CN111069819A - Welding quality prediction system and method based on artificial intelligence - Google Patents
Welding quality prediction system and method based on artificial intelligence Download PDFInfo
- Publication number
- CN111069819A CN111069819A CN201911185892.6A CN201911185892A CN111069819A CN 111069819 A CN111069819 A CN 111069819A CN 201911185892 A CN201911185892 A CN 201911185892A CN 111069819 A CN111069819 A CN 111069819A
- Authority
- CN
- China
- Prior art keywords
- welding
- data
- module
- quality prediction
- actual measurement
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
- B23K37/02—Carriages for supporting the welding or cutting element
- B23K37/0252—Steering means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K37/00—Auxiliary devices or processes, not specially adapted to a procedure covered by only one of the preceding main groups
Landscapes
- Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a welding quality prediction system and a method based on artificial intelligence, wherein the system comprises a server end, an edge end and an equipment end, and the equipment end comprises a welding module and a data acquisition module; the edge end comprises an online judging module and a result comparing module. The welding quality prediction result is obtained by prejudging the welding data acquired in real time, the poor welding quality prediction result is compared with the actual measurement result of the welding spot, and if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot, the judgment model is updated according to the welding data and the actual measurement result of the welding spot and is issued to the online judgment module; the welding data is pre-judged in real time, the bad welding spots are pre-judged in time, strict control on the welding quality of the automobile body is achieved, the cost of manual detection is reduced, the judgment model of the online judgment module is updated, the automatic optimization learning can be continuously carried out, and the detection efficiency and the accuracy of the welding spot quality are improved. The invention can be widely applied to the field of welding quality control.
Description
Technical Field
The invention relates to the field of welding quality control, in particular to a welding quality prediction system and method based on artificial intelligence.
Background
Welding is a process link which has the highest influence on the overall quality of the vehicle body, and the quality of the welding quality plays a key role in the overall quality of the vehicle body. The conventional method for detecting the welding quality of the vehicle body generally adopts the methods of manual sampling detection after welding, nondestructive detection by ultrasonic welding spots, semi-destructive and full-destructive manual detection and the like, the traditional method for detecting the welding quality of the welding spots cannot detect the quality of the welding spots in real time, the input manual detection cost is high, the detection efficiency is low, and the improvement of the welding process and the welding quality is severely restricted.
Disclosure of Invention
To solve the above technical problems, the present invention aims to: a welding quality prediction system and method based on artificial intelligence are provided.
The technical scheme adopted by the invention on one hand is as follows:
a welding quality prediction system based on artificial intelligence comprises a server side, an edge side and an equipment side, wherein the equipment side comprises:
welding the module;
the data acquisition module is used for acquiring welding data of welding spots in the welding module in real time;
the edge end includes:
and the online judging module is used for judging the welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be bad to the result comparison module.
The result comparison module is used for comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and transmitting the welding data and the actual measurement result of the welding spot to the server side if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot;
and the server is used for updating the judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to the online judgment module.
Further, the online judging module is specifically configured to perform digital feature or data curve feature analysis and classification on the welding data by using the judging module to obtain a welding quality prediction result.
Further, the server side includes:
the data processing module is used for preprocessing the welding data and the actual measurement result and dividing the preprocessed welding data and the actual measurement data into test set data and training set data;
the pattern recognition/rule extraction module is used for extracting the features of the training set data to obtain the training set data features;
and the model establishing and verifying module is used for updating the judgment model according to the data characteristics of the training set and verifying the judgment model by using the data of the test set.
Further, still include the interactive interface module, the interactive interface module includes:
the welding spot quality overview interface is used for displaying the welding quality prediction results and statistical information of all welding spots;
the defect prediction pushing interface is used for summarizing and pushing welding quality prediction results to be poor welding spot information;
and the actual measurement result feedback interface is used for feeding back the actual measurement result of the pushed welding spot to the result comparison module.
Further, the welding module includes a welding robot, a welding gun, a welding electrode cap, and a vehicle body.
Further, the data acquisition module comprises a welder and a data transmission medium, wherein the welder is used for generating and recording welding data, and the data transmission medium is used for transmitting the welding data to the online judgment module.
And the alarm system is used for triggering the PLC program to alarm when the on-line judgment module continuously judges that the number of the bad welding spots reaches the threshold value.
The technical scheme adopted by the other aspect of the invention is as follows:
a welding quality prediction method based on artificial intelligence comprises the following steps:
collecting welding data of welding points in a welding module in real time;
judging a welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be bad to a result comparison module;
comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot, transmitting the welding data and the actual measurement result of the welding spot to a server;
and updating a judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to an online judgment module.
Further, the step of determining a welding quality prediction result of the welding spot in real time according to the welding data includes:
and carrying out digital characteristic or data curve characteristic analysis and classification on the welding data by using the judgment model to obtain a welding quality prediction result.
Further, the step of updating the determination model according to the welding data and the actual measurement result includes the steps of:
dividing the welding data and the actual measurement result into test set data and training set data;
carrying out feature extraction on the training set data to obtain training set data features;
and updating the judgment model according to the data characteristics of the training set, and verifying the judgment model by using the test set data.
The invention has the beneficial effects that: the invention relates to a welding quality prediction system and a method based on artificial intelligence, which prejudge welding data collected in real time to obtain a welding quality prediction result, compare a poor welding quality prediction result with an actual measurement result of a welding spot, if the comparison is inconsistent, update a judgment model according to the welding data and the actual measurement result of the welding spot and send the judgment model to an online judgment module; the welding data is pre-judged in real time, the bad welding spots are pre-judged in time, strict control on the welding quality of the automobile body is achieved, the cost of manual detection is reduced, the judgment model of the online judgment module is updated, the automatic optimization learning can be continuously carried out, and the detection efficiency and the accuracy of the welding spot quality are improved.
Drawings
FIG. 1 is a block diagram of an artificial intelligence based weld quality prediction system according to an embodiment of the present invention;
FIG. 2 is a schematic view of the welding module of FIG. 1 according to the present invention;
FIG. 3 is a schematic view of an overview interface of the quality of the solder joints of FIG. 1 according to the present invention;
FIG. 4 is a schematic view of a defect detection push interface of FIG. 1 according to the present invention;
FIG. 5 is a schematic view of a measurement result feedback interface of FIG. 1 according to the present invention;
FIG. 6 is a flowchart of the operation of an artificial intelligence based weld quality prediction system in accordance with an embodiment of the present invention;
fig. 7 is a flowchart of a welding quality detection method based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
The conception, the specific structure and the technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and the accompanying drawings to fully understand the objects, the schemes and the effects of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a welding quality prediction system based on artificial intelligence, including a server side, an edge side, and an equipment side, where the equipment side includes:
welding the module;
the data acquisition module is used for acquiring welding data of welding spots in the welding module in real time;
the edge end includes:
and the online judging module is used for judging the welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be bad to the result comparison module.
The result comparison module is used for comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and transmitting the welding data and the actual measurement result of the welding spot to the server side if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot;
and the server is used for updating the judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to the online judgment module.
Specifically, the data acquisition module acquires welding data of a welding point in real time when the welding module works, wherein the welding data comprises data such as welding current, welding voltage, welding time and welding heat.
The online judging module is stored with a judging model obtained by early training, and the judging model is obtained by repeatedly training through a convolutional neural network model by utilizing early training data and is stored in the online judging module. The online judging module is used for pre-judging the welding data by utilizing a judging model to obtain a welding quality prediction result of the welding spot, and the welding quality prediction result comprises one of qualified welding quality and unqualified welding quality. And the online judging module transmits the welding quality result which is judged to be bad in advance to the result comparing module.
The result comparison module is used for comparing the welding quality prediction result judged to be bad by the online judgment module with the actual measurement result of the welding spot, the actual measurement result refers to the actual measurement result confirmed by manually performing actual measurement on the welding spot, and the actual measurement result comprises the size of the welding spot and the type of the defective welding spot. The result comparison module compares the welding quality prediction result of the welding spot with the actual measurement result of the welding spot, and if the actual measurement result shows that the welding spot has defects and the type of the defective welding spot is determined, the on-line judgment module accurately judges; the inconsistency between the poor welding quality prediction result and the actual measurement result of the welding spot means that if the welding spot has no defect, the online judgment module is indicated to be inaccurate in prejudgment, the welding quality prediction result is the poor welding spot, the quality is actually qualified, and when the welding quality prediction result is inconsistent with the actual measurement result, the welding data and the actual measurement result of the welding spot are transmitted to the server side.
