CN112809175B - Semiconductor laser-based welding method, device, equipment and storage medium - Google Patents

Semiconductor laser-based welding method, device, equipment and storage medium Download PDF

Info

Publication number
CN112809175B
CN112809175B CN202011611547.7A CN202011611547A CN112809175B CN 112809175 B CN112809175 B CN 112809175B CN 202011611547 A CN202011611547 A CN 202011611547A CN 112809175 B CN112809175 B CN 112809175B
Authority
CN
China
Prior art keywords
welding
semiconductor laser
weld
welded
laser
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011611547.7A
Other languages
Chinese (zh)
Other versions
CN112809175A (en
Inventor
毛森
杨雷
毛虎
牛飞飞
陆凯凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Ruisidun Optoelectronic Science And Technology Co ltd
Shenzhen Netopto Optoelectronics Co ltd
Original Assignee
Wuhan Ruisidun Optoelectronic Science And Technology Co ltd
Shenzhen Netopto Optoelectronics Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Ruisidun Optoelectronic Science And Technology Co ltd, Shenzhen Netopto Optoelectronics Co ltd filed Critical Wuhan Ruisidun Optoelectronic Science And Technology Co ltd
Priority to CN202011611547.7A priority Critical patent/CN112809175B/en
Publication of CN112809175A publication Critical patent/CN112809175A/en
Application granted granted Critical
Publication of CN112809175B publication Critical patent/CN112809175B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/20Bonding
    • B23K26/21Bonding by welding
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/02Positioning or observing the workpiece, e.g. with respect to the point of impact; Aligning, aiming or focusing the laser beam
    • B23K26/04Automatically aligning, aiming or focusing the laser beam, e.g. using the back-scattered light
    • B23K26/044Seam tracking
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/70Auxiliary operations or equipment
    • B23K26/702Auxiliary equipment
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K2101/00Articles made by soldering, welding or cutting
    • B23K2101/36Electric or electronic devices
    • B23K2101/40Semiconductor devices

Landscapes

  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Engineering & Computer Science (AREA)
  • Plasma & Fusion (AREA)
  • Mechanical Engineering (AREA)
  • Laser Beam Processing (AREA)

Abstract

The invention relates to the technical field of welding, and discloses a welding method, a welding device, welding equipment and a storage medium based on a semiconductor laser, wherein the method comprises the following steps: when a welding starting instruction is received, controlling a semiconductor laser to project laser stripes to a region to be welded at a preset angle according to the welding starting instruction; collecting weld image information of the area to be welded based on the laser stripes; and analyzing the welding seam image information to obtain corresponding welding regulation data so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the welding regulation data. The method comprises the steps of carrying out depth analysis on welding line image information of a region to be welded to obtain corresponding welding adjusting data, and controlling a semiconductor laser to emit corresponding laser beams according to the welding adjusting data to carry out tracking welding on the region to be welded so as to realize automatic tracking welding, and further, the welding precision and the welding efficiency are improved.

Description

Semiconductor laser-based welding method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of welding, in particular to a welding method, a welding device, welding equipment and a storage medium based on a semiconductor laser.
Background
Welding is an important product connection mode, plays an important role in the industrial field, and the improvement of welding efficiency can further improve production efficiency. In the prior art, weld image information is mostly acquired by a welding robot in real time so as to control the movement of a welding gun according to the weld image information. However, in the welding process, a large amount of noise caused by strong arc light and splashing influences exists in the welding seam image information acquired by the laser, so that the measurement precision of the welding seam position is reduced, and the welding quality is influenced.
The semiconductor laser is a laser device taking semiconductor materials as working substances, and has the following advantages besides the common characteristics of the laser: (1) the volume is small and the weight is light; (2) the driving power and current are low; (3) the efficiency is high, and the service life is long; (4) can be directly modulated electrically; (5) the optoelectronic device is easy to realize optoelectronic integration with various optoelectronic devices; (6) compatible with semiconductor manufacturing techniques; can be produced in large batch. Because of these characteristics, semiconductor lasers have gained wide attention and research from the world and have become the most rapidly developed and widely applied lasers in the world, which are commercialized and produced in the largest value when the lasers are first moved out of laboratories. Therefore, how to improve the welding automation degree and the welding efficiency based on the semiconductor laser becomes a problem to be solved urgently.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a welding method, a welding device, welding equipment and a storage medium based on a semiconductor laser, and aims to solve the technical problem of how to improve the welding precision and the welding efficiency based on the semiconductor laser.
In order to achieve the above object, the present invention provides a method for soldering based on a semiconductor laser, the method comprising the steps of:
when a welding starting instruction is received, controlling a semiconductor laser to project laser stripes to a region to be welded at a preset angle according to the welding starting instruction;
collecting weld image information of the area to be welded based on the laser stripes;
and analyzing the welding seam image information to obtain corresponding welding regulation data so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the welding regulation data.
Preferably, the step of analyzing the weld image information to obtain corresponding welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded includes the following steps:
carrying out image denoising processing and image enhancement processing on the welding seam image information to obtain a welding seam enhancement image;
carrying out image segmentation processing on the weld enhancement image to obtain a weld segmentation result;
performing feature extraction on the welding seam segmentation result to obtain welding seam feature data;
and generating welding regulation data according to the welding seam characteristic data so that the semiconductor laser emits corresponding laser beams according to the welding regulation data to weld the area to be welded.
Preferably, the step of generating welding adjustment data according to the weld feature data to enable the semiconductor laser to emit a corresponding laser beam according to the welding adjustment data to weld the region to be welded specifically includes:
constructing a welding coordinate system according to the welding seam characteristic data, and determining a welding center point based on the welding coordinate system;
and inputting the welding central point into a preset welding model to obtain welding regulation data so that the semiconductor laser emits a corresponding laser beam to weld the area to be welded according to the welding regulation data.
Preferably, before the step of inputting the welding center point into a preset welding model to obtain welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded, the method further includes:
extracting a welding seam sample image and sample adjusting data corresponding to the welding seam sample image from a preset welding training set, and determining a corresponding welding seam center point sample based on the welding seam sample image;
and taking the weld joint center point sample as a model input feature of a convolutional neural network model, taking the sample adjusting data as a model output feature of the convolutional neural network model, and training the convolutional neural network model according to the model input feature and the model output feature to obtain a preset welding model.
Preferably, the step of inputting the welding center point into a preset welding model to obtain welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded specifically includes:
inputting the welding center point into a preset welding model to obtain a welding candidate point;
and acquiring a relay center point based on the welding candidate points, so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the relay center point and the welding center point.
Preferably, the step of acquiring a relay center point based on the welding candidate points to enable the semiconductor laser to emit corresponding laser beams according to the relay center point and the welding center point to weld the to-be-welded area includes:
calculating the similarity between the welding candidate point and the welding central point by utilizing a Gaussian kernel function;
and sequencing the similarity, and selecting a first sequenced welding candidate point as a relay center point so that the semiconductor laser emits a corresponding laser beam to weld the area to be welded according to the relay center point and the welding center point.
Preferably, the step of inputting the welding center point into a preset welding model to obtain welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded specifically includes:
detecting whether the area to be welded meets the preset single-beam welding requirement or not according to the welding center point;
when the fact that the area to be welded does not meet the preset single-beam welding requirement is detected, the welding center point is input into a preset welding model, the number of laser beams, the laser power and the welding speed are obtained, and the semiconductor laser emits corresponding laser beams according to the number of the laser beams, the laser power and the welding speed to weld the area to be welded.
In order to achieve the above object, the present invention also provides a soldering apparatus based on a semiconductor laser, comprising:
the laser projection module is used for controlling the semiconductor laser to project laser stripes to a region to be welded at a preset angle according to a welding starting instruction when the welding starting instruction is received;
the welding line acquisition module is used for acquiring welding line image information of the area to be welded based on the laser stripes;
and the laser welding module is used for analyzing the welding seam image information to obtain corresponding welding adjustment data so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the welding adjustment data.
In addition, in order to achieve the above object, the present invention also proposes a semiconductor laser-based soldering apparatus, comprising: a semiconductor laser, a memory, a processor, and a semiconductor laser based welding program stored on the memory and executable on the processor, the semiconductor laser based welding program configured to implement the steps of the semiconductor laser based welding method as described above.
Furthermore, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a semiconductor laser based welding program, which when executed by a processor, implements the steps of the semiconductor laser based welding method as described above.
In the invention, when a welding starting instruction is received, a semiconductor laser is controlled to project laser stripes to a region to be welded at a preset angle according to the welding starting instruction, welding seam image information of the region to be welded is collected based on the laser stripes, the welding seam image information is analyzed, corresponding welding adjusting data is obtained, so that the semiconductor laser emits corresponding laser beams according to the welding adjusting data to weld the region to be welded, and the method is different from the prior art that large noise caused by strong arc light and splash influences exists in the welding seam image information collected by the laser to cause the reduction of welding seam position measuring precision and the reduction of welding quality. The automatic tracking welding is realized, and further, the welding precision and the welding efficiency are also improved.
Drawings
FIG. 1 is a schematic diagram of a semiconductor laser based welding apparatus in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of a semiconductor laser-based welding method according to the present invention;
FIG. 3 is a schematic flow chart of a second embodiment of a semiconductor laser-based soldering method according to the present invention;
FIG. 4 is a schematic flow chart of a third embodiment of a semiconductor laser-based soldering method according to the present invention;
fig. 5 is a block diagram of a first embodiment of a semiconductor laser-based soldering apparatus according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a semiconductor laser-based welding device in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the semiconductor laser based soldering apparatus may include: the processor 1001 includes, for example, a Central Processing Unit (CPU), a Micro Control Unit (MCU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005, and a semiconductor laser 1006. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of semiconductor laser-based welding apparatus and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is one type of storage medium, may include therein an operating system, a data storage module, a network communication module, a user interface module, and a welding program based on a semiconductor laser.
In the semiconductor laser-based welding apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the semiconductor laser based welding device of the present invention may be provided in the semiconductor laser based welding device, which calls the semiconductor laser based welding program stored in the memory 1005 through the processor 1001 and executes the semiconductor laser based welding method provided by the embodiment of the present invention. The semiconductor laser 1006 is mainly used for emitting a laser beam.
An embodiment of the present invention provides a welding method based on a semiconductor laser, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the welding method based on the semiconductor laser according to the present invention.
In this embodiment, the welding method based on a semiconductor laser includes the following steps:
step S10: when a welding starting instruction is received, controlling a semiconductor laser to project laser stripes to a region to be welded at a preset angle according to the welding starting instruction;
it should be noted that the main execution body of this embodiment is the above-mentioned processor, and the processor controls the semiconductor laser to project the laser stripe to the region to be welded at a preset angle according to the welding start instruction when receiving the welding start instruction, where the welding start instruction may be understood as instruction information input by a user to start the semiconductor laser, and may include a wavelength of the semiconductor laser, a threshold current (i.e., a current at which the laser tube starts to generate laser oscillation), an operating current (i.e., a driving current at which the laser tube reaches a rated output power), a divergence angle (i.e., an angle at which a light emitting band of the laser diode is opened in a direction perpendicular or parallel to the PN junction), a monitoring current (i.e., a current flowing through the PIN tube at the rated output power), and the preset angle may be set according to actual requirements, such as an angle of 30 degrees with a vertical downward direction (i.e., a vertical emission angle of 30 degrees), this embodiment is not limited in this regard. The area to be welded may be understood as a preset range of the weld, based on the upper edge and the lower edge of the weld, which may include a preset length, and the preset length may be determined according to the requirement, which is not limited in this embodiment.
Step S20: collecting weld image information of the area to be welded based on the laser stripes;
it is easily understood that, in order to improve the acquisition accuracy of the image information, when acquiring the weld image information of the region to be welded, a Charge Coupled Device (CCD) camera can be adopted to collect the welding seam image information of the area to be welded, namely, when the semiconductor laser is controlled to project the laser stripes to the area to be welded at the preset angle according to the welding starting instruction, the CCD camera can be controlled to collect the welding seam image information of the area to be welded based on the laser stripes transmitted to the area to be welded, the weld image information can be understood as the real-time imaging of the weld taken with a CCD camera, since the front of the CCD camera is provided with an optical filter, allowing the laser light to pass, and filtering out all other light, such as the welding arc, therefore, the accuracy of collecting the welding seam image information is improved, and the welding precision during welding based on the welding seam image information is further improved.
Step S30: and analyzing the welding seam image information to obtain corresponding welding regulation data so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the welding regulation data.
It should be noted that, in order to further improve the accuracy of the acquired weld image information and further improve the welding precision when welding is performed based on the weld image information, after the weld image information is obtained, the weld image information may be subjected to depth analysis, where the depth analysis includes, but is not limited to, performing image denoising processing, image enhancement processing, image segmentation processing, feature extraction, and the like on the weld image information to obtain welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded, and the welding adjustment data includes, but is not limited to, the number of laser beams, the laser power, and the welding speed of the semiconductor laser.
In the embodiment, when a welding start instruction is received, a semiconductor laser is controlled to project laser stripes to a region to be welded at a preset angle according to the welding start instruction, weld image information of the region to be welded is collected based on the laser stripes, the weld image information is analyzed, corresponding welding adjustment data is obtained, so that the semiconductor laser emits corresponding laser beams according to the welding adjustment data to weld the region to be welded, and the embodiment is different from the prior art that large noise caused by strong arc light and splash influences exists in the weld image information collected by the laser to reduce the measurement precision of the weld position and reduce the welding quality, the embodiment obtains the corresponding welding adjustment data by performing depth analysis on the weld image information of the region to be welded, and controls the semiconductor laser to emit the corresponding laser beams according to the welding adjustment data to perform tracking welding on the region to be welded, the automatic tracking welding is realized, and further, the welding precision and the welding efficiency are also improved.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of the semiconductor laser-based soldering method according to the present invention.
Based on the first embodiment described above, in the present embodiment, the step S30 includes:
step S301: carrying out image denoising processing and image enhancement processing on the welding seam image information to obtain a welding seam enhancement image;
step S302: carrying out image segmentation processing on the weld enhancement image to obtain a weld segmentation result;
step S303: performing feature extraction on the welding seam segmentation result to obtain welding seam feature data;
step S304: and generating welding regulation data according to the welding seam characteristic data so that the semiconductor laser emits corresponding laser beams according to the welding regulation data to weld the area to be welded.
It should be noted that, in order to further improve the accuracy of the acquired weld image information and further improve the welding precision when welding is performed based on the weld image information, the acquired weld image information may be subjected to image denoising processing by a median filtering method, then image enhancement processing is performed by a laplacian operator to improve the contrast ratio between the laser stripe and the surrounding background to obtain a weld enhancement image, then binarization processing is performed on the weld enhancement image to segment the weld laser stripe image to obtain a weld segmentation result, then feature extraction is performed by a particle filtering tracking method to obtain feature data for identifying the position information of the weld, that is, weld feature data, further, a welding center point may be determined according to the weld feature data, and welding adjustment data may be determined according to the welding center point, so that the semiconductor laser emits a corresponding laser beam to weld the region to be welded according to the welding regulation data, wherein the welding regulation data comprises but is not limited to the number of laser beams, the laser power and the welding speed.
In the specific implementation, the welding area to be welded is of a double-layer structure, a preset distance is required between an upper layer structure and a lower layer structure, the traditional single-beam laser cannot meet the welding requirement (at the moment, the welding with the single-beam laser is difficult to avoid, low in stability and relatively high in error, the exposed surface of the upper structure and the exposed surface of the lower structure are prone to protruding and deforming, and appearance quality is affected), the semiconductor laser is required to emit double-beam laser to perform laser welding on the welding area, in the welding process, the beam distance of the double-beam laser can be changed in real time to adjust the welding depth, and the laser power, the welding speed and the like of the semiconductor laser can be adjusted to improve the welding efficiency. Based on this, after the welding center point is determined, whether the area to be welded meets a preset single-beam welding requirement or not can be detected according to the welding center point, and when the area to be welded does not meet the preset single-beam welding requirement, the welding center point is input into a preset welding model to obtain the number of laser beams, the laser power and the welding speed, so that the semiconductor laser emits corresponding laser beams according to the number of the laser beams, the laser power and the welding speed to weld the area to be welded. The preset welding model can be obtained by extracting a welding seam sample image and sample adjusting data corresponding to the welding seam sample image from a preset welding training set, determining a corresponding welding seam central point sample based on the welding seam sample image, taking the welding seam central point sample as a model input feature of a convolutional neural network model, taking the sample adjusting data as a model output feature of the convolutional neural network model, and training the convolutional neural network model according to the model input feature and the model output feature, wherein the preset welding training set stores the welding seam sample image generated based on welding history data and the sample adjusting data corresponding to the welding seam sample image.
In this embodiment, the image denoising and the image enhancement are performed on the weld image information to obtain a weld enhancement image, the weld enhancement image is subjected to image segmentation to obtain a weld segmentation result, the weld segmentation result is subjected to feature extraction to obtain weld feature data, and welding adjustment data is generated according to the weld feature data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded. The accuracy of the weld image information is improved by carrying out image denoising processing, image enhancement processing, image segmentation processing and characteristic extraction weld characteristic data on the weld image information, the welding precision and the welding quality when welding is carried out based on the weld image information are further improved, and the number of laser beams, the laser power and the welding speed are obtained according to the weld characteristic data, so that the semiconductor laser emits corresponding laser beams according to the number of the laser beams, the laser power and the welding speed to weld the area to be welded, and the welding efficiency is improved.
Referring to fig. 4, fig. 4 is a schematic flow chart of a third embodiment of the semiconductor laser-based soldering method according to the present invention.
Based on the second embodiment, in this embodiment, the step S304 includes:
step S3041: constructing a welding coordinate system according to the welding seam characteristic data, and determining a welding center point based on the welding coordinate system;
it is easy to understand that, after the weld characteristic data for identifying the position information of the weld is obtained, a welding coordinate system may be constructed based on the weld characteristic data, the welding coordinate system is a three-dimensional coordinate system, the characteristics of the weld in terms of length, width and depth may be embodied based on the welding coordinate system, then the weld specific data is calculated to calculate the size information of the weld, and the welding center point is determined according to the size information of the weld and the coordinate information corresponding to the welding coordinate system, e.g., if the weld is square, it is the intersection point of the body diagonal.
Step S3042: and inputting the welding central point into a preset welding model to obtain welding regulation data so that the semiconductor laser emits a corresponding laser beam to weld the area to be welded according to the welding regulation data.
In a specific implementation, in order to obtain the welding adjustment data, before the welding center point is input into a preset welding model, the preset welding model is further constructed, specifically, a welding seam sample image and sample adjustment data corresponding to the welding seam sample image are extracted from a preset welding training set, and a corresponding welding seam center point sample is determined based on the welding seam sample image, then taking the weld joint center point sample as a model input feature of a convolutional neural network model, taking the sample adjustment data as a model output feature of the convolutional neural network model, and training the convolutional neural network model according to the model input features and the model output features to obtain the convolutional neural network model, and the preset welding training set is stored with a welding seam sample image generated based on the welding historical data and sample adjusting data corresponding to the welding seam sample image. In this embodiment, the welding candidate point may be a welding candidate point, which may be understood as a candidate point set of a next welding center point, and accordingly, the sample adjustment data may be a sample candidate point.
Further, the welding center point may be input into a preset welding model to obtain a welding candidate point, and then a relay center point is obtained based on the welding candidate point, so that the semiconductor laser emits a corresponding laser beam according to the relay center point and the welding center point to perform automatic tracking welding on the to-be-welded region. In a specific implementation, a gaussian kernel function can be used to calculate the similarity between a welding candidate point and the welding center point, then the similarities are ranked, and a first ranked welding candidate point (i.e., the welding candidate point with the highest recognition degree) is selected as a relay center point, so that the semiconductor laser emits a corresponding laser beam according to the relay center point and the welding center point to perform automatic tracking welding on the to-be-welded area.
In the implementation, a welding coordinate system is established according to the weld joint characteristic data, a welding central point is determined based on the welding coordinate system, the welding central point is input into a preset welding model to obtain a welding candidate point, and then a relay central point is obtained based on the welding candidate point, so that the semiconductor laser emits corresponding laser beams according to the relay central point and the welding central point to perform tracking welding on the area to be welded, and the welding automation degree and the welding efficiency are improved.
Furthermore, an embodiment of the present invention also provides a storage medium having a semiconductor laser based welding program stored thereon, which when executed by a processor implements the steps of the semiconductor laser based welding method as described above.
Referring to fig. 5, fig. 5 is a block diagram showing a first embodiment of a semiconductor laser-based soldering apparatus according to the present invention.
As shown in fig. 5, a semiconductor laser-based soldering apparatus according to an embodiment of the present invention includes:
the laser projection module 10 is used for controlling the semiconductor laser to project laser stripes to a region to be welded at a preset angle according to a welding starting instruction when the welding starting instruction is received;
the welding seam acquisition module 20 is used for acquiring welding seam image information of the area to be welded based on the laser stripes;
and the laser welding module 30 is configured to analyze the weld image information to obtain corresponding welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the to-be-welded area.
In the embodiment, when a welding start instruction is received, a semiconductor laser is controlled to project laser stripes to a region to be welded at a preset angle according to the welding start instruction, weld image information of the region to be welded is collected based on the laser stripes, the weld image information is analyzed, corresponding welding adjustment data is obtained, so that the semiconductor laser emits corresponding laser beams according to the welding adjustment data to weld the region to be welded, and the embodiment is different from the prior art that large noise caused by strong arc light and splash influences exists in the weld image information collected by the laser to reduce the measurement precision of the weld position and reduce the welding quality, the embodiment obtains the corresponding welding adjustment data by performing depth analysis on the weld image information of the region to be welded, and controls the semiconductor laser to emit the corresponding laser beams according to the welding adjustment data to perform tracking welding on the region to be welded, the automatic tracking welding is realized, and further, the welding precision and the welding efficiency are also improved.
A second embodiment of the semiconductor laser-based soldering apparatus of the present invention is proposed based on the above-described first embodiment of the semiconductor laser-based soldering apparatus of the present invention.
In this embodiment, the laser welding module 30 is further configured to perform image denoising and image enhancement on the weld image information to obtain a weld enhancement image;
the laser welding module 30 is further configured to perform image segmentation processing on the weld enhancement image to obtain a weld segmentation result;
the laser welding module 30 is further configured to perform feature extraction on the weld segmentation result to obtain weld feature data;
the laser welding module 30 is further configured to generate welding adjustment data according to the weld characteristic data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded.
The laser welding module 30 is further configured to construct a welding coordinate system according to the weld characteristic data, and determine a welding center point based on the welding coordinate system;
the laser welding module 30 is further configured to input the welding center point into a preset welding model to obtain welding adjustment data, so that the semiconductor laser emits a corresponding laser beam according to the welding adjustment data to weld the region to be welded. The laser welding module 30 is also used for
The laser welding module 30 is further configured to extract a weld sample image and sample adjustment data corresponding to the weld sample image from a preset welding training set, and determine a corresponding weld center point sample based on the weld sample image;
the laser welding module 30 is further configured to use the weld center point sample as a model input feature of a convolutional neural network model, use the sample adjustment data as a model output feature of the convolutional neural network model, and train the convolutional neural network model according to the model input feature and the model output feature to obtain a preset welding model.
The laser welding module 30 is further configured to input the welding center point into a preset welding model to obtain a welding candidate point;
the laser welding module 30 is further configured to obtain a relay center point based on the welding candidate point, so that the semiconductor laser emits a corresponding laser beam according to the relay center point and the welding center point to weld the to-be-welded area.
The laser welding module 30 is further configured to calculate a similarity between a welding candidate point and the welding center point by using a gaussian kernel function;
the laser welding module 30 is further configured to sort the similarity, and select a first sorted welding candidate point as a relay center point, so that the semiconductor laser emits a corresponding laser beam according to the relay center point and the welding center point to weld the to-be-welded area.
The laser welding module 30 is further configured to detect whether the area to be welded meets a preset single-beam welding requirement according to the welding center point;
the laser welding module 30 is further configured to, when it is detected that the area to be welded does not meet the preset single-beam welding requirement, input the welding center point into a preset welding model to obtain the number of laser beams, the laser power, and the welding speed, so that the semiconductor laser emits corresponding laser beams according to the number of laser beams, the laser power, and the welding speed to weld the area to be welded.
Other embodiments or specific implementation manners of the semiconductor laser-based welding device of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., a rom/ram, a magnetic disk, an optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (7)

1. A method of semiconductor laser based soldering, the method comprising the steps of:
when a welding starting instruction is received, controlling a semiconductor laser to project laser stripes to a region to be welded at a preset angle according to the welding starting instruction;
collecting weld image information of the area to be welded based on the laser stripes;
carrying out image denoising processing and image enhancement processing on the welding seam image information to obtain a welding seam enhancement image;
carrying out image segmentation processing on the weld enhancement image to obtain a weld segmentation result;
performing feature extraction on the welding seam segmentation result to obtain welding seam feature data;
generating welding regulation data according to the welding seam characteristic data so that the semiconductor laser emits corresponding laser beams according to the welding regulation data to weld the area to be welded;
constructing a welding coordinate system according to the welding seam characteristic data, and determining a welding center point based on the welding coordinate system;
detecting whether the area to be welded meets the preset single-beam welding requirement or not according to the welding center point;
when the fact that the area to be welded does not meet the preset single-beam welding requirement is detected, the welding center point is input into a preset welding model, the number of laser beams, the laser power and the welding speed are obtained, and the semiconductor laser emits corresponding laser beams according to the number of the laser beams, the laser power and the welding speed to weld the area to be welded.
2. The method according to claim 1, wherein before the step of inputting the welding center point into a preset welding model to obtain welding adjustment data so that the semiconductor laser emits a corresponding laser beam to weld the region to be welded according to the welding adjustment data, the method further comprises:
extracting a welding seam sample image and sample adjusting data corresponding to the welding seam sample image from a preset welding training set, and determining a corresponding welding seam center point sample based on the welding seam sample image;
and taking the weld joint center point sample as a model input feature of a convolutional neural network model, taking the sample adjusting data as a model output feature of the convolutional neural network model, and training the convolutional neural network model according to the model input feature and the model output feature to obtain a preset welding model.
3. The method according to claim 2, wherein the step of inputting the welding center point into a preset welding model to obtain welding adjustment data so that the semiconductor laser emits a corresponding laser beam to weld the region to be welded according to the welding adjustment data specifically comprises:
inputting the welding center point into a preset welding model to obtain a welding candidate point;
and acquiring a relay center point based on the welding candidate points, so that the semiconductor laser emits corresponding laser beams to weld the area to be welded according to the relay center point and the welding center point.
4. The method according to claim 3, wherein the step of obtaining a relay center point based on the welding candidate points so that the semiconductor laser emits a corresponding laser beam to weld the region to be welded according to the relay center point and the welding center point specifically comprises:
calculating the similarity between the welding candidate point and the welding central point by utilizing a Gaussian kernel function;
and sequencing the similarity, and selecting a first sequenced welding candidate point as a relay center point so that the semiconductor laser emits a corresponding laser beam to weld the area to be welded according to the relay center point and the welding center point.
5. A semiconductor laser based soldering apparatus, the apparatus comprising:
the laser projection module is used for controlling the semiconductor laser to project laser stripes to a region to be welded at a preset angle according to a welding starting instruction when the welding starting instruction is received;
the welding line acquisition module is used for acquiring welding line image information of the area to be welded based on the laser stripes;
the laser welding module is used for carrying out image denoising processing and image enhancement processing on the welding seam image information to obtain a welding seam enhancement image; carrying out image segmentation processing on the weld enhancement image to obtain a weld segmentation result; performing feature extraction on the welding seam segmentation result to obtain welding seam feature data; generating welding regulation data according to the welding seam characteristic data so that the semiconductor laser emits corresponding laser beams according to the welding regulation data to weld the area to be welded; constructing a welding coordinate system according to the welding seam characteristic data, and determining a welding center point based on the welding coordinate system; detecting whether the area to be welded meets the preset single-beam welding requirement or not according to the welding center point; when the fact that the area to be welded does not meet the preset single-beam welding requirement is detected, the welding center point is input into a preset welding model, the number of laser beams, the laser power and the welding speed are obtained, and the semiconductor laser emits corresponding laser beams according to the number of the laser beams, the laser power and the welding speed to weld the area to be welded.
6. A semiconductor laser based soldering apparatus, the apparatus comprising: a semiconductor laser, a memory, a processor, and a semiconductor laser based welding program stored on the memory and executable on the processor, the semiconductor laser based welding program configured to implement the steps of the semiconductor laser based welding method as recited in any of claims 1 to 4.
7. A storage medium having stored thereon a semiconductor laser based welding program, which when executed by a processor implements the steps of the semiconductor laser based welding method as claimed in any one of claims 1 to 4.
CN202011611547.7A 2020-12-29 2020-12-29 Semiconductor laser-based welding method, device, equipment and storage medium Active CN112809175B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011611547.7A CN112809175B (en) 2020-12-29 2020-12-29 Semiconductor laser-based welding method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011611547.7A CN112809175B (en) 2020-12-29 2020-12-29 Semiconductor laser-based welding method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112809175A CN112809175A (en) 2021-05-18
CN112809175B true CN112809175B (en) 2022-08-12

Family

ID=75854908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011611547.7A Active CN112809175B (en) 2020-12-29 2020-12-29 Semiconductor laser-based welding method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112809175B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117324769B (en) * 2023-11-14 2024-03-29 江西瑞升科技股份有限公司 Automatic precise laser welding method based on CCD visual detection

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109146866A (en) * 2018-08-23 2019-01-04 深圳市神视检验有限公司 The method and device that robot handles weld seam
CN109604777A (en) * 2017-12-07 2019-04-12 淮安信息职业技术学院 Welding seam traking system and method based on laser structure light
CN110064819A (en) * 2019-05-14 2019-07-30 苏州实创德光电科技有限公司 The extraction of cylinder longitudinal seam characteristic area, welding seam tracking method and system based on structure light
CN110480127A (en) * 2019-08-12 2019-11-22 广东工业大学 A kind of seam tracking system and method based on structured light visual sensing
CN110640268A (en) * 2019-09-26 2020-01-03 中车青岛四方机车车辆股份有限公司 Bogie machining process tracking method based on Internet of things technology

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109226967B (en) * 2018-07-25 2021-03-09 同高先进制造科技(太仓)有限公司 Active laser vision steady weld joint tracking system for laser-arc hybrid welding

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109604777A (en) * 2017-12-07 2019-04-12 淮安信息职业技术学院 Welding seam traking system and method based on laser structure light
CN109146866A (en) * 2018-08-23 2019-01-04 深圳市神视检验有限公司 The method and device that robot handles weld seam
CN110064819A (en) * 2019-05-14 2019-07-30 苏州实创德光电科技有限公司 The extraction of cylinder longitudinal seam characteristic area, welding seam tracking method and system based on structure light
CN110480127A (en) * 2019-08-12 2019-11-22 广东工业大学 A kind of seam tracking system and method based on structured light visual sensing
CN110640268A (en) * 2019-09-26 2020-01-03 中车青岛四方机车车辆股份有限公司 Bogie machining process tracking method based on Internet of things technology

Also Published As

Publication number Publication date
CN112809175A (en) 2021-05-18

Similar Documents

Publication Publication Date Title
CN111462110B (en) Welding seam quality detection method, device and system and electronic equipment
US7747080B2 (en) System and method for scanning edges of a workpiece
CN109492688B (en) Weld joint tracking method and device and computer readable storage medium
JP2021534481A (en) Obstacle or ground recognition and flight control methods, devices, equipment and storage media
CN108297115B (en) Autonomous repositioning method for robot
CN110879994A (en) Three-dimensional visual inspection detection method, system and device based on shape attention mechanism
CN112432647B (en) Carriage positioning method, device and system and computer readable storage medium
CN109986172B (en) Welding seam positioning method, equipment and system
CN112809175B (en) Semiconductor laser-based welding method, device, equipment and storage medium
CN113490965A (en) Image tracking processing method and device, computer equipment and storage medium
CN111179262A (en) Electric power inspection image hardware fitting detection method combined with shape attribute
CN114353807B (en) Robot positioning method and positioning device
CN101750018A (en) Non-contact real-time displacement measuring method and device in bending deformation process of work piece
CN110689556A (en) Tracking method and device and intelligent equipment
CN112685527B (en) Method, device and electronic system for establishing map
CN116160458B (en) Multi-sensor fusion rapid positioning method, equipment and system for mobile robot
CN113032272A (en) Automatic parking system test evaluation method, device, equipment and storage medium
CN115792919B (en) Method for identifying polluted hot spot area through horizontal scanning monitoring of aerosol laser radar
CN115055806B (en) Welding track tracking method and device based on visual tracking
CN114425774B (en) Robot walking road recognition method, robot walking road recognition device, and storage medium
CN115909253A (en) Target detection and model training method, device, equipment and storage medium
CN114777761A (en) Cleaning machine and map construction method
CN111539919B (en) Method and device for judging position and routing inspection of tower part
CN114519782A (en) Road edge extraction method and device
CN116372936B (en) Robot control method, robot, and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant