CN113808065A - Weld joint detection method and device, industrial robot and storage medium - Google Patents
Weld joint detection method and device, industrial robot and storage medium Download PDFInfo
- Publication number
- CN113808065A CN113808065A CN202010466271.1A CN202010466271A CN113808065A CN 113808065 A CN113808065 A CN 113808065A CN 202010466271 A CN202010466271 A CN 202010466271A CN 113808065 A CN113808065 A CN 113808065A
- Authority
- CN
- China
- Prior art keywords
- weld
- welding seam
- image
- detection model
- detected
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 139
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000003466 welding Methods 0.000 claims abstract description 168
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims description 31
- 238000005520 cutting process Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 230000008439 repair process Effects 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000003062 neural network model Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 13
- 238000007689 inspection Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 239000011324 bead Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention discloses a welding seam detection method, a welding seam detection device, an industrial robot and a storage medium, wherein the method comprises the following steps: acquiring a welding seam image of a welding seam segment to be detected; and inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model so as to determine the standard conformity of the welding seam displayed by the welding seam image. The technical scheme of the embodiment of the invention can improve the detection efficiency of the welding seam.
Description
Technical Field
The embodiment of the invention relates to the technical field of machining and manufacturing, in particular to a welding seam detection method and device, an industrial robot and a storage medium.
Background
With the development of electronic technology, computer technology, numerical control and robot technology, the technology of the automatic welding robot is mature from the beginning of 60 years and is widely applied in various industries.
In the aspect of welding operation, welding robot has replaced the manual welding of workman in the welding field, liberates the workman from smoke and dust, radiation and dangerous working environment on the one hand, and on the other hand can improve welding efficiency. However, in the aspect of welding quality detection, the welding result detection in the current hot working industry still needs to rely on intuition and experience of workers to judge whether the welding result is qualified, and the efficiency is low.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for detecting a weld, an industrial robot, and a storage medium, so as to improve the efficiency of detecting the weld.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of embodiments of the invention.
In a first aspect of the present disclosure, an embodiment of the present invention provides a weld detecting method, including:
acquiring a welding seam image of a welding seam segment to be detected;
and inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model, wherein the output result information is used for representing the standard conformity of the welding seam displayed by the welding seam image.
In one embodiment, the acquiring the weld image of the weld segment to be detected includes: in the welding process, if the length of the welding line segment to be detected reaches the preset length, the welding line image of the welding line segment to be detected is obtained.
In an embodiment, after obtaining the output result information of the weld detection model, the method further includes alarming and/or correcting the to-be-detected weld segment if the standard conformity of the weld displayed by the weld image is smaller than a predetermined conformity threshold.
In one embodiment, the acquiring the weld image of the weld segment to be detected includes: acquiring a surface contour image of a product to be detected, and performing image cutting on the surface contour image to acquire a plurality of welding seam images corresponding to a plurality of welding seam segments; inputting the weld image into a pre-trained weld detection model, and obtaining output result information of the weld detection model comprises the following steps: and respectively inputting the plurality of welding seam images into the pre-trained welding seam detection model to respectively obtain output result information of the welding seam detection model.
In an embodiment, after inputting any one of the plurality of weld images into the pre-trained weld detection model and obtaining the output result information of the weld detection model, the method further includes: if the standard conformity of the welding seam displayed by the welding seam image is determined to be less than the preset conformity threshold value by the output result information of the welding seam image, the unqualified record is carried out on the welding seam segment corresponding to the welding seam image.
In an embodiment, the method further includes determining to repair the product to be detected if a welding seam segment corresponding to any welding seam image obtained by cutting the surface profile image of the product to be detected has an unqualified record.
In one embodiment, the acquiring the surface profile image of the product to be detected includes: scanning the product to be detected through an industrial robot provided with a 3D laser scanner to obtain a surface profile image of the product to be detected;
performing image cutting on the surface profile image to obtain a plurality of weld images corresponding to a plurality of weld segments comprises: and intercepting the surface profile image of the product to be detected in a segmented manner to obtain a plurality of welding seam images corresponding to a plurality of welding seam segments.
In one embodiment, the weld detection model is trained by the following steps:
acquiring a training sample set, wherein the training sample comprises a welding seam sample image and a label used for indicating whether a welding seam displayed by the welding seam sample image is qualified or not;
determining an initialized weld detection model, wherein the initialized weld detection model comprises a target layer for outputting a standard conformance of a weld displayed in a weld image;
and by utilizing a machine learning method, taking the weld sample image in the training sample set as the input of the initialized weld detection model, taking the marking information corresponding to the input weld sample image as the expected output of the initialized weld detection model, and training to obtain the weld detection model.
In one embodiment, determining the initialized weld inspection model comprises: and determining the initialized welding seam detection model as a three-layer neural network model.
In a second aspect of the present disclosure, an embodiment of the present invention further provides a weld detecting apparatus, including:
the welding seam image acquisition unit is used for acquiring a welding seam image of a welding seam segment to be detected;
and the model detection unit is used for inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model, wherein the output result information is used for representing the standard conformity of the welding seam displayed by the welding seam image.
In an embodiment, the weld image acquiring unit is configured to: in the welding process, if the length of the welding line segment to be detected reaches the preset length, the welding line image of the welding line segment to be detected is obtained.
In an embodiment, the apparatus further includes a welding correction unit, configured to alarm and/or correct the to-be-detected weld segment if a standard conformity of the weld displayed by the weld image is smaller than a predetermined conformity threshold after obtaining the output result information of the weld detection model.
In an embodiment, the weld image acquiring unit is configured to: acquiring a surface contour image of a product to be detected, and performing image cutting on the surface contour image to acquire a plurality of welding seam images corresponding to a plurality of welding seam segments;
the model detection unit is used for: and respectively inputting the plurality of welding seam images into the pre-trained welding seam detection model to respectively obtain output result information of the welding seam detection model.
In an embodiment, the apparatus further includes a detection recording unit, configured to, after any one of the plurality of weld images is input to the pre-trained weld detection model and output result information of the weld detection model is obtained, perform unqualified recording on the weld segment corresponding to the weld image if the output result information of the weld image determines that a standard conformity of the weld displayed by the weld image is smaller than a predetermined conformity threshold.
In an embodiment, the apparatus further includes a repair determining unit, configured to determine to repair the product to be detected if a welding seam segment corresponding to any welding seam image obtained by cutting the surface profile image of the product to be detected has an unqualified record.
In an embodiment, the weld image acquiring unit is configured to: scanning the product to be detected through an industrial robot provided with a 3D laser scanner to obtain a surface profile image of the product to be detected; and intercepting the surface profile image of the product to be detected in a segmented manner to obtain a plurality of welding seam images corresponding to a plurality of welding seam segments.
In one embodiment, the weld detection model is trained by the following modules:
the system comprises a sample acquisition module, a comparison module and a comparison module, wherein the sample acquisition module is used for acquiring a training sample set, and the training sample comprises a welding seam sample image and a label used for indicating whether a welding seam displayed by the welding seam sample image is qualified or not;
a model determination module to determine an initialized weld detection model, wherein the initialized weld detection model includes a target layer to output a standard conformance of a weld displayed in a weld image;
and the model training module is used for utilizing a machine learning device to take the weld sample image in the training sample set as the input of the initialized weld detection model, take the marking information corresponding to the input weld sample image as the expected output of the initialized weld detection model, and train to obtain the weld detection model.
In one embodiment, determining the initialized weld inspection model comprises: and determining the initialized welding seam detection model as a three-layer neural network model.
In a third aspect of the present disclosure, an industrial robot is provided. The industrial robot includes: a processor; and a memory for storing executable instructions that, when executed by the processor, cause the industrial robot to perform the method of the first aspect.
In a fourth aspect of the disclosure, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the method in the first aspect.
The technical scheme provided by the embodiment of the invention has the beneficial technical effects that:
according to the embodiment of the invention, after the welding seam image of the welding seam segment to be detected is obtained, the welding seam image is input into the welding seam detection model which is trained in advance, and the standard conformity of the welding seam displayed by the welding seam image is determined according to the output result of the welding seam detection model. The technical scheme of the embodiment of the invention can improve the detection efficiency of the welding seam.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly described below, and it is obvious that the drawings in the following description are only a part of the embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the contents of the embodiments of the present invention and the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a weld inspection method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a method for training a weld inspection model according to an embodiment of the present disclosure;
FIG. 3 is a schematic flow chart of another weld detection method provided in accordance with an embodiment of the present invention;
FIG. 4 is a schematic flow chart of another weld detection method provided in accordance with an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a weld detecting apparatus according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram illustrating a training apparatus for a weld inspection model according to an embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of another weld detecting apparatus provided in accordance with an embodiment of the present invention;
fig. 8 shows a schematic structural view of an industrial robot suitable for implementing an embodiment of the invention.
Detailed Description
In order to make the technical problems solved, the technical solutions adopted and the technical effects achieved by the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments, but not all embodiments, of the embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, belong to the scope of protection of the embodiments of the present invention.
It should be noted that the terms "system" and "network" are often used interchangeably herein in embodiments of the present invention. Reference to "and/or" in embodiments of the invention is intended to include any and all combinations of one or more of the associated listed items. The terms "first", "second", and the like in the description and claims of the present disclosure and in the drawings are used for distinguishing between different objects and not for limiting a particular order.
It should be further noted that, in the embodiments of the present invention, each of the following embodiments may be executed alone, or may be executed in combination with each other, and the embodiments of the present invention are not limited in this respect.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The technical solutions of the embodiments of the present invention are further described by the following detailed description with reference to the accompanying drawings.
Fig. 1 shows a schematic flow chart of a weld detecting method provided in an embodiment of the present invention, which is applicable to a case of automatically detecting a weld of a product, and the method can be executed by a weld detecting apparatus configured in an industrial robot, as shown in fig. 1, where the weld detecting method according to the embodiment includes:
in step S110, a weld image of a weld segment to be detected is acquired.
It should be noted that the time for obtaining the weld image of the weld segment to be detected is related to the specific application scenario of the technical scheme of this embodiment, and the technical scheme of this embodiment may be used for performing weld detection in real time during the weld process, so as to correct the weld in time when the standard is not met, and may also be used for detecting the finished product at the product quality detection stage, so as to determine whether each product is qualified in terms of weld.
For example, if the technical scheme of this embodiment can be used for performing weld joint detection in real time in a weld joint process, in the weld joint process, if it is detected that the length of the weld joint segment to be detected reaches a predetermined length, a weld joint image of the weld joint segment to be detected is obtained.
For another example, if the technical scheme of this embodiment is used for detecting a finished product at a product quality detection stage, a surface profile image of the product to be detected may be obtained, and the surface profile image is subjected to image cutting to obtain a plurality of weld images corresponding to a plurality of weld segments, so as to respectively detect the plurality of weld images.
In step S120, the weld image is input to a weld detection model trained in advance, and output result information of the weld detection model is obtained, where the output result information is used to indicate a standard conformity of a weld displayed by the weld image.
The weld detection model can be obtained through various training modes, fig. 2 shows a flow diagram of a training method of the weld detection model, and as shown in fig. 2, the training method of the weld detection model comprises the following steps:
in step S210, a training sample set is obtained, where the training sample includes a weld sample image and a label used for indicating whether a weld displayed by the weld sample image is qualified.
In step S220, an initialized bead detection model is determined, wherein the initialized bead detection model includes a target layer for outputting a standard conformity of a bead displayed in a bead image.
In step S230, using a machine learning method, the weld sample image in the training sample set is used as an input of the initialized weld detection model, and the annotation information corresponding to the input weld sample image is used as an expected output of the initialized weld detection model, so as to obtain the weld detection model through training.
In some embodiments, determining the initialized weld inspection model comprises: and determining the initialized welding seam detection model as a three-layer neural network model.
According to the embodiment, after the welding seam image of the welding seam segment to be detected is obtained, the welding seam image is input into the pre-trained welding seam detection model, the standard conformity degree of the welding seam displayed by the welding seam image is determined according to the output result of the welding seam detection model, the welding seam quality can be automatically identified by a robot for controlling the welding seam in the welding seam process, or whether the product is qualified in the aspect of the welding seam is automatically determined in the product quality inspection stage, excessive manual participation is avoided, and the welding seam detection efficiency can be improved.
Fig. 3 is a schematic flow chart of another weld joint detection method provided in an embodiment of the present invention, which is applicable to a situation of performing weld joint detection in real time during a weld joint process, and the method may be performed by a weld joint detection apparatus configured in an industrial robot, as shown in fig. 1, the weld joint detection method according to the embodiment includes:
in step S310, in the welding process, if it is detected that the length of the to-be-detected welding seam segment reaches the predetermined length, a welding seam image of the to-be-detected welding seam segment is obtained.
In step S320, the weld image is input to a pre-trained weld detection model, and output result information of the weld detection model is obtained, where the output result information is used to indicate a standard conformity of a weld displayed by the weld image.
The weld detection model can be obtained through various training modes, and fig. 2 shows a schematic flow chart of a training method of the weld detection model, which is not described in detail in this embodiment.
In step S330, if the standard conformity of the weld seam displayed by the weld seam image is smaller than a predetermined conformity threshold, an alarm is issued and/or the weld seam segment to be detected is corrected.
For example, the robot can be controlled to automatically correct by prompting workers to perform manual correction through alarming.
According to the method, the welding seam image is input into the pre-trained welding seam detection model in the welding seam process of the product, the welding seam displayed by the welding seam image is determined to be not in accordance with the standard according to the output result of the welding seam detection model, then alarming or timely correcting is carried out, and the rate of qualified products can be improved.
Fig. 4 is a schematic flow chart of another weld joint detection method provided by an embodiment of the present invention, which can be applied to the case of automatically detecting a weld joint of a product, and which can be performed by a weld joint detection apparatus configured in an industrial robot.
Before controlling the industrial robot to detect, a user can input some basic production information, such as a threshold value for judging the qualification of a product workpiece, a machine scanning speed and the like, by using input equipment such as a mouse, a keyboard and the like according to actual requirements.
The user inputs some basic information of production, such as threshold value for judging the qualification of the product workpiece, machine scanning speed and the like, by using input equipment such as a mouse, a keyboard and the like according to the actual requirements of the user.
As shown in fig. 4, the weld detecting method according to the present embodiment includes:
in step S410, a surface contour image of a product to be detected is acquired, and the surface contour image is subjected to image cutting to acquire a plurality of weld images corresponding to a plurality of weld segments.
It should be noted that, when the industrial robot is controlled to detect products in batches, automatic path planning and automatic collision prevention of the industrial robot can be realized through an algorithm in the industrial robot controller, the real-time space coordinate of the current workpiece is calculated, and the industrial robot is guided to automatically complete a workpiece scanning task.
The welding product workpiece is scanned by an industrial robot equipped with a 3D laser scanner. Surface profile data for a large number of acceptable products and unacceptable workpieces is obtained by a 3D imaging system.
The method for obtaining the surface contour image of the product to be detected can adopt various methods, for example, the product to be detected can be scanned by an industrial robot provided with a 3D laser scanner, so that the surface contour image of the product to be detected is obtained.
After the surface profile image of the product to be detected is obtained, a plurality of welding seam images corresponding to a plurality of welding seam segments can be obtained through segmentation and interception. Thus, the mode of detecting one welding seam segment at a time can improve the detection precision.
In step S420, the plurality of weld images are respectively input to the pre-trained weld detection model, and output result information of the weld detection model is respectively obtained.
In step S430, if the output result information of the weld image determines that the standard conformity of the weld displayed by the weld image is smaller than the predetermined conformity threshold, performing an unqualified record on the weld segment corresponding to the weld image.
In step S440, if there is an unqualified record in the weld segment corresponding to any weld image obtained by cutting the surface profile image of the product to be detected, it is determined that the product to be detected is repaired.
According to the quality detection method and the quality detection device, quality detection in the aspect of welding seams is carried out on finished products in the product quality detection stage, after the welding seam quality of each segment is determined, whether the whole product is qualified in the aspect of welding seams is determined according to the recording result of each segment, whether the product is repaired is determined, automatic detection can be carried out on the welding seams of the product, labor cost is reduced, and the product detection precision can be further improved in a mode of carrying out sectional detection on the surface outline image of the product.
As an implementation of the methods shown in the above figures, the present application provides an embodiment of a weld detecting apparatus, and fig. 5 shows a schematic structural diagram of the weld detecting apparatus provided in this embodiment, where the embodiment of the apparatus corresponds to the method embodiments shown in fig. 1 to 4, and the apparatus may be specifically applied to various industrial robots. As shown in fig. 5, the weld detecting apparatus according to the present embodiment includes a weld image acquiring unit 510 and a model detecting unit 520.
The weld image acquiring unit 510 is configured to acquire a weld image of a weld segment to be detected.
The model detection unit 520 is configured to input the weld image into a pre-trained weld detection model, and obtain output result information of the weld detection model, where the output result information is used to represent a standard conformity of a weld displayed by the weld image.
In some embodiments, the weld image obtaining unit 510 is configured to further obtain a weld image of the weld segment to be detected if it is detected that the length of the weld segment to be detected reaches a predetermined length during the welding process.
In some embodiments, the apparatus further includes a welding correction unit (not shown in fig. 5) configured to, after obtaining the output result information of the weld detection model, alarm and/or correct the to-be-detected weld segment if a standard conformity of the weld displayed in the weld image is smaller than a predetermined conformity threshold.
In some embodiments, the weld inspection model may be trained in various ways, and fig. 6 shows a schematic structural diagram of a training apparatus for a weld inspection model, which may be trained by the following sample acquiring module 610, the model determining module 620, and the model training module 630, as shown in fig. 6.
The sample acquiring module 610 is configured to acquire a training sample set, where a training sample includes a weld sample image and an annotation indicating whether a weld displayed by the weld sample image is qualified.
The model determination module 620 is configured for determining an initialized weld detection model, wherein the initialized weld detection model comprises a target layer for outputting a standard conformance of a weld displayed in a weld image.
The model training module 630 is configured to train the weld detection model by using a machine learning apparatus, using the weld sample image in the training sample set as an input of the initialized weld detection model, and using the annotation information corresponding to the input weld sample image as an expected output of the initialized weld detection model.
In some embodiments, the model determination module 620 configured to determine an initialized weld detection model may include: configured to determine the initialized weld detection model as a three-layer neural network model.
The welding seam detection device provided by the embodiment can execute the welding seam detection method provided by the embodiment of the method disclosed by the invention, and has corresponding functional modules and beneficial effects of the execution method.
Fig. 7 is a schematic structural diagram of another weld joint detection apparatus according to an embodiment of the present invention, and as shown in fig. 7, the weld joint detection apparatus according to the embodiment includes: a weld image acquisition unit 710, a model detection unit 720, a detection recording unit 730, and a rework determination unit 740.
The weld image acquiring unit 710 is configured to acquire a weld image of a weld segment to be detected.
The model detection unit 720 is configured to input the weld image into a pre-trained weld detection model, and obtain output result information of the weld detection model, where the output result information is used to represent a standard conformity of a weld displayed by the weld image.
The detection recording unit 730 is configured to perform an unqualified recording on the weld segment corresponding to the weld image if the output result information of the weld image determines that the standard conformity of the weld displayed by the weld image is smaller than a predetermined conformity threshold.
The repair determining unit 740 is configured to determine to repair the product to be detected if a welding seam segment corresponding to any welding seam image obtained by cutting the surface profile image of the product to be detected has an unqualified record.
In some embodiments, the weld image obtaining unit 710 is configured to obtain a surface profile image of a product to be detected, and perform image cutting on the surface profile image to obtain a plurality of weld images corresponding to a plurality of weld segments;
the model detection unit 720 is configured to input the plurality of weld images to the pre-trained weld detection models respectively, and obtain output result information of the weld detection models respectively.
In some embodiments, the weld image obtaining unit 710 is configured to scan the product to be detected by an industrial robot equipped with a 3D laser scanner, so as to obtain a surface profile image of the product to be detected; and intercepting the surface profile image of the product to be detected in a segmented manner to obtain a plurality of welding seam images corresponding to a plurality of welding seam segments.
In some embodiments, the weld detection model may be obtained through multiple training modes, and fig. 6 shows a schematic structural diagram of a training apparatus for a weld detection model, which is not described in detail in this embodiment.
The welding seam detection device provided by the embodiment can execute the welding seam detection method provided by the embodiment of the method disclosed by the invention, and has corresponding functional modules and beneficial effects of the execution method.
Referring now to fig. 8, a schematic diagram of an industrial robot 800 suitable for use in implementing an embodiment of the present invention is shown. The terminal device in the embodiments of the present invention may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle terminal (e.g., a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. The industrial robot shown in fig. 8 is only an example, and should not bring any limitation to the function and the range of use of the embodiment of the present invention.
As shown in fig. 8, an industrial robot 800 may include a processing device (e.g., a central processing unit, a graphic processor, etc.) 801 that may perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage device 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data necessary for the operation of the industrial robot 800 are also stored. The processing apparatus 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
Generally, the following devices may be connected to the I/O interface 805: input devices 806 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage 808 including, for example, magnetic tape, hard disk, etc.; and a communication device 809. The communication means 809 may allow the industrial robot 800 to communicate wirelessly or by wire with other devices to exchange data. Although fig. 8 illustrates an industrial robot 800 having various devices, it is to be understood that not all of the illustrated devices are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.
In particular, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as a computer software program. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 809, or installed from the storage means 808, or installed from the ROM 802. The computer program, when executed by the processing apparatus 801, performs the above-described functions defined in the methods of embodiments of the present invention.
It should be noted that the computer readable medium mentioned above can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In embodiments of the invention, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In yet another embodiment of the invention, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be included in the industrial robot; or may be separate and not assembled into the industrial robot.
The computer readable medium carries one or more programs which, when executed by the industrial robot, cause the industrial robot to: acquiring a welding seam image of a welding seam segment to be detected; and inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model, wherein the output result information is used for representing the standard conformity of the welding seam displayed by the welding seam image.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present invention may be implemented by software or hardware. Where the name of a unit does not in some cases constitute a limitation of the unit itself, for example, the first retrieving unit may also be described as a "unit for retrieving at least two internet protocol addresses".
The foregoing description is only a preferred embodiment of the invention and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the disclosure in the embodiments of the present invention is not limited to the specific combinations of the above-described features, but also encompasses other embodiments in which any combination of the above-described features or their equivalents is possible without departing from the spirit of the disclosure. For example, the above features and (but not limited to) the features with similar functions disclosed in the embodiments of the present invention are mutually replaced to form the technical solution.
Claims (12)
1. A weld detection method, comprising:
acquiring a welding seam image of a welding seam segment to be detected;
and inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model, wherein the output result information is used for representing the standard conformity of the welding seam displayed by the welding seam image.
2. The method of claim 1, wherein acquiring a weld image of a weld segment to be detected comprises:
in the welding process, if the length of the welding line segment to be detected reaches the preset length, the welding line image of the welding line segment to be detected is obtained.
3. The method according to claim 2, characterized by further comprising, after obtaining the output result information of the weld detection model, alarming and/or correcting the weld segment to be detected if the standard conformity of the weld displayed by the weld image is less than a predetermined conformity threshold.
4. The method of claim 1, wherein acquiring a weld image of a weld segment to be detected comprises: acquiring a surface contour image of a product to be detected, and performing image cutting on the surface contour image to acquire a plurality of welding seam images corresponding to a plurality of welding seam segments;
inputting the weld image into a pre-trained weld detection model, and obtaining output result information of the weld detection model comprises the following steps: and respectively inputting the plurality of welding seam images into the pre-trained welding seam detection model to respectively obtain output result information of the welding seam detection model.
5. The method according to claim 4, wherein after inputting any one of the plurality of weld images into the pre-trained weld detection model and obtaining the output result information of the weld detection model, the method further comprises:
if the standard conformity of the welding seam displayed by the welding seam image is determined to be less than the preset conformity threshold value by the output result information of the welding seam image, the unqualified record is carried out on the welding seam segment corresponding to the welding seam image.
6. The method according to claim 5, further comprising determining to repair the product to be detected if a welding line segment corresponding to any welding line image obtained by cutting the surface profile image of the product to be detected has an unqualified record.
7. The method of claim 4, wherein acquiring the surface profile image of the product to be inspected comprises:
scanning the product to be detected through an industrial robot provided with a 3D laser scanner to obtain a surface profile image of the product to be detected;
performing image cutting on the surface profile image to obtain a plurality of weld images corresponding to a plurality of weld segments comprises:
and intercepting the surface profile image of the product to be detected in a segmented manner to obtain a plurality of welding seam images corresponding to a plurality of welding seam segments.
8. The method according to any one of claims 1 to 7, wherein the weld detection model is trained by:
acquiring a training sample set, wherein the training sample comprises a welding seam sample image and a label used for indicating whether a welding seam displayed by the welding seam sample image is qualified or not;
determining an initialized weld detection model, wherein the initialized weld detection model comprises a target layer for outputting a standard conformance of a weld displayed in a weld image;
and by utilizing a machine learning method, taking the weld sample image in the training sample set as the input of the initialized weld detection model, taking the marking information corresponding to the input weld sample image as the expected output of the initialized weld detection model, and training to obtain the weld detection model.
9. The method of claim 8, wherein determining an initialized weld detection model comprises: and determining the initialized welding seam detection model as a three-layer neural network model.
10. A weld detecting apparatus, comprising:
the welding seam image acquisition unit is used for acquiring a welding seam image of a welding seam segment to be detected;
and the model detection unit is used for inputting the welding seam image into a pre-trained welding seam detection model to obtain output result information of the welding seam detection model, wherein the output result information is used for representing the standard conformity of the welding seam displayed by the welding seam image.
11. An industrial robot, characterized by comprising:
a processor; and
a memory for storing executable instructions that, when executed by the one or more processors, cause the industrial robot to perform the method of any of claims 1-9.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010466271.1A CN113808065A (en) | 2020-05-28 | 2020-05-28 | Weld joint detection method and device, industrial robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010466271.1A CN113808065A (en) | 2020-05-28 | 2020-05-28 | Weld joint detection method and device, industrial robot and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113808065A true CN113808065A (en) | 2021-12-17 |
Family
ID=78943625
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010466271.1A Pending CN113808065A (en) | 2020-05-28 | 2020-05-28 | Weld joint detection method and device, industrial robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808065A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1546996A (en) * | 2003-12-12 | 2004-11-17 | 上海交通大学 | Active infrared CCD weld seam detecting device |
| CN107451997A (en) * | 2017-07-31 | 2017-12-08 | 南昌航空大学 | A kind of automatic identifying method of the welding line ultrasonic TOFD D scanning defect types based on deep learning |
| CN109580653A (en) * | 2018-11-06 | 2019-04-05 | 深圳技术大学（筹） | A kind of rail fastener image-pickup method |
| CN109886298A (en) * | 2019-01-16 | 2019-06-14 | 江苏大学 | A kind of detection method for quality of welding line based on convolutional neural networks |
| CN110969611A (en) * | 2019-12-03 | 2020-04-07 | 广州特种承压设备检测研究院 | Pipeline weld defect detection method, device and system and storage medium |
-
2020
- 2020-05-28 CN CN202010466271.1A patent/CN113808065A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1546996A (en) * | 2003-12-12 | 2004-11-17 | 上海交通大学 | Active infrared CCD weld seam detecting device |
| CN107451997A (en) * | 2017-07-31 | 2017-12-08 | 南昌航空大学 | A kind of automatic identifying method of the welding line ultrasonic TOFD D scanning defect types based on deep learning |
| CN109580653A (en) * | 2018-11-06 | 2019-04-05 | 深圳技术大学（筹） | A kind of rail fastener image-pickup method |
| CN109886298A (en) * | 2019-01-16 | 2019-06-14 | 江苏大学 | A kind of detection method for quality of welding line based on convolutional neural networks |
| CN110969611A (en) * | 2019-12-03 | 2020-04-07 | 广州特种承压设备检测研究院 | Pipeline weld defect detection method, device and system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3937128A2 (en) | Image defect detection method and apparatus, electronic device, storage medium and product | |
| CN115641332B (en) | Method, device, medium and equipment for detecting product edge appearance defects | |
| CN109741295B (en) | Product quality detection method and device | |
| CN112884743B (en) | Detection method and device, detection equipment and storage medium | |
| CN110570146A (en) | Product sorting method and device and computer readable storage medium | |
| CN111428374A (en) | Part defect detection method, device, equipment and storage medium | |
| CN116245808A (en) | Workpiece defect detection method and device, electronic equipment and storage medium | |
| CN109986172A (en) | A kind of weld and HAZ method, equipment and system | |
| CN114167189B (en) | Welding defect detection method, electronic equipment and storage medium | |
| CN113808065A (en) | Weld joint detection method and device, industrial robot and storage medium | |
| CN113218328A (en) | Equipment maintenance method, device, equipment and medium based on three-dimensional laser scanning | |
| CN114074321A (en) | Robot calibration method and device | |
| CN111325160A (en) | Method and apparatus for generating information | |
| CN117372674A (en) | Image prediction frame overlapping processing method, device, equipment and storage medium | |
| CN113192070B (en) | Weld image processing method and system based on computer vision | |
| JP2022135007A (en) | Work propriety determination device | |
| CN113989135A (en) | Image restoration method and device, electronic equipment and storage medium | |
| CN116239019A (en) | Intelligent port crane operation monitoring method and system | |
| CN116977241A (en) | Method, apparatus, computer readable storage medium and computer program product for detecting defects in a vehicle component | |
| CN114841255A (en) | Detection model training method, device, equipment, storage medium and program product | |
| CN114708239A (en) | Glue width detection method and device, electronic equipment and storage medium | |
| CN115100110A (en) | Defect detection method, device and equipment for polarized lens and readable storage medium | |
| US20170309087A1 (en) | Method for Enabling a Trained Professional to Perform a Remote Inspection of a Vehicle | |
| JP2024120127A (en) | Analysis device, analysis system, analysis method, and analysis program | |
| CN117934809A (en) | Multi-model cascading target detection method, system, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |