Dimensional standard identification system for flat steel bars

Abstract

The present invention relates to a size standard identification system for flat steel bars. The system includes: a mobile sensing device, which is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar; an area analysis device, which is used to send an area deviation signal when the intelligently analyzed top surface area of ​​the flat steel bar is not within the top surface area distribution range of the flat steel bar of standard size. Through this system, an AI processing model can be used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, that is, the top surface area of ​​the flat steel bar based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image, and send an area deviation signal when the top surface area of ​​the flat steel bar is not within the top surface area distribution range of the flat steel bar of standard size, thereby completing the size standard identification processing based on the visual analysis results of the top surface area of ​​the flat steel bar on site.

Description

Technical Field

[0001] The present invention relates to the field of flat steel bars, and more particularly to a size standard identification system for flat steel bars. Background Art

[0002] Flat steel bars refer to steel with a width of 12-300mm, a thickness of 3-60mm, a rectangular cross section and slightly blunt edges. Flat steel bars can be finished steel products, or they can be used as blanks for welded pipes and thin plate blanks for laminated thin plates. Flat steel bars can be used as finished products to make hoops, tools and mechanical parts, and as frame structural parts and escalators in buildings. Flat steel bars can be produced in fixed thickness, width and length according to user needs, which reduces cutting for users, saves processes, reduces labor and material consumption, and also reduces processing losses of raw materials, saving time, effort and materials. The products have been professionally used in steel structure manufacturing, machinery manufacturing, automobile industry, mining machinery, lifting machinery and other industrial materials.

[0003] After each flat steel bar is manufactured, it is expected that its various dimensional data will be tested for qualification. Only qualified flat steel bars can be safely put into the manufacturing and production of subsequent products. However, the differences in dimensional data between each piece of the same batch of flat steel bars are subtle. For example, the differences in top surface area data between each piece of the same batch of flat steel bars are subtle, which makes it difficult to identify and process the top surface area of ​​each flat steel bar with high precision. Summary of the invention

[0004] In order to solve the technical problems in related fields, the present invention provides a size standard identification system for flat steel bars, which intelligently analyzes the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, by adopting an AI processing model based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. When the top surface area of ​​the flat steel bar is not within the top surface area distribution range of flat steel bars of standard size, an area deviation signal is issued; and when the top surface area of ​​the flat steel bar is within the top surface area distribution range of flat steel bars of standard size, an area compliance signal is issued, thereby completing the size standard identification processing based on the on-site visualization analysis results of the top surface area of ​​the flat steel bars.

[0005] The present invention needs to have at least the following three important invention points:

[0006] Firstly: according to the channel imaging features corresponding to the flat steel bar, the sub-image occupied by the flat steel bar is extracted from the sequential conversion image as the target sub-image, wherein the channel imaging features corresponding to the flat steel bar are the R channel value interval, the G channel value interval and the B channel value interval of the flat steel bar in the RGB color space;

[0007] Secondly: an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. The AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image, wherein the various picture parameters of the target sub-picture include the number of pixels occupied by the target sub-picture, the number of rows of occupied pixel rows, the number of columns of occupied pixel columns, and the depth of field values ​​corresponding to each occupied pixel;

[0008] Again: area analysis equipment is used to send out an area deviation signal when the top surface area of ​​the flat steel bar is not within the top surface area distribution range of the flat steel bar of standard size, and to send out an area compliance signal when the top surface area of ​​the flat steel bar is within the top surface area distribution range of the flat steel bar of standard size, thereby completing the size standard identification processing based on the on-site visualization analysis results of the top surface area of ​​the flat steel bar.

