CN115439463A - Method and device for determining welding quality, processor and welding quality diagnosis system - Google Patents
Method and device for determining welding quality, processor and welding quality diagnosis system Download PDFInfo
- Publication number
- CN115439463A CN115439463A CN202211183849.8A CN202211183849A CN115439463A CN 115439463 A CN115439463 A CN 115439463A CN 202211183849 A CN202211183849 A CN 202211183849A CN 115439463 A CN115439463 A CN 115439463A
- Authority
- CN
- China
- Prior art keywords
- welding
- information
- quality
- parameters
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Numerical Control (AREA)
Abstract
The application provides a method, a device, a processor and a system for determining welding quality, wherein the method comprises the following steps: acquiring welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process; and inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of pieces of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. The method and the device solve the problems that an online detection welding system in the prior art can only analyze a few welding quality influencing parameters of welding, and is not comprehensive enough and low in accuracy.
Description
Technical Field
The application relates to the field of welding diagnosis, in particular to a method, a device, a processor and a system for determining welding quality.
Background
The welding has wide application, but the welding is basically detected after welding at present, and especially the welding quality detection of some large structural members is basically detected uniformly and comprehensively by taking a detection instrument from a manufacturer to a field, so that the cost is high and the efficiency is not high. Moreover, the application of effective on-line real-time welding detection is lacked, welding defects have to be found through detection of professional instruments under the condition that the whole welding is finished, and rework is performed again in many cases, but higher progress cost and quality cost are generated at the moment. In addition, the existing on-line detection welding system can only analyze a few welding quality parameters influencing welding, and is not comprehensive enough and has not high accuracy.
Disclosure of Invention
The application mainly aims to provide a method, a device, a processor and a welding quality diagnosis system for determining welding quality, so as to solve the problems that an online detection welding system in the prior art can only analyze a few welding quality parameters which affect welding, and is not comprehensive and low in accuracy.
In order to achieve the above object, according to an aspect of the present application, there is provided a method of determining welding quality, including: acquiring welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, a welding audio frequency spectrum and an arc light brightness frequency spectrum of a welding robot in a welding process; and inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information.
Optionally, before the welding information is input to a quality diagnosis model for analysis and diagnosis, and welding quality information representing whether the welding quality is qualified is obtained, the method further includes: constructing a plurality of neural network models, and training the neural network models by adopting a plurality of groups of data to obtain a plurality of first sub-models, wherein each group of data in the plurality of groups of data comprises historical welding parameters and corresponding historical welding quality information; and constructing a second submodel, wherein the second submodel is connected with the output ends of all the first submodels, the second submodel is used for determining the qualified rate according to the output result of each first submodel, outputting the welding quality information according to the qualified rate and a preset threshold, outputting the welding quality information representing that the welding quality is qualified under the condition that the qualified rate is greater than or equal to the preset threshold, and outputting the welding quality information representing that the welding quality is unqualified under the condition that the qualified rate is less than the preset threshold, and the qualified rate is the ratio of the number of the output results representing that the welding quality is qualified to the total number of the output results.
Optionally, the step of inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified includes: and inputting the welding parameters into the first submodel in a one-to-one correspondence manner, so that the first submodel outputs the output results to the second submodel according to the welding parameters, and the second submodel determines and outputs the welding quality information according to the output results.
Optionally, acquiring the attitude change rate of the welding robot during the welding process, the motion parameter and the welding gun swing parameter includes: controlling a first sensor to collect attitude data of the welding robot in real time and filtering the attitude data; calculating the change rate of the filtered attitude data to obtain the attitude change rate; controlling a second sensor to acquire the movement speed of the welding robot in each movement direction and the swing speed of the welding gun, and filtering the movement speed and the swing speed to obtain the movement speed of the welding robot and the swing speed of the welding gun; and controlling a third sensor to acquire motion acceleration of the welding robot in each motion direction and swing acceleration of the welding gun, and filtering the motion acceleration and the swing acceleration, wherein the filtered motion speed and the filtered motion acceleration form the motion parameter, and the filtered swing speed and the filtered swing acceleration form the swing parameter of the welding gun.
Optionally, obtaining the welding audio frequency spectrum and the arc brightness spectrum comprises: controlling an audio acquisition device to acquire welding sounds in a welding process in real time, and performing Fourier transform processing on the welding sounds to obtain an audio frequency spectrum; and controlling a scanning device to carry out brightness scanning on the arc in the welding process to obtain an arc brightness image, and carrying out image processing on the arc brightness image to obtain the arc brightness frequency spectrum.
Optionally, the plurality of welding parameters further comprises at least one of: weld groove information, weld puddle shape information, weld puddle temperature information, welding current and welding voltage of the welding robot.
Optionally, the obtaining welding information further comprises at least one of: controlling a first image acquisition device to acquire a weld groove image in real time, and carrying out image processing on the weld groove image to obtain weld groove information; controlling a second image acquisition device to acquire a molten pool image in real time, and carrying out image processing on the molten pool image to obtain the molten pool shape information; controlling a third image acquisition device to acquire a molten pool heat distribution image in real time, and carrying out image processing on the molten pool heat distribution image to obtain molten pool temperature information; controlling a current sensor to collect current data of the welding robot in the welding process in real time, and filtering the current data to obtain the welding current; and controlling a voltage sensor to collect voltage data of the welding robot in the welding process in real time, and filtering the voltage data to obtain the welding voltage.
According to another aspect of the present application, there is provided a welding quality determination apparatus, including an acquisition unit and an input unit, wherein the acquisition unit is configured to acquire welding information, the welding information includes a plurality of welding parameters, the plurality of welding parameters includes a posture change rate of a welding robot during welding, a motion parameter, a gun swing parameter, a welding audio frequency spectrum, and an arc brightness frequency spectrum; the input unit is used for inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and historical welding quality information corresponding to each piece of historical welding information.
According to yet another aspect of the application, a processor for running a program is provided, wherein the program when running performs any one of the methods.
According to still another aspect of the present application, there is provided a weld quality diagnostic system including: a welding robot and a welding quality determination apparatus comprising one or more processors, memory, a controller, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the welding quality diagnostic methods.
By applying the technical scheme, in the method for determining the welding quality, firstly, welding information comprising a plurality of welding parameters is obtained, wherein the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process; and then, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an on-line detection welding system in the prior art, the on-line detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
FIG. 1 illustrates a schematic diagram of a method of determining weld quality according to an embodiment of the present application;
FIG. 2 shows a weld quality diagnostic process schematic according to an embodiment of the present application;
fig. 3 shows a schematic diagram of a weld quality determination apparatus according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It will be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present. Also, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element or "connected" to the other element through a third element.
As described in the background art, the on-line welding detection system in the prior art can only analyze a few welding quality parameters affecting welding, and is not comprehensive enough and has low accuracy.
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for determining weld quality, it being noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system, such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than presented herein.
Fig. 1 is a flowchart of a method of determining weld quality according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S101, obtaining welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process;
specifically, the step S101 includes: controlling a first sensor to collect attitude data of the welding robot in real time and filtering the attitude data; calculating the change rate of the attitude data after filtering to obtain the change rate of the attitude; controlling a second sensor to acquire the movement speed of the welding robot in each movement direction and the swing speed of the welding gun, and filtering the movement speed and the swing speed to obtain the movement speed of the welding robot and the swing speed of the welding gun; and controlling a third sensor to acquire motion acceleration of the welding robot in each motion direction and swing acceleration of the welding gun, and filtering the motion acceleration and the swing acceleration, wherein the filtered motion speed and the filtered motion acceleration form the motion parameter, and the filtered swing speed and the filtered swing acceleration form the swing parameter of the welding gun. The gesture data of the welding robot, the movement speed of the welding robot in each movement direction, the swing speed of the welding gun and the movement acceleration of the welding robot in each movement direction and the swing acceleration of the welding gun are collected in real time through the first sensor, the second sensor and the third sensor, the obtained information is subjected to filtering processing, movement parameters are obtained, and the welding quality information is further ensured to be more comprehensive.
In order to further facilitate the subsequent determination of whether the welding quality information is qualified, in a more specific embodiment, the obtaining of the welding audio frequency spectrum and the arc luminance spectrum includes: controlling an audio acquisition device to acquire welding sounds in a welding process in real time, and performing Fourier transform processing on the welding sounds to obtain the audio frequency spectrum; and controlling a scanning device to carry out brightness scanning on the arc in the welding process to obtain an arc brightness image, and carrying out image processing on the arc brightness image to obtain the arc brightness frequency spectrum. The audio frequency spectrum and the arc light brightness spectrum are obtained by processing the welding sound and the arc light brightness collected in real time, and then the obtained welding information is input to a quality diagnosis model for analysis, and finally whether the welding quality is qualified or not is determined.
It should be noted that the scanning device is configured to scan the light of the arc during welding 1000 times per second, but the scanning frequency is not limited to 1000 times per second, and those skilled in the art can flexibly configure the scanning device according to the actual situation.
Step S102, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to the historical welding information.
In the method for determining the welding quality, firstly, welding information comprising a plurality of welding parameters is obtained, wherein the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc brightness spectrum of a welding robot in the welding process; and then, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an online detection welding system in the prior art, the online detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
In the method of the present application, the step S102 includes: and inputting the welding parameters into the first submodel in a one-to-one correspondence manner, so that the first submodel outputs the output result to the second submodel according to the welding parameters, and the second submodel determines and outputs the welding quality information according to each output result. Specifically, as shown in fig. 2, according to the present application, whether each welding parameter is qualified is determined in advance through a first submodel corresponding to each parameter, then the output result of each first submodel is input to a second submodel, the qualification rate of the welding parameter is determined according to the ratio of the qualified welding quality quantity output by each first submodel to the total quantity of the output results of all first submodels, and finally the output result of the second submodel is input to a quality diagnosis model, so that the information whether the final welding quality is qualified is obtained.
In order to obtain more comprehensive welding quality information, it should be noted that the plurality of welding parameters further includes at least one of the following: weld groove information, molten pool shape information, molten pool temperature information, welding current and welding voltage of the welding robot.
In an optional embodiment, the acquiring welding information further includes at least one of: controlling a first image acquisition device to acquire a welding seam groove image in real time, and carrying out image processing on the welding seam groove image to obtain the welding seam groove information; controlling a second image acquisition device to acquire a molten pool image in real time, and carrying out image processing on the molten pool image to obtain the molten pool shape information; controlling a third image acquisition device to acquire a molten pool heat distribution image in real time, and carrying out image processing on the molten pool heat distribution image to obtain the molten pool temperature information; controlling a current sensor to collect current data of the welding robot in the welding process in real time, and filtering the current data to obtain the welding current; and controlling a voltage sensor to acquire voltage data of the welding robot in the welding process in real time, and filtering the voltage data to obtain the welding voltage. Through to the above-mentioned weld groove image that acquires in real time, carry out image processing with molten bath image and molten bath heat distribution image and obtain weld groove information, molten bath shape information and molten bath temperature information, and carry out filtering process at the current data of above-mentioned welding process and welding robot at the voltage data of above-mentioned welding process of welding robot to the welding robot that acquires in real time, obtain welding current and welding voltage, carry out the analysis to above-mentioned information data through first sub-analysis model, it is more comprehensive to have further guaranteed welding quality information.
According to the method and the device, quality diagnosis is carried out on each acquired information in advance, and the reason that the welding quality is unqualified is found out in advance according to whether each information is qualified or not, so that the quality problem can be detected by visual inspection of welding problem points or a simple portable welding quality detector, the detection is effectively screened, the detection efficiency and the effectiveness are improved, the detection is more targeted, the detection efficiency is improved, the detection cost is reduced, quality reworking is carried out in advance, the quality cost is reduced, and the welding operation quality is improved.
Moreover, after the first sub-model detects unqualified information, the position of the robot with the quality problem in workpiece welding operation can be effectively positioned in real time, the welding quality can be detected in a targeted manner after welding, the quality problem can be analyzed and positioned conveniently, data in the welding process can be traced and analyzed, and root cause analysis can be performed on the generated welding quality problem.
In the present application, the image processing includes: at least one of the image gray scale processing, the binarization processing and the image segmentation processing, of course, in order to better analyze information in the acquired image, the image processing in the present application is not limited to the image gray scale processing, the binarization processing and the image segmentation processing described above, and those skilled in the art can flexibly process the information according to actual situations.
In a more specific embodiment, before step S102, the method further includes:
step S201, constructing a plurality of neural network models, and training the neural network models by adopting a plurality of groups of data to obtain a plurality of first submodels, wherein each group of data in the plurality of groups of data comprises historical welding parameters and corresponding historical welding quality information;
step S202 is to construct a second submodel, where the second submodel is connected to output terminals of all the first submodels, the second submodel is configured to determine a yield according to an output result of each of the first submodels, output the welding quality information according to the yield and a predetermined threshold, output the welding quality information indicating that the welding quality is acceptable when the yield is greater than or equal to the predetermined threshold, and output the welding quality information indicating that the welding quality is unacceptable when the yield is less than the predetermined threshold, and the yield is a ratio of the number of output results indicating that the welding quality is acceptable to the total number of output results.
The second submodel receives the information whether the welding parameters output by the first submodel are qualified or not, the qualified rate is determined, the information is compared with the preset threshold value, under the condition that the output qualified rate is larger than or equal to the preset threshold value, the number of the welding parameters meeting the welding quality requirement is enough, only a small number of the welding parameters are unqualified, the integral welding quality is qualified, and under the condition that the output qualified rate is smaller than the preset threshold value, the number of the welding parameters which do not meet the welding quality requirement is too much, and the integral welding quality is unqualified. By determining the integral qualification rate of the welding parameters, the problem that the test data of one or two welding parameters are inaccurate in the welding process, so that the integral welding quality judgment is influenced can be solved, and the over-judgment is prevented.
The predetermined threshold is set to 90%, and of course, the predetermined threshold is not limited to 90%, and those skilled in the art can flexibly set the predetermined threshold according to actual situations.
Example 2
The embodiment of the present application further provides a device for determining welding quality, which corresponds to the method shown in fig. 1, and it should be noted that the device for determining welding quality according to the embodiment of the present application can be used to execute the method for determining welding quality provided by the embodiment of the present application. The following describes a device for determining the quality of a weld provided in an embodiment of the present application.
Fig. 3 is a schematic diagram of a device for determining the quality of a weld according to an embodiment of the present application. As shown in fig. 3, the following is specifically explained:
the device for determining the welding quality comprises an acquisition unit 10 and an input unit 20, wherein the acquisition unit 10 is used for acquiring welding information, the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swinging parameters, a welding audio frequency spectrum and an arc brightness frequency spectrum of a welding robot in a welding process; the input unit 20 is configured to input the welding information into a quality diagnosis model, which is created based on a plurality of pieces of historical welding information and historical welding quality information corresponding to each piece of historical welding information, to perform analysis and diagnosis, and obtain welding quality information indicating whether the welding quality is acceptable.
In the welding quality determination apparatus of the present application, welding information including a plurality of welding parameters including a posture change rate of a welding robot during welding, a motion parameter, a torch weaving parameter, a welding audio frequency spectrum, and an arc luminance spectrum is acquired by an acquisition unit; and inputting the welding information into a quality diagnosis model through an input unit for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an online detection welding system in the prior art, the online detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
The device further comprises a first construction unit and a second construction unit, wherein the first construction unit is used for constructing a plurality of neural network models before the welding information is input to a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified or not, and training the neural network models by adopting a plurality of groups of data to obtain a plurality of first sub-models, and each group of data in the plurality of groups of data comprises historical welding parameters and corresponding historical welding quality information; the second building means is configured to build a second submodel, the second submodel being connected to output terminals of all the first submodels, the second submodel being configured to determine a yield from output results of the respective first submodels, and to output the welding quality information based on the yield and a predetermined threshold, the second submodel being configured to output the welding quality information indicating that the welding quality is acceptable when the yield is greater than or equal to the predetermined threshold, and the second submodel being configured to output the welding quality information indicating that the welding quality is unacceptable when the yield is less than the predetermined threshold, the yield being a ratio of the number of output results indicating that the welding quality is acceptable to the total number of output results.
In an optional embodiment, the input unit of the present application includes an input module, where the input module is configured to input the welding parameters into the first sub-model in a one-to-one correspondence manner, so that the first sub-model outputs the output result to the second sub-model according to the welding parameters, and the second sub-model determines and outputs the welding quality information according to each output result.
More specifically, the acquiring unit of the present application includes a first control module, a calculating module, a second control module, and a third control module, where the first control module is configured to control a first sensor to acquire pose data of the welding robot in real time, and perform filtering processing on the pose data; the calculation module is used for calculating the change rate of the filtered attitude data to obtain the attitude change rate; the second control module is used for controlling a second sensor to acquire the movement speed of the welding robot and the swing speed of the welding gun in each movement direction, and filtering the movement speed and the swing speed to obtain the movement speed of the welding robot and the swing speed of the welding gun; the third control module is configured to control a third sensor to acquire a motion acceleration of the welding robot in each motion direction and a weaving acceleration of the welding gun, and perform filtering processing on the motion acceleration and the weaving acceleration, where the filtered motion velocity and the filtered weaving acceleration constitute the motion parameter, and the filtered weaving velocity and the filtered weaving acceleration constitute the weaving parameter of the welding gun.
Optionally, the obtaining unit of the present application includes a fourth control module and a fifth control module, where the fourth control module is configured to control an audio acquisition device to acquire welding sound in a welding process in real time, and perform fourier transform processing on the welding sound to obtain the audio frequency spectrum; the fifth control module is used for controlling the scanning equipment to carry out brightness scanning on the arc in the welding process to obtain an arc brightness image, and carrying out image processing on the arc brightness image to obtain the arc brightness frequency spectrum.
It should be noted that, a plurality of the above welding parameters of the present application further include at least one of: weld groove information, molten pool shape information, molten pool temperature information, welding current and welding voltage of the welding robot.
Specifically, the acquiring unit comprises a sixth control module, a seventh control module, an eighth control module, a ninth control module and a tenth control module, wherein the sixth control module is used for controlling the first image acquisition device to acquire the welding seam groove image in real time and carrying out image processing on the welding seam groove image to obtain the welding seam groove information; the seventh control module is used for controlling a second image acquisition device to acquire a molten pool image in real time and carrying out image processing on the molten pool image to obtain the molten pool shape information; the eighth control module is used for controlling a third image acquisition device to acquire a molten pool heat distribution image in real time and carrying out image processing on the molten pool heat distribution image to obtain the molten pool temperature information; the ninth control module is used for controlling a current sensor to collect current data of the welding robot in the welding process in real time and filtering the current data to obtain the welding current; the tenth control module is used for controlling the voltage sensor to collect voltage data of the welding robot in the welding process in real time, and filtering the voltage data to obtain the welding voltage.
Example 3
According to an embodiment of the present application, there is provided a computer-readable storage medium including a stored program, where the program, when executed, controls an apparatus in which the computer-readable storage medium is located to execute the method for determining the welding quality.
Step S101, obtaining welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process;
step S102, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to the historical welding information.
Example 4
An embodiment of the present invention provides a welding quality diagnosis system, including a welding robot and a welding quality determination apparatus, wherein the welding quality determination apparatus includes one or more processors, a memory, a controller, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the above welding quality diagnosis methods.
In a welding quality diagnosis system of the present application, comprising a welding robot and a welding quality determination device, wherein the welding quality determination device comprises one or more processors, memories, controllers, and one or more programs, the one or more programs comprising instructions for performing any of the above welding quality diagnosis methods, first, obtaining welding information comprising a plurality of welding parameters, wherein the plurality of welding parameters comprises a posture change rate of the welding robot during welding, a motion parameter, a welding gun swing parameter, a welding audio frequency spectrum, and an arc luminance spectrum; and then, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an online detection welding system in the prior art, the online detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
Example 5
The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:
step S101, obtaining welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process;
step S102, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to the historical welding information.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.
From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:
1) In the method for determining the welding quality, firstly, welding information comprising a plurality of welding parameters is obtained, wherein the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc brightness spectrum of a welding robot in the welding process; and then, inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an online detection welding system in the prior art, the online detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
2) In the device for determining welding quality, welding information comprising a plurality of welding parameters is obtained through an obtaining unit, wherein the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc brightness spectrum of a welding robot in a welding process; and inputting the welding information into a quality diagnosis model through an input unit for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information. Compared with an online detection welding system in the prior art, the online detection welding system can only analyze a few welding quality parameters which are influenced by welding, and is not comprehensive enough and low in accuracy.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method of determining weld quality, comprising:
acquiring welding information, wherein the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process;
and inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information.
2. The method of claim 1, wherein prior to inputting the weld information into a quality diagnostic model for analytical diagnosis, the method further comprises:
constructing a plurality of neural network models, and training the neural network models by adopting a plurality of groups of data to obtain a plurality of first sub-models, wherein each group of data in the plurality of groups of data comprises historical welding parameters and corresponding historical welding quality information;
and constructing a second submodel, wherein the second submodel is connected with the output ends of all the first submodels, the second submodel is used for determining the qualified rate according to the output result of each first submodel, outputting the welding quality information according to the qualified rate and a preset threshold, outputting the welding quality information representing that the welding quality is qualified under the condition that the qualified rate is greater than or equal to the preset threshold, and outputting the welding quality information representing that the welding quality is unqualified under the condition that the qualified rate is less than the preset threshold, and the qualified rate is the ratio of the number of the output results representing that the welding quality is qualified to the total number of the output results.
3. The method of claim 2, wherein inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is acceptable comprises:
and inputting the welding parameters into the first submodel in one-to-one correspondence, so that the first submodel outputs the output result to the second submodel according to the welding parameters, and the second submodel determines and outputs the welding quality information according to each output result.
4. The method of claim 1, wherein obtaining the pose change rate of the welding robot, the motion parameters, and the gun swing parameters during the welding process comprises:
controlling a first sensor to collect attitude data of the welding robot in real time and filtering the attitude data;
calculating the change rate of the filtered attitude data to obtain the attitude change rate;
controlling a second sensor to acquire the movement speed of the welding robot in each movement direction and the swing speed of the welding gun, and filtering the movement speed and the swing speed to obtain the movement speed of the welding robot and the swing speed of the welding gun;
and controlling a third sensor to acquire motion acceleration of the welding robot in each motion direction and swing acceleration of the welding gun, and filtering the motion acceleration and the swing acceleration, wherein the filtered motion speed and the filtered motion acceleration form the motion parameter, and the filtered swing speed and the filtered swing acceleration form the swing parameter of the welding gun.
5. The method of claim 1, wherein obtaining the welding audio spectrum and the arc brightness spectrum comprises:
controlling an audio acquisition device to acquire welding sound in a welding process in real time, and performing Fourier transform processing on the welding sound to obtain an audio frequency spectrum;
and controlling a scanning device to carry out brightness scanning on the arc in the welding process to obtain an arc brightness image, and carrying out image processing on the arc brightness image to obtain the arc brightness frequency spectrum.
6. The method of any of claims 1 to 5, wherein the plurality of welding parameters further comprises at least one of: weld groove information, weld puddle shape information, weld puddle temperature information, welding current and welding voltage of the welding robot.
7. The method of claim 6, wherein obtaining welding information further comprises at least one of:
controlling first image acquisition equipment to acquire a welding seam groove image in real time, and carrying out image processing on the welding seam groove image to obtain welding seam groove information;
controlling a second image acquisition device to acquire a molten pool image in real time, and carrying out image processing on the molten pool image to obtain the molten pool shape information;
controlling a third image acquisition device to acquire a molten pool heat distribution image in real time, and carrying out image processing on the molten pool heat distribution image to obtain molten pool temperature information;
controlling a current sensor to collect current data of the welding robot in the welding process in real time, and filtering the current data to obtain the welding current;
and controlling a voltage sensor to collect voltage data of the welding robot in the welding process in real time, and filtering the voltage data to obtain the welding voltage.
8. A weld quality determination apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring welding information, the welding information comprises a plurality of welding parameters, and the plurality of welding parameters comprise attitude change rate, motion parameters, welding gun swing parameters, welding audio frequency spectrum and arc light brightness spectrum of a welding robot in the welding process;
and the input unit is used for inputting the welding information into a quality diagnosis model for analysis and diagnosis to obtain welding quality information representing whether the welding quality is qualified, wherein the quality diagnosis model is established according to a plurality of historical welding information and the historical welding quality information corresponding to each piece of historical welding information.
9. A processor, characterized in that the processor is configured to run a program, wherein the program when running performs the method of any of claims 1 to 7.
10. A weld quality diagnostic system, comprising: a welding robot and a welding quality determination apparatus comprising one or more processors, memory, a controller, and one or more programs, wherein,
the one or more programs stored in the memory and configured to be executed by the one or more processors include instructions for performing the weld quality diagnostic method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211183849.8A CN115439463A (en) | 2022-09-27 | 2022-09-27 | Method and device for determining welding quality, processor and welding quality diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211183849.8A CN115439463A (en) | 2022-09-27 | 2022-09-27 | Method and device for determining welding quality, processor and welding quality diagnosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115439463A true CN115439463A (en) | 2022-12-06 |
Family
ID=84249823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211183849.8A Pending CN115439463A (en) | 2022-09-27 | 2022-09-27 | Method and device for determining welding quality, processor and welding quality diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115439463A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436769A (en) * | 2023-12-20 | 2024-01-23 | 山东方垠智能制造有限公司 | Structural part welding quality monitoring method, system, storage medium and equipment |
-
2022
- 2022-09-27 CN CN202211183849.8A patent/CN115439463A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117436769A (en) * | 2023-12-20 | 2024-01-23 | 山东方垠智能制造有限公司 | Structural part welding quality monitoring method, system, storage medium and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10782668B2 (en) | Development of control applications in augmented reality environment | |
| US10997711B2 (en) | Appearance inspection device | |
| KR101986400B1 (en) | System and method for monitoring weld quality | |
| US20190041808A1 (en) | Controller and machine learning device | |
| JP2018181217A (en) | Acceleration/deceleration control apparatus | |
| CN115439463A (en) | Method and device for determining welding quality, processor and welding quality diagnosis system | |
| CN112091472B (en) | Welding process quality fusion judgment method and device | |
| CN115166618B (en) | Current transformer error evaluation method for non-stable output | |
| JP7151547B2 (en) | Predictive control development device, predictive control development method, and predictive control development program | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| Mishra et al. | Industry 4.0 in welding | |
| CN111451608A (en) | Welding method, welding device, storage medium and processor | |
| CN113554645B (en) | Industrial anomaly detection method and device based on WGAN | |
| Bauer | Cloud automation and economic efficiency | |
| CN112763231B (en) | Lane keeping auxiliary system function evaluation method, device, terminal and storage medium | |
| CN109102486B (en) | Surface defect detection method and device based on machine learning | |
| CN116618878A (en) | Pre-welding process parameter determination method, welding quality online prediction method, device and storage medium | |
| Huang et al. | Edge computing-based virtual measuring machine for process-parallel prediction of workpiece quality in metal cutting | |
| KR20240064037A (en) | How to identify and characterize surface defects of objects and cracks in brake discs by artificial intelligence through fatigue testing | |
| CN114638096A (en) | Method, device and equipment for displaying logic among program variables and storage medium | |
| CN113592800A (en) | Image scanning method and device based on dynamic scanning parameters | |
| Laube et al. | Analyzing Arc Welding Techniques improves Skill Level Assessment in Industrial Manufacturing Processes | |
| CN111665740B (en) | Simulation method and device of robot | |
| CN111291464A (en) | Dynamic equivalence method and device for power system | |
| JP7395954B2 (en) | NC data quality judgment device and processing device |
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 |