The online judgment module has misjudgment, which indicates that the judgment model for pre-judging the defective welding spot in the online judgment module is not accurate enough, so that the judgment model in the online judgment module needs to be updated. And the server side updates the judgment model according to the uploaded welding data and the actual measurement result of the welding spot, and issues the judgment model to the online judgment module to update the model in the online judgment module.
Further, as a preferred embodiment, the online determination module is specifically configured to perform digital feature or data curve feature analysis and classification on the welding data by using the determination model to obtain a welding quality prediction result.
Further as a preferred embodiment, the server includes:
the data processing module is used for preprocessing the welding data and the actual measurement result and dividing the preprocessed welding data and the actual measurement data into test set data and training set data;
and the model establishing and verifying module is used for updating the judgment model according to the data characteristics of the training set and verifying the judgment model by using the data of the test set.
Specifically, the server side updates the judgment model according to the welding data and the actual measurement result transmitted by the result comparison module, and sends the verified judgment model to the online judgment module for detecting and judging the quality of the subsequent welding spot.
The data processing module performs data preprocessing on data transmitted to the server, the data preprocessing includes data normalization and normalization operations on welding data and actual measurement results, and division of training set data and test set data on the welding data and the actual measurement results after preprocessing, the division of the training set and the test set can adopt a random extraction mode, and the welding data and the actual measurement results are divided into the training set data and the test set data according to a certain proportion, for example, the random extraction mode can be adopted, 80% of the welding data and the actual measurement results are used as the training set data, and 20% of the welding data and the prediction results are used as the test set data.
The pattern recognition/rule extraction module is used for extracting features of the training set data, wherein the feature extraction refers to feature extraction from features of the training set data or graphic features of a data curve through a convolutional neural network model and an Adaboost algorithm. The convolutional neural network model is distinguished through convolutional layer simulation characteristics, data dimensionality is reduced through a pooling layer, and classification results are output through a full-connection layer. The basic principle of the Adaboost algorithm can be expressed as: by adopting the iterative idea, each round of training can generate a weak learner, the generated weak learner can participate in the next round of training, N rounds of iterative training can generate N weak learners, and the N weak learners are reasonably combined together to form a strong learner.
And the model establishing and verifying module is used for updating the judgment model according to the training set data characteristics extracted by the pattern recognition/rule extraction module and verifying the judgment model. The verification judgment model is used for inputting test set data into the neural network for testing and counting the accuracy of a test result, and the accuracy can be preset according to actual conditions. If the accuracy meets the requirement, the judgment model is issued to an online judgment module for pre-judging the subsequent welding data; if the accuracy rate does not meet the requirement, returning to the pattern recognition/rule extraction module to perform feature extraction and updating on the test set data, and then updating the judgment model again in the model establishing and verifying module. When the server end receives the feedback data and needs to update the judgment model, a random gradient ascent algorithm is adopted, and the basic idea of the random gradient ascent algorithm is as follows: when the data volume in the data sample set is large, part of data in the data sample set is randomly selected to represent the whole data set, so that the data sample set is reduced, and the aims of reducing the calculated amount and reducing the algorithm time complexity are fulfilled. The random gradient algorithm can realize that the operation of updating the model is completed when new training set data comes, and the whole training data set in the previous stage does not need to be read again for batch processing, so the algorithm improves the operation efficiency.
Further as a preferred embodiment, the system further comprises an interactive interface module, wherein the interactive interface module comprises:
the welding spot quality overview interface is used for displaying the welding quality prediction results and statistical information of all welding spots;
the defect prediction pushing interface is used for summarizing and pushing welding quality prediction results to be poor welding spot information;
and the actual measurement result feedback interface is used for feeding back the actual measurement result of the pushed welding spot to the result comparison module.
Specifically, as shown in fig. 3, the welding quality overview interface is used for displaying the welding quality prediction results and statistical information of all welding spots of a specific welding robot at a specific station, the displayed information includes the welding quality qualification rate of each welding robot and the welding quality prediction results of each welding spot, transparent production is realized, and the welding quality prediction results of the welding spots are determined by the online determination module. As shown in fig. 4, the defect detection and pushing interface may summarize and push information of all welding spots determined by the online determination module to have defects, and provide suggested measures. After seeing the welding spot information of the defect detection pushing interface, the worker can go to a specific station to perform appearance quality judgment and size measurement on the pushed welding spot, as shown in fig. 5, if the welding spot has a defect, the defect type is selected, an actual measurement result is obtained through actual measurement confirmation, and the actual measurement result is transmitted to the result comparison module through the actual measurement result feedback interface.
Further as a preferred embodiment, as shown in fig. 2, the welding module includes a welding robot 1, a welding gun 2, a welding electrode cap 3, and a vehicle body 4.
Specifically, the welding robot drives a welding electrode cap installed on a welding gun during working, and a series of welding spots are formed during welding of a vehicle body.
Further as a preferred embodiment, the data acquisition module includes a welder and a data transmission medium for transmitting the welding data to the online determination module.
Specifically, the welding machine can generate and store welding data corresponding to the welding points when the welding robot welds the vehicle body, and the data transmission medium transmits the welding data to the online judgment module in real time.
Further as a preferred embodiment, the welding quality prediction device further comprises an alarm system, wherein the alarm system is used for triggering the PLC program to alarm when the online judgment module continuously judges that the number of the bad welding spots reaches the threshold value.
Specifically, the defect detection pushing interface continuously updates the information of the defective welding spots, if the number of the bad welding spots in the welding quality prediction result continuously detected and determined by the online determination module reaches a threshold value, the alarm system can trigger the PLC program to give an alarm, and remind a worker to timely arrive at the station to perform equipment point inspection maintenance on the quality of the welding spots, so that the problem of large product quality caused by a large number of defective welding spots is solved. The threshold value can be preset according to actual conditions.
In order to more fully understand the welding quality prediction system based on artificial intelligence, as shown in fig. 6, the invention further provides a work flow chart of the system, and the specific implementation steps are as follows:
s101, a welding robot receives a control program instruction on a welding production line and drives a welding electrode cap arranged on a welding gun to weld a vehicle body;
s102, generating and recording welding data such as welding current, welding voltage, welding time, welding heat and the like on a welding machine in the welding process;
s103, the data acquisition module transmits the welding data in the welding machine to the online judgment module in real time through a data transmission medium.
And S104, analyzing the welding data from the data acquisition module by the online judgment module through a judgment model obtained by early training to obtain a welding quality prediction result of the welding spot, and realizing real-time prejudgment and monitoring of the welding quality of the welding spot.
And S105, the interactive interface module displays the quality prediction results and the statistical information of the welding spots of the welding robots corresponding to the specific stations through a welding spot quality overview interface. And the defect detection pushing interface collects and pushes the information of the welding spots with poor welding quality prediction results judged by the online judging module, continuously updates data according to the continuous increase of the welding spots, and gives an alarm if the number of the welding spots with poor welding quality prediction results continuously predicted by the online judging module reaches a threshold value.
S106, the staff judges the actual appearance quality and measures the size of the poor welding spot according to the pushed welding quality prediction result, and whether the defect exists is confirmed. As shown in fig. 5, if the solder joint has a defect, the defect type is selected, and then the actual measurement result is fed back to the result comparison module through the actual measurement result feedback interface.
S107, the result comparison module compares the poor welding quality prediction result with the actual measurement result of the welding spot, and if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot, the result comparison module transmits the welding data and the actual measurement result of the welding spot to the server side.
And S108, updating and verifying the model by using the mode identification/rule extraction module and the model establishment and verification module according to the welding data and the actual measurement result transmitted to the server, and re-issuing the verified judgment model to the online judgment module.
Corresponding to fig. 1, referring to fig. 7, an embodiment of the present invention further provides an artificial intelligence based welding quality detection method, including the following steps:
s1, collecting welding data of welding points in the welding module in real time;
and S2, judging the welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be poor to the result comparison module.
S3, comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot, transmitting the welding data and the actual measurement result of the welding spot to a server;
and S4, updating the judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to the online judgment module.
Further preferably, the step of determining a welding quality prediction result of the welding spot in real time according to the welding data includes:
and carrying out digital characteristic or data curve characteristic analysis and classification on the welding data by using the judgment model to obtain a welding quality prediction result.
Further preferably, the step of updating the determination model based on the welding data and the actual measurement result includes the steps of:
dividing the welding data and the actual measurement result into test set data and training set data;
carrying out feature extraction on the training set data to obtain training set data features;
and updating the judgment model according to the data characteristics of the training set, and verifying the judgment model by using the test set data.
The contents in the above method embodiments are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above method embodiment, and the beneficial effects achieved by the present system embodiment are also the same as those achieved by the above method embodiment.
The step numbers in the above method embodiments are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.
The contents in the above method embodiments are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above method embodiment, and the beneficial effects achieved by the present system embodiment are also the same as those achieved by the above method embodiment.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
The step numbers in the above method embodiments are set for convenience of illustration only, the order between the steps is not limited at all, and the execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A welding quality prediction system based on artificial intelligence is characterized by comprising a server side, an edge side and an equipment side, wherein the equipment side comprises:
welding the module;
the data acquisition module is used for acquiring welding data of welding spots in the welding module in real time;
the edge end includes:
and the online judging module is used for judging the welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be bad to the result comparison module.
The result comparison module is used for comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and transmitting the welding data and the actual measurement result of the welding spot to the server side if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot;
and the server is used for updating the judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to the online judgment module.
2. The welding quality prediction system based on artificial intelligence of claim 1, wherein the online decision module is specifically configured to perform digital feature or data curve feature analysis and classification on the welding data by using a decision model to obtain a welding quality prediction result.
3. The artificial intelligence based weld quality prediction system of claim 1, wherein the server-side comprises:
the data processing module is used for preprocessing the welding data and the actual measurement result and dividing the preprocessed welding data and the actual measurement data into test set data and training set data;
the pattern recognition/rule extraction module is used for extracting the features of the training set data to obtain the training set data features;
and the model establishing and verifying module is used for updating the judgment model according to the data characteristics of the training set and verifying the judgment model by using the data of the test set.
4. The artificial intelligence based weld quality prediction system of claim 1, further comprising an interactive interface module comprising:
the welding spot quality overview interface is used for displaying the welding quality prediction results and statistical information of all welding spots;
the defect prediction pushing interface is used for summarizing and pushing welding quality prediction results to be poor welding spot information;
and the actual measurement result feedback interface is used for feeding back the actual measurement result of the pushed welding spot to the result comparison module.
5. The artificial intelligence based welding quality prediction system of claim 1, wherein the welding module comprises a welding robot, a welding gun, a welding electrode cap, and a vehicle body.
6. The artificial intelligence based welding quality prediction system of claim 1, wherein the data acquisition module comprises a welder for generating and recording welding data and a data transmission medium for transmitting the welding data to the online decision module.
7. The artificial intelligence based welding quality prediction system of claim 1, further comprising an alarm system, wherein the alarm system is configured to trigger a PLC program to alarm when the online determination module continuously determines that the number of bad welding spots reaches a threshold.
8. A welding quality prediction method based on artificial intelligence is characterized by comprising the following steps:
collecting welding data of welding points in a welding module in real time;
judging a welding quality prediction result of the welding spot in real time according to the welding data and transmitting the welding quality prediction result judged to be bad to a result comparison module;
comparing the poor welding quality prediction result with the actual measurement result of the welding spot, and if the poor welding quality prediction result is inconsistent with the actual measurement result of the welding spot, transmitting the welding data and the actual measurement result of the welding spot to a server;
and updating a judgment model according to the welding data and the actual measurement result transmitted by the result comparison module and sending the judgment model to an online judgment module.
9. The artificial intelligence based welding quality detection method as claimed in claim 8, wherein the step of determining the welding quality prediction result of the welding spot in real time according to the welding data comprises:
and carrying out digital characteristic or data curve characteristic analysis and classification on the welding data by using the judgment model to obtain a welding quality prediction result.
10. The method of claim 8, wherein the step of updating the decision model based on the welding data and the measured results comprises the steps of:
dividing the welding data and the actual measurement result into test set data and training set data;
carrying out feature extraction on the training set data to obtain training set data features;
and updating the judgment model according to the data characteristics of the training set, and verifying the judgment model by using the test set data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911185892.6A CN111069819A (en) | 2019-11-27 | 2019-11-27 | Welding quality prediction system and method based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911185892.6A CN111069819A (en) | 2019-11-27 | 2019-11-27 | Welding quality prediction system and method based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111069819A true CN111069819A (en) | 2020-04-28 |
Family
ID=70311925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911185892.6A Pending CN111069819A (en) | 2019-11-27 | 2019-11-27 | Welding quality prediction system and method based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111069819A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487708A (en) * | 2020-11-24 | 2021-03-12 | 山西三友和智慧信息技术股份有限公司 | Resistance spot welding quality prediction method based on ensemble learning |
CN112548504A (en) * | 2020-12-20 | 2021-03-26 | 上海倚胜机电设备有限公司 | Vehicle door welding process |
CN113084388A (en) * | 2021-03-29 | 2021-07-09 | 广州明珞装备股份有限公司 | Welding quality detection method, system, device and storage medium |
CN113172373A (en) * | 2021-04-25 | 2021-07-27 | 中铁十四局集团有限公司 | System for monitoring processes of internal cutting and welding of steel |
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 |
CN113487149A (en) * | 2021-06-24 | 2021-10-08 | 东风汽车集团股份有限公司 | Welding spot abnormity identification system and method based on Catboost K-fold cross verification |
CN113780900A (en) * | 2021-11-09 | 2021-12-10 | 深圳市裕展精密科技有限公司 | Welding detection system and method based on edge calculation |
CN114037277A (en) * | 2021-08-09 | 2022-02-11 | 承德石油高等专科学校 | Steel mill unmanned workshop monitoring method and system based on deep learning |
CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
CN117733439A (en) * | 2024-01-19 | 2024-03-22 | 西咸新区大熊星座智能科技有限公司 | Welding robot with weld joint forming quality real-time prediction function |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1766587A (en) * | 2005-10-13 | 2006-05-03 | 上海交通大学 | Real-time quality detection and alarm method for car body spot welding |
JP2014144468A (en) * | 2013-01-29 | 2014-08-14 | Toyota Motor East Japan Inc | Welding quality guaranteeing device and welding quality guaranteeing method |
CN104730109A (en) * | 2015-02-28 | 2015-06-24 | 重庆理工大学 | Test method for welding spot quality of resistance spot welding based on dynamic resistance curve |
JP2015134359A (en) * | 2014-01-16 | 2015-07-27 | トヨタ自動車株式会社 | Welding quality inspection method, and welding quality inspection device |
CN106077988A (en) * | 2015-04-28 | 2016-11-09 | 发那科株式会社 | Point quality diagnostic system |
CN108956653A (en) * | 2018-05-31 | 2018-12-07 | 广东正业科技股份有限公司 | A kind of quality of welding spot detection method, system, device and readable storage medium storing program for executing |
CN109447403A (en) * | 2018-09-20 | 2019-03-08 | 中国核工业二三建设有限公司 | A kind of welding defect analysis system and method based on big data |
CN109614486A (en) * | 2018-11-28 | 2019-04-12 | 宇捷东方(北京)科技有限公司 | A kind of service automatic Recommendation System and method based on natural language processing technique |
CN109940305A (en) * | 2019-03-19 | 2019-06-28 | 天津大学 | Laser Deep Penetration Welding intelligent monitor system and method based on plasma electric signal |
-
2019
- 2019-11-27 CN CN201911185892.6A patent/CN111069819A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1766587A (en) * | 2005-10-13 | 2006-05-03 | 上海交通大学 | Real-time quality detection and alarm method for car body spot welding |
JP2014144468A (en) * | 2013-01-29 | 2014-08-14 | Toyota Motor East Japan Inc | Welding quality guaranteeing device and welding quality guaranteeing method |
JP2015134359A (en) * | 2014-01-16 | 2015-07-27 | トヨタ自動車株式会社 | Welding quality inspection method, and welding quality inspection device |
CN104730109A (en) * | 2015-02-28 | 2015-06-24 | 重庆理工大学 | Test method for welding spot quality of resistance spot welding based on dynamic resistance curve |
CN106077988A (en) * | 2015-04-28 | 2016-11-09 | 发那科株式会社 | Point quality diagnostic system |
CN108956653A (en) * | 2018-05-31 | 2018-12-07 | 广东正业科技股份有限公司 | A kind of quality of welding spot detection method, system, device and readable storage medium storing program for executing |
CN109447403A (en) * | 2018-09-20 | 2019-03-08 | 中国核工业二三建设有限公司 | A kind of welding defect analysis system and method based on big data |
CN109614486A (en) * | 2018-11-28 | 2019-04-12 | 宇捷东方(北京)科技有限公司 | A kind of service automatic Recommendation System and method based on natural language processing technique |
CN109940305A (en) * | 2019-03-19 | 2019-06-28 | 天津大学 | Laser Deep Penetration Welding intelligent monitor system and method based on plasma electric signal |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112487708A (en) * | 2020-11-24 | 2021-03-12 | 山西三友和智慧信息技术股份有限公司 | Resistance spot welding quality prediction method based on ensemble learning |
CN112548504A (en) * | 2020-12-20 | 2021-03-26 | 上海倚胜机电设备有限公司 | Vehicle door welding process |
CN113084388A (en) * | 2021-03-29 | 2021-07-09 | 广州明珞装备股份有限公司 | Welding quality detection method, system, device and storage medium |
CN113084388B (en) * | 2021-03-29 | 2023-05-09 | 广州明珞装备股份有限公司 | Welding quality detection method, system, device and storage medium |
CN113172373B (en) * | 2021-04-25 | 2022-07-15 | 中铁十四局集团有限公司 | System for monitoring processes of internal cutting and welding of steel |
CN113172373A (en) * | 2021-04-25 | 2021-07-27 | 中铁十四局集团有限公司 | System for monitoring processes of internal cutting and welding of steel |
CN113487149A (en) * | 2021-06-24 | 2021-10-08 | 东风汽车集团股份有限公司 | Welding spot abnormity identification system and method based on Catboost K-fold cross verification |
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 |
CN114037277A (en) * | 2021-08-09 | 2022-02-11 | 承德石油高等专科学校 | Steel mill unmanned workshop monitoring method and system based on deep learning |
CN113780900A (en) * | 2021-11-09 | 2021-12-10 | 深圳市裕展精密科技有限公司 | Welding detection system and method based on edge calculation |
CN114444986B (en) * | 2022-04-11 | 2022-06-03 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
CN117733439A (en) * | 2024-01-19 | 2024-03-22 | 西咸新区大熊星座智能科技有限公司 | Welding robot with weld joint forming quality real-time prediction function |
CN117733439B (en) * | 2024-01-19 | 2024-05-28 | 西咸新区大熊星座智能科技有限公司 | Welding robot with weld joint forming quality real-time prediction function |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111069819A (en) | Welding quality prediction system and method based on artificial intelligence | |
CN111815572B (en) | Method for detecting welding quality of lithium battery based on convolutional neural network | |
CN113870260B (en) | Welding defect real-time detection method and system based on high-frequency time sequence data | |
US8925791B2 (en) | Binary classification of items of interest in a repeatable process | |
CN104457841B (en) | Resistance spot welding quality on-line monitoring method | |
CN113780900B (en) | Welding detection system and method based on edge calculation | |
CN112487708A (en) | Resistance spot welding quality prediction method based on ensemble learning | |
CN117309065B (en) | Unmanned aerial vehicle-based remote monitoring method and system for converter station | |
CN113516285A (en) | Product quality analysis and prediction method in production of automatic assembly detection production line | |
CN111754737A (en) | Online identification and evaluation device and method for installation acceptance of metering device | |
CN113553762A (en) | Neural network for analyzing welding spots based on welding curve and establishing method | |
CN112015149A (en) | Lightweight vehicle body connection quality auxiliary judgment method | |
CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
CN113469388B (en) | Maintenance system and method for rail transit vehicle | |
CN115391613A (en) | Production line 3D operation and maintenance method, operation and maintenance system, storage medium and equipment | |
CN114330491B (en) | Method for optimizing welding spot quality by analyzing and guiding resistance spot welding curve | |
CN113469991B (en) | Visual online detection method for laser welding spot of lithium battery tab | |
CN111062364A (en) | Deep learning-based assembly operation monitoring method and device | |
CN118275442A (en) | Quality detection system and method for printed circuit board | |
CN112686838B (en) | Rapid detection device and detection method for ship anchor chain flash welding system | |
CN118052793A (en) | Real-time monitoring system and method for plush toy production process | |
CN113487149B (en) | Welding spot abnormity identification system and method based on Catboost K-fold cross verification | |
CN116008301A (en) | Method for detecting welding quality of vehicle body plate | |
CN109447403A (en) | A kind of welding defect analysis system and method based on big data | |
CN113927217A (en) | Intelligent welding 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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 101 and 201, building C3, No. 11, Kaiyuan Avenue, Huangpu District, Guangzhou City, Guangdong Province Applicant after: Guangzhou mingluo Equipment Co.,Ltd. Address before: Room 101 and 201, building C3, No. 11, Kaiyuan Avenue, Huangpu District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU MINO AUTOMOTIVE EQUIPMENT Co.,Ltd. |