CN109886298A - A kind of detection method for quality of welding line based on convolutional neural networks - Google Patents
A kind of detection method for quality of welding line based on convolutional neural networks Download PDFInfo
- Publication number
- CN109886298A CN109886298A CN201910041065.3A CN201910041065A CN109886298A CN 109886298 A CN109886298 A CN 109886298A CN 201910041065 A CN201910041065 A CN 201910041065A CN 109886298 A CN109886298 A CN 109886298A
- Authority
- CN
- China
- Prior art keywords
- layer
- image
- super
- neural networks
- convolutional neural
- 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.)
- Granted
Links
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of detection method for quality of welding line based on convolutional neural networks.One, Image Acquisition: acquisition welding point image, and record acquisition time mark function and weldment information record function；Two, weldqualities analysis: step 1, capture positioning is carried out to welded seam area using convolutional neural networks, it is positioned by rectangle frame and extracts weld inspection region, then the welded seam area image detected is pre-processed, and pre-processed results feeding step 2 tests and analyzes weldquality.Step 2, butt welding contact region carries out quality testing, judge whether weld seam to be detected is qualified, the pad region captured is amplified with cubic spline interpolation first, then amplified welding region is subjected to welding quality inspection by convolutional neural networks, detection model training is carried out after butt welding contact sample and the pretreatment of non-solder point sample data, carries out weldquality analysis detection using detection model.Step 3. carries out respective handling to testing result.
Description
Technical field
The invention belongs to field of machine vision, and specially Industrial Image Detecting identifies field, in particular to a kind of based on volume
The face of weld image detecting method of product neural network.Quality is carried out to weld seam by the detection identification to face of weld image
Detection.
Background technique
It is immature due to welding procedure on the production line of human weld, it frequently can lead to rosin joint, solder skip crosses weldering etc.
Phenomenon, more solder joint situations for more complicated workpiece, on the especially complicated face of weld, it is easier to lead to solder skip.Detection at present
Quality of welding spot is to be largely dependent upon the technology and experience of detection workman in this way by artificial detection, can generate mostly
Many unstable factors, and the workload of worker is increased, so that working efficiency is low.Traditional image detection identification
Method requires to correct by the image to each angle for more weld point images on complicated welding surface, then passes through figure
It is detected as the method for positioning and template matching, and stability is not highly susceptible to by force the interference of environment, and then leads to missing inspection
Or false retrieval；Or by the sliding window on image, and the feature in window is extracted, and combining classification device carries out
Classification and Detection, the sliding window on picture will lead to calculation amount increase, the parameter of the characteristics of image and classifier that manually extract
Adjust the detection accuracy of identification that then will affect weld point image.
Existing related patents, such as the patent of application number 201710818297.6, the quality of welding spot detection based on deep learning
Method, only target area is handled to treated.How to realize and detection zone is carried out by convolutional neural networks
Positioning is captured, and completes the quality testing to weld seam, there is presently no correlation technique appearances.
The invention proposes a kind of detection method for quality of welding line based on convolutional neural networks.To welded seam area to be detected
Capture positioning is carried out, and quality testing is carried out to the region.
Summary of the invention
The present invention is directed to the deficiency of existing welding quality inspection technology, proposes a kind of weld seam based on convolutional neural networks
The method of quality testing screening.By acquiring face of weld image, quality analysis is carried out to weld seam, screens matter based on the analysis results
Measure underproof weldment.
In order to achieve the above object, technical solution provided by the invention is a kind of face of weld based on convolutional neural networks
Quality determining method, including following steps: Image Acquisition, weldquality analysis, testing result processing.
One, Image Acquisition: being realized using high-resolution industry camera, has scanning, the typing function of welding point image
Can, it realizes pad Image Acquisition and is transferred to the function of quality analysis module, record acquisition time mark function and weldment
Information record function.
Two, weldqualities analysis: weldquality analysis the following steps are included:
Step 1, welded seam area positioning capturing is carried out to image to be detected: welded seam area is carried out using convolutional neural networks
Positioning is captured, is positioned by rectangle frame and extracts weld inspection region, then the welded seam area image detected is pre-processed,
And the quality testing analysis module that pre-processed results are sent into step 2 tests and analyzes weldquality.
Step 2, quality testing is carried out to the pad region captured, judges whether weld seam to be detected is qualified.To guarantee
The clarity of welded seam area amplifies the pad region captured with cubic spline interpolation.The weldering that will be previously detected
After connecing region amplification, welding quality inspection is carried out by convolutional neural networks to the region.To a large amount of pad samples and non-weldering
Detection model training is carried out after the pretreatment of contact sample data, and (training normal weld sample and abnormal weld seam sample are each in this example
12500 are used for quality testing model).Specifically:
Step 2.1, the training of convolutional neural networks.It, will be by pre- place under the tensorflow frame of Ubuntu system
12500 normal weld images of reason and 12500 abnormal weld image data are divided into training set, training set label, test set,
Test set label.Using back propagation learning algorithm and stochastic gradient descent method.According to the big of the loss value of propagated forward
Small, Lai Jinhang backpropagation iteration updates each layer of convolutional neural networks of weight.Until the loss value of model is intended to restrain
When, indicate that model training is completed.
Step 2.2, the feature extraction of weld image.Every piece image in data set is input to described in back
In convolutional neural networks, according to above-mentioned trained detection model, weld image feature under the model is extracted, model
Layer second from the bottom obtains the feature of the image using full process of convolution.
Step 2.3, the identification of weld image.A weld image to be sorted is given, trained depth is input to
It practises in model, obtains feature of the image under convolutional neural networks, and use classifier pair in the last layer of network model
Image carries out quality testing.
The processing of three, testing results: testing result processing module includes: data memory module, data disaply moudle, weldment report
Alert screening module, abnormal data memory module.
Beneficial effects of the present invention:
The beneficial effects of the present invention are convolutional neural networks to carry out welding quality analysis to weld image, avoids existing
Cumbersome detecting step in method, and positioning capturing can be carried out to welded seam area automatically.Furthermore display module of the invention
Quality testing can be monitored in real time and warning reminding.
Detailed description of the invention
Fig. 1 is the method for the present invention design flow diagram.
Fig. 2 is welded seam area positioning capturing neural network structure figure of the present invention.
Fig. 3 is that network structure is detected in target area to be selected.
Fig. 4 is welding quality inspection flow chart of the present invention.
Fig. 5 is welding quality inspection neural network structure figure of the present invention.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings.
Whole implementation process such as Fig. 1 of the invention, is acquired weld image, saves acquired image information, and
Weld seam area to be tested positioning capturing is carried out to the image of acquisition, quality testing is carried out to the detection zone captured.
Testing result is carried out the following processing:
1. more new image information adds quality measurements into image information entry.
2. saving the weld image information of abnormal results.
3. showing weld image quality measurements information.
4. pair abnormal weld image detected an analysis result carries out alert process.
5. analyzing result butt-welding fitting according to abnormal weld information to be screened.
Specific implementation:
One, Image Acquisition
Pad image capture module realized using existing high-resolution camera, have welding point image scanning,
Input function realizes pad Image Acquisition and is transferred to the function of quality analysis module, record acquisition time mark function with
And weldment information record function.
Image acquisition device completes the pad information acquired after acquisition to the transmission of quality analysis module, including pad
Image, image acquisition time and weldment labelled notation.
Weld point image point folding: such as the surface pores of pad, undercut, overlap, burn-through and face of weld crackle, weld seam ruler
Very little deviation etc..It, must be clean by the splash and dirt removal of surrounding near weld seam before Image Acquisition.
The analysis of two, weldqualities
Weldquality analysis the following steps are included:
Step 1, detection welded seam area positioning capturing is carried out to image to be detected:
Capture positioning is carried out to welded seam area using convolutional neural networks, is positioned by rectangle frame and extracts weld seam detection area
Then domain pre-processes the welded seam area image detected, and result is sent into quality testing analysis module to weld seam matter
Amount is tested and analyzed.
The step of design of convolutional neural networks shown in Fig. 2:
Convolutional layer: navigating to target area in order to detect, first using the convolutional layer+active coating+pond on one group of basis
Change the characteristic pattern that layer extracts image.This feature figure be shared for subsequent RPN (Region Proposal Networks) layer and
Full articulamentum.All convolutional layers are all: convolution kernel is having a size of 3, framing mask 1.All pond layers are all: convolution kernel ruler
Very little is 2, and convolution kernel moving step length is 2.
Fig. 3 show RPN (Region Proposal Networks) layer, and RPN network is for generating alternative target detection
Region.The layer judges that regional ensemble belongs to target prospect or background by softmax, and frame recurrenceization is recycled to correct area
Domain set obtains accurate alternative target region.
The generation of regional ensemble: being as unit of super-pixel, frame favored area is that super-pixel each of divides super picture
Plain region and super-pixel critical zone obtain regional ensemble by super-pixel region and super-pixel critical zone, can so subtract
Few calculation amount.
Rectangle frame adjustment criteria: it is diffused or shrinks according to the Critical Matrices of super-pixel.The size of rectangle frame to be selected is
Generate maximum rectangle frame shared by super-pixel or super-pixel group.
Frame sliding: the image traversal based on breadth First.According to traverse path, slider box selects frame, slides every time all
Guarantee that rectangle frame region is the maximum rectangular area of current super-pixel covering.
Frame is adjusted: based on adjacent super-pixel maximum comparability max (si) carry out super-pixel merging adjusting
Merge rule: calculating super-pixel similarity: si=d (xi, yi) wherein siSuper-pixel x is covered for rectangleiWith adjacent super
Pixel yiSimilarity, be adopted as rectangle covering super-pixel xiWith adjacent super-pixel yiEuclidean distance indicate.Merge critical super picture
The maximum super-pixel of similarity forms new super-pixel region in element.Rectangular shaped rim is the maximum square of new super-pixel region overlay
Shape region.
Frame quality evaluation IOU (Intersection-over-Union) value calculate: using marking area testing result with
Intersection between standard results label is the same as the value in the union between marking area testing result and standard results as IOU.
Target area judgement: calculate whether the region detected is target area using the characteristic pattern for detecting region, together
Shi Zaici adjusts frame region and obtains the final exact position of detection block.
Be illustrated in figure 4 to capture treat welded seam area carry out quality testing and judge weld seam whether He Ge process.
Input is weld image to be detected, obtains the spy of image by trained depth convolutional neural networks model extraction
Sign, classifies according to weldquality classification, last output category result.
For the clarity for guaranteeing welded seam area, the welded seam area captured is amplified with cubic spline interpolation, previously
After the doubtful welded seam area amplification detected, welding quality inspection is carried out by convolutional neural networks to the region.By to big
(the normal weld sample trained in the present embodiment is trained after amount normal weld sample and the pretreatment of improper weld seam sample data
This is used for quality testing model with each 12500, improper weld seam sample).
(1) the design module of convolutional neural networks
If Fig. 5 is the convolutional neural networks model that the present invention designs, by input layer, hidden layer, output layer is formed:
A. input layer
Input layer is the weld image that data weld seam captures localization region.
B. hidden layer
Convolutional layer: successively choosing convolution kernel is 3*3, and the convolutional layer of 1*1, each layer of port number be identical as input layer.
Activation primitive:Wherein x indicates characteristic pattern to be activated in each layer.
Pond layer: using the convolution kernel of 2*2, maximum Chi Huacao is carried out to the output after convolution operation after convolutional layer
Make.
C. output layer
The full convolutional layer connection of the last one of output layer and hidden layer, the dimension of output is two, and each dimension indicates normal
The probability of weld image and abnormal weld image.
Including 6 groups of convolutional layers, 1 group of full articulamentum；In preceding 4 groups of convolutional layers each group include convolution kernel be 3*3 convolutional layer,
Active coating and pond layer.Two groups are convolutional layer that convolution kernel is 1*1 afterwards.Last full articulamentum is that welding quality inspection result is defeated
Out.
(2) training of convolutional neural networks
Under the tensorflow frame of Ubuntu system, will by pretreated 12500 normal weld images and
The processing image data of 12500 abnormal weld seams is divided into training set, training set label, test set, test set label.Using reversed
Propagate learning algorithm and stochastic gradient descent method.According to the size of the loss value of propagated forward, Lai Jinhang backpropagation iteration
Update each layer of convolutional neural networks of weight.When the loss value of model is intended to convergence, indicate that model training is complete
At.
(3) feature extraction of weld image
Every piece image in data set is input in convolutional neural networks described in back, has been instructed according to above-mentioned
The detection model perfected extracts the feature of weld image under the model, is obtained by the full convolutional layer of layer second from the bottom.
(4) identification of weld image
A weld point image to be sorted is given, is input in the trained convolutional neural networks model of the present invention, obtains
Feature under the convolutional neural networks model of image, and quality testing is carried out to image in the last layer.
Three, result treatments
Data result processing includes: data storage, and data are shown, weldment alarm screening, abnormal data storage.
Data storage: it is used to store image capture module acquired image data by memory module and data are analyzed
The output data of module, each data include: weldquality analysis as a result, image acquisition time, weldment marker number.
Data are shown: the data by reading memory module, display weld seam detection result in image acquisition time axis
Trend.When there are unqualified solder joint data, display detection abnormal alarm.
Abnormal data storage: Abnormal welding point data are stored by abnormal data memory module, each data include: residual
Weldment number, image acquisition time, quality measurements where secondary weld seam.
The screening alarm of four, weldments
When quality measurements are lower than normality threshold, following steps are executed:
1. storing weldment information and testing result to abnormal data memory module
2. sending abnormal signal to alarm system, alarm is triggered, display module shows abnormal data and alarms.
3. according to the abnormal results information flag defect ware weldment detected.
4. being screened according to abnormal data defect ware weldment.
The series of detailed descriptions listed above only for feasible embodiment of the invention specifically
Protection scope bright, that they are not intended to limit the invention, it is all without departing from equivalent implementations made by technical spirit of the present invention
Or change should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of detection method for quality of welding line based on convolutional neural networks, which comprises the steps of:
Step 1 Image Acquisition: acquisition welding point image, and record acquisition time mark function and weldment information record function
Energy；
The analysis of step 2 weldquality: the following steps are included:
Step 1, welded seam area positioning capturing is carried out to image to be detected: welded seam area is captured using convolutional neural networks
Positioning is positioned by rectangle frame and extracts weld inspection region, then pre-processed to the welded seam area image detected, and will
The quality testing analysis module that pre-processed results are sent into step 2 tests and analyzes weldquality；
Step 2, quality testing is carried out to the pad region captured, judges whether weld seam to be detected is qualified；It is first guarantee
The clarity of welded seam area amplifies the pad region captured with cubic spline interpolation, the weldering that then will test
After connecing region amplification, welding quality inspection is carried out by convolutional neural networks to the region, to a large amount of pad samples and non-weldering
Detection model training is carried out after the pretreatment of contact sample data, carries out weldquality analysis detection using trained model；
Step 3 carries out respective handling to testing result.
2. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 1, which is characterized in that institute
It states in step 2, training normal weld sample and abnormal weld seam each 12500, sample are used for quality testing model.
3. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 2, which is characterized in that institute
The specific implementation for stating step 2 includes the following steps:
Step 2.1, pretreated 12500 normal weld images and 12500 training of convolutional neural networks model: will be passed through
Abnormal weld image data are divided into training set, training set label, test set, test set label, using back propagation learning algorithm,
It carries out backpropagation iteration according to the size of the loss value of propagated forward with stochastic gradient descent method and updates convolutional Neural net
The weight that each layer of network indicates that model training is completed when the loss value of model is intended to convergence；
Step 2.2, every piece image in data set the feature extraction of weld image: is input to convolution described in back
In neural network, according to above-mentioned trained convolutional neural networks detection model, weld image is extracted under the model
The layer second from the bottom of feature, model obtains the feature of the image using full process of convolution；
Step 2.3, the identification of weld image: a weld image to be detected is given, trained deep learning mould is input to
In type, feature of the image under convolutional neural networks is obtained, and use classifier to image in the last layer of network model
Carry out quality testing.
4. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 3, which is characterized in that institute
The training for stating convolutional neural networks model is realized under the tensorflow frame of Ubuntu system.
5. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 3, which is characterized in that step
In rapid 2.1, the design method of the convolutional neural networks model includes:
It designs convolutional layer: extracting the characteristic pattern of image, this feature figure using one group of basis convolutional layer+active coating+pond layer first
It is shared for subsequent RPN layers and full articulamentum；All convolutional layers are all: convolution kernel is having a size of 3, framing mask 1；It is all
Pond layer be all: for convolution kernel having a size of 2, convolution kernel moving step length is 2.
RPN layers: RPN layer of design is used to generate alternative target detection zone, which judges that regional ensemble belongs to mesh by softmax
Mark prospect or background recycle frame recurrenceization to carry out correcting region set and obtain accurate alternative target region；
Design section set: the generation of regional ensemble is as unit of super-pixel, and it is every that frame favored area is that super-pixel divides
A super-pixel region and super-pixel critical zone obtain regional ensemble by super-pixel region and super-pixel critical zone；
Design rectangle frame adjustment criteria: it is diffused or shrinks according to the Critical Matrices of super-pixel, the size of rectangle frame to be selected is
Generate maximum rectangle frame shared by super-pixel or super-pixel group；
Design frame sliding: the image traversal based on breadth First, according to traverse path, slider box selects frame, slides every time all
Guarantee that rectangle frame region is the maximum rectangular area of current super-pixel covering；
It designs frame to adjust: based on adjacent super-pixel maximum comparability max (si) carry out super-pixel merging adjusting；
Design merges rule: calculating super-pixel similarity: si=d (xi,yi) wherein siSuper-pixel x is covered for rectangleiWith adjacent super
Pixel yiSimilarity, be adopted as rectangle covering super-pixel xiWith adjacent super-pixel yiEuclidean distance indicate；Merge critical super picture
The maximum super-pixel of similarity forms new super-pixel region in element, and rectangular shaped rim is the maximum square of new super-pixel region overlay
Shape region；
Design frame quality evaluation IOU (Intersection-over-Union) value calculating method: using marking area detection knot
Intersection between fruit and standard results label in the union between marking area testing result and standard results as IOU's
Value；
Design object region decision method: calculate whether the region detected is target area using the characteristic pattern for detecting region
Domain, while adjustment frame region obtains the final exact position of detection block again.
6. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 5, which is characterized in that institute
The convolutional neural networks model of design includes input layer, hidden layer, output layer, in which:
Input layer: input layer is the weld image that data weld seam captures localization region；
Hidden layer: including convolutional layer and pond layer；Convolutional layer: convolution kernel is chosen successively as 3*3, the convolutional layer of 1*1, each layer leads to
Road number is identical as input layer；Activation primitive is set as:Wherein x indicates characteristic pattern to be activated in each layer；Pond
Change layer: using the convolution kernel of 2*2, maximum pondization operation being carried out to the output after convolution operation after convolutional layer；
Output layer: the full convolutional layer connection of the last one of output layer and hidden layer, the dimension of output is 2, and each dimension indicates just
The probability of normal weld image and abnormal weld image；Including 6 groups of convolutional layers, 1 group of full articulamentum；Each group in preceding 4 groups of convolutional layers
Convolutional layer, active coating and the pond layer for being 3*3 including convolution kernel, latter two groups are convolutional layer that convolution kernel is 1*1, last complete to connect
Layer is connect as the output of welding quality inspection result.
7. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 1, which is characterized in that institute
Step 3 is stated, the processing to testing result includes: more new image information, and/or adds quality measurements to image information item
In mesh, and/or the weld image information of abnormal results is saved, and/or display weld image quality measurements information, and/or
Alert process is carried out to the abnormal weld image analysis result detected, and/or result butt welding is analyzed according to abnormal weld information
Part carries out screening alarm.
8. a kind of detection method for quality of welding line based on convolutional neural networks according to claim 7, which is characterized in that institute
It states butt-welding fitting and screen alarming and refer to when testing result is lower than normality threshold, execute following:
1) stores weldment information and testing result to abnormal data memory module；
2) sends abnormal signal to alarm system, triggers alarm, display module shows abnormal data and alarms；
3) is according to the abnormal results information flag defect ware weldment detected；
4) is screened according to abnormal data defect ware weldment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910041065.3A CN109886298B (en) | 2019-01-16 | 2019-01-16 | Weld quality detection method based on convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910041065.3A CN109886298B (en) | 2019-01-16 | 2019-01-16 | Weld quality detection method based on convolutional neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109886298A true CN109886298A (en) | 2019-06-14 |
| CN109886298B CN109886298B (en) | 2023-06-16 |
Family
ID=66926043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910041065.3A Active CN109886298B (en) | 2019-01-16 | 2019-01-16 | Weld quality detection method based on convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109886298B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570400A (en) * | 2019-08-19 | 2019-12-13 | 河北极目楚天微电子科技有限公司 | Information processing method and device for chip 3D packaging detection |
| CN111037549A (en) * | 2019-11-29 | 2020-04-21 | 重庆顺泰铁塔制造有限公司 | Welding track processing method and system based on 3D scanning and TensorFlow algorithm |
| CN111421231A (en) * | 2020-04-07 | 2020-07-17 | 湖南汽车工程职业学院 | Omnibearing laser welding production line and welding method thereof |
| CN111882557A (en) * | 2020-09-28 | 2020-11-03 | 成都睿沿科技有限公司 | Welding defect detection method and device, electronic equipment and storage medium |
| CN112171057A (en) * | 2020-09-10 | 2021-01-05 | 五邑大学 | Quality detection method and device based on laser welding and storage medium |
| CN112183957A (en) * | 2020-09-10 | 2021-01-05 | 五邑大学 | Welding quality detection method and device and storage medium |
| CN112285114A (en) * | 2020-09-29 | 2021-01-29 | 华南理工大学 | Enameled wire spot welding quality detection system and method based on machine vision |
| CN113256620A (en) * | 2021-06-25 | 2021-08-13 | 南京思飞捷软件科技有限公司 | Vehicle body welding quality information judging method based on difference convolution neural network |
| CN113325068A (en) * | 2021-04-29 | 2021-08-31 | 河南工业大学 | Weld joint welding quality detection method and system based on fuzzy control |
| CN113421304A (en) * | 2021-06-21 | 2021-09-21 | 沈阳派得林科技有限责任公司 | Intelligent positioning method for industrial radiographic negative image weld bead area |
| CN113432644A (en) * | 2021-06-16 | 2021-09-24 | 苏州艾美睿智能系统有限公司 | Unmanned carrier abnormity detection system and detection method |
| CN113478483A (en) * | 2021-07-02 | 2021-10-08 | 普瑞特机械制造股份有限公司 | Mobile robot welding method and system based on stainless steel storage tank |
| CN113658132A (en) * | 2021-08-16 | 2021-11-16 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| EP3915712A1 (en) * | 2020-04-08 | 2021-12-01 | Robert Bosch GmbH | Method of optimizing welding parameters for welding control, method for providing a trained algorithm for machine learning and welding control |
| CN113808065A (en) * | 2020-05-28 | 2021-12-17 | 青岛海尔工业智能研究院有限公司 | Weld joint detection method and device, industrial robot and storage medium |
| CN116038112A (en) * | 2022-12-06 | 2023-05-02 | 西南石油大学 | Laser tracking large-scale curved plate fillet welding system and method |
| CN117047274A (en) * | 2023-09-05 | 2023-11-14 | 浙江人驰汽车配件有限公司 | Internal bracing type double-welding tensioning wheel and intelligent processing method thereof |
| DE102023201384A1 (en) | 2023-02-17 | 2024-08-22 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method and system for qualifying a welded joint between at least two components |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
| CN109001211A (en) * | 2018-06-08 | 2018-12-14 | 苏州赛克安信息技术有限公司 | Welds seam for long distance pipeline detection system and method based on convolutional neural networks |
| CN109142547A (en) * | 2018-08-08 | 2019-01-04 | 广东省智能制造研究所 | A kind of online lossless detection method of acoustics based on convolutional neural networks |
-
2019
- 2019-01-16 CN CN201910041065.3A patent/CN109886298B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105891215A (en) * | 2016-03-31 | 2016-08-24 | 浙江工业大学 | Welding visual detection method and device based on convolutional neural network |
| CN109001211A (en) * | 2018-06-08 | 2018-12-14 | 苏州赛克安信息技术有限公司 | Welds seam for long distance pipeline detection system and method based on convolutional neural networks |
| CN109142547A (en) * | 2018-08-08 | 2019-01-04 | 广东省智能制造研究所 | A kind of online lossless detection method of acoustics based on convolutional neural networks |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570400A (en) * | 2019-08-19 | 2019-12-13 | 河北极目楚天微电子科技有限公司 | Information processing method and device for chip 3D packaging detection |
| CN110570400B (en) * | 2019-08-19 | 2022-11-11 | 河北极目楚天微电子科技有限公司 | Information processing method and device for chip 3D packaging detection |
| CN111037549A (en) * | 2019-11-29 | 2020-04-21 | 重庆顺泰铁塔制造有限公司 | Welding track processing method and system based on 3D scanning and TensorFlow algorithm |
| CN111421231A (en) * | 2020-04-07 | 2020-07-17 | 湖南汽车工程职业学院 | Omnibearing laser welding production line and welding method thereof |
| EP3915712A1 (en) * | 2020-04-08 | 2021-12-01 | Robert Bosch GmbH | Method of optimizing welding parameters for welding control, method for providing a trained algorithm for machine learning and welding control |
| CN113808065A (en) * | 2020-05-28 | 2021-12-17 | 青岛海尔工业智能研究院有限公司 | Weld joint detection method and device, industrial robot and storage medium |
| CN112183957A (en) * | 2020-09-10 | 2021-01-05 | 五邑大学 | Welding quality detection method and device and storage medium |
| CN112171057A (en) * | 2020-09-10 | 2021-01-05 | 五邑大学 | Quality detection method and device based on laser welding and storage medium |
| CN112171057B (en) * | 2020-09-10 | 2022-04-08 | 五邑大学 | Quality detection method and device based on laser welding and storage medium |
| CN111882557A (en) * | 2020-09-28 | 2020-11-03 | 成都睿沿科技有限公司 | Welding defect detection method and device, electronic equipment and storage medium |
| CN111882557B (en) * | 2020-09-28 | 2021-01-05 | 成都睿沿科技有限公司 | Welding defect detection method and device, electronic equipment and storage medium |
| CN112285114A (en) * | 2020-09-29 | 2021-01-29 | 华南理工大学 | Enameled wire spot welding quality detection system and method based on machine vision |
| CN113325068B (en) * | 2021-04-29 | 2024-02-02 | 河南工业大学 | Weld quality detection method and detection system based on fuzzy control |
| CN113325068A (en) * | 2021-04-29 | 2021-08-31 | 河南工业大学 | Weld joint welding quality detection method and system based on fuzzy control |
| CN113432644A (en) * | 2021-06-16 | 2021-09-24 | 苏州艾美睿智能系统有限公司 | Unmanned carrier abnormity detection system and detection method |
| CN113421304A (en) * | 2021-06-21 | 2021-09-21 | 沈阳派得林科技有限责任公司 | Intelligent positioning method for industrial radiographic negative image weld bead area |
| CN113421304B (en) * | 2021-06-21 | 2024-05-28 | 沈阳派得林科技有限责任公司 | Intelligent positioning method for welding bead area of industrial ray film image |
| CN113256620A (en) * | 2021-06-25 | 2021-08-13 | 南京思飞捷软件科技有限公司 | Vehicle body welding quality information judging method based on difference convolution neural network |
| CN113478483A (en) * | 2021-07-02 | 2021-10-08 | 普瑞特机械制造股份有限公司 | Mobile robot welding method and system based on stainless steel storage tank |
| CN113658132A (en) * | 2021-08-16 | 2021-11-16 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| CN113658132B (en) * | 2021-08-16 | 2022-08-19 | 沭阳九鼎钢铁有限公司 | Computer vision-based structural part weld joint detection method |
| CN116038112A (en) * | 2022-12-06 | 2023-05-02 | 西南石油大学 | Laser tracking large-scale curved plate fillet welding system and method |
| DE102023201384A1 (en) | 2023-02-17 | 2024-08-22 | Robert Bosch Gesellschaft mit beschränkter Haftung | Method and system for qualifying a welded joint between at least two components |
| CN117047274A (en) * | 2023-09-05 | 2023-11-14 | 浙江人驰汽车配件有限公司 | Internal bracing type double-welding tensioning wheel and intelligent processing method thereof |
| CN117047274B (en) * | 2023-09-05 | 2024-03-19 | 浙江人驰汽车配件有限公司 | Internal bracing type double-welding tensioning wheel and intelligent processing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109886298B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109886298A (en) | A kind of detection method for quality of welding line based on convolutional neural networks | |
| CN113362326B (en) | Method and device for detecting defects of welding spots of battery | |
| CN110570410B (en) | Detection method for automatically identifying and detecting weld defects | |
| CN111080622B (en) | Neural network training method, workpiece surface defect classification and detection method and device | |
| CN106952250A (en) | A kind of metal plate and belt detection method of surface flaw and device based on Faster R CNN networks | |
| CN106934800A (en) | A kind of metal plate and belt detection method of surface flaw and device based on YOLO9000 networks | |
| CN111815572B (en) | Method for detecting welding quality of lithium battery based on convolutional neural network | |
| CN102441737B (en) | Apparatus and method for determining shape of end of welding bead | |
| CN108109137A (en) | The Machine Vision Inspecting System and method of vehicle part | |
| CN108520274A (en) | High reflecting surface defect inspection method based on image procossing and neural network classification | |
| WO2021251064A1 (en) | Information processing device, determination method, and information processing program | |
| CN109859177A (en) | Industrial x-ray image assessment method and device based on deep learning | |
| CN104268505A (en) | Automatic cloth defect point detection and recognition device and method based on machine vision | |
| CN111815555A (en) | Metal additive manufacturing image detection method and device combining anti-neural network with local binary | |
| CN109308489A (en) | Method for detecting welding quality of element arc welding | |
| CN104636760A (en) | Positioning method for welding seam | |
| KR102230886B1 (en) | Projection welding defect detection system based on image recognition | |
| CN111591715A (en) | Belt longitudinal tearing detection method and device | |
| CN116188459B (en) | Line laser rapid identification method and system for belt tearing detection | |
| CN109507205A (en) | A kind of vision detection system and its detection method | |
| CN108414531A (en) | A kind of fexible film defect detecting device and its detection method based on machine vision | |
| CN109557104A (en) | A kind of timber based on deep learning preferably saws intelligent detecting method | |
| CN115601359A (en) | Welding seam detection method and device | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN115035092A (en) | Image-based bottle detection method, device, equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230518 Address after: Room 12, 3rd Floor, Building 3, No. 2 Xingsheng West Road, Jinniu High tech Industrial Park, Chengdu City, Sichuan Province, 610037 Applicant after: Chengdu Rongsheng Technology Co.,Ltd. Address before: Room 1002-1003, Building A, Zhiyun Industrial Park, No. 13 Huaxing Road, Henglang Community, Dalang Street, Longhua District, Shenzhen City, Guangdong Province, 518109 Applicant before: Shenzhen Wanzhida Technology Co.,Ltd. Effective date of registration: 20230518 Address after: Room 1002-1003, Building A, Zhiyun Industrial Park, No. 13 Huaxing Road, Henglang Community, Dalang Street, Longhua District, Shenzhen City, Guangdong Province, 518109 Applicant after: Shenzhen Wanzhida Technology Co.,Ltd. Address before: Zhenjiang City, Jiangsu Province, 212013 Jingkou District Road No. 301 Applicant before: JIANGSU University |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |