CN116008301A - Method for detecting welding quality of vehicle body plate - Google Patents
Method for detecting welding quality of vehicle body plate Download PDFInfo
- Publication number
- CN116008301A CN116008301A CN202211412158.0A CN202211412158A CN116008301A CN 116008301 A CN116008301 A CN 116008301A CN 202211412158 A CN202211412158 A CN 202211412158A CN 116008301 A CN116008301 A CN 116008301A
- Authority
- CN
- China
- Prior art keywords
- welding
- data
- vehicle body
- quality
- body plate
- 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
- 238000003466 welding Methods 0.000 title claims abstract description 232
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 62
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 210000004209 hair Anatomy 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
A method based on welding quality detection of a vehicle body plate comprises the steps of installing corresponding sensor equipment on a welding robot, performing multiple times of welding, shooting pictures at welding points through a camera during welding, and detecting current and voltage of the welding points during welding through a current detection device and a voltage detection device; taking welding action data of a welding machine, current, voltage and resistance of a welding spot, and welding lines, gaps and radians of a welding part obtained based on the pictures as input, and taking mass fraction of a welding result as output to form a plurality of first sample data; performing main analysis processing on the plurality of first sample data, taking the data corresponding to the screened input characteristic types as input, and taking the quality fraction of a new welding result formed by final weights as output to form a plurality of second sample data; and performing model training by taking the second sample data as training data to obtain a vehicle body plate welding quality detection model for subsequent vehicle body plate welding quality detection.
Description
Technical Field
The invention relates to the field of welding quality detection, in particular to a method for detecting welding quality based on a vehicle body plate, which is used for detecting the welding quality after the welding of the vehicle body plate in an automobile manufacturing process is finished.
Background
In the process of the automobile manufacturing industry, the standard process flow comprises a stamping workshop, a welding workshop, a coating workshop and a general assembly workshop, and an automobile can be produced by the automobile manufacturing from a steel plate through the processes of the four core workshops, and is successfully taken off line after passing a series of quality detection and qualification. However, in this process, the quality of the weld of the vehicle body is a critical factor for the quality of the manufacture of the vehicle body and the reliability of the vehicle body. The main indexes of the welding quality are the accuracy, the area and the thickness of the welded body plate, the welding strength and the like of the welded body plate, and determine whether the body of the automobile reaches the national standard strength and hardness. The vehicle is used for grasping factors related to welding size and strength of the sheet metal parts, grasping rules of the sheet metal parts and performing optimization control, and is a core for improving the welding quality of the vehicle body. The vehicle body welding quality detection means and system are an important index when the vehicle body is produced and welded, and as the quality factors of the vehicle body welding are numerous, complex and changeable, the welding size, the welding precision and the welding angle are changed, the influence factors comprise the positioning point selection of the vehicle body and parts, the design of a size chain, the design of a clamp, the tolerance distribution, the maintenance of the clamp and the tool, the monitoring of the sizes of the parts and the assembly and other large factors can influence the welding quality; from the perspective of the welding strength of the vehicle body, the influencing factors comprise welding time, current, voltage, pressure and other factors; from the perspective of fatigue reliability of welded structures, influencing factors include material properties, part structure, weld spot distribution, material thickness, and the like. Therefore, it is necessary to provide a reliable method and system for detecting welding quality based on a vehicle body plate, so as to improve the welding quality of the vehicle body, promote the quality improvement of the whole vehicle, improve the manufacturing efficiency, reduce the manufacturing cost and shorten the development and verification period.
Disclosure of Invention
The invention provides a method for detecting welding quality based on a vehicle body plate, which aims to solve the technical problems and comprises the following steps:
s1, installing corresponding sensor equipment on a welding robot for welding a vehicle body plate, wherein the welding robot comprises a camera, a current detection device and a voltage detection device;
s2, performing multiple welding, wherein a picture at a welding point is shot through a camera during welding, and the current and the voltage of the welding point during welding are detected through a current detection device and a voltage detection device;
s3, taking welding action data of a welding machine, current, voltage and resistance of a welding spot, and welding lines, gaps and radians of a welding position obtained based on the pictures as input, and taking mass fraction of a welding result as output to form a plurality of first sample data; wherein, the mass fraction is obtained according to the following method: presetting standard data of various types of data in the input, setting a preset tolerance zone on the basis, determining the scores of the various types of data according to the degree of deviation from the tolerance zone, and weighting all the scores based on preset weights to obtain a final quality score;
s4, performing main analysis processing on the plurality of first sample data, adopting the first sample data as test data to perform testing, continuously adjusting the tolerance zone and the weight according to the accuracy of quality detection, finally selecting an input characteristic type with larger weight from the input as a data type with higher relevance with welding quality, taking data corresponding to the screened input characteristic type as input, and taking the quality fraction of a new welding result formed by the final weight as output to form a plurality of second sample data;
and S5, performing model training by taking the second sample data as training data to obtain a vehicle body plate welding quality detection model for subsequent vehicle body plate welding quality detection.
Further, in the method for detecting welding quality of vehicle body plates, each sensor device is electrically connected and controlled by the corresponding welding robot to perform data acquisition control, each welding robot is connected to the server cluster through the switch device, the pictures acquired in the step S2 and the current and the voltage are accessed to the server cluster after data cleaning operation is performed through the edge computing box, and the server cluster performs subsequent steps of processing.
Further, in the method based on the welding quality detection of the vehicle body plate, the data cleaning operation comprises the steps of rejecting invalid or missing data and classifying the data.
Furthermore, in the method based on the welding quality detection of the vehicle body plate, different vehicle body plate welding quality detection models are respectively established aiming at different vehicle types and different welding spots.
Further, in the method based on the welding quality detection of the vehicle body plate, the training of the model comprises training by adopting any one of the following models: BP neural network, random forest.
Further, in the method for detecting welding quality of a vehicle body panel according to the present invention, the welding motion data includes: the welding point welding coordinate position, welding time, welding angle, used clamp and welding material.
Further, in the method based on the welding quality detection of the vehicle body plate, after the quality of each welding spot of the vehicle body plate is detected by adopting the welding quality detection model of the vehicle body plate, the quality of each welding spot of the current whole vehicle body is comprehensively converged, comprehensive analysis is carried out, and finally the welding whole quality condition of the current whole vehicle body is obtained.
Further, in the method for detecting the welding quality of the vehicle body plate according to the present invention, the current detection device measures the current value of the welding point through the current CT coil, and the voltage detection device measures the voltage through a voltage detection line electrically connected to the voltage detection chip as an input, and sends the measured data to the edge side box for data collection by using Ethernet communication.
Furthermore, in the method for detecting the welding quality of the vehicle body plate, the camera is provided with the visual detection system software, the hardware of the camera is arranged on the arm of each welding robot, the visual detection system of the camera is highly integrated with the welding robots, a communication mechanism of the two parties is established, photographing instructions related to photographing hairs can be received by the welding robot controller, the photographing instructions comprise photographing at what angle, photographing times, welding process videos and the like, and the camera can respond to the instructions according to different instructions and output the responding results to a folder specified in advance for classified storage.
The method for detecting the welding quality of the vehicle body plate has the following technical effects: the invention can detect the welding quality of a vehicle body, takes the welding action data of a welding machine, the current, the voltage and the resistance of a welding spot, and the welding lines, the gaps and the radian of a welding part obtained based on the pictures as input, takes the mass fraction of a welding result as output, determines the data type with higher relevance of the welding quality through principal component analysis, determines whether the influence factors influencing the welding quality are more comprehensive, can effectively provide the recognition speed, simultaneously finds out the weight and the tolerance zone related to the physical characteristics of the welding spot through a large amount of test data, realizes the self-optimization of the quality judgment of the welding spot of a system and tries to find out more key physical characteristics of the welding spot, continuously self-learns the model, continuously self-revises the accurate range tolerance of each characteristic, and can effectively improve the accuracy of the welding quality detection.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a system architecture diagram of an embodiment of a method for detecting weld quality of a body panel in accordance with the present invention;
FIG. 2 is a signal diagram of an embodiment of a method for detecting weld quality based on a body panel according to the present invention;
FIG. 3 is a weld spot diagram of the CRV model in Honda of Dongfeng.
Detailed Description
For a clearer understanding of technical features, objects and effects of the present invention, a detailed description of embodiments of the present invention will be made with reference to the accompanying drawings.
The method for detecting the welding quality of the vehicle body plate comprises the following steps:
s1, installing corresponding sensor equipment on a welding robot for welding a vehicle body plate, wherein the welding robot comprises a camera, a current detection device and a voltage detection device.
The current detection device is used for measuring the current value of the welding point through a current CT coil, the voltage detection device is used for measuring the voltage through a voltage detection wire which is electrically connected with a voltage detection chip as input, the camera is preferably a high-definition AI camera, and the sensors can be arranged on a welding arm of the welding robot.
S2, performing multiple welding, shooting pictures at welding points through a camera during welding, and detecting current and voltage of the welding points during welding through a current detection device and a voltage detection device.
Referring to fig. 1 and fig. 2, in this embodiment, each sensor device is electrically connected to and controlled by a corresponding welding robot to perform data acquisition control, each welding robot is connected to a server cluster through a switch device, and the image acquired in step S2 and the current and the voltage can be subjected to data cleaning operation through an edge computing box, and then are connected to the server cluster by Ethernet communication, and the server cluster performs the processing of the subsequent steps. The invalid or missing data is subjected to optimization treatment through the edge computing box, the invalid or missing data can be removed, the data can be further classified, the accuracy and the integrity of the data are guaranteed through the cleaned data, and meanwhile the data pressure of the server cluster is relieved.
The camera is provided with visual detection system software simultaneously, the hardware of the camera is arranged on the arm of each welding robot, the visual detection system of the camera is highly integrated with the welding robots, a communication mechanism of both sides is established, photographing instructions related to photographing hairs by a welding robot controller can be received, the photographing instructions comprise photographing at what angle, photographing times, welding process videos and the like, the camera can respond to the instructions according to different instructions, and the responding results are output to a folder specified in advance for classified storage.
The ratio of the voltage to the resistance is calculated to obtain the resistance value.
S3, taking welding action data of a welding machine, current, voltage and resistance of a welding spot, and welding lines, gaps and radians of a welding position obtained based on the pictures as input, and taking mass fraction of a welding result as output to form a plurality of first sample data; wherein, the mass fraction is obtained according to the following method: and presetting standard data of various types of data in the input, setting a preset tolerance zone on the basis of the standard data, determining the scores of the various types of data according to the degree of deviation from the tolerance zone, and weighting all the scores based on preset weights to obtain the final quality score.
The welding action data includes: the welding point welding coordinate position, welding time, welding angle, used clamp and welding material.
Different vehicle body plate welding quality detection models are respectively established aiming at different vehicle types and different welding spots.
Taking the automobile model produced by three manufacturers in Toyo Honda as an example, the automobile models produced by the third factory at present are CRV, XRV and URV automobiles, and a plurality of automobiles with different models can be derived according to different configurations of the automobiles, so that a set of model library is required to be constructed as standard data for all the automobile models produced by the Toyo Honda, and the model library mainly comprises a welding spot picture model library produced by a camera, a welding spot current voltage resistance model library accessed by a sensor and a welding action database. Simultaneously calculating tolerance range values meeting the standard, wherein each measuring point is provided with a qualified standard database; it is also necessary to collect samples with various problems, such as bubbles, impurities, cracks and the like in the welding, which cause the disqualification of welding spots, and construct a disqualification standard database for each measuring point.
S4, performing main analysis processing on the plurality of first sample data, adopting the first sample data as test data to perform testing, continuously adjusting the tolerance zone and the weight according to the accuracy of quality detection, finally selecting an input characteristic type with larger weight from the input as a data type with higher relevance with welding quality, taking data corresponding to the screened input characteristic type as input, and taking the quality fraction of a new welding result formed by the final weight as output to form a plurality of second sample data;
as shown in fig. 3, the current CRV has 38 measurement points, each measurement point has a welding point picture model library, a large number of picture libraries are collected through offline qualified welding samples, including a qualified product sample library with a non-passing angle according to model collection and a welding unqualified product library with different defects classified, and for the purpose of continuously improving the accuracy of the picture model, the picture sample library is continuously perfected, enriched and improved in mass pictures collected in the later stage, the model is revised, self-learning and self-revision are performed, and the picture detection model is more and more accurate.
And S5, performing model training by taking the second sample data as training data to obtain a vehicle body plate welding quality detection model for subsequent vehicle body plate welding quality detection. After the quality of each welding spot of the vehicle body plate is detected by adopting a vehicle body plate welding quality detection model, the quality of each welding spot of the current whole vehicle body is comprehensively converged, comprehensive analysis is carried out, and finally the welding whole quality condition of the current whole vehicle body is obtained. Model training includes training using any of the following models: the BP neural network and the random forest can also adopt other common models or modified versions thereof.
When the detection model is used for quality detection, a set of virtual simulation system can be constructed, field vehicle type data, welding action data of a welding machine, current, voltage and resistance of welding spots, pictures of the welded welding spots and welding quality result data are all mapped in the virtual simulation system, each action of the field robot is made, the welding coordinate position of each welding spot, the X axis, the Y axis, the Z axis, the welding angle, the welding time, the pause time and welding materials are synchronously mapped in the simulation system, meanwhile, a camera shoots welding pictures of the welding spots in real time, the welding effect of the welding spots and the lines of the welding spot surfaces are mapped in the model according to actual picture data by a certain picture processing technical means. Through the virtual simulation system, the welding quality detection system can be continuously learned, revised and improved, meanwhile, when the data volume of the model reaches a certain amount, the model of the welding quality can be rapidly detected through a specific algorithm model, and the quality of welding spots can be predicted in advance according to indexes such as the current welding process, angle and time, whether the quality of the welding spots is qualified or not and whether the quality detection standard is met or not can be predicted in advance. The method can predict the result in advance, so that the welding quality is possibly unqualified when a certain welding process is improper, and the welding process is reversely revised on the premise that a model can be prefabricated in advance and the later welding process is revised to remedy the previous misoperation, the error conditions such as welding are not standardized, and the like, so that the welding quality of each welding spot can be finally detected out quickly, and meanwhile, the welding result of the welding spot can be predicted, and the welding process is reversely revised, so that the welding spot quality accords with the ultrahigh quality level.
The method for detecting the welding quality of the vehicle body plate has the following technical effects: the invention can detect the welding quality of the vehicle body, takes the welding action data of a welding machine, the current, the voltage and the resistance of a welding spot, and the welding lines, the gaps and the radian of a welding part obtained based on the pictures as input, takes the mass fraction of a welding result as output, determines the data type with higher relevance of the welding quality through principal component analysis, can effectively provide the recognition speed while determining the influence factors influencing the welding quality more comprehensively, and simultaneously finds out the weight and the tolerance zone related to the physical characteristics of the welding spot through a large amount of test data, realizes the self-optimization of the quality judgment of the welding spot of a system and tries to find out more key physical characteristics of the welding spot, continuously self-learns the model, continuously revises the accurate range tolerance of each characteristic, and can effectively improve the accuracy of the welding quality detection.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are to be protected by the present invention.
Claims (9)
1. The method for detecting the welding quality of the vehicle body plate is characterized by comprising the following steps of:
s1, installing corresponding sensor equipment on a welding robot for welding a vehicle body plate, wherein the welding robot comprises a camera, a current detection device and a voltage detection device;
s2, performing multiple welding, wherein a picture at a welding point is shot through a camera during welding, and the current and the voltage of the welding point during welding are detected through a current detection device and a voltage detection device;
s3, taking welding action data of a welding machine, current, voltage and resistance of a welding spot, and welding lines, gaps and radians of a welding position obtained based on the pictures as input, and taking mass fraction of a welding result as output to form a plurality of first sample data; wherein, the mass fraction is obtained according to the following method: presetting standard data of various types of data in the input, setting a preset tolerance zone on the basis, determining the scores of the various types of data according to the degree of deviation from the tolerance zone, and weighting all the scores based on preset weights to obtain a final quality score;
s4, performing main analysis processing on the plurality of first sample data, adopting the first sample data as test data to perform testing, continuously adjusting the tolerance zone and the weight according to the accuracy of quality detection, finally selecting an input characteristic type with larger weight from the input as a data type with higher relevance with welding quality, taking data corresponding to the screened input characteristic type as input, and taking the quality fraction of a new welding result formed by the final weight as output to form a plurality of second sample data;
and S5, performing model training by taking the second sample data as training data to obtain a vehicle body plate welding quality detection model for subsequent vehicle body plate welding quality detection.
2. The method for detecting the welding quality of the vehicle body plate according to claim 1, wherein each sensor device is electrically connected and controlled by the corresponding welding robot to perform data acquisition control, each welding robot is connected to a server cluster through a switch device, the pictures acquired in step S2 and the current and the voltage are accessed to the server cluster after data cleaning operation is performed through an edge computing box, and the server cluster performs the processing of the subsequent step.
3. The method of claim 2, wherein the data cleansing operation includes culling invalid or missing data and classifying the data.
4. The method for detecting the welding quality of the vehicle body plate according to claim 1, wherein different vehicle body plate welding quality detection models are respectively established for different vehicle types and different welding spots.
5. The method for vehicle body panel weld quality detection according to claim 1, wherein the model training comprises training using any one of the following models: BP neural network, random forest.
6. The method for vehicle body panel weld quality detection of claim 1, wherein the welding action data comprises: the welding point welding coordinate position, welding time, welding angle, used clamp and welding material.
7. The method for detecting the welding quality of the vehicle body plate according to claim 1, wherein after the quality of each welding spot of the vehicle body plate is detected by adopting a vehicle body plate welding quality detection model, the quality of each welding spot of the current whole vehicle body is comprehensively converged, comprehensive analysis is carried out, and finally the welding whole quality condition of the current whole vehicle body is obtained.
8. The method according to claim 1, wherein the current detecting means is a means for measuring a current value of a welding point by a current CT coil, and the voltage detecting means is a means for measuring a voltage by a voltage detecting wire electrically connected to a voltage detecting chip as an input, and transmitting the measured data to an edge side box for data collection by Ethernet communication.
9. The method for detecting the welding quality of the vehicle body plate according to claim 1, wherein the camera is provided with visual detection system software at the same time, the hardware of the camera is installed on the arm of each welding robot, the visual detection system of the camera is highly integrated with the welding robot, a communication mechanism of both sides is established, photographing instructions related to photographing hairs by a welding robot controller can be accepted, including photographing at what angle, photographing times, welding process videos and the like, the camera can respond to the instructions according to different instructions, and meanwhile, the responding results are output to a file folder specified in advance for classification and storage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211412158.0A CN116008301A (en) | 2022-11-11 | 2022-11-11 | Method for detecting welding quality of vehicle body plate |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211412158.0A CN116008301A (en) | 2022-11-11 | 2022-11-11 | Method for detecting welding quality of vehicle body plate |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116008301A true CN116008301A (en) | 2023-04-25 |
Family
ID=86022238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211412158.0A Pending CN116008301A (en) | 2022-11-11 | 2022-11-11 | Method for detecting welding quality of vehicle body plate |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116008301A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882063A (en) * | 2023-07-24 | 2023-10-13 | 深圳市南方众悦科技有限公司 | Self-adaptive selection analysis method and system for automobile parts |
-
2022
- 2022-11-11 CN CN202211412158.0A patent/CN116008301A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116882063A (en) * | 2023-07-24 | 2023-10-13 | 深圳市南方众悦科技有限公司 | Self-adaptive selection analysis method and system for automobile parts |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111929309B (en) | Cast part appearance defect detection method and system based on machine vision | |
| CN107657603B (en) | Industrial appearance detection method based on intelligent vision | |
| US10803573B2 (en) | Method for automated detection of defects in cast wheel products | |
| CN104457841B (en) | Resistance spot welding quality on-line monitoring method | |
| Liu et al. | Digital twin and data-driven quality prediction of complex die-casting manufacturing | |
| CN111069819A (en) | Welding quality prediction system and method based on artificial intelligence | |
| CN111815572A (en) | Method for detecting welding quality of lithium battery based on convolutional neural network | |
| US20230142578A1 (en) | System and method for detecting welding based on edge computing | |
| CN116008301A (en) | Method for detecting welding quality of vehicle body plate | |
| US11682112B2 (en) | Inspection device and machine learning method | |
| CN116618878A (en) | Pre-welding process parameter determination method, welding quality online prediction method, device and storage medium | |
| CN112557445B (en) | Defect online detection method, device and system based on additive manufacturing | |
| Lee et al. | Development of real-time diagnosis framework for angular misalignment of robot spot-welding system based on machine learning | |
| CN116881530B (en) | Device surface defect detection system based on deep learning | |
| CN107335908A (en) | The automation random device found for feature and its use in repetitive process | |
| CN116698642A (en) | Work station control method and system for production of automobile repair tool | |
| US11521120B2 (en) | Inspection apparatus and machine learning method | |
| CN117436769A (en) | Structural part welding quality monitoring method, system, storage medium and equipment | |
| CN110320802B (en) | Complex system signal time sequence identification method based on data visualization | |
| CN114819768B (en) | Condenser lead-out wire welding control system | |
| CN114454179B (en) | Automatic correction system and method for joints of intelligent robot hand | |
| CN116296305A (en) | Method for diagnosing rear material blocking part of bending machine with online fault self-diagnosis function | |
| JP2000510947A (en) | Test system for real time / offline applications | |
| CN116222988A (en) | Laser cutting machine rack system fault diagnosis method integrating intelligent learning algorithm | |
| CN115200513A (en) | Coaxiality jumping detection, analysis and control system for rotating body clamp |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room C305, 3 / F, building C, taizihu cultural Digital Creative Industrial Park, 18 Shenlong Avenue, Wuhan Economic and Technological Development Zone, Hubei Province Applicant after: Datang Internet technology (Wuhan) Co.,Ltd. Applicant after: Guotou Fusion Technology Co.,Ltd. Address before: Room C305, 3 / F, building C, taizihu cultural Digital Creative Industrial Park, 18 Shenlong Avenue, Wuhan Economic and Technological Development Zone, Hubei Province Applicant before: Datang Internet technology (Wuhan) Co.,Ltd. Country or region before: China Applicant before: DATANG TELECOM CONVERGENCE COMMUNICATIONS CO.,LTD. |
|
| CB02 | Change of applicant information |