CN116297683A - Deep learning-based welding arc defect identification method and system - Google Patents
Deep learning-based welding arc defect identification method and system Download PDFInfo
- Publication number
- CN116297683A CN116297683A CN202310081264.3A CN202310081264A CN116297683A CN 116297683 A CN116297683 A CN 116297683A CN 202310081264 A CN202310081264 A CN 202310081264A CN 116297683 A CN116297683 A CN 116297683A
- Authority
- CN
- China
- Prior art keywords
- welding
- data
- voltage
- actual
- current
- 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 170
- 230000007547 defect Effects 0.000 title claims abstract description 101
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000013135 deep learning Methods 0.000 title claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 230000008569 process Effects 0.000 claims abstract description 28
- 239000000463 material Substances 0.000 claims abstract description 8
- 238000003062 neural network model Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 8
- WYTGDNHDOZPMIW-RCBQFDQVSA-N alstonine Natural products C1=CC2=C3C=CC=CC3=NC2=C2N1C[C@H]1[C@H](C)OC=C(C(=O)OC)[C@H]1C2 WYTGDNHDOZPMIW-RCBQFDQVSA-N 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 6
- 239000007789 gas Substances 0.000 description 5
- 230000003993 interaction Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
-
- 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
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Arc Welding Control (AREA)
Abstract
The invention relates to the technical field of welding, in particular to a welding arc defect identification method and system based on deep learning, wherein the method comprises the following steps: obtaining basic data of the welding equipment, wherein the basic data comprises: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current; creating a waveform file for recording actual voltage and actual current in a welding process by using the basic data; in the welding process of the welding equipment, acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file; converting the recorded waveform file into graph data; and inputting the graph data into a pre-trained welding defect detection model to obtain the type of the welding defect. The voltage and current data are less interfered by the outside in the acquisition process, the data acquisition is more convenient and accurate, detection equipment and detection procedures are not required to be added, the detection cost is reduced, and the detection efficiency is improved.
Description
Technical Field
The invention relates to the technical field of welding, in particular to a welding arc defect identification method and system based on deep learning.
Background
Currently, common welding quality detection methods include X-ray detection, ultrasonic detection, pressure detection and the like; the detection means are realized by purchasing corresponding detection equipment and adding corresponding detection procedures, so that the cost is increased for metal processing factories and the productivity is reduced;
with the wide application of artificial intelligence algorithms represented by deep learning, the currently known welding quality detection method further comprises welding audio frequency + big data analysis, welding seam photographing + artificial intelligence visual recognition and the like, however, due to complex processing field environment, field noise pollution, light pollution and the like have great influence on the acquisition of audio data and image data, thereby influencing the recognition accuracy.
Disclosure of Invention
Aiming at the problems, the embodiment of the invention provides a welding arc defect identification method and a system based on deep learning.
In one aspect of the present invention, a method for identifying welding arc defects based on deep learning is provided, including:
obtaining basic data of the welding equipment, wherein the basic data comprises: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current;
creating a waveform file for recording actual voltage and actual current in a welding process by using the basic data;
in the welding process of the welding equipment, acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file;
converting the recorded waveform file into graph data;
and inputting the graph data into a pre-trained welding defect detection model to obtain the type of the welding defect.
Optionally, the process of converting the recorded waveform file into graph data includes:
reading the actual voltage and the actual current recorded in the waveform file, and screening out the data that the current in the read actual voltage and the actual current is zero and the voltage is no-load voltage;
aiming at the screened data, constructing a two-dimensional array of behavior voltage and current;
the constructed bit array is converted into map data using the python map processing method.
Optionally, the training process of the welding defect detection model includes:
obtaining sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free, burn-through, arc breaking, arc drawing and weld serpentine;
converting the waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
comparing the estimated welding defect type with the corresponding welding defect type in the sample data, adjusting parameters in the initial neural network model and increasing the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to the step of converting the waveform file in the sample data into the graph data and inputting the graph data into the initial neural network model to obtain the estimated welding defect type, and taking the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
Optionally, the process of collecting the actual voltage and the actual current of the welding includes:
when the actual voltage and/or the actual current are detected to be greater than the predetermined threshold value by the transformer, recording of the actual voltage and the actual current is started.
In still another aspect of the present invention, there is further provided a welding arc defect recognition system based on deep learning, which is characterized by comprising:
the welding device comprises a data acquisition unit, a welding unit and a data processing unit, wherein the data acquisition unit is used for acquiring basic data of the welding device, and the basic data comprises: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current;
a file creation unit for creating a waveform file for recording an actual voltage and an actual current in a welding process using the basic data;
the data acquisition unit is used for acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file in the welding process of the welding equipment;
a data calculation unit for converting the recorded waveform file into graph data;
and the data transmission unit is used for inputting the graph data into the pre-trained welding defect detection model to obtain the welding defect type.
Optionally, the data calculation unit is specifically configured to:
reading the actual voltage and the actual current recorded in the waveform file, and screening out the data that the current in the read actual voltage and the actual current is zero and the voltage is no-load voltage;
aiming at the screened data, constructing a two-dimensional array of behavior voltage and current;
the constructed bit array is converted into map data using the python map processing method.
Optionally, a model training unit is also included for
Obtaining sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free, burn-through, arc breaking, arc drawing and weld serpentine;
converting the waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
comparing the estimated welding defect type with the corresponding welding defect type in the sample data, adjusting parameters in the initial neural network model and increasing the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to the step of converting the waveform file in the sample data into the graph data and inputting the graph data into the initial neural network model to obtain the estimated welding defect type, and taking the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
Optionally, the data acquisition unit is specifically configured to start recording the actual voltage and the actual current after detecting that the actual voltage and/or the actual current are greater than a predetermined threshold through the transformer.
Compared with the prior art, the invention has the beneficial effects that: the voltage and current data are less interfered by the outside in the acquisition process, the data acquisition is more convenient and accurate, detection equipment and detection procedures are not required to be added, the detection cost is reduced, and the detection efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate and together with the description serve to explain the invention. In the drawings:
fig. 1 is a schematic flow chart of a welding arc defect recognition method based on deep learning according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data conversion process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a model training process according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a welding arc defect recognition system based on deep learning according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of an identification system architecture according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a waveform data acquisition and calculation device according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the following embodiments and the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent. The exemplary embodiments of the present invention and the descriptions thereof are used herein to explain the present invention, but are not intended to limit the invention.
Referring to fig. 1, a welding arc defect identification method based on deep learning provided by an embodiment of the invention includes:
s100, acquiring basic data of welding equipment.
Wherein the base data comprises: the device type, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current.
S110, creating a waveform file for recording actual voltage and actual current in the welding process by using the basic data.
In implementation, the waveform file may be a file with an extension of csv, where the name of the waveform file is named by using basic data, and the naming format is: model-shielding gas-welding wire material-welding wire diameter-pulse presence-absence-preset current-preset voltage.
S120, collecting actual voltage and actual current of welding in the welding process of the welding equipment, and recording the actual voltage and the actual current in a waveform file.
In implementation, a mutual inductor is commonly used for collecting voltage and current in the current technical background; specifically, recording of the actual voltage and the actual current is started when the actual voltage and/or the actual current is detected to be greater than a predetermined threshold value by the transformer.
S130, converting the recorded waveform file into graph data.
In practice, when the duration of no-load voltage after the welding starts is different due to the difference of the dry extension of the welding, the model calculation is difficult, so that the waveform file needs to be processed, which specifically includes:
s131, reading actual voltage and actual current recorded in a waveform file, and screening out data of zero current and no-load voltage in the read actual voltage and actual current;
s132, constructing a two-dimensional array of behavior voltage and column current aiming at the screened data;
s133, converting the constructed two-bit array into graph data by using a python graph processing method, namely converting a waveform file of voltage and current into a visual picture.
And S140, inputting the graph data into a pre-trained welding defect detection model to obtain the welding defect type.
In practice, the training process of the welding defect detection model shown in fig. 3 includes:
s141, acquiring sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free (normal), burn-through, arc breakage, arc discharge and weld serpentine;
s142, converting a waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
s143, comparing the estimated welding defect type with the corresponding welding defect type in the sample data, executing S144 to adjust parameters in the initial neural network model and increase the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to S142, and executing S145 to take the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
In the implementation, the model training process can be combined with the welding defect type to name the waveform file, and the naming format is as follows: defect type-model-shielding gas-wire material-wire diameter-pulse presence-preset current-preset voltage. Csv, e.g., normal-500 GS 6-MAG-carbon steel-1.2-pulse presence-200-28. Csv.
In the training process, the actual voltage and the actual current can be acquired for different welding equipment (welding machine/welding robot) under the conditions of different shielding gases, welding wire materials, welding wire diameters, pulse existence, preset current, preset voltage and the like to obtain sample data and record the corresponding actual welding defect types, and one recording form is shown in the following table 1:
table 1 sample data example
In the training process, sample data can be divided into a training set and a testing set, wherein the training set is used for model training, the testing set is used for evaluating the performance of a model, and the training set is required to be further enlarged for training after the evaluation is not up to standard until a final welding defect detection model is obtained.
Referring to fig. 4, still another aspect of the present invention provides a schematic structural diagram of a deep learning-based welding arc defect recognition system, including:
a data acquisition unit 400, configured to acquire basic data of the welding device, where the basic data includes: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current;
a file creation unit 410 for creating a waveform file for recording an actual voltage and an actual current in a welding process using the basic data;
the data acquisition unit 420 is used for acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file in the welding process of the welding equipment;
a data calculation unit 430 for converting the recorded waveform file into graph data;
and a data transmission unit 440 for inputting the graph data into the pre-trained welding defect detection model to obtain the welding defect type.
In implementation, the data calculation unit 430 is specifically configured to:
reading the actual voltage and the actual current recorded in the waveform file, and screening out the data that the current in the read actual voltage and the actual current is zero and the voltage is no-load voltage;
aiming at the screened data, constructing a two-dimensional array of behavior voltage and current;
the constructed bit array is converted into map data using the python map processing method.
In practice, the system also comprises a model training unit for
Obtaining sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free, burn-through, arc breaking, arc drawing and weld serpentine;
converting the waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
comparing the estimated welding defect type with the corresponding welding defect type in the sample data, adjusting parameters in the initial neural network model and increasing the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to the step of converting the waveform file in the sample data into the graph data and inputting the graph data into the initial neural network model to obtain the estimated welding defect type, and taking the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
In practice, the data acquisition unit 420 is specifically configured to start recording the actual voltage and the actual current after detecting that the actual voltage and/or the actual current are greater than a predetermined threshold value through the transformer.
In one implementation, referring to fig. 5 and 6, each functional unit may be integrated in a waveform data acquisition and calculation device, in this implementation, an operator may input basic data of a welding power source through a UI interaction unit, and after receiving the basic data, the waveform data calculation unit creates a waveform file and stores the waveform file in a memory; after welding is started, acquiring actual voltage and actual current through a waveform data acquisition unit, writing acquired data into a waveform file through a waveform data calculation unit, converting the waveform file into graph data through a data transmission unit after the data are written into the waveform file, uploading the graph data to a server through the data transmission unit, training a welding defect detection model in advance in the server, storing the trained welding defect detection model, inputting the graph data into the welding defect detection model to obtain a corresponding welding defect type after the server receives the graph data, and sending the welding defect type to the data transmission unit, wherein the waveform data calculation unit can display the detection result through a UI interaction unit after the data transmission unit receives the detection result;
in another implementation manner, the server may further send the trained welding defect detection model to a memory in the waveform data acquisition and calculation device for storage through the data transmission unit, and the waveform data calculation unit may directly call the welding defect detection model in the memory to detect the welding defect after converting the waveform file into the map data, and display the detection result through the UI interaction unit.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.
Claims (8)
1. The welding arc defect identification method based on deep learning is characterized by comprising the following steps of:
obtaining basic data of the welding equipment, wherein the basic data comprises: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current;
creating a waveform file for recording actual voltage and actual current in a welding process by using the basic data;
in the welding process of the welding equipment, acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file;
converting the recorded waveform file into graph data;
and inputting the graph data into a pre-trained welding defect detection model to obtain the type of the welding defect.
2. The deep learning based welding arc defect identification method of claim 1, wherein the process of converting the recorded waveform file into map data comprises:
reading the actual voltage and the actual current recorded in the waveform file, and screening out the data that the current in the read actual voltage and the actual current is zero and the voltage is no-load voltage;
aiming at the screened data, constructing a two-dimensional array of behavior voltage and current;
the constructed bit array is converted into map data using the python map processing method.
3. The deep learning based welding arc defect identification method of claim 1, wherein the training process of the welding defect detection model comprises:
obtaining sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free, burn-through, arc breaking, arc drawing and weld serpentine;
converting the waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
comparing the estimated welding defect type with the corresponding welding defect type in the sample data, adjusting parameters in the initial neural network model and increasing the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to the step of converting the waveform file in the sample data into the graph data and inputting the graph data into the initial neural network model to obtain the estimated welding defect type, and taking the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
4. A method of deep learning based weld arc defect identification as defined in any one of claims 1-3 wherein the process of collecting the actual voltage and actual current of the weld comprises:
when the actual voltage and/or the actual current are detected to be greater than the predetermined threshold value by the transformer, recording of the actual voltage and the actual current is started.
5. A deep learning based welding arc defect identification system, comprising:
the welding device comprises a data acquisition unit, a welding unit and a data processing unit, wherein the data acquisition unit is used for acquiring basic data of the welding device, and the basic data comprises: the device model, the shielding gas, the welding wire material, the welding wire diameter, the pulse existence, the preset voltage and the preset current;
a file creation unit for creating a waveform file for recording an actual voltage and an actual current in a welding process using the basic data;
the data acquisition unit is used for acquiring the actual voltage and the actual current of welding and recording the actual voltage and the actual current in a waveform file in the welding process of the welding equipment;
a data calculation unit for converting the recorded waveform file into graph data;
and the data transmission unit is used for inputting the graph data into the pre-trained welding defect detection model to obtain the welding defect type.
6. The deep learning based welding arc defect identification system of claim 5, wherein the data calculation unit is specifically configured to:
reading the actual voltage and the actual current recorded in the waveform file, and screening out the data that the current in the read actual voltage and the actual current is zero and the voltage is no-load voltage;
aiming at the screened data, constructing a two-dimensional array of behavior voltage and current;
the constructed bit array is converted into map data using the python map processing method.
7. The deep learning based welding arc defect identification system of claim 5 further comprising a model training unit for
Obtaining sample data, wherein the sample data comprises a waveform file and a practically corresponding welding defect type, and the welding defect type comprises defect-free, burn-through, arc breaking, arc drawing and weld serpentine;
converting the waveform file in the sample data into graph data, and inputting the graph data into an initial neural network model to obtain a predicted welding defect type;
comparing the estimated welding defect type with the corresponding welding defect type in the sample data, adjusting parameters in the initial neural network model and increasing the data volume of the sample data under the condition that the estimated welding defect type does not accord with the expectation, returning to the step of converting the waveform file in the sample data into the graph data and inputting the graph data into the initial neural network model to obtain the estimated welding defect type, and taking the current initial neural network model as a welding defect detection model until the obtained estimated welding defect type accords with the expectation.
8. The deep learning based welding arc defect identification system of any of claims 5-7, wherein the data acquisition unit is adapted to start recording the actual voltage and the actual current after detecting that the actual voltage and/or the actual current is greater than a predetermined threshold by means of the transformer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310081264.3A CN116297683A (en) | 2023-02-07 | 2023-02-07 | Deep learning-based welding arc defect identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310081264.3A CN116297683A (en) | 2023-02-07 | 2023-02-07 | Deep learning-based welding arc defect identification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116297683A true CN116297683A (en) | 2023-06-23 |
Family
ID=86833300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310081264.3A Pending CN116297683A (en) | 2023-02-07 | 2023-02-07 | Deep learning-based welding arc defect identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116297683A (en) |
-
2023
- 2023-02-07 CN CN202310081264.3A patent/CN116297683A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020038389A1 (en) | Welding seam negative defect recognition method | |
| CN113758932B (en) | Deep learning-based visual detection method for defects of lithium battery diaphragm | |
| US6424151B2 (en) | Method and apparatus for evaluation of eddy current testing signal | |
| KR930017660A (en) | Arc welding control method, automatic arc welding device, neural network computer training method | |
| JPH10235490A (en) | Method for evaluating weld state of electric welding machine and device therefor | |
| CN105913059A (en) | Vehicle VIN code automatic identifying system and control method therefor | |
| JP2019191117A (en) | Image processing device, image processing method, and program | |
| CN115496728A (en) | Method and system for detecting defects of seal nail | |
| CN116381053A (en) | Ultrasonic detection method and system for welding metal materials | |
| CN116798036B (en) | Method and device for identifying and checking answer sheet objective question identification result | |
| CN114799610A (en) | Welding quality real-time detection method and system based on inverse Fourier transform and self-encoder | |
| CN111353611A (en) | Automatic generation system and method for in-service inspection and overhaul inspection report of nuclear power station | |
| CN113554645B (en) | Industrial anomaly detection method and device based on WGAN | |
| CN116297683A (en) | Deep learning-based welding arc defect identification method and system | |
| CN118013963A (en) | Method and device for identifying and replacing sensitive words | |
| CN111738991A (en) | Method for creating digital ray detection model of weld defects | |
| CN114596926B (en) | Steel grade identification method, laser-induced breakdown spectroscopy device and storage medium | |
| CN116551263A (en) | Visual control method and system for welding position selection | |
| CN114187256A (en) | Method for detecting defects of welding seam X-ray photograph | |
| CN114648522A (en) | Method, system, equipment and storage medium for detecting defects of circumferential weld of small-diameter pipe | |
| CN111610205A (en) | X-ray image defect detection device for metal parts | |
| CN114627126B (en) | Nuclear fuel rod defect detection method and device and nuclear reaction system | |
| CN113808067B (en) | Circuit board detection method, visual detection equipment and device with storage function | |
| CN117047248A (en) | Online detection method, system and device for welding quality of resistance spot welding | |
| CN117817211B (en) | Welding automation control method and system based on machine vision |
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 |