so that an operator can be prompted about the defect detection condition to make a next accurate decision.
As one embodiment, the station spacing between adjacent detection stations on the detection turntable is equal. Further, the station spacing is more than or equal to the diameter of the piece to be detected, and the station spacing is less than or equal to the module spacing between the adjacent detection modules.
In the specific implementation process, the bearing to be detected is placed on the transparent detection turntable 2 through the conveying belt or the mechanical arm of the previous station, and a bearing (determined according to the diameter (D) of the bearing) is placed at a certain distance (D) at each interval, wherein D is larger than or equal to D, but is not larger than the distance between adjacent visual modules, otherwise, the detection speed can be reduced, so that the bearings are ensured to be orderly and efficiently detected, and the detection device is suitable for a product production line.
Referring to fig. 14, based on the same inventive principle, an embodiment of the present application further provides a defect detection system for a perforated metal piece, where the defect detection system for a perforated metal piece further includes a transparent detection turntable and a plurality of detection modules; the transparent detection turntable is provided with a plurality of detection stations;
the system comprises:
the first control module is used for controlling the transparent detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition regions of the plurality of detection modules when rotating along with the transparent detection turntable;
the second control module is used for controlling the first detection module to collect a first image of the piece to be detected when the piece to be detected passes through a first detection module of the plurality of detection modules, and determining whether a defect exists on the first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface;
the third control module is used for controlling the second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules if the first surface has no defects, and determining whether the second surface of the piece to be detected has defects or not based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
and the fourth control module is used for controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition if the first surface has defects.
It should be noted that, in this embodiment, each module in the defect detection system for a metal piece with a hole corresponds to each step in the defect detection method for a metal piece with a hole in the foregoing embodiment one by one, and therefore, the specific implementation of this embodiment may refer to the implementation of the defect detection method for an image recognition metal piece with a hole, and details thereof are not described here.
Furthermore, in an embodiment, the present application further provides a computer storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the steps of the method in the foregoing embodiments.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, and may be stored in a portion of a file that holds other programs or data, such as in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a multimedia terminal (e.g., a mobile phone, a computer, a television receiver, or a network device) to perform the method according to the embodiments of the present application.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.

Claims (16)

1. The defect detection method for the metal piece with the hole is characterized by being used for a defect detection device for the metal piece with the hole, and the defect detection device for the metal piece with the hole further comprises a detection turntable and a plurality of detection modules; the detection turntable is provided with a plurality of detection stations;
the method comprises the following steps:
controlling the detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition regions of the plurality of detection modules when rotating along with the detection turntable;
when the piece to be detected passes through a first detection module of the plurality of detection modules, controlling the first detection module to acquire a first image of the piece to be detected, and determining whether a defect exists on a first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface;
if the first surface has no defect, controlling a second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules, and determining whether the second surface of the piece to be detected has a defect based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
and if the first surface has defects, controlling the detection module through which the piece to be detected passes after the first detection module not to acquire images.
2. The method of claim 1, wherein the detection carousel is a transparent detection carousel; the plurality of detection modules comprise an inner wall detection module, an upper surface detection module, a lower surface detection module and a side detection module; the first detection module is any one of an inner wall detection module, an upper surface detection module, a lower surface detection module and a side detection module.
3. The method according to claim 2, wherein the plurality of detection modules are sequentially arranged along the rotation direction of the transparent detection turntable according to the defect severity or defect occurrence probability; and the defect severity is the defect severity of the detection surface corresponding to the detection module.
4. The method as claimed in claim 3, wherein the inner wall detection module, the upper surface detection module, the lower surface detection module and the side detection module are sequentially arranged along a rotation direction of the transparent detection turntable.
5. The method of claim 2, wherein the step of controlling the rotation of the transparent detection turntable is followed by the step of:
when the to-be-detected piece is detected to be placed in the detection station, generating a virtual tracing code of the to-be-detected piece; the virtual tracing code comprises an identifier of the to-be-detected piece and an initialized defect detection result;
if the first surface has defects, the step of controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition any more, comprises the following steps:
and if the first surface has defects, updating the defect detection result in the virtual tracing code, and controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition.
6. The method according to claim 5, wherein the part to be detected is identified by the generation time of the tracing code, and the initialized defect detection result comprises that the part to be detected is detected to be defect-free and each detection surface is defect-free;
if the first surface has defects, the step of updating the defect detection result in the virtual traceback code includes:
and if the first surface has defects, updating the initialization defect detection result to obtain a defect detection result, wherein the defect detection result comprises that the first surface has defects and the piece to be detected has defects.
7. The method of claim 2, wherein the apparatus further comprises a sensor;
after the step of controlling the rotation of the transparent detection turntable, the method further comprises the following steps:
when station information acquired by the sensor is received, controlling the first detection module to acquire a first image of the piece to be detected; and the station information is information that the detection station passes through the first detection module.
8. The method of claim 2, wherein when the first inspection module is a top surface inspection module;
when detecting that it passes through first detection module in a plurality of detection modules to wait to detect the piece, control first detection module gather wait to detect the step of the first image of piece, include:
when the piece to be detected passes through a first detection module of the plurality of detection modules, acquiring a first image of the piece to be detected under the condition that the working distance WD of a lens of the first detection module is controlled to meet a first relational expression;
the first relation is:
Figure 471687DEST_PATH_IMAGE001
wherein d is the diameter of the first surface, and H is the horizontal field angle of the lens of the first detection module.
9. The method according to claim 2, wherein the side detection module comprises N groups of area-array cameras, the N groups of area-array cameras are arranged around a target position in an encircling manner, the target position is a position passed by the detection station in the rotation process of the transparent detection turntable, and N is an integer greater than or equal to 4;
when the first detection module is a side detection module, when detecting that the piece to be detected passes through a first detection module of the plurality of detection modules, the step of controlling the first detection module to acquire a first image of the piece to be detected comprises the following steps:
and when the piece to be detected passes through the side detection module, controlling N groups of area-array cameras to simultaneously acquire side images of the piece to be detected, wherein each group of area-array cameras acquires an image of 1/N area of the side of the piece to be detected.
10. The method of claim 2, wherein the member to be inspected comprises a first upper surface and a second upper surface; the upper surface detection module comprises a first upper surface detection module and a second upper surface detection module, the first upper surface detection module is used for collecting a first upper surface image, and the second upper surface detection module is used for collecting a second upper surface image; the first upper surface detection module and the second upper surface detection module are identical in structure;
the first upper surface detection module or the second upper surface detection module comprises a second support and a first camera movably connected to the second support, and a lens of the first camera faces the detection station from the upper part of the transparent detection turntable, so that the first camera is used for collecting a first upper surface image or a second upper surface image of the perforated metal part from the upper part of the transparent detection turntable;
the lower surface detection module comprises a third support and a second camera movably connected to the third support, and a lens of the second camera faces the detection station from the lower part of the transparent detection turntable, so that the second camera is used for collecting the lower surface image of the perforated metal piece from the lower part of the transparent detection turntable.
11. The method of claim 1, wherein the device for detecting defects of the perforated metal piece further comprises a touch screen;
after determining that the to-be-detected piece has the defect, the method further comprises the following steps:
and sending the defect detection result to the touch screen so that the touch screen displays the defect detection result.
12. A method according to any one of claims 1 to 11, wherein the station spacing between adjacent inspection stations on the inspection carousel is equal.
13. The method according to claim 12, wherein the station pitch is equal to or greater than the diameter of the piece to be detected, and the station pitch is equal to or less than the module pitch between adjacent detection modules.
14. The defect detection system for the perforated metal piece is characterized by being used for a defect detection device for the perforated metal piece, and the defect detection device for the perforated metal piece further comprises a transparent detection turntable and a plurality of detection modules; the transparent detection turntable is provided with a plurality of detection stations;
the system comprises:
the first control module is used for controlling the transparent detection turntable to rotate so that the to-be-detected piece in the detection station sequentially passes through the image acquisition regions of the plurality of detection modules when rotating along with the transparent detection turntable;
the second control module is used for controlling the first detection module to collect a first image of the piece to be detected when the piece to be detected passes through a first detection module of the plurality of detection modules, and determining whether a defect exists on the first surface of the piece to be detected based on the first image; wherein the first image is an image of the first surface;
the third control module is used for controlling the second detection module to collect a second image of the piece to be detected when the piece to be detected passes through a second detection module of the plurality of detection modules if the first surface has no defects, and determining whether the second surface of the piece to be detected has defects or not based on the second image; the second image is an image of the second surface, and the second detection module is a detection module through which the piece to be detected passes after the first detection module;
and the fourth control module is used for controlling the detection module, through which the piece to be detected passes after the first detection module, not to perform image acquisition if the first surface has defects.
15. A device for detecting defects of a perforated metal part, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 13.
16. A computer-readable storage medium, having a computer program stored thereon, which, when executed by a processor, performs the method of any one of claims 1-13.
CN202111365981.6A 2021-11-18 2021-11-18 Method, system and device for detecting defects of metal piece with hole and storage medium Active CN113793338B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111365981.6A CN113793338B (en) 2021-11-18 2021-11-18 Method, system and device for detecting defects of metal piece with hole and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111365981.6A CN113793338B (en) 2021-11-18 2021-11-18 Method, system and device for detecting defects of metal piece with hole and storage medium

Publications (2)

Publication Number Publication Date
CN113793338A true CN113793338A (en) 2021-12-14
CN113793338B CN113793338B (en) 2022-02-11

Family

ID=78877362

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111365981.6A Active CN113793338B (en) 2021-11-18 2021-11-18 Method, system and device for detecting defects of metal piece with hole and storage medium

Country Status (1)

Country Link
CN (1) CN113793338B (en)

Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030156471A1 (en) * 2000-04-05 2003-08-21 Hiroshi Ueda Information recording device, information recording method, and program
JP2007085759A (en) * 2005-09-20 2007-04-05 Seiko Epson Corp Inspection method and inspection device
JP2013108826A (en) * 2011-11-21 2013-06-06 Sharp Corp Semiconductor substrate inspection method, wiring defect inspection program, and wiring defect inspection program recording medium
CN103149215A (en) * 2013-02-27 2013-06-12 中国计量学院 Method and device for detecting defects of toughened glass insulator
CN106251352A (en) * 2016-07-29 2016-12-21 武汉大学 A kind of cover defect inspection method based on image procossing
CN106622991A (en) * 2016-12-30 2017-05-10 河南奇测电子科技有限公司 Cylindrical work piece surface detecting assembly line, detection method and gesture adjusting device
CN106872474A (en) * 2017-03-08 2017-06-20 苏州易瑞得电子科技有限公司 Exploded perspective vision testing machine and its detection method
CN208092793U (en) * 2018-04-02 2018-11-13 珠海格力电器股份有限公司 The detection platform of enamel coating defect
CN208350673U (en) * 2018-06-29 2019-01-08 广州兴森快捷电路科技有限公司 defect detecting system
CN109492940A (en) * 2018-12-06 2019-03-19 华中科技大学 A kind of casting furnace lodge follow-up of quality method for moulding pouring product line
CN109692820A (en) * 2018-12-19 2019-04-30 河南大学 Optical fiber metalwork surface defect on-line measuring device and method based on image procossing
CN209072641U (en) * 2018-12-28 2019-07-05 深圳眼千里科技有限公司 A kind of camera module automatic detecting machine
CN110142230A (en) * 2019-05-23 2019-08-20 北京阿丘机器人科技有限公司 A kind of method and device detecting open defect
CN110161046A (en) * 2019-05-28 2019-08-23 华中科技大学 A kind of moulding appearance detecting method and system based on stroboscopic light source
CN110441313A (en) * 2019-07-30 2019-11-12 天津工程机械研究院有限公司 A kind of multistation, multiangle visual surface defects detection system
CN210742146U (en) * 2019-07-30 2020-06-12 天津工程机械研究院有限公司 Multi-station and multi-angle visual surface defect detection system
CN211303873U (en) * 2019-09-11 2020-08-21 杭州智感科技有限公司 Side defect detection device
CN111650725A (en) * 2020-07-03 2020-09-11 天津欧菲光电有限公司 Optical imaging system, image capturing module and electronic device
CN111833347A (en) * 2020-07-31 2020-10-27 广东电网有限责任公司 Transmission line damper defect detection method and related device
CN112037222A (en) * 2020-11-04 2020-12-04 武汉精测电子集团股份有限公司 Automatic updating method and system of neural network model
CN113269759A (en) * 2021-05-28 2021-08-17 中冶赛迪重庆信息技术有限公司 Steel coil information detection method, system, medium and terminal based on image recognition
CN113447493A (en) * 2021-07-30 2021-09-28 安徽工程大学 Bearing ring defect detection device and detection method

Patent Citations (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030156471A1 (en) * 2000-04-05 2003-08-21 Hiroshi Ueda Information recording device, information recording method, and program
JP2007085759A (en) * 2005-09-20 2007-04-05 Seiko Epson Corp Inspection method and inspection device
JP2013108826A (en) * 2011-11-21 2013-06-06 Sharp Corp Semiconductor substrate inspection method, wiring defect inspection program, and wiring defect inspection program recording medium
CN103149215A (en) * 2013-02-27 2013-06-12 中国计量学院 Method and device for detecting defects of toughened glass insulator
CN106251352A (en) * 2016-07-29 2016-12-21 武汉大学 A kind of cover defect inspection method based on image procossing
CN106622991A (en) * 2016-12-30 2017-05-10 河南奇测电子科技有限公司 Cylindrical work piece surface detecting assembly line, detection method and gesture adjusting device
CN106872474A (en) * 2017-03-08 2017-06-20 苏州易瑞得电子科技有限公司 Exploded perspective vision testing machine and its detection method
CN208092793U (en) * 2018-04-02 2018-11-13 珠海格力电器股份有限公司 The detection platform of enamel coating defect
CN208350673U (en) * 2018-06-29 2019-01-08 广州兴森快捷电路科技有限公司 defect detecting system
CN109492940A (en) * 2018-12-06 2019-03-19 华中科技大学 A kind of casting furnace lodge follow-up of quality method for moulding pouring product line
CN109692820A (en) * 2018-12-19 2019-04-30 河南大学 Optical fiber metalwork surface defect on-line measuring device and method based on image procossing
CN209072641U (en) * 2018-12-28 2019-07-05 深圳眼千里科技有限公司 A kind of camera module automatic detecting machine
CN110142230A (en) * 2019-05-23 2019-08-20 北京阿丘机器人科技有限公司 A kind of method and device detecting open defect
CN110161046A (en) * 2019-05-28 2019-08-23 华中科技大学 A kind of moulding appearance detecting method and system based on stroboscopic light source
CN110441313A (en) * 2019-07-30 2019-11-12 天津工程机械研究院有限公司 A kind of multistation, multiangle visual surface defects detection system
CN210742146U (en) * 2019-07-30 2020-06-12 天津工程机械研究院有限公司 Multi-station and multi-angle visual surface defect detection system
CN211303873U (en) * 2019-09-11 2020-08-21 杭州智感科技有限公司 Side defect detection device
CN111650725A (en) * 2020-07-03 2020-09-11 天津欧菲光电有限公司 Optical imaging system, image capturing module and electronic device
CN111833347A (en) * 2020-07-31 2020-10-27 广东电网有限责任公司 Transmission line damper defect detection method and related device
CN112037222A (en) * 2020-11-04 2020-12-04 武汉精测电子集团股份有限公司 Automatic updating method and system of neural network model
CN113269759A (en) * 2021-05-28 2021-08-17 中冶赛迪重庆信息技术有限公司 Steel coil information detection method, system, medium and terminal based on image recognition
CN113447493A (en) * 2021-07-30 2021-09-28 安徽工程大学 Bearing ring defect detection device and detection method

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
YUEMING GUO等: "Defect detection in atomic-resolution images via unsupervised learning with translational invariance", 《NPJ COMPUTATIONAL MATERIALS》 *
夏贤华: "基于机器视觉的瓶口螺纹在线检测系统研究与开发", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
崔毅: "箱体类零件加工过程信息管理系统研发", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 *
李泽辉: "抛光砖表面缺陷视觉检测系统及算法研究", 《万方数据》 *

Also Published As

Publication number Publication date
CN113793338B (en) 2022-02-11

Similar Documents

Publication Publication Date Title
CN104483320B (en) Digitized defect detection device and detection method of industrial denitration catalyst
CN101738401A (en) Defect inspection device and defect inspection method
CN105486700A (en) System for detecting defects of transparent object and use method thereof
CN114693673A (en) Glass detection method and device, electronic equipment and computer-readable storage medium
CN113724240A (en) Refrigerator caster detection method, system and device based on visual identification
CN202066794U (en) Full-automatic key detection device
CN206505030U (en) A kind of automatic line detector of automobile stamping
CN113793338B (en) Method, system and device for detecting defects of metal piece with hole and storage medium
CN101097398B (en) Lens testing device and method
JP2001070455A (en) Method for inspecting pattern width of stent surface
CN110596118A (en) Print pattern detection method and print pattern detection device
CN110058439B (en) Method and apparatus for removing foreign matter on color filter
CN216247726U (en) Device for detecting defects of metal piece with hole
CN108020474A (en) A kind of quality detecting system for fatigue test specimen
CN103383730A (en) Automatic BNC terminal detecting machine and work method thereof
CN109839061B (en) Lens module detection method and system
CN110567403B (en) Code scanning equipment coaxiality detection method and system
CN112927222B (en) Method for realizing multi-type photovoltaic array hot spot detection based on hybrid improved Faster R-CNN
CN114529537A (en) Abnormal target detection method, system, equipment and medium for photovoltaic panel
CN113984790A (en) Lens quality detection method and device
JP2004286708A (en) Defect detection apparatus, method, and program
CN218138496U (en) Punching equipment for flexible circuit board
CN112085722B (en) Training sample image acquisition method and device
CN106680280A (en) Image detection device and image detection method for washing machine thin-film switch
CN117470872B (en) Board splitting quality detection method and device, board splitting machine and circuit board production line

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
GR01 Patent grant
GR01 Patent grant