CN115684177A - Automatic detection system and method for automobile tire defects - Google Patents
Automatic detection system and method for automobile tire defects Download PDFInfo
- Publication number
- CN115684177A CN115684177A CN202211331349.4A CN202211331349A CN115684177A CN 115684177 A CN115684177 A CN 115684177A CN 202211331349 A CN202211331349 A CN 202211331349A CN 115684177 A CN115684177 A CN 115684177A
- Authority
- CN
- China
- Prior art keywords
- tire
- sliding table
- point cloud
- camera
- table base
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 61
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000006870 function Effects 0.000 claims abstract description 28
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 229910000831 Steel Inorganic materials 0.000 claims description 9
- 239000010959 steel Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 239000010755 BS 2869 Class G Substances 0.000 claims description 6
- 238000012886 linear function Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 230000032683 aging Effects 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000003466 welding Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses an automatic detection system and method for automobile tire defects, and aims to solve the problems of automatic detection and defect classification of automobile tire defects. The automatic automobile tire defect detection system mainly comprises a cylindrical guide rail (1), a sliding block (2), a sliding table base (3), an RGB-D camera (4), a screw rod (5) and a motor (6). The RGB-D camera (4) is a three-dimensional camera with the functions of depth and color measurement, and the RGB-D camera (4) is placed on the top of the second sliding block (2) and fixed through bolts. The automatic detection method for the automobile tire defects comprises the steps of automatic collection of tire tread point clouds, automatic classification of three-dimensional point clouds of automobile tire characteristics and the like, and provides an automatic detection system and method for the automobile tire defects, which have the advantages of simple structure, high detection precision and small classification error.
Description
Technical Field
The invention relates to automobile detection equipment and a detection method, in particular to an automatic detection system and a method for automobile tire defects.
Background
With the continuous development of the automobile industry, the intelligent detection and diagnosis of automobiles are also concerned. The tire is one of the most important parts of the automobile, and the normal working performance of the tire is an important guarantee for traffic safety. Studies have shown that tire defects are one of the major causes of traffic accidents. Most of the prior detection of tire treads still stay in a manual observation stage, and the method not only causes certain errors, but also wastes time and labor. How to detect the tire tread of an automobile tire by using a machine vision method is very important to automatically acquire the defect position and the type of the tire. In order to realize three-dimensional point cloud reconstruction of the appearance characteristics of the automobile tire, an automatic automobile tire defect detection system and method are designed.
Disclosure of Invention
The invention provides an automatic detection system and method for automobile tire defects, aiming at solving the problems of low automation degree, large detection error and the like of the prior art device in the process of reconstructing three-dimensional point cloud characteristics of an automobile tire, and realizing automatic detection and classification of automobile tire shape defects. The method mainly comprises a cross sliding table consisting of an RGB-D camera and two small sliding tables, and realizes automatic detection and classification of tire three-dimensional point clouds by rolling the tire on the ground and automatically scanning the three-dimensional point clouds on the tire tread by using the RGB-D camera.
The invention is realized by adopting the following technical scheme by combining the attached drawings of the specification:
the automatic detection system for the automobile tire defects comprises a cylindrical guide rail, a sliding block, a sliding table base, an RGB-D camera, a lead screw and a motor;
the sliding table base is placed in a foundation pit and fixed with a foundation bolt, a threaded hole of the sliding block is in threaded fit connection with a lead screw, the lead screw penetrates through holes in two sides of the sliding table base and is in clearance fit with the sliding table base, a bolt penetrates through a small circular through hole in one side of the sliding table base and is fixedly connected with a motor thread, an output shaft of the motor is fixedly connected with one end of the lead screw through a coupler, through holes of the sliding block are in sliding fit with two cylindrical guide rails respectively, the two cylindrical guide rails are welded and fixed with the inner side of the sliding table base, the top surface of the sliding block is coplanar with the ground, a second sliding table base is placed on the top surface of the sliding block and is fixedly connected with the sliding block thread, a threaded hole of the second sliding block is in threaded fit connection with a second lead screw, the second lead screw penetrates through holes in two sides of the second sliding table base and is in clearance fit with the second sliding table base, a bolt penetrates through a small circular through hole in one side of the second sliding table base and is fixedly connected with a second motor thread, an output shaft of the second motor is fixedly connected with one end of the second lead screw through a coupler, through holes of the second sliding block and is in sliding fit with the two cylindrical guide rails respectively, the inner side of the second sliding table base, a RGB-D camera is placed on the top of the second sliding block and is fixed with the bolt.
The cylindrical guide rail in the technical scheme is a smooth cylindrical part.
In the technical scheme, the sliding block is a cuboid part made of steel materials, a threaded hole is processed in the top surface of the sliding block, and a threaded through hole and a circular through hole are processed in the side surface of the sliding block.
In the technical scheme, the sliding table base is a U-shaped part formed by welding steel plates, circular through holes are formed in two sides of the sliding table base, and small circular through holes are formed in the periphery of the circular through hole in one side of the sliding table base.
The RGB-D camera in the technical scheme is a three-dimensional camera with depth and color measurement functions.
The screw rod in the technical proposal is a slender cylinder part which is made of steel material and has two cylindrical ends and a thread processed in the middle part,
the motor in the technical scheme is a standard stepping motor or a servo motor with a threaded hole machined in one side of an output shaft.
The automatic detection method for the automobile tire defects comprises the following specific steps:
the first step is as follows: the automatic detection method for the automobile tire defect comprises the following steps of automatically collecting point clouds of tire treads:
fixedly connecting an RGB-D camera with a sliding block bolt of a cross sliding table, and enabling the RGB-D camera to observe and detect a tire; the tire rolls to the RGB-D camera in the forward driving process of the automobile, the motor and the cross sliding table drive the RGB-D camera to move left and right to the position right opposite to the tire surface of the tire to be detected according to tire point cloud signals collected by the RGB-D camera, then the motor and the cross sliding table keep a constant distance with the tire to be detected and move back and forth, and then three-dimensional point clouds of the characteristics of the tire to be detected in the forward and backward movement processes of the automobile are extracted.
The second step is that: automatic classification of three-dimensional point cloud of automobile tire characteristics:
first of all, a linear function of the tire point cloud input is established, i.e.
z=f(w T x+b)
Wherein x is an input vector of the tire point cloud, w is a weight vector parameter identified by the tire point cloud, and b is a bias;
classifying the common defects of aging cracks, eccentric wear, sharp object puncture, bulges, patterns, pittings, scratches, cuts, pits and the like on the surface of the automobile tire into K categories, wherein the posterior probability of each defect category is
Wherein G is k And G j Is one of K tire defect categories;
for generative models of multi-classification problems of tire defects, the posterior probability of a tire point cloud classification is given by an activation function transformation, i.e.
Wherein i k =w k T Theta, theta being a certain tyre defect class G k The feature vector of (2);
then determining tire point cloud identification parameters w in the classification model by using a maximum likelihood method, wherein the likelihood function is
Wherein y is nk =y k (θ n ),t n For a certain tyre defect class G k Characteristic vector theta of k T is an N x K matrix of target variables, the element is T nk ;
Defining an error function by taking the negative logarithm of the likelihood function to obtain a cross entropy error function of the multi-classification problem of the tire point cloud, namely
Taking the gradient of the error function with respect to the tire point cloud identification parameter w, i.e.
The error function of the tire point cloud is updated by iteration through a method of descending sequential gradients, namely
Where H is the Hessian matrix whose elements consist of the second derivative of the tire point cloud error function J (w) with respect to w, i.e.
Finally, obtaining a trained tire point cloud identification parameter w, and inputting a linear function z = f (w) by using the tire point cloud T x + b) classifying and predicting different defect conditions of the tire.
The invention has the beneficial effects that:
1. the invention adopts an RGB-D camera to carry out three-dimensional point cloud reconstruction on the characteristics of the automobile tire. Firstly, the RGB-D camera is fixedly connected with a sliding block of the cross sliding table, and the tire tread and the RGB-D camera are ensured to be on the same straight line. By rolling of the tires of the automobile in the driving process, the cross sliding table is used for driving the RGB-D camera to move front and back and left and right, three-dimensional point clouds with characteristics of the automobile tires can be automatically and comprehensively extracted, and the defects of the automobile tires can be detected by classifying the point clouds.
2. The invention automatically classifies the defects of the characteristics of the automobile tires by using a machine learning logistic regression method, realizes iterative training of tire point cloud classification by using a gradient descent method, and has the advantages of easy realization, high training efficiency, high accuracy and the like.
3. The tire defect detection system designed by the invention solves the problems of low manual detection precision, low automation degree of the conventional tire detection mode and the like. The RGB-D camera is used for carrying out three-dimensional point cloud reconstruction and classification on the characteristics of the automobile tire, and the method has the beneficial effect of realizing safe driving of the automobile.
Drawings
FIG. 1 is an overall isometric view of an automatic vehicle tire defect detection system;
FIG. 2 is an axonometric view of a cylindrical guide rail 1, a slide block 2 and a sliding table base 3 in the automatic detection system for automobile tire defects;
fig. 3 is an isometric view of the slide block 2 in the automatic detection system for automobile tire defects;
FIG. 4 is an axonometric view of a cylindrical guide rail 1 and a sliding table base 3 in the automatic detection system for automobile tire defects;
fig. 5 is an isometric view of the RGB-D camera 4 in the automatic detection system for automobile tire defects;
fig. 6 is an isometric view of the lead screw 5 in the automatic detection system for automobile tire defects;
fig. 7 is an isometric view of the motor 6 in the automatic vehicle tire defect detection system;
FIG. 8 is a flow chart of an automatic detection method for vehicle tire defects;
in the figure: 1. the device comprises a cylindrical guide rail, 2 sliding blocks, 3 sliding table bases, 4 RGB-D cameras, 5 lead screws and 6 motors.
Detailed Description
The invention is described in further detail below with reference to the attached drawing figures:
referring to fig. 1 to 7, the automatic detection system for automobile tire defects comprises a cylindrical guide rail 1, a slide block 2, a sliding table base 3, an RGB-D camera 4, a screw 5 and a motor 6.
The sliding table base 3 is a U-shaped part formed by welding steel plates, circular through holes are processed on two sides of the sliding table base 3, small circular through holes are processed on the periphery of the circular through hole on one side of the sliding table base 3, the sliding table base 3 is placed in a foundation pit and is fixed with a foundation bolt and a foundation, the screw 5 is a slender cylinder part which is made of steel materials, two ends of the slender cylinder part are cylindrical, the middle of the slender cylinder part is processed with threads, the sliding block 2 is a cuboid part made of steel materials, a threaded hole is processed on the top surface of the sliding block 2, a threaded through hole and a circular through hole are processed on the side surface of the sliding block 2, the threaded hole of the sliding block 2 is in threaded fit connection with the screw 5, the screw 5 penetrates through holes on two sides of the sliding table base 3 and is in clearance fit with the sliding table base 3, the motor 6 is a standard stepping motor or a servo motor with a threaded hole processed on one side of an output shaft, and the bolt penetrates through the small circular through hole on one side of the sliding table base 3 and is fixedly connected with the motor 6 through threads, an output shaft of a motor 6 is fixedly connected with one end of a screw 5 through a coupler, the cylindrical guide rails 1 are smooth cylindrical parts, through holes of a sliding block 2 are respectively in sliding fit with the two cylindrical guide rails 1, the two cylindrical guide rails 1 are welded and fixed with the inner side of a sliding table base 3, the top surface of the sliding block 2 is coplanar with the ground, a second sliding table base 3 is placed on the top surface of the sliding block 2 and is in threaded fixed connection with the sliding block 2, a threaded hole of the second sliding block 2 is in threaded fit with a second screw 5, the second screw 5 penetrates through holes on two sides of the second sliding table base 3 and is in clearance fit with the second sliding table base 3, a bolt penetrates through a small circular through hole on one side of the second sliding table base 3 and is in threaded fixed connection with a second motor 6, an output shaft of the second motor 6 is fixedly connected with one end of the second screw 5 through a coupler, and through holes of the second sliding block 2 are respectively in sliding fit with the two cylindrical guide rails 1, two second cylindrical guide rails 1 and the inboard welded fastening of second slip table base 3, RGB-D camera 4 is a three-dimensional camera that has degree of depth and color measurement function, and RGB-D camera 4 places and uses the bolt fastening at the top of second slider 2.
Referring to fig. 8, the automatic detection method for the automobile tire defect can be divided into the following two steps:
the first step is as follows: the automatic detection method for the automobile tire defect comprises the following steps of automatically collecting point clouds of tire treads:
fixedly connecting the RGB-D camera 4 with a sliding block 2 of the cross sliding table through a bolt, and enabling the RGB-D camera 4 to observe and detect the tire; the tire rolls to the RGB-D camera 4 in the forward driving process of the automobile, the motor 6 and the cross sliding table drive the RGB-D camera 4 to move left and right to the position right opposite to the tire surface of the tire to be detected according to the tire point cloud signals collected by the RGB-D camera 4, then the motor keeps a constant distance with the tire to be detected and moves back and forth, and then the three-dimensional point cloud of the characteristics of the tire to be detected in the forward and backward movement processes of the automobile is extracted.
The second step: automatic classification of three-dimensional point cloud of automobile tire characteristics:
first of all, a linear function of the tire point cloud input is established, i.e.
z=f(w T x+b)
Wherein x is an input vector of the tire point cloud, w is a weight vector parameter of the tire point cloud identification, and b is an offset;
classifying the common defects of aging cracks, eccentric wear, sharp object stabbing, bulges, patterns and pittings and the like on the surface of the automobile tire into K categories, wherein the posterior probability of each defect category is
Wherein G k And G j Is one of K tire defect categories;
for generative models of multi-classification problems of tire defects, the posterior probability of a tire point cloud classification is given by an activation function transformation, i.e.
Wherein i k =w k T Theta, theta being a certain tyre defect class G k The feature vector of (2);
then determining tire point cloud identification parameters w in the classification model by using a maximum likelihood method, wherein the likelihood function is
Wherein y is nk =y k (θ n ),t n For a certain tyre defect class G k Characteristic vector theta of k T is an N x K matrix of target variables, the element is T nk ;
Defining an error function by taking the negative logarithm of the likelihood function to obtain a cross entropy error function of the multi-classification problem of the tire point cloud, namely
Taking the gradient of the error function with respect to the tire point cloud identification parameter w, i.e.
The error function of the tire point cloud is updated by iteration through a method of descending sequential gradients, namely
Where H is a Hessian matrix whose elements consist of the second derivative of the tire point cloud error function J (w) with respect to w, i.e.
Finally obtaining a trained tire point cloud identification parameter w, and inputting a linear function z = f (w) by using the tire point cloud T x + b) classifying and predicting different defect conditions of the tire.
Claims (8)
1. An automatic detection system for automobile tire defects is characterized by comprising a cylindrical guide rail (1), a sliding block (2), a sliding table base (3), an RGB-D camera (4), a lead screw (5) and a motor (6);
a sliding table base (3) is placed in a foundation pit and fixed with a foundation by using foundation bolts, a threaded hole of a sliding block (2) is in threaded fit connection with a lead screw (5), the lead screw (5) penetrates through holes on two sides of the sliding table base (3) and is in clearance fit with the sliding table base (3), a bolt penetrates through a small circular through hole on one side of the sliding table base (3) and is in threaded fixed connection with a motor (6), an output shaft of the motor (6) is in threaded fixed connection with one end of the lead screw (5) through a coupler, through holes of the sliding block (2) are in sliding fit with two cylindrical guide rails (1) respectively, the two cylindrical guide rails (1) are welded and fixed with the inner side of the sliding table base (3), the top surface of the sliding block (2) is coplanar with the ground, the second sliding table base (3) is placed on the top surface of the sliding block (2) and is in threaded fixed connection with the sliding block (2), a threaded hole of the second sliding block (2) is in threaded fit connection with the second lead screw (5), the second lead screw (5) penetrates through holes on two sides of the second sliding table base (3) and is in clearance fit with the second sliding table base (3), the second lead screw hole of the second sliding table base (6), the second sliding block (6) is connected with the second motor through the second shaft coupler, the second sliding shaft of the second sliding block (6), the two second cylindrical guide rails (1) are fixedly welded with the inner sides of the second sliding table bases (3), and the RGB-D camera (4) is placed at the top of the second sliding block (2) and fixed through bolts.
2. The automatic detection system for defects of vehicle tyres as claimed in claim 1, wherein said cylindrical guide (1) is a smooth cylindrical part.
3. The automatic detection system for the defects of the automobile tires according to claim 1, characterized in that the slide block (2) is a cuboid part made of steel material, the top surface of the slide block (2) is provided with a threaded hole, and the side surface of the slide block (2) is provided with a threaded through hole and a round through hole.
4. The automatic automobile tire defect detection system according to claim 1, characterized in that the sliding table base (3) is a U-shaped part formed by welding steel plates, circular through holes are processed at two sides of the sliding table base (3), and small circular through holes are processed around the circular through holes at one side of the sliding table base (3).
5. The automatic vehicle tire defect detection system according to claim 1, wherein said RGB-D camera (4) is a three-dimensional camera with depth and color measurement functions.
6. The automatic detection system for the defects of the automobile tires according to claim 1, characterized in that the lead screw (5) is a slender cylinder part which is made of steel material, has cylindrical two ends and is provided with threads in the middle.
7. The automatic detection system for the defects of the automobile tires according to claim 1, characterized in that the motor (6) is a standard stepping motor or a servo motor with a threaded hole formed on one side of an output shaft.
8. The detection method of the automatic detection system for the defects of the automobile tires according to claims 1 to 7, characterized by comprising the following steps:
the first step is as follows: the automatic detection method for the automobile tire defect comprises the following steps of automatically collecting point clouds of tire treads:
fixedly connecting an RGB-D camera (4) with a sliding block (2) of the cross sliding table through bolts, and enabling the RGB-D camera (4) to observe and detect a tire; the tire rolls towards the RGB-D camera (4) in the forward driving process of the automobile, the motor (6) and the cross sliding table drive the RGB-D camera (4) to move left and right to the position right opposite to the tire surface of the tire to be detected according to a tire point cloud signal collected by the RGB-D camera (4), then the motor keeps a constant distance with the tire to be detected and moves back and forth, and then the three-dimensional point cloud of the characteristics of the tire to be detected in the forward and backward movement processes of the automobile is extracted;
the second step is that: automatic classification of three-dimensional point cloud of automobile tire characteristics:
first of all, a linear function of the tire point cloud input is established, i.e.
z=f(w T x+b)
Wherein x is an input vector of the tire point cloud, w is a weight vector parameter identified by the tire point cloud, and b is a bias;
classifying the common defects of aging cracks, eccentric wear, sharp object puncture, bulges, patterns, pittings, scratches, cuts, pits and the like on the surface of the automobile tire into K categories, wherein the posterior probability of each defect category is
Wherein G is k And G j Is one of K tire defect categories;
for generative models of tire defect multi-classification problems, the posterior probability of a tire point cloud classification is given by an activation function transformation, i.e.
Wherein i k =w k T Theta, theta being a certain tyre defect class G k The feature vector of (2);
then determining tire point cloud identification parameters w in the classification model by using a maximum likelihood method, wherein the likelihood function is
Wherein y is nk =y k (θ n ),t n For a certain tyre defect class G k Characteristic vector theta of k T is an N K matrix of target variables, the element is T nk ;
Defining an error function by taking the negative logarithm of the likelihood function to obtain a cross entropy error function of the multi-classification problem of the tire point cloud, namely
Taking the gradient of the error function with respect to the tire point cloud identification parameter w, i.e.
The error function of the tire point cloud is updated by iteration through a method of descending sequential gradients, namely
Where H is the Hessian matrix whose elements consist of the second derivative of the tire point cloud error function J (w) with respect to w, i.e.
Finally obtaining a trained tire point cloud identification parameter w, and inputting a linear function z = f (w) by using the tire point cloud T x + b) to classify and predict different defect conditions of the tire.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211331349.4A CN115684177A (en) | 2022-10-20 | 2022-10-20 | Automatic detection system and method for automobile tire defects |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211331349.4A CN115684177A (en) | 2022-10-20 | 2022-10-20 | Automatic detection system and method for automobile tire defects |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115684177A true CN115684177A (en) | 2023-02-03 |
Family
ID=85046370
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211331349.4A Pending CN115684177A (en) | 2022-10-20 | 2022-10-20 | Automatic detection system and method for automobile tire defects |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115684177A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105115976A (en) * | 2015-06-24 | 2015-12-02 | 上海图甲信息科技有限公司 | Detection system and method for wear defects of track |
CN106408011A (en) * | 2016-09-09 | 2017-02-15 | 厦门大学 | Laser scanning three-dimensional point cloud tree automatic classifying method based on deep learning |
CN106500620A (en) * | 2016-10-31 | 2017-03-15 | 吉林大学 | Automobile tire morphology detector based on active vision |
CN108007364A (en) * | 2018-01-22 | 2018-05-08 | 广东理工学院 | A kind of tile detection device and detection method based on RGB-D cameras |
CN110291376A (en) * | 2017-02-14 | 2019-09-27 | 塔克那自动化控制股份责任有限公司 | Equipment for defect at the end of production process on inspection and inspection tire |
CN111122598A (en) * | 2019-12-16 | 2020-05-08 | 北京冶自欧博科技发展有限公司 | Three-dimensional detection system and method for surface defects of steel rail |
CN113432897A (en) * | 2021-06-25 | 2021-09-24 | 中国铁建重工集团股份有限公司 | Detection system and detection method for tire wear of straddle type monorail train |
DE102021106429A1 (en) * | 2021-03-16 | 2022-09-22 | forty2 Technologies GmbH | Defect detection in additive manufacturing |
CN115184364A (en) * | 2022-07-06 | 2022-10-14 | 青岛科技大学 | Tire bubble defect detection method and system based on 3D point cloud |
-
2022
- 2022-10-20 CN CN202211331349.4A patent/CN115684177A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105115976A (en) * | 2015-06-24 | 2015-12-02 | 上海图甲信息科技有限公司 | Detection system and method for wear defects of track |
CN106408011A (en) * | 2016-09-09 | 2017-02-15 | 厦门大学 | Laser scanning three-dimensional point cloud tree automatic classifying method based on deep learning |
CN106500620A (en) * | 2016-10-31 | 2017-03-15 | 吉林大学 | Automobile tire morphology detector based on active vision |
CN110291376A (en) * | 2017-02-14 | 2019-09-27 | 塔克那自动化控制股份责任有限公司 | Equipment for defect at the end of production process on inspection and inspection tire |
CN108007364A (en) * | 2018-01-22 | 2018-05-08 | 广东理工学院 | A kind of tile detection device and detection method based on RGB-D cameras |
CN111122598A (en) * | 2019-12-16 | 2020-05-08 | 北京冶自欧博科技发展有限公司 | Three-dimensional detection system and method for surface defects of steel rail |
DE102021106429A1 (en) * | 2021-03-16 | 2022-09-22 | forty2 Technologies GmbH | Defect detection in additive manufacturing |
CN113432897A (en) * | 2021-06-25 | 2021-09-24 | 中国铁建重工集团股份有限公司 | Detection system and detection method for tire wear of straddle type monorail train |
CN115184364A (en) * | 2022-07-06 | 2022-10-14 | 青岛科技大学 | Tire bubble defect detection method and system based on 3D point cloud |
Non-Patent Citations (1)
Title |
---|
JULIA BERGMANN 等: "Tool failure recognition using inconsistent data", PROCEDIA CIRP, vol. 107, 26 May 2022 (2022-05-26) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103499585B (en) | Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision | |
AU2022349296A1 (en) | Road surface technical condition detection method and device based on three-dimensional contour | |
CN110779937A (en) | Casting product internal defect intelligent detection device | |
CN206139527U (en) | Panoramic vision potato is selected separately and defect detecting device | |
CN113378725B (en) | Multi-scale-channel attention network-based tool fault diagnosis method, equipment and storage medium | |
WO2013007479A1 (en) | Optical device and method for inspecting tires | |
CN1843822A (en) | Dynamic detection system of train wheel pair and detection method thereof | |
CN102496161A (en) | Method for extracting contour of image of printed circuit board (PCB) | |
CN206803950U (en) | A kind of tire tread on-line measuring device | |
CN114354639A (en) | Weld defect real-time detection method and system based on 3D point cloud | |
CN114714145B (en) | Graham angle field enhanced contrast learning monitoring method for cutter wear state | |
CN111445471A (en) | Product surface defect detection method and device based on deep learning and machine vision | |
CN112419289B (en) | Intelligent detection method for urban subway rail fastener defects | |
CN115684177A (en) | Automatic detection system and method for automobile tire defects | |
CN112394035B (en) | Intelligent automobile chassis detection method and device | |
CN117589480B (en) | Tire abnormal state detecting system | |
CN117152093B (en) | Tire defect detection system and method based on data fusion and deep learning | |
CN114426039B (en) | Point cloud data processing method based on urban rail train wheel tread | |
CN116593493A (en) | Device and method for detecting defects of inner surface of steel pipe at high speed | |
Yang et al. | Research on data analysis and Quality Control based on P control chart | |
CN112014046A (en) | Combine harvester assembling quality vibration monitoring test bed and test method | |
Yin et al. | Research on feature extraction of local binary pattern of SLM powder bed gray image | |
DE102015002663B4 (en) | Method and device for inexpensive cutting of profiles in vehicle tires | |
CN218895754U (en) | Full tire pattern degree of depth automated inspection equipment | |
CN115620041B (en) | Pavement disease sensing and service state evaluation method |
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 |