[0009] According to the present invention, a size standard identification system for flat steel bars is provided, the system comprising:

[0010] The mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar, so as to obtain and output a corresponding instant sensing image;

[0011] a sequential conversion device, connected to the mobile sensing device and comprising an artifact removal device, a filtering operation device and a range extension device, for sequentially performing an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation on the received instantaneous sensing image to obtain and output a corresponding sequential conversion image;

[0012] A channel storage device is used to pre-store channel imaging features corresponding to the flat steel bar, wherein the channel imaging features corresponding to the flat steel bar are an R channel value interval, a G channel value interval, and a B channel value interval of the flat steel bar in an RGB color space;

[0013] A feature operation device, connected to the sequential conversion device and the channel storage device, respectively, for extracting the sub-image occupied by the flat steel bar from the sequential conversion image as the target sub-image according to the channel imaging feature corresponding to the flat steel bar;

[0014] A signal processing device connected to the feature operation device, used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image using an AI processing model, wherein the AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image;

[0015] an area analysis device connected to the signal processing device, used to send an area deviation signal when the top surface area of ​​the flat steel bar is not within the top surface area distribution interval of the flat steel bar of standard size, and also used to send an area compliance signal when the top surface area of ​​the flat steel bar is within the top surface area distribution interval of the flat steel bar of standard size;

[0016] Among them, an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. The AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image, including: various picture parameters of the target sub-picture include the number of pixels occupied by the target sub-picture, the number of rows of occupied pixel rows, the number of columns of occupied pixel columns, and the depth of field values ​​corresponding to each occupied pixel.

[0017] The size standard identification system for flat steel bars of the present invention has stable operation and compact structure. Since the AI ​​processing model can be used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, that is, the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image, and when the top surface area of ​​the flat steel bar is not within the top surface area distribution range of the flat steel bar of standard size, an area deviation signal is issued, thereby completing the size standard identification processing based on the visual analysis result of the top surface area of ​​the flat steel bar on site. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Those skilled in the art may better understand the numerous advantages of the present invention by referring to the accompanying drawings, in which:

[0019] Figure 1 It is a schematic structural diagram of a size standard identification system for flat steel bars according to a primary embodiment of the present invention.

[0020] Figure 2 It is a schematic structural diagram of a size standard identification system for flat steel bars according to a secondary embodiment of the present invention.

[0021] Figure 31 is a schematic structural diagram of a size standard identification system for flat steel bars according to yet another embodiment of the present invention. DETAILED DESCRIPTION

[0022] Figure 1 1 is a schematic diagram of a system for identifying the size standard of a flat steel bar according to a primary embodiment of the present invention, the system comprising:

[0023] The mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar, so as to obtain and output a corresponding instant sensing image;

[0024] For example, the mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before being put into use to face the top surface of the flat steel bar to perform a photoelectric sensing operation to obtain and output a corresponding instant sensing image, including: the photoelectric sensing component can be selected as a CCD sensing device or a CMOS sensing device;

[0025] a sequential conversion device, connected to the mobile sensing device and comprising an artifact removal device, a filtering operation device and a range extension device, for sequentially performing an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation on the received instantaneous sensing image to obtain and output a corresponding sequential conversion image;

[0026] A channel storage device is used to pre-store channel imaging features corresponding to the flat steel bar, wherein the channel imaging features corresponding to the flat steel bar are an R channel value interval, a G channel value interval, and a B channel value interval of the flat steel bar in an RGB color space;

[0027] A feature operation device, connected to the sequential conversion device and the channel storage device, respectively, for extracting the sub-image occupied by the flat steel bar from the sequential conversion image as the target sub-image according to the channel imaging feature corresponding to the flat steel bar;

[0028] A signal processing device connected to the feature operation device, used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image using an AI processing model, wherein the AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image;

[0029] an area analysis device connected to the signal processing device, used to send an area deviation signal when the top surface area of ​​the flat steel bar is not within the top surface area distribution interval of the flat steel bar of standard size, and also used to send an area compliance signal when the top surface area of ​​the flat steel bar is within the top surface area distribution interval of the flat steel bar of standard size;

[0030] Among them, an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, that is, the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. The AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image, including: various picture parameters of the target sub-picture include the number of pixels occupied by the target sub-picture, the number of rows of occupied pixel rows, the number of columns of occupied pixel columns, and the depth of field values ​​corresponding to each occupied pixel;

