CN113780464B - Bogie fastener looseness prevention mark detection method - Google Patents
Bogie fastener looseness prevention mark detection method Download PDFInfo
- Publication number
- CN113780464B CN113780464B CN202111126078.4A CN202111126078A CN113780464B CN 113780464 B CN113780464 B CN 113780464B CN 202111126078 A CN202111126078 A CN 202111126078A CN 113780464 B CN113780464 B CN 113780464B
- Authority
- CN
- China
- Prior art keywords
- image
- bogie
- classifier
- loosening
- mark
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a track traffic bogie overhauling technology, in particular to a bogie fastener anti-loosening mark detection method. S1, standard model data of various fasteners in a bogie of a specified model and standard sample data of anti-loosening marks of all fasteners are obtained; s2, training a classifier with a three-layer cascade structure by using the standard sample data obtained in the S1, and packaging the trained classifier in an image data processing system; s3, acquiring anti-loosening identification images of all fasteners on the bogie to be inspected of the same type; s4, preprocessing the anti-loosening identification image obtained in the step S3; s5, inputting the step image preprocessing result into a classifier with a three-layer cascade structure for classification; and S6, comparing the classification result in the step S5 with the corresponding sample parameters, so as to judge whether the anti-loosening mark is qualified. The anti-loosening mark recognition rate is improved, the image data processing and analyzing speed is improved, the anti-loosening mark recognition device has learning capacity, and can be suitable for bogies of various types.
Description
Technical Field
The invention relates to a track traffic bogie overhauling technology, in particular to a bogie fastener anti-loosening mark detection method.
Background
At present, screw thread connection is adopted in most cases between all fixedly connected parts on a bogie of a railway train, and various forms such as bolts and nuts, air valves and pipe joints are adopted in the screw thread connection. The threaded connection has the advantage of convenient installation and disassembly.
However, it is difficult to avoid vibration during the running of the train, and as the train runs for a long time, a problem of loosening occurs at the threaded connection due to accumulation of vibration. Thereby causing the related equipment to fail to operate normally and seriously endangering the driving safety. Therefore, the checking of the screw connection (fastener) is an important link of train overhaul and maintenance, and the checking of the fastener anti-loosening mark is an important content of the clamping check operation after the bogie is assembled. In order to easily identify whether the threaded connection is loosened, anti-loosening marks are made on the threaded connection fastened on the bogie, so that whether the anti-loosening marks are aligned and complete can be checked to judge whether the threaded connection on the bogie is loosened.
During train maintenance, the check of the anti-loosening mark at the threaded connection position on the bogie comprises a plurality of methods such as manual visual inspection, automatic detection based on model matching, intelligent detection based on deep learning and the like. These three methods and their shortcomings are described one by one.
Manual visual inspection: the traditional method is checked by visual inspection by staff, taking a picture of the threaded connection on the train bogie and keeping the data. When overhauling, need the staff at the train bottom, whether confirm locking sign dislocation through the people's eye, judge whether locking sign aligns, guarantee follow-up inspection and maintenance work's development. Still another manual visual inspection method is to take a picture of a position with an anti-loosening mark on a bogie at the bottom of a car through various automatic devices, and then a worker checks the position with the abnormal anti-loosening mark by watching the picture. Hundreds of thousands of pictures are acquired by one train of motor cars, and the mode consumes extremely manpower and material resources. So that a team needs more than ten people to work uninterruptedly.
Automatic detection method based on model matching: the method is mainly used for detecting anti-loosening marks at the hexagon bolts by modeling and matching the same fastener, but if the bolts are just loosened and then rotated by an integral multiple of 60 degrees, misjudgment occurs in the method; the method can not finish the detection of the anti-loosening marks of the circular pipe clamp and the like.
Intelligent detection method based on deep learning: the intelligent detection method carries out sample training through a large amount of data, so that a high recognition rate can be obtained. The intelligent detection method based on deep learning needs hundreds of millions of data for training samples to improve the recognition rate; however, for non-popular data sets, this is a time consuming, labor consuming and extremely difficult task to achieve. Moreover, the intelligent detection method based on deep learning lacks robustness, and the detection structure can be influenced by environmental changes, illumination differences and the like.
Disclosure of Invention
The invention provides an intelligent bogie fastener anti-loosening mark detection method for solving the problems that detection of the bogie fastener anti-loosening mark is time-consuming, laborious, easy to influence the recognition rate by the environment and the like.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the method for detecting the anti-loosening mark of the bogie fastener is used for a composite robot with an autonomous positioning navigation function and used for image acquisition, and an image data processing system, and comprises the following steps:
S1, standard model data of various fasteners in a bogie of a specified model and standard sample data of anti-loosening marks of all fasteners are obtained;
s2, training a classifier with a three-layer cascade structure by using the standard sample data obtained in the S1, and packaging the trained classifier in an image data processing system;
s3, acquiring anti-loosening identification images of all fasteners on the bogie to be inspected of the same type;
s4, preprocessing the anti-loosening identification image obtained in the step S3 to obtain data used in the subsequent step;
S5, inputting the image preprocessing result in the step S4 into the classifier with the three-layer cascade structure for classification;
and S6, comparing the classification result in the step S5 with the corresponding sample parameters, so as to judge whether the anti-loosening mark is qualified.
Compared with the prior art, the method for detecting the anti-loosening mark of the fastener has the beneficial effects that:
(1) The recognition rate of the anti-loose mark is improved. The invention can carry out various classification and identification on the complex anti-loosening marked image data, greatly reduces the problems of non-identification, false identification and the like caused by the problems of illumination, angles, dirt coverage and the like, and has the overall correct identification rate of more than 99.2 percent.
(2) The speed of image data processing and analysis is improved. The speed is faster in training than convolutional neural networks, especially for large training sets, which have slightly higher recognition rates than neural networks. The number of required training samples is small, the operation is simpler and more convenient, the running speed of software is greatly improved, and the real-time detection effect can be achieved.
(3) The bogie has learning capability and can adapt to a plurality of bogies of different models. Compared with a model matching mode, the method is better in adaptability. The invention is not limited to a certain bogie, can train samples aiming at national standard bolts of different models, and can be suitable for any vehicle type; through continuous training of the classifier, the method can adapt to vehicle types with various specifications.
In order to obtain better technical effects, the invention can be further improved on the basis of the technical scheme.
Further, the step of acquiring standard sample data in step S1 is as follows:
s11: selecting a bogie which is newly delivered from a factory or subjected to card control inspection so as to ensure that all images in the acquired standard sample data are clear and complete, and fixedly placing the designated bogie on a bogie positioning platform with a lifting function;
S12: the composite robot is used for teaching and photographing the bogie anti-loosening mark, the image data processing system utilizes the fastener standard model data to carry out model matching on the photographed image data, the types and the models of the fasteners on the bogie are determined, and the position information of the fasteners is recorded; recording the traveling route, image acquisition points and position and posture information of the composite robot when acquiring images, and forming a teaching program corresponding to the designated bogie model;
s13: the image data processing system segments and identifies the shot image to obtain an image of the fastener looseness prevention mark.
Further, in step S3, S31: placing the bogie to be tested on the bogie positioning platform in the same mode and posture, and completing image acquisition in the same position and posture by the composite robot according to the teaching program of the bogie with the corresponding model; s32: the image data processing unit divides and identifies the acquired image to acquire the looseness prevention identification image to be detected.
Further, in step S3, after the composite robot reaches the taught image acquisition point, the composite robot performs secondary positioning, and adjusts the position and posture of image acquisition according to the secondary positioning result.
Further, in step S2, the three-layer cascade structure classifier includes 8 sub-classifiers in total; wherein the first layer classifier comprises an HSV classifier and a color component classifier; the second layer classifier comprises a brightness classifier and a contrast classifier; the third layer of classifiers includes a length classifier, a width classifier, an area classifier and a morphology classifier.
Further, the specific steps of the image preprocessing in step S4 are as follows:
S41: filtering the anti-loosening identification image data; performing white balance processing on the filtered image; then, performing distortion correction processing on the image subjected to the white balance processing, and storing the image subjected to the distortion correction processing;
s42: converting the image after distortion correction into an RGB color space image and storing the RGB color space image; decomposing the image of the RGB color space into a single-channel image to respectively obtain corresponding R, G and B values; and obtaining and storing corresponding HSV color space images by using the values of R, G and B.
Further, when detecting the bogies with various specifications, attaching specification marks at the designated positions of the bogies to be detected before detection, and acquiring model information of the bogies to be detected by the composite robot through collecting and identifying the specification marks; and selecting and executing a corresponding teaching program according to the bogie model information to complete the image acquisition operation.
Drawings
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
Fig. 2 is an image processing flow chart of an embodiment of the present invention.
FIG. 3 is a structural relationship and a flow chart of a cascade classifier in an embodiment of the invention.
Fig. 4 is a layout diagram of two-dimensional codes in a work area when the embodiment of the invention is used.
Detailed Description
The main inventive concept of the present invention is as follows: based on an industrial robot and a high-definition imaging technology, shooting images of locking marks of each fastener on a bogie in a proper pose; and then the shot (acquired) images are segmented, processed, classified and identified by utilizing an image processing technology. The method mainly comprises the steps of identifying a fastener looseness prevention mark through colors and classifying a cascade structure classifier based on a clustering algorithm; and comprehensively comparing the anti-loosening mark with the corresponding standard sample parameters, and judging whether the anti-loosening mark is qualified or not.
The composite robot applied by the invention mainly comprises an AGV, a base, a UR mechanical arm (6 shafts are connected in series), an image acquisition device (an industrial camera and an industrial lens), a controller, an industrial computer and the like.
The AGV is used as a traveling part of the composite robot and used for realizing autonomous movement and navigation of the composite robot. The base is fixedly arranged on the AGV, and the UR mechanical arm is fixed on the base. The image acquisition device is arranged at the tail end of the UR mechanical arm, and multi-angle photographing is realized by utilizing the flexibility of the UR mechanical arm so as to meet the photographing needs of anti-loosening marks of different fasteners. The base is in a box or frame structure, and the controller and the industrial personal computer are arranged in the base; the AGV and the UR mechanical arm are respectively and electrically connected with the controller and connected with signals; the controller and the image acquisition device are respectively and electrically connected with the industrial personal computer and connected with signals.
The image data processing system according to the present invention includes an image preprocessing module, an image analysis and recognition module, a data storage module, and the like.
The present invention will be described in detail below with reference to the accompanying drawings and examples.
The bogie fastener looseness prevention mark detection method comprises the following steps:
S1, standard model data of various fasteners in a bogie of a specified model and standard sample data of anti-loosening marks of all fasteners are obtained.
S2, training the classifier with the three-layer cascade structure by using the standard sample data acquired in the S1, and packaging the trained classifier in an image data processing system.
S3, obtaining anti-loosening identification images of the fasteners on the bogie to be inspected of the same type.
S4, preprocessing the anti-loosening identification image obtained in the step S3 to obtain data used in the subsequent step.
And S5, inputting the image preprocessing result in the step S4 into the classifier with the three-layer cascade structure for classification.
And S6, comparing the classification result in the step S5 with the corresponding sample parameters, so as to judge whether the anti-loosening mark is qualified.
The bogie anti-loosening identification checking operation is carried out by using the method practically, and the steps S1 and S2 are all preliminary preparation work. After the adjustment is finished in practice, the bogie anti-loosening identification card control checking operation can be completed according to the flow shown in figure 1.
When the detection method provided by the invention is used for identifying the anti-loosening mark, the following implementation modes can be selected preferentially.
As a preferred embodiment, the detailed procedure for obtaining the standard sample data in step S1 is as follows:
S11: and selecting a bogie which is newly delivered or subjected to card control inspection so as to ensure that all images in the acquired standard sample data are clear and complete, and fixedly placing the designated bogie on a bogie positioning platform with a lifting function.
The bogie with all fastener anti-loosening marks complete and nondestructive is selected for image acquisition so as to obtain high-quality standard sample data.
S12: the composite robot is used for teaching and photographing the bogie anti-loosening mark, the image data processing system utilizes the fastener standard model data to carry out model matching on the photographed image data, the types and the models of the fasteners on the bogie are determined, and the position information of the fasteners is recorded; and recording the traveling route, the image acquisition point and the position and posture information of the composite robot when acquiring images, and forming a teaching program corresponding to the specified bogie model.
S13: the image data processing system segments and identifies the shot image to obtain an image of the fastener looseness prevention mark. The image is segmented to obtain and keep a complete anti-loosening identification image, so that the data processing capacity of a later algorithm can be greatly reduced.
As a preferred embodiment, in step S3:
S31: and placing the bogie to be detected on the bogie positioning platform in the same mode and in the same gesture, and completing image acquisition in the same position and gesture by the composite robot according to the teaching program of the bogie with the corresponding model.
S32: the image data processing unit divides and identifies the acquired image to acquire the looseness prevention identification image to be detected.
In this process (S31), the compound robot performs an image acquisition operation according to the teaching program. In this embodiment, the compound robot navigation adopts a mode of scanning two-dimension codes. On the ground of the clamping control operation area, corresponding two-dimensional codes are laid around the fixed positions of the bogies according to the teaching positions, and the two-dimensional code layout situation of the embodiment is shown in fig. 4. In the actual implementation process, a plurality of two-dimensional codes are attached to the running route of the compound robot, and the more the number of the two-dimensional codes is in the running process, the smaller the running error of the compound robot is, so that the smaller the following working error is. When the invention is implemented, the composite robot can also adopt other navigation modes, such as magnetic stripe navigation, laser navigation or visual navigation, and the like, according to the field situation and the actual needs. As long as the positioning requirements and the applicable site conditions can be met, the AGV navigation mode (namely the navigation mode of the composite robot) can be used.
As a preferred embodiment, in step S3, after the composite robot reaches the taught image acquisition point, the composite robot performs secondary positioning, and adjusts the position and posture of image acquisition according to the secondary positioning result.
The purpose of carrying out secondary location is mainly in order to solve the deviation of bogie placement position and the condition such as missed detection or beat that locking sign position deviation caused.
The secondary positioning method is mainly used for calculating the deviation between the shooting pose of the locking mark of the fastener and the teaching pose through the pose of the fastener in the world coordinate system and the current position of the mechanical arm in the compound robot. Offset compensation is then completed by movement of the UR robotic arm in the compound robot, and then the fastener is again image captured (photographed).
As a preferred embodiment, in step S2, the three-layer cascade structure classifier includes 8 sub-classifiers in total; wherein the first layer classifier comprises an HSV classifier and a color component classifier; the second layer classifier comprises a brightness classifier and a contrast classifier; the third layer of classifiers includes a length classifier, a width classifier, an area classifier and a morphology classifier.
The color classifier is used for screening out an anti-loosening mark image, and the anti-loosening mark is marked by adopting red, and the red becomes magenta after being diluted after long-time use, so that the first layer of classifier performs color screening by setting a threshold value of related colors; in the second layer of classifier, the contrast classifier uses contrast to make the mark line more prominent, on the basis of which, the second discrimination is carried out by using tone, the brightness classifier screens the mark line according to the brightness of the image; and the third layer classifier is used for comprehensively classifying and screening the length, width, area and shape (shape and posture) of the comprehensive anti-loosening mark. The relative pixel distance between the marks is used for the segment mark lines to make a determination.
As a preferred embodiment, referring to fig. 2, the specific steps of the image preprocessing in step S4 are as follows:
S41: filtering the anti-loosening identification image data; performing white balance processing on the filtered image; and then carrying out distortion correction processing on the image subjected to the white balance processing, and storing the image subjected to the distortion correction processing.
Image preprocessing operation: the image data processing system carries out filtering processing on the original image of the anti-loosening mark to remove noise points in the image; white balance processing is carried out on the filtered image, so that deviation of the color of the image caused by illumination problem is reduced; and finally, performing distortion correction processing on the image subjected to the white balance processing, wherein the purpose of the distortion correction processing is to reduce distortion caused by the deviation of lens manufacturing precision and assembly process, thereby solving the problem of distortion of an original image caused by the distortion.
S42: converting the image after distortion correction into an RGB color space image and storing the RGB color space image; decomposing the image of the RGB color space into a single-channel image to respectively obtain corresponding R, G and B values; and obtaining and storing corresponding HSV color space images by using the values of R, G and B.
The decomposed looseness prevention identification image data is converted into HSV color space from RGB color space, three components of H (chroma), S (saturation) and V (brightness) are extracted, and the specific flow of the process is as follows:
Min := min([R, G, B])；
Max := max([R, G, B])；
V := Max；
S := (Max - Min) / Max；
If (R= =Max)
H = ((G-B)/(Max-Min)) #/3;
if (G= Max)
H = (2+ (B-R)/(Max-Min)) #/3;
if (B= Max)
H = (4+ (R-G)/(Max-Min)) × pi/3.
In the above process, H is [0;2 pi ], S is [0;1], and V is [0;1].
After the image preprocessing is completed, classifying algorithm identification is carried out on the looseness prevention identification image data of the RGB color space and the HSV color space by adopting a selection tree classifier algorithm, and the specific flow of the algorithm is shown in the figure 3.
When the bogie with various specifications is required to be detected, attaching specification marks at the specified positions of the bogies to be detected before detection, and acquiring and identifying the specification marks by the composite robot to obtain the model information of the bogies to be detected; and selecting and executing a corresponding teaching program according to the bogie model information to complete the image acquisition operation.
The following supplementary description is also provided to better understand the present invention.
① Through secondary positioning (UR mechanical arm photographing pose and photographing path planning), the anti-loosening mark can be effectively and accurately positioned, and the problem of low recognition rate when a mark line is recognized in a large area is solved; the image data to be collected and processed are greatly reduced, the image processing time is shortened, more accurate data is provided for classifying and identifying subsequent images, and the identification rate of the anti-loosening mark is further improved.
② The anti-loosening identification original image data acquired by the image acquisition device and the characteristic parameter data analyzed and identified by the image data processing system are stored in the corresponding storage modules of the image data processing system. And identifying and extracting various characteristic parameter data of the classified anti-loosening marks, wherein the characteristic parameters comprise the maximum width, the minimum width, the continuity, the skew and the positions in a world coordinate system of the anti-loosening marks.
③ Training principle of classifier and relation between classifiers: the sets of sample classes for each feature in each trainer sample are mutually exclusive, and the union of all sets is all sample classes. Based on such a rule, a set of corresponding classifiers is trained.
In training the classifier, for each feature classifier, the output result is determined according to the result obtained by comparing a certain feature value of the sample with the threshold value of the classifier.
Claims (3)
1. The method for detecting the anti-loosening mark of the bogie fastener is used for a composite robot with an autonomous positioning navigation function and used for image acquisition and an image data processing system, and is characterized by comprising the following steps of:
S1, standard model data of various fasteners in a bogie of a specified model and standard sample data of anti-loosening marks of all fasteners are obtained;
s11: selecting a bogie which is newly delivered from a factory or subjected to card control inspection so as to ensure that all images in the acquired standard sample data are clear and complete, and fixedly placing the designated bogie on a bogie positioning platform with a lifting function;
S12: the composite robot is used for teaching and photographing the bogie anti-loosening mark, the image data processing system utilizes the fastener standard model data to carry out model matching on the photographed image data, the types and the models of the fasteners on the bogie are determined, and the position information of the fasteners is recorded; recording the travel route, image acquisition points and position and posture information of the composite robot when acquiring images, and forming a teaching program corresponding to the bogie of the specified model;
s13: the image data processing system segments and identifies the shot image to obtain an image of the fastener anti-loosening mark;
s2, training a classifier with a three-layer cascade structure by using the standard sample data obtained in the S1, and packaging the trained classifier in an image data processing system;
In step S2, the three-layer cascade structure classifier includes 8 sub-classifiers in total; the first layer classifier comprises an HSV classifier and an RGB classifier; the second layer classifier comprises a brightness classifier and a contrast classifier; the third layer of classifier comprises a length classifier, a width classifier, an area classifier and a morphology classifier;
s3, acquiring anti-loosening identification images of all fasteners on the bogie to be inspected of the same type;
s4, preprocessing the anti-loosening identification image obtained in the step S3 to obtain data used in the subsequent step;
S5, inputting the image preprocessing result in the step S4 into the classifier with the three-layer cascade structure for classification;
and S6, comparing the classification result in the step S5 with the corresponding sample parameters, so as to judge whether the anti-loosening mark is qualified.
2. The bogie fastener loosening prevention mark detection method according to claim 1, wherein the specific steps of the image preprocessing in step S4 are as follows:
S41: filtering the anti-loosening identification image data; performing white balance processing on the filtered image; then, performing distortion correction processing on the image subjected to the white balance processing, and storing the image subjected to the distortion correction processing;
s42: converting the image after distortion correction into an RGB color space image and storing the RGB color space image; decomposing the image of the RGB color space into a single-channel image to respectively obtain corresponding R, G and B values; and obtaining and storing corresponding HSV color space images by using the values of R, G and B.
3. The bogie fastener loosening prevention identification detection method according to claim 1, wherein: when detecting the bogies with various specifications, attaching specification marks at the designated positions of the bogies to be detected before detection, and acquiring model information of the bogies to be detected by the composite robot through collecting and identifying the specification marks; and selecting and executing a corresponding teaching program according to the bogie model information to complete the image acquisition operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126078.4A CN113780464B (en) | 2021-09-26 | 2021-09-26 | Bogie fastener looseness prevention mark detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111126078.4A CN113780464B (en) | 2021-09-26 | 2021-09-26 | Bogie fastener looseness prevention mark detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113780464A CN113780464A (en) | 2021-12-10 |
| CN113780464B true CN113780464B (en) | 2024-10-15 |
Family
ID=78853348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111126078.4A Active CN113780464B (en) | 2021-09-26 | 2021-09-26 | Bogie fastener looseness prevention mark detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113780464B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114563411A (en) * | 2022-03-04 | 2022-05-31 | 成都盛锴科技有限公司 | Bogie assembly quality detection system |
| CN114563412A (en) * | 2022-03-04 | 2022-05-31 | 成都盛锴科技有限公司 | A kind of bogie assembly quality detection method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121996A (en) * | 2017-11-21 | 2018-06-05 | 武汉中元华电软件有限公司 | A kind of hard pressing plate state identification method of power screen cabinet based on machine vision |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102324038B (en) * | 2011-09-06 | 2014-04-16 | 北京林业大学 | Plant species identification method based on digital image |
| JP6475409B2 (en) * | 2013-12-20 | 2019-02-27 | 蛇の目ミシン工業株式会社 | Robot, robot control method, and robot control program |
| CN106372667B (en) * | 2016-08-31 | 2019-04-16 | 西南交通大学 | A kind of high iron catenary diagonal brace sleeve part screw defective mode detection method |
| CN106971182A (en) * | 2017-02-06 | 2017-07-21 | 王兴照 | Embedded electric power relay pressing plate is thrown and moves back state Intelligent Identify device and implementation method |
| CN107590498B (en) * | 2017-09-27 | 2020-09-01 | 哈尔滨工业大学 | Self-adaptive automobile instrument detection method based on character segmentation cascade two classifiers |
| CN107679508A (en) * | 2017-10-17 | 2018-02-09 | 广州汽车集团股份有限公司 | Road traffic sign detection recognition methods, apparatus and system |
| CN208746024U (en) * | 2018-06-05 | 2019-04-16 | 成都精工华耀科技有限公司 | A kind of train fastener loosening detection system based on manual identification's image |
| CN208206469U (en) * | 2018-06-05 | 2018-12-07 | 成都精工华耀科技有限公司 | A kind of fastener loosening detection device |
| CN109190456B (en) * | 2018-07-19 | 2020-11-20 | 中国人民解放军战略支援部队信息工程大学 | Multi-feature fusion overhead pedestrian detection method based on aggregated channel features and gray level co-occurrence matrix |
| CN111368852A (en) * | 2018-12-26 | 2020-07-03 | 沈阳新松机器人自动化股份有限公司 | Article identification and pre-sorting system and method based on deep learning and robot |
| CN110009602B (en) * | 2019-03-08 | 2020-08-11 | 唐山百川智能机器股份有限公司 | A method for detecting whether a fastener is loose |
| CN112857841A (en) * | 2021-01-06 | 2021-05-28 | 中车唐山机车车辆有限公司 | Visual detection system of bogie |
-
2021
- 2021-09-26 CN CN202111126078.4A patent/CN113780464B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108121996A (en) * | 2017-11-21 | 2018-06-05 | 武汉中元华电软件有限公司 | A kind of hard pressing plate state identification method of power screen cabinet based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113780464A (en) | 2021-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113379712B (en) | A computer vision-based method and system for detection of steel bridge bolt diseases | |
| KR20210157000A (en) | System and method for underbody inspection of vehicle | |
| CN107292870B (en) | Track plug fault detection method and system based on image alignment and detection network model | |
| CN117557570B (en) | A rail vehicle abnormality detection method and system | |
| CN113780464B (en) | Bogie fastener looseness prevention mark detection method | |
| CN114758322B (en) | Road quality detection system based on machine identification | |
| CN115953726B (en) | Machine vision container surface damage detection method and system | |
| CN113516629A (en) | TFDS passed the job intelligent detection system | |
| CN115147367B (en) | Anti-loosening line detection method based on machine vision | |
| CN108961276B (en) | Method and system for automatic collection of inspection data of distribution lines based on visual servoing | |
| CN117593528B (en) | Rail vehicle bolt loosening detection method based on machine vision | |
| CN111605578A (en) | A railway track inspection method using drones to carry 3D equipment | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN118411571B (en) | Bolt abnormality detection method for railway vehicle | |
| CN114511519A (en) | An image processing-based detection method for missing bolts at the bottom of trains | |
| CN121010879A (en) | A cloud-edge collaborative detection method, system, and inspection equipment for rail vehicles. | |
| CN120259290B (en) | A method and system for detecting loose bolts in rail vehicles | |
| CN118298387A (en) | Method and system for dynamically monitoring railway vehicle abnormality on line based on image detection | |
| CN119417830B (en) | A method for judging bolt looseness based on detecting the minimum bounding box | |
| CN119200664A (en) | A kind of autonomous inspection system and method of ski resort cableway based on drone | |
| CN105447496A (en) | Docking airplane model identification and verification method and system based on machine vision | |
| CN114863420B (en) | Defect detection method and device | |
| CN115810010B (en) | Train pantograph online detection method and system | |
| KR20240059088A (en) | Position determination apparatus and method of display manufacturing facility | |
| CN111583176B (en) | An image-based lightning protection simulation disk component fault detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |