WO2024124707A1 - 一种面向弯管加工的弯曲角度检测方法、系统及电子设备 - Google Patents

一种面向弯管加工的弯曲角度检测方法、系统及电子设备 Download PDF

Info

Publication number
WO2024124707A1
WO2024124707A1 PCT/CN2023/079724 CN2023079724W WO2024124707A1 WO 2024124707 A1 WO2024124707 A1 WO 2024124707A1 CN 2023079724 W CN2023079724 W CN 2023079724W WO 2024124707 A1 WO2024124707 A1 WO 2024124707A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
bending
pipe
straight line
region
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.)
Ceased
Application number
PCT/CN2023/079724
Other languages
English (en)
French (fr)
Inventor
李良有
周正东
彭春岩
张灵维
张良
王元宾
席伟江
宋泽峰
芦冰
许云飞
吉文韬
王嘉文
周逸凡
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.)
Zhejiang Changxing Heliang Intelligent Equipment Co Ltd
Nanjing University of Aeronautics and Astronautics
Original Assignee
Zhejiang Changxing Heliang Intelligent Equipment Co Ltd
Nanjing University of Aeronautics and Astronautics
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 Zhejiang Changxing Heliang Intelligent Equipment Co Ltd, Nanjing University of Aeronautics and Astronautics filed Critical Zhejiang Changxing Heliang Intelligent Equipment Co Ltd
Priority to DE112023005213.1T priority Critical patent/DE112023005213T5/de
Priority to US18/249,633 priority patent/US12608901B2/en
Publication of WO2024124707A1 publication Critical patent/WO2024124707A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/30—Erosion or dilatation, e.g. thinning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Definitions

  • the present invention relates to the technical field of pipe bending processing, and in particular to a bending angle detection method, system and electronic equipment for pipe bending processing.
  • Pipe bending machines are commonly used equipment for bending metal pipes. Due to factors such as material springback, the actual bending angle is inaccurate, the product quality is unstable, and the qualified rate of bent pipe products is reduced.
  • the purpose of the present invention is to provide a bending angle detection method, system and electronic equipment for pipe bending processing, so as to provide a bending angle detection method and system with low cost, high efficiency and strong versatility.
  • the present invention provides the following solutions:
  • the present invention provides a bending angle detection method for pipe bending, the detection method comprising the following steps:
  • Binarization is performed on the image to be identified and the region of interest is extracted to obtain two straight line segment region binary images; the image to be identified is an image of a processed bent pipe;
  • the bending angle is calculated based on the binary images of the two straight line segment areas.
  • binarizing the image to be identified and extracting the region of interest to obtain two straight line segment region binarized images specifically includes:
  • the image to be identified is registered with sample images in a pipe bending processing image database to obtain a registration transformation matrix;
  • the pipe bending processing image database includes sample images obtained after each bending and translation during the pipe bending process, and the sample images include: a reference image, a marked pipe bending area of interest, and two straight line segment areas adjacent to the current bending;
  • the coordinates of the curved pipe region of interest and the two straight line segment regions adjacent to the current bend in the sample image are transformed by using the transformation matrix to obtain the curved pipe region of interest and the two straight line segment regions adjacent to the current bend in the image to be identified;
  • Two straight line segment regions adjacent to the current bend in the image to be identified are intercepted from the binary image of the bent pipe region of interest to obtain two binary images of the straight line segment regions.
  • the step of calculating the bending angle according to the binarized images of the two straight line segment regions specifically includes:
  • the angle between the two line segments is calculated based on their straight line equations to obtain the bending angle.
  • a bending angle detection system for pipe bending comprising:
  • An image processing module is used to perform binarization on the image to be identified and extract the region of interest to obtain two binarized images of the straight line segment region;
  • the image to be identified is an image of a processed bent pipe;
  • the bending angle analysis module is used to calculate the bending angle according to the binary images of two straight line segment areas.
  • the image processing module includes:
  • a registration unit is used to register the image to be identified with the sample images in the pipe bending processing image database to obtain a registration transformation matrix;
  • the image to be identified is an image of a processed pipe bending
  • the pipe bending processing image database includes sample images obtained after each bending and translation during the pipe bending process, and the sample images include: a reference image, a marked pipe bending region of interest, and two straight line segment regions adjacent to the current bending;
  • a coordinate transformation unit used to perform coordinate transformation on the curved pipe region of interest and two straight line segment regions adjacent to the current bend in the sample image using a transformation matrix, so as to obtain the curved pipe region of interest and two straight line segment regions adjacent to the current bend in the image to be identified;
  • the image extraction unit of the bent pipe region of interest is used to intercept the bent pipe region of interest in the image to be identified and obtain an image of the bent pipe region of interest;
  • a binarization unit used for binarizing the image of the bent pipe region of interest to obtain a binarized image of the bent pipe region of interest
  • the two straight line segment area binary image extraction unit is used to intercept two straight line segment areas adjacent to the current bend in the image to be identified from the binary image of the interested bend area to obtain two straight line segment area binary images.
  • the bending angle analysis module specifically includes:
  • a refinement unit used for refining the two straight line segment region images
  • a straight line fitting unit is used to perform straight line fitting on two refined pixel coordinates to obtain straight line equations of two line segments
  • the bending angle calculation unit is used to calculate the angle between the two line segments according to the straight line equations of the two line segments to obtain the bending angle.
  • An electronic device comprising a memory arranged at each participant, A processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above detection method when executing the computer program.
  • An online detection method for pipe bending processing comprising the following steps:
  • the image acquisition condition is that two adjacent control signals are bending and translation, and the translation movement is completed;
  • the image of the processed bent pipe is acquired as the image to be identified;
  • the bending angle is determined based on the image to be identified
  • the bending error is fed back to the control system of the pipe bending processing equipment to adjust the processing parameters.
  • the collecting of the image of the processed bent pipe as the image to be identified specifically includes:
  • the position of the optical camera is adjusted by using an electric control base so that the optical camera can obtain an image including the processed bent pipe;
  • the optical camera is controlled to collect images of the processed bent pipe as images to be identified.
  • An online detection system for pipe bending processing comprising: an online control module, an image acquisition module, an image processing module, a bending angle analysis module and an error feedback module;
  • the online control module is used to perform the following steps:
  • the image acquisition condition is that two adjacent control signals are bending and translation, and the translation movement is completed;
  • the image acquisition module is used to acquire an image of the processed bent pipe as an image to be identified when the image acquisition conditions are met;
  • the image processing module is used to perform binarization on the image to be identified and extract the region of interest to obtain two binarized images of the straight line segment region;
  • the image to be identified is an image of a processed bent pipe;
  • the bending angle analysis module is used to calculate the bending angle according to the binary images of the two straight line segment areas;
  • the error feedback module is used to compare the bending angle with the bending angle required by the pipe bending process to obtain a bending angle error; and feed back the bending error to the control system of the pipe bending equipment to adjust the processing parameters.
  • the present invention discloses the following technical effects:
  • the present invention discloses a bending angle detection method for pipe bending processing, the detection method comprises the following steps: binarizing an image to be identified and extracting a region of interest to obtain two straight line segment region binarized images; the image to be identified is an image of a processed pipe bending; and the bending angle is calculated according to the two straight line segment region binarized images.
  • the present invention provides an image-based bending angle online measurement method and system, which has the advantages of low cost, high efficiency and strong versatility.
  • FIG1 is a flowchart of image processing provided by an embodiment of the present invention.
  • FIG2 is a flow chart of tortuosity analysis provided by an embodiment of the present invention.
  • FIG3 is a flow chart of an online detection method for pipe bending provided by an embodiment of the present invention.
  • FIG4 is a structural diagram of an online detection system for pipe bending provided by an embodiment of the present invention.
  • FIG. 5 is a flow chart of image acquisition provided by an embodiment of the present invention.
  • the purpose of the present invention is to provide a bending angle detection method, system and electronic equipment for pipe bending processing, so as to provide a bending angle detection method and system with low cost, high efficiency and strong versatility.
  • the embodiment of the present invention provides a bending angle detection method for pipe bending, the detection method comprising the following steps:
  • the image to be identified is binarized and the region of interest is extracted to obtain two straight line segment region binarized images; the image to be identified is an image of a processed bent pipe.
  • the bending angle is calculated based on the binary images of the two straight line segment areas.
  • binarization and extraction of regions of interest are performed on the image to be identified to obtain two binarized images of straight line segment regions, specifically including:
  • the image to be identified is registered with the sample images in the pipe bending processing image database to obtain a registration transformation matrix;
  • the pipe bending processing image database includes sample images obtained after each bending and translation during the pipe bending process, and the sample images include: a reference image, a marked pipe bending area of interest, and two straight line segment areas adjacent to the current bend.
  • the coordinates of the curved pipe region of interest and the two straight line segment regions adjacent to the current bend in the sample image are transformed by using the transformation matrix to obtain the curved pipe region of interest and the two straight line segment regions adjacent to the current bend in the image to be identified.
  • the interested curved pipe region in the image to be identified is intercepted from the image to be identified to obtain an interested curved pipe region image, and the interested curved pipe region image is binarized to obtain an interested curved pipe region binarized image.
  • the two straight line segment regions are obtained by binarizing the two straight line segment regions.
  • the calculation of the bending angle according to the binarized images of the two straight line segment regions specifically includes:
  • the angle between the two line segments is calculated based on their straight line equations to obtain the bending angle.
  • Embodiment 1 of the present invention further provides a bending angle detection system for pipe bending, the detection system comprising:
  • the image processing module is used to perform binarization on the image to be identified and extract the region of interest to obtain two straight line segment region binarization images; the image to be identified is an image of a processed bent pipe.
  • the image processing module comprises:
  • a registration unit is used to register the image to be identified with the sample images in the pipe bending processing image database to obtain a registration transformation matrix;
  • the image to be identified is an image of a processed pipe bending
  • the pipe bending processing image database includes sample images obtained after each bending and translation during the pipe bending process, and the sample images include: a reference image, a marked pipe bending region of interest, and two straight line segment regions adjacent to the current bending;
  • a coordinate transformation unit used to perform coordinate transformation on the curved pipe region of interest and two straight line segment regions adjacent to the current bend in the sample image using a transformation matrix, so as to obtain the curved pipe region of interest and two straight line segment regions adjacent to the current bend in the image to be identified;
  • the image extraction unit of the bent pipe region of interest is used to intercept the bent pipe region of interest in the image to be identified and obtain an image of the bent pipe region of interest;
  • a binarization unit used for binarizing the image of the bent pipe region of interest to obtain a binarized image of the bent pipe region of interest
  • the two straight line segment area binary image extraction unit is used to intercept two straight line segment areas adjacent to the current bend in the image to be identified from the binary image of the interested bend area to obtain two straight line segment area binary images.
  • the bending angle analysis module is used to calculate the bending angle according to the binary images of two straight line segment areas.
  • the bending angle analysis module specifically includes:
  • the refinement unit is used to refine the two straight line segment region images.
  • the straight line fitting unit is used to perform straight line fitting on the two refined pixel coordinates to obtain straight line equations of the two line segments.
  • the bending angle calculation unit is used to calculate the angle between the two line segments according to the straight line equations of the two line segments to obtain the bending angle.
  • Embodiment 1 of the present invention also provides an electronic device, comprising a memory disposed at each participant, a processor disposed at each participant, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned detection method when executing the computer program.
  • Embodiment 2 of the present invention provides an online detection method for pipe bending processing, as shown in FIG3 , the online detection method comprises the following steps:
  • a control signal for the pipe bending process is obtained from a control end of the pipe bending process equipment.
  • the image acquisition condition is that two adjacent control signals are bending and translation, and the translation movement is completed.
  • the image of the processed bent pipe is collected as the image to be identified.
  • the bending angle is determined based on the image to be identified.
  • the bending angle is compared with the bending angle required by the pipe bending process to obtain the bending angle error.
  • the bending error is fed back to the control system of the pipe bending processing equipment to adjust the processing parameters.
  • the image of the processed bent pipe is collected as the image to be identified, specifically including:
  • the position of the optical camera is adjusted by using an electric control base so that the optical camera can obtain an image including the processed bent pipe;
  • An embodiment of the present invention further provides an online detection system for pipe bending processing, as shown in Figure 4, the online detection system includes: an online control module, an image acquisition module, an image processing module, a bending angle analysis module and an error feedback module; the online control module receives a control signal from the pipe bending processing equipment, distinguishes the control signal logic, generates an image acquisition control signal, and sends it to the image acquisition module; the image acquisition module acquires images of the pipe bending processing site; the image processing module processes the acquired images to obtain images of the current bending area; the bending angle analysis module processes the images of the area of interest to obtain the bending angle and the bending angle error, and sends them to the control terminal of the pipe bending processing equipment.
  • the image acquisition process specifically includes:
  • the position of the optical camera is adjusted by using an electric control base so that the optical camera can acquire an image including the processed bent pipe.
  • the control signal of the pipe bending process is obtained from the control end of the pipe bending process equipment.
  • the image processing process includes the following steps:
  • the current image is registered with the images in the annotated bending tube processing image library to obtain the best matching annotated reference image and image registration transformation matrix.
  • the region of the curved pipe of interest and the regions of the two straight line segments in the current acquired image are obtained.
  • the bending angle analysis includes the following steps:
  • the calculated bending angle is compared with the bending angle required by the processing technology to obtain the bending angle error calculation.
  • the embodiment of the present invention collects images after each bending, aligns them with the images in the image database, determines two line segment areas adjacent to the bending area, uses image processing to obtain the straight line equations of the two line segments, and then obtains the actual bending angle. This can effectively improve the quality of the product and timely grasp the bending processing conditions. It has the characteristics of low cost, high efficiency and strong versatility.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

本发明公开了一种面向弯管加工的弯曲角度检测方法，所述检测方法包括如下步骤：对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；根据两个直线段区域的二值化图像，计算弯曲角度。本发明提供一种基于图像的弯曲角度在线测量方法和系统，具有成本低、效率高、通用性强的优势。

Description

一种面向弯管加工的弯曲角度检测方法、系统及电子设备
本发明要求于2022年12月16日提交中国专利局、申请号为202211621210.3、发明名称为“一种面向弯管加工的弯曲角度检测方法、系统及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本发明中。
技术领域
本发明涉及弯管加工技术领域，特别是涉及一种面向弯管加工的弯曲角度检测方法、系统及电子设备。
背景技术
弯管机是金属管材弯曲成形的常用设备，由于材料回弹等因素使得实际弯曲角度不准确，产品质量不稳定，降低了弯管产品的合格率。
利用在线测量技术对弯管加工制造过程进行检测，获取每次折弯后的实际弯曲角度，可有效提高弯管产品检测效率，将检测系统与控制系统相连接，可为工艺参数的及时调整提供有效的数据，从而有效提高弯管产品的质量和合格率，降低成本。
在现有技术中，通常根据质量控制规程对弯管产品质量进行离线检测，效率低，成本高，无法对加工过程进行在线检测，生产质量趋势未知，不合格率较高。随着图像处理和计算机视觉技术的发展，在弯管成形领域已提出了一些运用光学成像技术进行弯曲角度测量的方法，如Katona等人(Procedia CIRP，2016)利用三维激光扫描仪对弯管进行无接触的弯曲角度测量，但是这种设备成本高、测量耗时，难以满足弯管加工在线检测的需求。Simonetto等人(INT JADV MANUF TECH，2021)提出将惯性测量单元(Inertial Measurement Unit，IMU)嵌入到芯棒进行回弹测量的方法，但是这种方法仅适用于利用芯棒进行弯管加工的情况。
发明内容
本发明的目的是提供一种面向弯管加工的弯曲角度检测方法、系统及电子设备，以提供一种成本低、效率高、通用性强的弯曲角度检测方法及系统。
为实现上述目的，本发明提供了如下方案：
本发明提供一种面向弯管加工的弯曲角度检测方法，所述检测方法包括如下步骤：
对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
根据两个直线段区域的二值化图像，计算弯曲角度。
可选的，所述对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像，具体包括：
将所述待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像，并对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像；
从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻的两个直线段区域，得到两个直线段区域二值化图像。
可选的，所述根据两个直线段区域二值化图像，计算弯曲角度，具体包括：
对两个直线段区域图像进行细化；
对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程；
根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
一种面向弯管加工的弯曲角度检测系统，所述检测系统包括：
图像处理模块，用于对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
弯曲角度分析模块，用于根据两个直线段区域的二值化图像，计算弯曲角度。
可选的，所述图像处理模块包括：
配准单元，用于将待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述待识别图像为加工弯管的图像，所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
坐标变换单元，用于利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
感兴趣弯管区域图像提取单元，用于从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像；
二值化单元，用于对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像；
两个直线段区域二值化图像提取单元，用于从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻的两个直线段区域，得到两个直线段区域二值化图像。
可选的，所述弯曲角度分析模块，具体包括：
细化单元，用于对两个直线段区域图像进行细化；
直线拟合单元，用于对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程；
弯曲角度计算单元，用于根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
一种电子设备，包括布设于各参与方的存储器、布设于各参与方的 处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述的检测方法。
一种面向弯管加工的在线检测方法，所述在线检测方法包括如下步骤：
从弯管加工设备的控制端获得弯管加工的控制信号；
根据所述控制信号判断是否符合图像采集条件；所述图像采集条件为相邻两个控制信号为折弯和平移，且平移运动结束；
当不符合图像采集条件时，返回步骤“从弯管加工设备的控制端获得弯管加工的控制信号”；
当符合图像采集条件时，采集加工弯管的图像，作为待识别图像；
采用上述的检测方法，基于所述待识别图像确定弯曲角度；
将所述弯曲角度与弯管加工工艺要求的弯曲角度进行比对，得到弯曲角度误差；
将所述弯曲误差反馈给弯管加工设备的控制系统，进行加工参数的调整。
可选的，所述采集加工弯管的图像，作为待识别图像，具体包括：
利用电控基座调整光学相机位置，使光学相机能获取包含加工弯管的图像；
控制所述光学相机采集加工弯管的图像，作为待识别图像。
一种面向弯管加工的在线检测系统，所述在线检测系统包括：在线控制模块、图像采集模块、图像处理模块、弯曲角度分析模块和误差反馈模块；
所述在线控制模块用于执行如下步骤：
从弯管加工设备的控制端获得弯管加工的控制信号；
根据所述控制信号判断是否符合图像采集条件；所述图像采集条件为相邻两个控制信号为折弯和平移，且平移运动结束；
所述图像采集模块，用于当符合图像采集条件时，采集加工弯管的图像，作为待识别图像；
所述图像处理模块，用于对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
所述弯曲角度分析模块，用于根据两个直线段区域的二值化图像，计算弯曲角度；
所述误差反馈模块，用于将所述弯曲角度与弯管加工工艺要求的弯曲角度进行比对，得到弯曲角度误差；将所述弯曲误差反馈给弯管加工设备的控制系统，进行加工参数的调整。
根据本发明提供的具体实施例，本发明公开了以下技术效果：
本发明公开一种面向弯管加工的弯曲角度检测方法，所述检测方法包括如下步骤：对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；根据两个直线段区域的二值化图像，计算弯曲角度。本发明提供一种基于图像的弯曲角度在线测量方法和系统，具有成本低、效率高、通用性强的优势。
说明书附图
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的图像处理的流程图；
图2为本发明实施例提供的弯曲度分析的流程图；