[0031] Wherein, the sequential conversion device, connected to the mobile sensing device and comprising an artifact removal device, a filtering operation device and a range extension device, is used to sequentially perform an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation on the received instant sensing image to obtain and output a corresponding sequential conversion image, comprising: the artifact removal device, the filtering operation device and the range extension device are used to perform an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation respectively;

[0032] The mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before it is put into use to face the top surface of the flat steel bar to perform a photoelectric sensing operation to obtain and output a corresponding instant sensing image. The network control interface is connected to the mobile execution component to receive a network control command to drive the mobile execution component to move;

[0033] Among them, the mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, which is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar to obtain and output a corresponding instant sensing image. It also includes: the mobile execution component is arranged directly above the photoelectric sensing component to drive the photoelectric sensing component to move.

[0034] Figure 2 It is a schematic structural diagram of a size standard identification system for flat steel bars according to a secondary embodiment of the present invention.

[0035] and Figure 1 different, Figure 2The dimension standard identification system for flat steel bars may also include the following components:

[0036] an altitude sensor device, connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device, respectively, for measuring the current real-time altitude values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively;

[0037] Wherein, the height sensor device is respectively connected with the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to respectively measure the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device, including: the height sensor device includes a plurality of height measurement units, which are respectively connected with the feature operation device, the artifact removal device, the filter operation device and the range extension device, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device;

[0038] Wherein, the height sensor device includes a plurality of height measurement units, which are used to be connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, including: the plurality of height measurement units are a plurality of height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively;

[0039] Wherein, the plurality of height measurement units are a plurality of height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, so as to complete the respective measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, including: the structures of the plurality of height sensors are the same;

[0040] Among them, the multiple height measurement units are multiple height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, and also include: the multiple height sensors have the same height measurement upper limit value and height measurement lower limit value.

[0041] Figure 3 1 is a schematic structural diagram of a size standard identification system for flat steel bars according to yet another embodiment of the present invention.

[0042] and Figure 1 different, Figure 3 The dimension standard identification system for flat steel bars may also include the following components:

[0043] a playback processing device, connected to the plurality of altitude sensors of the feature operation device, the artifact removal device, the filter operation device, and the range extension device, respectively, for synchronously playing the current real-time altitude values ​​of the feature operation device, the artifact removal device, the filter operation device, and the range extension device respectively;

[0044] Wherein, the playback processing device is respectively connected to a plurality of height sensors of the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to synchronously play the current real-time height values ​​of each of the feature operation device, the artifact removal device, the filter operation device and the range extension device, including: the playback processing device is a character display device;

[0045] Among them, the playback processing device is respectively connected to multiple height sensors of the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to synchronously play the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device, including: the playback processing device is a voice playback device.

[0046] In addition, in the size standard identification system for flat steel bars, an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image, wherein the AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image, and further includes: synchronously inputting various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image into the AI ​​processing model;

[0047] And wherein, an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. The AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image. It also includes: running the AI ​​processing model to obtain the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar output by the AI ​​processing model.

[0048] Although only certain embodiments of the present invention have been described in detail above, those skilled in the art will readily appreciate that many modifications may be made in the embodiments without substantially departing from the novel teachings and advantages of the present invention. Therefore, all of these modifications should be included within the scope of the present invention.

Claims

1. A size standard identification system for flat steel bars, characterized in that: The system comprises: The mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar, so as to obtain and output a corresponding instant sensing image; a sequential conversion device, connected to the mobile sensing device and comprising an artifact removal device, a filtering operation device and a range extension device, for sequentially performing an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation on the received instantaneous sensing image to obtain and output a corresponding sequential conversion image; A channel storage device is used to pre-store channel imaging features corresponding to the flat steel bar, wherein the channel imaging features corresponding to the flat steel bar are an R channel value interval, a G channel value interval, and a B channel value interval of the flat steel bar in an RGB color space; A feature operation device, connected to the sequential conversion device and the channel storage device, respectively, for extracting the sub-image occupied by the flat steel bar from the sequential conversion image as the target sub-image according to the channel imaging feature corresponding to the flat steel bar; A signal processing device connected to the feature operation device, used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image using an AI processing model, wherein the AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image; an area analysis device connected to the signal processing device, used to send an area deviation signal when the top surface area of ​​the flat steel bar is not within the top surface area distribution interval of the flat steel bar of standard size, and also used to send an area compliance signal when the top surface area of ​​the flat steel bar is within the top surface area distribution interval of the flat steel bar of standard size; Among them, an AI processing model is used to intelligently analyze the surface area of ​​the flat steel bar corresponding to the imaging lens direction, i.e., the top surface area of ​​the flat steel bar, based on various picture parameters of the target sub-picture and the lens focal length corresponding to the sequential conversion image. The AI ​​processing model is a deep neural network and the number of hidden layers of the deep neural network is monotonically positively correlated with the resolution of the sequential conversion image, including: various picture parameters of the target sub-picture include the number of pixels occupied by the target sub-picture, the number of rows of occupied pixel rows, the number of columns of occupied pixel columns, and the depth of field values ​​corresponding to each occupied pixel.

2. The size standard identification system for flat steel bars according to claim 1, characterized in that: A sequential conversion device, connected to the mobile sensing device and comprising an artifact removal device, a filtering operation device and a range extension device, for sequentially performing an artifact removal operation, a harmonic mean filtering operation and a dynamic range extension operation on the received instant sensing image to obtain and output a corresponding sequential conversion image, comprising: the artifact removal device, the filtering operation device and the range extension device are respectively used to perform the artifact removal operation, the harmonic mean filtering operation and the dynamic range extension operation; The mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, and is used to move to the top of the flat steel bar before it is put into use to face the top surface of the flat steel bar to perform a photoelectric sensing operation to obtain and output a corresponding instant sensing image. The network control interface is connected to the mobile execution component to receive a network control command to drive the mobile execution component to move; Among them, the mobile sensing device includes a network control interface, a mobile execution component and a photoelectric sensing component, which is used to move to the top of the flat steel bar before it is put into use to perform a photoelectric sensing operation facing the top surface of the flat steel bar to obtain and output a corresponding instant sensing image. It also includes: the mobile execution component is arranged directly above the photoelectric sensing component to drive the photoelectric sensing component to move.

3. The size standard identification system for flat steel bars according to claim 2, characterized in that: The system further comprises: an altitude sensor device, connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device, respectively, for measuring the current real-time altitude values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively; Among them, the height sensor device is respectively connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to respectively measure the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device. The height sensor device includes multiple height measurement units, which are used to be respectively connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device to complete the respective measurements of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device.

4. The size standard identification system for flat steel bars according to claim 3, characterized in that: The height sensor device includes multiple height measurement units, which are used to be connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively. The multiple height measurement units are multiple height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device respectively.

5. The size standard identification system for flat steel bars according to claim 4, characterized in that: The multiple height measurement units are multiple height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, including: the structures of the multiple height sensors are the same.

6. The size standard identification system for flat steel bars according to claim 5, characterized in that: The multiple height measurement units are multiple height sensors, which are used to be connected to the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, so as to complete the measurement of the current real-time height values ​​of the feature operation device, the artifact removal device, the filtering operation device and the range extension device respectively, and also include: the multiple height sensors have the same height measurement upper limit value and height measurement lower limit value.

7. The size standard identification system for flat steel bars according to any one of claims 3 to 6, characterized in that: The system further comprises: A playback processing device is respectively connected to multiple height sensors of the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to synchronously play the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device.

8. The size standard identification system for flat steel bars according to claim 7, characterized in that: A playback processing device is respectively connected to multiple height sensors of the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to synchronously play the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device, including: the playback processing device is a character display device.

9. The size standard identification system for flat steel bars according to claim 7, characterized in that: A playback processing device is respectively connected to multiple height sensors of the feature operation device, the artifact removal device, the filter operation device and the range extension device, and is used to synchronously play the current real-time height values ​​of the feature operation device, the artifact removal device, the filter operation device and the range extension device, including: the playback processing device is a voice playback device.

Images