CN115375637A - Detection apparatus for tire color point - Google Patents

Detection apparatus for tire color point Download PDF

Info

Publication number
CN115375637A
CN115375637A CN202210948953.5A CN202210948953A CN115375637A CN 115375637 A CN115375637 A CN 115375637A CN 202210948953 A CN202210948953 A CN 202210948953A CN 115375637 A CN115375637 A CN 115375637A
Authority
CN
China
Prior art keywords
image acquisition
color point
tire
wheel
acquisition system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210948953.5A
Other languages
Chinese (zh)
Inventor
张子男
张淳
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.)
Sh Intelligent Equipment Shanghai Co ltd
Original Assignee
Sh Intelligent Equipment Shanghai 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 Sh Intelligent Equipment Shanghai Co ltd filed Critical Sh Intelligent Equipment Shanghai Co ltd
Priority to CN202210948953.5A priority Critical patent/CN115375637A/en
Publication of CN115375637A publication Critical patent/CN115375637A/en
Pending legal-status Critical Current

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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/084Backpropagation, e.g. using gradient descent
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/80Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/90Determination of colour characteristics
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10028Range image; Depth image; 3D point clouds
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20081Training; Learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20084Artificial neural networks [ANN]
    • 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
    • G06T2207/30244Camera pose

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention provides a detection device for a tire color point, which comprises: the device comprises a conveying mechanism, a centering mechanism, a rotating mechanism, a programmable logic controller, an image acquisition system and a power supply, wherein the image acquisition system comprises a 2D image acquisition device, a 3D image acquisition device, a light source and an industrial computer, and the detection device of the color point of the tire can simultaneously acquire and process two-dimensional and three-dimensional data of the surface of the wheel and obtain the position, the color, the size and the defect of the color point from the data.

Description

Detection apparatus for tire color point
Technical Field
The invention relates to the technical field of tire production or assembly, in particular to the technical field of position and defect detection of color points of tires.
Background
The wheel color point has various uses such as a light point indicating balance, a high and low point of run-out, and the like. Thus, the color point of the wheel is an important indicator after the wheel is produced. The method has very important significance for later wheel assembly.
The colored spots of the wheel may have various defects such as breakage, warping, etc. due to reasons in production or during transportation. These defects have a relatively large effect on the later assembly of the wheel. It is necessary to perform a check to ensure that the colour spot is intact.
The prior art mainly relies on 2D vision for detecting the color point, and there are great limitations for detecting the color point, such as failure to detect the warpage of the color point, and the 2D vision is susceptible to ambient light for detecting the color point.
Disclosure of Invention
In order to overcome the technical defects, the invention aims to provide a device for detecting a color point of a tire, which structurally comprises: the device comprises a conveying mechanism, a centering mechanism, a rotating mechanism, a programmable logic controller, an image acquisition system and a power supply, wherein the image acquisition system comprises a 2D image acquisition device, a 3D image acquisition device, a light source and an industrial computer, and the detection device of the tire color point can simultaneously acquire and process two-dimensional and three-dimensional data of the surface of the wheel and obtain the position, the color, the size and the defects of the color point from the data.
Furthermore, the image acquisition system is based on deep learning, the deep learning refers to a deep neural network, the deep neural network is a discrimination model, and a back propagation algorithm can be used for training. In particular, deep learning refers to deep learning, which means that a Deep Neural Network (DNN) is a framework of deep learning, which is a neural network with at least one hidden layer. Similar to the shallow neural network, the deep neural network can also provide modeling for a complex nonlinear system, but the extra levels provide higher abstraction levels for the model, thereby improving the capability of the model. Deep neural networks are a discriminant model that can be trained using back-propagation algorithms.
Further, a device for detecting the color point of a tire, wherein a programmable logic controller comprises a memory, a processor, and a program stored on said memory and operable on said processor, said program when executed by said processor implementing the steps of:
step S1: wheel alignment, centering being the basis for subsequent wheel clamping and rotation
Step S2: wheel clamping and rotation operation
And step S3: when the wheel rotates to a certain speed, an image acquisition starting signal is generated to the image acquisition system
And step S4: after the image acquisition system finishes image acquisition, a signal is sent to inform the wheel to stop rotating
Step S5: after the image acquisition system finishes image processing, a processing result signal is sent to the conveying mechanism, and the conveying mechanism conveys the wheels to respective specified positions according to whether the processing result is qualified or unqualified
Furthermore, the 2D image acquisition equipment comprises a light source and an industrial camera, the industrial camera can be divided into an area-array camera and a line-array camera, and the type of the camera can be selected according to actual requirements.
Further, the 3D image capturing device is a laser profiler using a laser triangulation principle, or a 3D camera using a structured light principle. The 3D image acquisition equipment is used for acquiring three-dimensional point cloud data of the surface of the tire.
After the technical scheme is adopted, compared with the prior art, the method has the following beneficial effects: the advantages of 2D and 3D vision are exerted simultaneously, and various attributes of the wheel color points are detected. The method specifically comprises the following steps:
color point localization using 3D camera intensity mode
Color classification using color pictures of a 2D camera
Integrity determination of color points using intensity patterns of 3D cameras
The dot cloud data of the 3D camera is used to determine the color dot size and determine whether or not there is warping. The size range of the color point of the tire which can be detected is 5-15mm, and the detection precision of the tire size is 0.1mm.
The device and the method for detecting the color points of the tire are color point detection methods based on 2-dimensional and 3-dimensional vision. The method can be used for detecting the color point defects in tire production (such as color defects, size defects, shape integrity defects, warping defects and the like of color points) and determining the positions of the color point in the tire assembling process.
Drawings
FIG. 1 is a sectional view of the apparatus for detecting a color point of a tire according to the present invention.
The reference numbers illustrate:
1. equipment base
2. Wheel lifting part
3.3D image acquisition device
4. Equipment frame
5. Electric machine
6. Main shaft
Detailed Description
The advantages of the invention are further illustrated in the following description of specific embodiments in conjunction with the accompanying drawings. It is to be understood by persons skilled in the art that the following detailed description is illustrative and not restrictive, and is not to be taken as limiting the scope of the invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
Example 1
As shown in fig. 1, the apparatus for detecting a color point of a tire of the present embodiment includes: the device comprises a device base 1, a conveying mechanism (see a wheel lifting part 2 in fig. 1), a 3D image acquisition device 3, a device frame 4, a motor 5, a main shaft 6, a centering mechanism, a rotating mechanism, a programmable logic controller, an image acquisition system and a power supply, wherein the image acquisition system comprises a 2D image acquisition device, a light source and an industrial computer. The power supply and the programmable logic controller are packaged in a small electrical cabinet. The programmable controller is formed by modularly combining an internal CPU, a memory for storing computer programs and data, a processor, an input/output unit, a power supply module, a digital analog unit and the like, and controls various types of mechanical equipment or production processes through digital or analog input/output.
The principle of the method for detecting the defects of the colored points of the tire by adopting the detection device is as follows:
(1) The wheels are fixed on the rotating mechanism, and in the rotating process, the 2D and 3D vision sensors collect image information.
(2) The invention relates to a core component:
a controller: the controller of the actuator is a set of embedded processor system or Programmable Logic Controller (PLC), is a main control unit of the whole image acquisition system, and controls the rotation of the wheels and the work of the image acquisition equipment.
2D/3D image acquisition device: 2D/3D image information including color points of the tire surface is collected during wheel rotation.
Motor, transmission equipment and anchor clamps: as a carrier for wheels and a source of rotary power
(3) The invention relates to a core technology: an image processing system based on deep learning. The main functions of the image processing system include: and judging the position of the color point and detecting the color point. The primary function of position detection is to find the colored spots on the tire surface that need to be detected. The color point detection is to detect information on colors using a 2D/3D image. Information that can be detected includes: whether the color, shape, size, appearance are complete, and whether there is warping.
The technical indexes of the color point defect detection equipment are as follows:
1) Detecting the range; the size range of the color point is 5-15mm
2) And (3) size detection precision: 0.1mm
3) Communication interface: and (4) a network port.
The color point defect detection device related to the embodiment adopts 2D and 3D vision sensors to detect simultaneously. Calibration between 2D and 3D cameras is first required to ensure that cameras mounted in different positions can have the same coordinate system. The 3D camera simultaneously acquires a gray-scale image and a point cloud image by using a laser light source of the 3D camera. The gray map is used for positioning and detecting integrity. The point cloud picture is used for detecting defects such as warping. The 2D camera performs detection such as color dot type.
It should be noted that the embodiments of the present invention have been described in terms of preferred embodiments, and not by way of limitation, and that those skilled in the art can make modifications and variations of the embodiments described above without departing from the spirit of the invention.

Claims (5)

1. A device for detecting a color point of a tire, comprising: the device comprises a conveying mechanism, a centering mechanism, a rotating mechanism, a programmable logic controller, an image acquisition system and a power supply, wherein the image acquisition system comprises a 2D image acquisition device, a 3D image acquisition device, a light source and an industrial computer, and the detection device of the color point of the tire can simultaneously acquire and process two-dimensional and three-dimensional data of the surface of the wheel and obtain the position, the color, the size and the defect of the color point from the data.
2. The apparatus for detecting the color point of a tire according to claim 1, wherein said image acquisition system is an image acquisition system based on deep learning, said deep learning is a deep neural network, said deep neural network is a discriminant model, and said discriminant model can be trained by using back propagation algorithm.
3. The apparatus for detecting the color point of a tire as in claim 1, wherein the programmable logic controller comprises a memory, a processor, and a program stored on said memory and operable on said processor, said program when executed by said processor performing the steps of:
step S1: wheel centering, wherein centering is the basis for subsequent wheel clamping and rotation;
step S2: wheel clamping and rotation operations;
and step S3: after the wheel rotates to a certain speed, sending an image acquisition starting signal to an image acquisition system;
and step S4: after the image acquisition system finishes image acquisition, sending a signal to inform the wheel to stop rotating;
step S5: and after the image acquisition system finishes image processing, a processing result signal is sent to the conveying mechanism, and the conveying mechanism conveys the wheels to respective specified positions according to whether the processing result is qualified or unqualified.
4. The apparatus for detecting the color point of a tire as set forth in claim 1, wherein said 2D image capturing device comprises a light source and an industrial camera, said industrial camera being further divided into an area camera and a line camera, said 2D image capturing device being adapted to capture 2-dimensional images of the surface of the wheel.
5. The apparatus for detecting the color point of a tire as claimed in claim 1, wherein said 3D image capturing device is a laser profiler using the principle of laser triangulation or a 3D camera using the principle of structured light, and said 3D image capturing device is used for capturing three-dimensional point cloud data of the tire surface.
CN202210948953.5A 2022-08-09 2022-08-09 Detection apparatus for tire color point Pending CN115375637A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210948953.5A CN115375637A (en) 2022-08-09 2022-08-09 Detection apparatus for tire color point

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210948953.5A CN115375637A (en) 2022-08-09 2022-08-09 Detection apparatus for tire color point

Publications (1)

Publication Number Publication Date
CN115375637A true CN115375637A (en) 2022-11-22

Family

ID=84063767

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210948953.5A Pending CN115375637A (en) 2022-08-09 2022-08-09 Detection apparatus for tire color point

Country Status (1)

Country Link
CN (1) CN115375637A (en)

Similar Documents

Publication Publication Date Title
CN208672539U (en) A kind of foliated glass edge faults detection device based on Image Acquisition
CN103604808B (en) A kind of bottle cap defective vision detection method
CN109341527B (en) Automatic shadow compensation structured light projection three-dimensional measurement system and method
CN115156093A (en) Battery shell defect detection method, system and device
CN105301007A (en) Linear array CCD-based ABS gear ring defect online detection device and method
CN111982921A (en) Hole defect detection method and device, conveying platform and storage medium
WO2013078708A1 (en) Automatic optical detection method and automatic optical detection device
CN112884743B (en) Detection method and device, detection equipment and storage medium
CN110966956A (en) Binocular vision-based three-dimensional detection device and method
CN113358070B (en) Automobile brake pad flatness and pin height detection system and detection method thereof
CN113418933B (en) Flying shooting visual imaging detection system and method for detecting large-size object
CN113566733B (en) Line laser vision three-dimensional scanning device and method
CN108133477A (en) A kind of object detecting method and intelligent machine arm
Xia et al. Workpieces sorting system based on industrial robot of machine vision
CN114280075A (en) Online visual inspection system and method for surface defects of pipe parts
CN114820439A (en) PCB bare board defect detection system and method based on AOI
CN113504239A (en) Quality control data analysis method
WO2019203840A1 (en) Three-dimensional calibration target
CN107633508A (en) One kind metering product printed substrate outward appearance verification method and system
CN110779933A (en) Surface point cloud data acquisition method and system based on 3D visual sensing array
CN115375637A (en) Detection apparatus for tire color point
JP2019194549A (en) Inspection method for tire mold side plate
CN116125489A (en) Indoor object three-dimensional detection method, computer equipment and storage medium
Huang et al. Line laser based researches on a three-dimensional measuring system
CN210181656U (en) Cloth defect detection device

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