图3为本发明实施例提供的面向弯管加工的在线检测方法的流程图；
图4为本发明实施例提供的面向弯管加工的在线检测系统的结构图；
图5为本发明实施例提供的图像采集的流程图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案 进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明的目的是提供一种面向弯管加工的弯曲角度检测方法、系统及电子设备，以提供一种成本低、效率高、通用性强的弯曲角度检测方法及系统。
以下结合附图对本发明的实施例作进一步详细描述。
实施例1
本发明实施例提供一种面向弯管加工的弯曲角度检测方法，所述检测方法包括如下步骤：
对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像。
根据两个直线段区域的二值化图像，计算弯曲角度。
其中，对待识别图像进行二值化及感兴趣区域提取的方式有很多，比如边缘检测、神经网络模型等，但是都不适用于弯管加工中直线段区域的提取。如图1所示，本发明实施例中，对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像，具体包括：
将所述待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域。
利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域。
从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像，并对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像。
从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻 的两个直线段区域，得到两个直线段区域二值化图像。
如图2所示，所述根据两个直线段区域二值化图像，计算弯曲角度，具体包括：
对两个直线段区域图像进行细化。
对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程。
根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
本发明实施例1还提供一种面向弯管加工的弯曲角度检测系统，所述检测系统包括：
图像处理模块，用于对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像。
所述图像处理模块包括：
配准单元，用于将待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述待识别图像为加工弯管的图像，所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
坐标变换单元，用于利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
感兴趣弯管区域图像提取单元，用于从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像；
二值化单元，用于对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像；
两个直线段区域二值化图像提取单元，用于从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻的两个直线段区域，得到两个直线段区域二值化图像。
弯曲角度分析模块，用于根据两个直线段区域的二值化图像，计算弯曲角度。
所述弯曲角度分析模块，具体包括：
细化单元，用于对两个直线段区域图像进行细化。
直线拟合单元，用于对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程。
弯曲角度计算单元，用于根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
本发明实施例1还提供一种电子设备，包括布设于各参与方的存储器、布设于各参与方的处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述的检测方法。
实施例2
本发明实施例2提供一种面向弯管加工的在线检测方法，如图3所示，所述在线检测方法包括如下步骤：
从弯管加工设备的控制端获得弯管加工的控制信号。
根据所述控制信号判断是否符合图像采集条件；所述图像采集条件为相邻两个控制信号为折弯和平移，且平移运动结束。
当不符合图像采集条件时，返回步骤“从弯管加工设备的控制端获得弯管加工的控制信号”。
当符合图像采集条件时，采集加工弯管的图像，作为待识别图像，
采用上述的检测方法，基于所述待识别图像确定弯曲角度，
将所述弯曲角度与弯管加工工艺要求的弯曲角度进行比对，得到弯曲角度误差，
将所述弯曲误差反馈给弯管加工设备的控制系统，进行加工参数的调整。
其中，采集加工弯管的图像，作为待识别图像，具体包括：
利用电控基座调整光学相机位置，使光学相机能获取包含加工弯管的图像；
从弯管加工设备控制端获得弯管加工的控制信号；
判断是否符合图像采集的条件。若相邻两个控制信号为折弯和平移，且平移运动结束，则符合图像采集的条件，否则不符合图像采集的条件。
产生图像采集的控制信号。若符合图像采集的条件，则产生图像采集的控制信号。
执行图像采集，并将图像保存于存储介质中。
本发明实施例还提供一种面向弯管加工的在线检测系统，如图4所示，所述在线检测系统包括：在线控制模块、图像采集模块、图像处理模块、弯曲角度分析模块和误差反馈模块；在线控制模块接受来自弯管加工设备的控制信号，对控制信号逻辑进行判别，产生图像采集的控制信号，发送给图像采集模块；图像采集模块采集弯管加工现场的图像；图像处理模块对采集的图像进行处理获取当前折弯区域的图像；弯曲角度分析模块对感兴趣区域的图像进行处理，获得弯曲角度以及弯曲角度误差，并将其发送到弯管加工设备控制终端。
如图5所示，图像采集的过程具体包括：
利用电控基座调整光学相机位置，使光学相机能获取包含加工弯管的图像。
从弯管加工设备控制端获得弯管加工的控制信号。
判断是否符合图像采集的条件。若相邻两个控制信号为折弯和平移，且平移运动结束，则符合图像采集的条件，否则不符合图像采集的条件。
产生图像采集的控制信号。若符合图像采集的条件，则产生图像采集的控制信号。
执行图像采集，并将图像保存于存储介质中。
如图1所示，图像处理过程包括以下步骤：
将当前图像与带标注的弯管加工图像库中的图像进行图像配准，得到匹配最优的带标注的基准图像及图像配准变换矩阵。
根据变换矩阵和带标注的基准图像，得到当前采集图像中感兴趣弯管区域及两个直线段的区域。
对当前采集图像中感兴趣弯管区域的图像进行二值化处理，并根据 当前采集图像中两个直线段的区域得到两个直线段区域的二值化图像。
如图2所示，弯曲角度分析包括以下步骤：
对两个直线段区域的二值化图像进行图像细化；
对细化后的两个直线段区域进行直线拟合，得到两个直线方程；
根据两条直线方程计算直线之间的夹角，即弯曲的角度；
将计算得到的弯曲角度与加工工艺要求的弯曲角度进行比较得到弯曲角度误差计算。
本发明实施例通过采集每次折弯后的图像，与图像数据库中的图像进行配准，确定弯曲区域相邻的两条线段区域，运用图像处理获得两条线段的直线方程，进而得到实际弯曲的角度，可有效提高产品的质量，及时掌握弯管加工工况，具有成本低、效率高、通用性强的特点。
以上结合附图对本发明的实施例进行了描述，但是本发明并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本发明的启示下，在不脱离本发明宗旨和权利要求所保护的范围情况下，还可做出很多形式，这些均属于本发明的保护之内。

Claims (10)

  1. 一种面向弯管加工的弯曲角度检测方法，其特征在于，所述检测方法包括如下步骤：
    对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
    根据两个直线段区域的二值化图像，计算弯曲角度。
  2. 根据权利要求1所述的面向弯管加工的弯曲角度检测方法，其特征在于，所述对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像，具体包括：
    将所述待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
    利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
    从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像，并对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像；
    从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻的两个直线段区域，得到两个直线段区域二值化图像。
  3. 根据权利要求1所述的面向弯管加工的弯曲角度检测方法，其特征在于，所述根据两个直线段区域二值化图像，计算弯曲角度，具体包括：
    对两个直线段区域图像进行细化；
    对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程；
    根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
  4. 一种面向弯管加工的弯曲角度检测系统，其特征在于，所述检测系统包括：
    图像处理模块，用于对待识别图像进行二值化及感兴趣区域提取，获 得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
    弯曲角度分析模块，用于根据两个直线段区域的二值化图像，计算弯曲角度。
  5. 根据权利要求4所述的面向弯管加工的弯曲角度检测系统，其特征在于，图像处理模块包括：
    配准单元，用于将待识别图像与弯管加工图像数据库中的样本图像进行配准，获得配准变换矩阵；所述待识别图像为加工弯管的图像，所述弯管加工图像数据库包括弯管加工过程中每次折弯并平移后获得的样本图像，所述样本图像包括：基准图像、标注的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
    坐标变换单元，用于利用变换矩阵对样本图像的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域进行坐标变换，获取待识别图像中的感兴趣弯管区域以及与当前折弯相邻的两个直线段区域；
    感兴趣弯管区域图像提取单元，用于从待识别图像中截取待识别图像中的感兴趣弯管区域，获得感兴趣弯管区域图像；
    二值化单元，用于对所述感兴趣弯管区域图像进行二值化，得到感兴趣弯管区域二值化图像；
    两个直线段区域二值化图像提取单元，用于从感兴趣弯管区域二值化图像中截取待识别图像中的当前折弯相邻的两个直线段区域，得到两个直线段区域二值化图像。
  6. 根据权利要求4所述的面向弯管加工的弯曲角度检测系统，其特征在于，所述弯曲角度分析模块，具体包括：
    细化单元，用于对两个直线段区域图像进行细化；
    直线拟合单元，用于对两个细化后的像素坐标进行直线拟合，得到两条线段的直线方程；
    弯曲角度计算单元，用于根据两条线段的直线方程计算两条线段之间的夹角，得到弯曲角度。
  7. 一种电子设备，其特征在于，包括布设于各参与方的存储器、布设 于各参与方的处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如权利要求1至3中任一项所述的检测方法。
  8. 一种面向弯管加工的在线检测方法，其特征在于，所述在线检测方法包括如下步骤：
    从弯管加工设备的控制端获得弯管加工的控制信号；
    根据所述控制信号判断是否符合图像采集条件；所述图像采集条件为相邻两个控制信号为折弯和平移，且平移运动结束；
    当不符合图像采集条件时，返回步骤“从弯管加工设备的控制端获得弯管加工的控制信号”；
    当符合图像采集条件时，采集加工弯管的图像，作为待识别图像；
    采用权利要求1-3任一项所述的检测方法，基于所述待识别图像确定弯曲角度；
    将所述弯曲角度与弯管加工工艺要求的弯曲角度进行比对，得到弯曲角度误差；
    将所述弯曲误差反馈给弯管加工设备的控制系统，进行加工参数的调整。
  9. 根据权利要求8所述的面向弯管加工的在线检测方法，其特征在于，所述采集加工弯管的图像，作为待识别图像，具体包括：
    利用电控基座调整光学相机位置，使光学相机能获取包含加工弯管的图像；
    控制所述光学相机采集加工弯管的图像，作为待识别图像。
  10. 一种面向弯管加工的在线检测系统，其特征在于，所述在线检测系统包括：在线控制模块、图像采集模块、图像处理模块、弯曲角度分析模块和误差反馈模块；
    所述在线控制模块用于执行如下步骤：
    从弯管加工设备的控制端获得弯管加工的控制信号；
    根据所述控制信号判断是否符合图像采集条件；所述图像采集条件为 相邻两个控制信号为折弯和平移，且平移运动结束；
    所述图像采集模块，用于当符合图像采集条件时，采集加工弯管的图像，作为待识别图像；
    所述图像处理模块，用于对待识别图像进行二值化及感兴趣区域提取，获得两个直线段区域二值化图像；所述待识别图像为加工弯管的图像；
    所述弯曲角度分析模块，用于根据两个直线段区域的二值化图像，计算弯曲角度；
    所述误差反馈模块，用于将所述弯曲角度与弯管加工工艺要求的弯曲角度进行比对，得到弯曲角度误差；将所述弯曲误差反馈给弯管加工设备的控制系统，进行加工参数的调整。
PCT/CN2023/079724 2022-12-16 2023-03-06 一种面向弯管加工的弯曲角度检测方法、系统及电子设备 Ceased WO2024124707A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
DE112023005213.1T DE112023005213T5 (de) 2022-12-16 2023-03-06 Verfahren und System zum Erfassen eines Biegewinkels beim Bearbeiten eines Biegerohrs und elektronisches Gerät
US18/249,633 US12608901B2 (en) 2022-12-16 2023-03-06 Bending angle detection method and system for tube bending and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211621210.3 2022-12-16
CN202211621210.3A CN116012576B (zh) 2022-12-16 2022-12-16 一种面向弯管加工的弯曲角度检测方法、系统及电子设备

Publications (1)

Publication Number Publication Date
WO2024124707A1 true WO2024124707A1 (zh) 2024-06-20

Family

ID=86025872

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/079724 Ceased WO2024124707A1 (zh) 2022-12-16 2023-03-06 一种面向弯管加工的弯曲角度检测方法、系统及电子设备

Country Status (4)

Country Link
US (1) US12608901B2 (zh)
CN (1) CN116012576B (zh)
DE (1) DE112023005213T5 (zh)
WO (1) WO2024124707A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119103998A (zh) * 2024-11-08 2024-12-10 正能机械科技(张家港)有限公司 一种弯管机管路弯曲角度测量方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101898211A (zh) * 2010-07-23 2010-12-01 杭州捷塔科技有限公司 用于弯管加工中的在线检测与补偿系统
CN103438836A (zh) * 2013-08-23 2013-12-11 中联重科股份有限公司 折弯件折弯角度测量设备、系统及方法
US20160292875A1 (en) * 2013-12-19 2016-10-06 Olympus Corporation Image processing apparatus, image processing method, and computer-readable recording medium
CN109146950A (zh) * 2018-09-30 2019-01-04 燕山大学 一种利用板材热弯曲工艺弯曲角在线测量方法
CN113298856A (zh) * 2021-05-28 2021-08-24 上海联影医疗科技股份有限公司 一种图像配准方法、装置、设备和介质
CN115060199A (zh) * 2022-06-08 2022-09-16 深视灵(宁波)工业科技有限公司 基于二维成像的弯管机管路弯曲角度在线测量方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH11125514A (ja) * 1997-10-22 1999-05-11 Komatsu Ltd 曲げ角度検出装置
AT515944B1 (de) * 2014-10-16 2016-01-15 Trumpf Maschinen Austria Gmbh Biegewinkel-Messverfahren
CN107008786B (zh) * 2017-03-21 2019-01-01 南京航空航天大学 三维弯管首尾几何精确位置的自由成形动态优化方法
JP7594495B2 (ja) * 2021-05-21 2024-12-04 株式会社クボタ 屈曲角の判定方法および判定装置
CN115345924B (zh) * 2022-06-30 2025-10-31 南京航空航天大学 一种基于多目相机线激光扫描的弯管测量方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101898211A (zh) * 2010-07-23 2010-12-01 杭州捷塔科技有限公司 用于弯管加工中的在线检测与补偿系统
CN103438836A (zh) * 2013-08-23 2013-12-11 中联重科股份有限公司 折弯件折弯角度测量设备、系统及方法
US20160292875A1 (en) * 2013-12-19 2016-10-06 Olympus Corporation Image processing apparatus, image processing method, and computer-readable recording medium
CN109146950A (zh) * 2018-09-30 2019-01-04 燕山大学 一种利用板材热弯曲工艺弯曲角在线测量方法
CN113298856A (zh) * 2021-05-28 2021-08-24 上海联影医疗科技股份有限公司 一种图像配准方法、装置、设备和介质
CN115060199A (zh) * 2022-06-08 2022-09-16 深视灵(宁波)工业科技有限公司 基于二维成像的弯管机管路弯曲角度在线测量方法及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119103998A (zh) * 2024-11-08 2024-12-10 正能机械科技(张家港)有限公司 一种弯管机管路弯曲角度测量方法及系统

Also Published As

Publication number Publication date
US12608901B2 (en) 2026-04-21
US20260017914A1 (en) 2026-01-15
DE112023005213T5 (de) 2025-10-02
CN116012576A (zh) 2023-04-25
CN116012576B (zh) 2026-01-02

Similar Documents

Publication Publication Date Title
CN114034704A (zh) 一种基于多源数据融合的废旧轧辊三维检测装置及方法
CN114581385B (zh) 一种基于圆定位的焊缝缺陷区域映射方法
CN109986172B (zh) 一种焊缝定位方法、设备及系统
CN114147397B (zh) 一种识别3d特征的自动柔性点拼焊系统
CN107388991B (zh) 一种端面多圆角轴类零件圆角半径测量方法
CN112238292A (zh) 一种基于视觉的搅拌摩擦焊机器人空间曲线轨迹跟踪方法
CN117670887A (zh) 一种基于机器视觉的锡焊高度及缺陷检测方法
CN115035092A (zh) 基于图像的瓶体检测方法、装置、设备及存储介质
CN118537339B (zh) 一种基于磨砂机的零部件表面质量的评估方法及系统
CN108389184A (zh) 一种基于机器视觉的工件制孔数检测方法
WO2024124707A1 (zh) 一种面向弯管加工的弯曲角度检测方法、系统及电子设备
Ji et al. Computer vision–based surface defect identification method for weld images
CN118247330A (zh) 基于动作协同的无缝钢管智能分析系统
CN117350967A (zh) 一种基于光学检测晶圆外观缺陷检测系统及其方法
CN119359715A (zh) 基于图像处理的焊枪主板缺陷检测方法和系统
CN118655084A (zh) 表面缺陷检测方法、系统、电子设备和存储介质
CN117830230A (zh) 基于ai特征识别的管道环焊缝缺陷检测方法和系统
CN114663402B (zh) 一种基于Hough直线检测和曲线拟合的线缆脱垂检测方法
CN118691595A (zh) 一种基于图像识别的连接器生产缺陷检测方法及系统
CN113240629A (zh) 基于边缘的图像匹配窄间隙焊缝初始点定位装置和方法
CN118392870A (zh) Ic芯片缺陷检测方法、系统、设备及存储介质
Mu Application of ROI-based image processing technology in mechanical component size measurement
CN110349174B (zh) 一种滑轨多参数测量方法以及测量装置
CN114519704A (zh) 一种通讯电器金属零部件表面划痕缺陷检测方法
CN116429170B (zh) 一种板坯质量检测方法

Legal Events

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

Ref document number: 23901925

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 112023005213

Country of ref document: DE

WWP Wipo information: published in national office

Ref document number: 112023005213

Country of ref document: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23901925

Country of ref document: EP

Kind code of ref document: A1