CN115609112A - Welding parameter determination method, device and medium thereof - Google Patents
Welding parameter determination method, device and medium thereof Download PDFInfo
- Publication number
- CN115609112A CN115609112A CN202211371227.8A CN202211371227A CN115609112A CN 115609112 A CN115609112 A CN 115609112A CN 202211371227 A CN202211371227 A CN 202211371227A CN 115609112 A CN115609112 A CN 115609112A
- Authority
- CN
- China
- Prior art keywords
- welding
- parameters
- quality
- material information
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/095—Monitoring or automatic control of welding parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K9/00—Arc welding or cutting
- B23K9/32—Accessories
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Plasma & Fusion (AREA)
- Mechanical Engineering (AREA)
- General Factory Administration (AREA)
Abstract
The application discloses a method, a device and a medium for determining welding parameters, which relate to the technical field of welding and are used for providing guidance for an actual welding process, and aiming at the problems that the existing welding parameter determination mode has high requirements on technicians, low efficiency and can not ensure quality, the method for determining the welding parameters is provided, a prediction model is trained in advance according to welding material information, the welding parameters and historical data of corresponding quality parameters as a data set, so that the corresponding welding parameters can be deduced reversely through inputting the welding material information and the requirements on the output quality parameters, the expected welding quality of the welding parameters obtained in such a way is ensured, compared with the existing method of repeatedly trial and error and debugging through the experience of the technicians, the efficiency is higher, meanwhile, the output of a large number of unqualified products due to trial production is avoided, unnecessary loss is avoided, and the production requirements of the actual welding process are better met.
Description
Technical Field
The present disclosure relates to the field of welding technologies, and in particular, to a method and an apparatus for determining welding parameters, and a medium thereof.
Background
The welding technology is a key technology in various production and manufacturing processes, and the quality of a finished product is determined by the welding quality in the production process in large part. The quality of welding quality is closely related to the welding parameters set by the welding equipment, and when any one of the material, the material thickness, the size of a welding rod and the like of a welding material is changed, the welding parameters need to be adjusted to obtain better welding quality.
At present, before a welding process is carried out, a technician adjusts welding parameters through personal experience, but the success rate of the parameter adjustment mode is low, the adjustment to a proper parameter can be carried out only by repeatedly trying, the workload is huge, meanwhile, the effect cannot be guaranteed, generally, after the parameters are adjusted, the trial production is continuously carried out for inspection, a large number of unqualified products are caused, and the production is seriously influenced if welding materials are frequently replaced.
Therefore, a method for determining welding parameters is urgently needed by those skilled in the art, and the problems that the adjustment of the welding parameters depending on manual experience is high in requirement on the technical personnel, the efficiency is low, and the welding quality cannot be guaranteed are solved.
Disclosure of Invention
The application aims to provide a welding parameter determination method, a welding parameter determination device and a welding parameter determination medium, so as to solve the problems that the adjustment of welding parameters depending on manual experience is high in requirements on technical personnel, low in efficiency and incapable of ensuring welding quality.
In order to solve the above technical problem, the present application provides a welding parameter determining method, including:
acquiring welding material information;
calling a prediction model; the prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning frame;
and inputting the welding material information into the prediction model to obtain the welding parameters meeting the preset quality standard.
Preferably, the welding material information includes material thickness information and material information;
correspondingly, after the welding material information is obtained, the method further comprises the following steps:
and performing regularization processing on the material information.
Preferably, the quality parameters include welding process stability, quality score and spatter rate;
correspondingly, the preset quality standard comprises the following steps: a first threshold corresponding to a stability of the welding process, a second threshold corresponding to a quality score, and a third threshold corresponding to a spatter rate.
Preferably, the inputting of the welding material information into the prediction model to obtain the welding parameters meeting the preset quality standard comprises:
and inputting the welding material information into the prediction model as characteristic parameters, and acquiring the welding parameters which are output by the prediction model and have the welding process stability higher than a first threshold, the quality score higher than a second threshold and the spattering rate lower than a third threshold.
Preferably, the method further comprises the following steps:
and periodically acquiring welding material data, welding parameter data and corresponding quality parameter data in the actual welding process, and updating a data set to optimize the prediction model.
Preferably, after obtaining the welding parameters meeting the preset quality standard, the method further comprises:
and acquiring station information, and sending the welding parameters to a corresponding station display screen according to the station information.
Preferably, the method further comprises the following steps:
and if the welding parameters meeting the preset quality standard are not obtained, returning to the preset default welding parameters and giving an alarm.
In order to solve the above technical problem, the present application further provides a welding parameter determining apparatus, including:
the information acquisition module is used for acquiring welding material information;
the model calling module is used for calling the prediction model; the prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning frame;
and the parameter prediction module is used for inputting the welding material information into the prediction model so as to obtain the welding parameters meeting the preset quality standard.
Preferably, the welding parameter determination device further includes:
and the data processing module is used for carrying out regularization processing on the material information.
And the model optimization module is used for periodically acquiring welding material data, welding parameter data and corresponding quality parameter data in the actual welding process, and updating the data set so as to optimize the prediction model.
And the parameter display module is used for acquiring the station information and sending the welding parameters to the corresponding station display screen according to the station information.
And the abnormity warning module is used for returning to preset default welding parameters and giving a warning if the welding parameters meeting the preset quality standard are not obtained.
In order to solve the above technical problem, the present application further provides a welding parameter determining apparatus, including:
a memory for storing a computer program;
a processor for implementing the steps of the welding parameter determination method as described above when executing a computer program.
In order to solve the above technical problem, the present application further provides a computer readable storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the welding parameter determination method as described above.
According to the welding parameter determining method, the supervised multi-output regression model is trained on the basis of the deep learning framework by taking the historical data of the welding material information, the welding parameters and the corresponding quality parameters as a data set in advance, so that in the subsequent welding process, the input welding material information and the quality parameters corresponding to the welding parameters can be predicted through the prediction model, the welding parameters can be obtained by taking the preset quality standard as the output target of the prediction model and taking the current welding material information as the characteristic parameters, and the obtained welding parameters can meet the quality acceptance requirements of the actual welding process when the trained prediction model has enough performance.
The welding parameter determination device and the computer-readable storage medium provided by the application correspond to the method, and the effects are the same as those of the method.
Drawings
In order to more clearly illustrate the embodiments of the present application, the drawings needed for the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings can be obtained by those skilled in the art without inventive effort.
FIG. 1 is a flow chart of a method of determining welding parameters provided by the present invention;
FIG. 2 is a flow chart of another method of weld parameter determination provided by the present invention;
FIG. 3 is a block diagram of a welding parameter determination apparatus according to the present invention;
fig. 4 is a block diagram of another welding parameter determination apparatus provided in the present invention.
Detailed Description
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 a part of the embodiments of the present application, and not all the embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the present application.
The core of the application is to provide a welding parameter determination method, a welding parameter determination device and a medium thereof.
In order that those skilled in the art will better understand the disclosure, the following detailed description is given with reference to the accompanying drawings.
At present, welding parameters are determined mainly through experience of workers, trial production is carried out, then the welding parameters are repeatedly debugged according to the welding quality of the produced product until the welding quality of the produced product meets the requirements, and the welding parameter determination process is finished. The method has high requirements on technicians, and the processes of debugging welding parameters and trial production waste a large amount of manpower, material resources and time, cause unnecessary loss while having low efficiency, and particularly, objects to be welded, such as a vehicle body-in-white, have thousands of welding points, and the welding materials and the welding parameters required by different welding points are not necessarily the same, so that all the welding parameters of the whole body-in-white are more difficult to determine.
In order to solve the above problem, the present application provides a welding parameter determining method, as shown in fig. 1, including:
s11: and acquiring welding material information.
S12: and calling a prediction model.
The prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning frame;
s13: and inputting the welding material information into the prediction model to obtain the welding parameters meeting the preset quality standard.
In the actual welding process, the welding process of different products is different, and correspondingly required welding materials and welding parameters are also different.
Also exemplified for the production of body-in-white, weld material information includes, but is not limited to: the method comprises the following steps that information such as the number of layers, the thickness and the material of a welded plate, whether glue is applied or not and the like are taken into consideration, and the welding material information is preferably selected to be material thickness information and material information in view of the influence effect of different welding material information on welding quality and the convenience in subsequent prediction model training and calculation; welding parameters include, but are not limited to: welding current, electrode pressure, welding duration and grinding times; likewise, quality parameters used to assess weld quality include, but are not limited to: stability in welding process, quality score, spattering rate, half-failure qualification rate, full-failure qualification rate and eddy current measurement qualification rate.
It should be noted that the welding material information and the welding parameters may be obtained from a device, such as a group control device in a production plant, which plays a role in controlling and supervising the production process, for example, the group control device may collect actual welding data including the welding material information and the welding parameters.
It should be noted that, for the acquisition of the quality parameters, since the welding quality is relatively determined according to the actual situation, before the prediction model is not established, manual inspection is performed by sampling, breaking and disassembling and the like, the original quality parameter data is recorded, and the judgment can be performed on whether the welding process is stable, the quantitative score of the welding quality, the probability of the spattering situation occurring in the welding process and the like, so as to obtain the original data of the quality parameters.
After a sufficient amount of data is obtained, the prediction model can be trained through mechanical learning, so that the understanding is easy, the welding material information and the welding parameters correspond to the welding quality parameters, namely, the data set is a data set with input results, the corresponding machine learning mode is supervised learning, the welding material information and the welding parameters serve as input, and the quality parameters serve as output.
Since the welding material information, the welding parameters, and the quality parameters as the output include a plurality of pieces of sub information, the established prediction model is a multiple-input multiple-output model, and can be realized by a plurality of machine learning methods, such as establishing a plurality of multiple-input single-output models, a wrapper multiple-input regression algorithm (multioutputregresor), and an auto-learning framework (autosklearn, autokeras, etc.) preferred by the above embodiments. Technicians can select a proper method to establish the prediction model according to the requirements of an actual manufacturing process and a welding process, and the method for judging the quality of the prediction effect can be used for judging by taking Mean Absolute Error (MAE) as an evaluation index. For example, when the application scenario is a body-in-white manufacturing process of a vehicle, a multi-layer neural network model established by an automatic learning framework autokeras can be preferably used as the prediction model.
In addition, since various welding materials are involved in the welding process, for example, more than 100 different materials are involved in the vehicle body-in-white processing process, and the material name is not standard as the material information, and the subsequent determination of the welding parameters cannot be realized, the present embodiment provides a preferred embodiment: and carrying out regularization processing on the material information.
Specifically, the method can be implemented by characterizing specific parameters of the material, such as yield strength, tensile strength, hardness, elongation after fracture, and other parameters related to the material of different materials, and selecting different regularization treatments according to the requirements of different welding processes.
It should be further noted that, even if the same characteristic parameter of the same material is used, the specific numerical values of different welding materials are not completely consistent and are mostly in a certain range, which brings certain trouble to the training and prediction of the subsequent model, so that in the process of regularizing the material information, a certain representative characteristic value can be used as a specific value of a certain characteristic parameter of a certain material, so as to simplify the subsequent process and improve the prediction accuracy.
According to the welding parameter determination method, through the pre-trained prediction model, after welding material information is input as characteristic parameters, corresponding welding parameters can be reversely deduced according to output quality parameters meeting preset standards, namely, the welding parameters with the predicted welding quality meeting actual engineering requirements are determined, the welding parameters are recommended to each welding station as preferred welding parameters, guidance is provided for the actual welding process, improvement of the welding quality is facilitated, manual repeated debugging of technicians is not relied on, requirements for the technicians are low, efficiency is higher, repeated trial production is not needed, unnecessary loss is avoided, and requirements of actual welding production are better met.
As can be seen from the above examples, the weld quality parameters for different welding processes are not necessarily the same, but based on common and general requirements, this example provides a preferred embodiment, and the above quality parameters include: stability of the welding process, quality scores and spatter rates.
The stability of the welding process, i.e. the stability of the entire welding process, is evaluated, generally expressed in percentages, a higher value indicating a better stability of the weld; the quality score is determined according to actual welding needs, the quality scores of the same welding finished product under different application scenes may be different, and are generally represented by a score, wherein the higher the score is, the better the welding quality is, and in one possible embodiment, the full score of the quality score is 120; the spatter rate is a probability of spattering of metal or the like during welding, and is also expressed in percentage, and generally, the lower the spatter rate, the better.
Corresponding to the above-mentioned preferred solutions for the quality parameters, the preset quality criteria may preferably be three preset threshold values, corresponding to the above-mentioned welding process stability, quality score and spattering rate, respectively. The higher the stability and the quality score of the welding process, the better the welding process stability and the quality score are, the greater the corresponding threshold value is, the preset quality standard is met, and the smaller the spattering rate is, the better the spattering rate is, the less the corresponding threshold value is, the preset quality requirement is met.
More specifically, the present embodiment further provides an instantiated application scenario example, and for the welding manufacturing process of the vehicle body in white, the first threshold corresponding to the stability of the welding process is 95%, that is, the stability exceeding 95% is considered to meet the standard; the second threshold corresponding to the quality score is 103, that is, if the quality score exceeds 103, the criterion is considered to be satisfied; the third threshold value for the spattering rate is 5%, i.e. a spattering rate below 5% is considered to fulfill the criterion. Further, when all the three quality parameters meet the standard, the corresponding welding parameter is considered to meet the preset quality standard and can be used as a recommended welding parameter to guide the actual welding process.
On the basis of the embodiment, the welding parameters meeting the preset quality standard are obtained through the prediction model, namely: and inputting the current welding material information serving as a characteristic parameter into a prediction model, and calculating a welding parameter by taking the process stability larger than a first threshold, the quality score larger than a second threshold and the spattering rate lower than a third threshold as target parameters to obtain the welding parameter, namely the welding parameter which is preferably used for guiding the actual welding production.
It should be noted that, as can be seen from the above, the prediction accuracy of the prediction model is the most direct influencing factor for determining the welding quality of the welding parameters determined by the welding parameter determination method provided by the present application, so for improving the accuracy of the prediction model, the present embodiment further provides a preferred scheme:
and periodically acquiring welding material data, welding parameter data and corresponding quality parameter data in the actual welding process, and updating a data set to optimize the prediction model.
Besides the optimal scheme that the prediction accuracy of the prediction model is improved by continuously acquiring new actual welding data to increase the number of data set samples, the multi-output regression prediction model realized based on the deep learning framework has self-learning capability, and can continuously learn through the prediction of self welding parameters to continuously optimize a mechanism model, so that the prediction accuracy is further improved.
According to the preferred scheme provided by the embodiment, a relatively universal quality parameter combination is provided, a corresponding threshold value is preset for each quality parameter, and whether the preset quality standard is met or not is determined through comparison with the corresponding threshold value, so that welding parameters with relatively good expected quality are determined according to a prediction model, and guidance is provided for an actual welding process. In addition, in order to ensure the guiding effect of the method and improve the welding quality, the embodiment also updates the data set by continuously acquiring new actual welding data, and continuously optimizes the mechanism model by combining the self-learning capability of the regression model so as to improve the accuracy of prediction, thereby ensuring the welding quality according to the optimal welding parameters of the prediction model.
It is readily appreciated that in a practical production environment, a production shop is usually welding manufacturing in units of stations, and welding processes may differ from station to station, so that for one station it is only interested in the welding parameters required by the welding process currently being performed by the station. Therefore, in order to provide guidance effect for the method in a targeted manner, this embodiment provides a preferred embodiment, and after obtaining the welding parameters meeting the preset quality standard, as shown in fig. 2, the method further includes:
s14: and acquiring station information, and sending the welding parameters to a corresponding station display screen according to the station information.
In a production workshop, a station is usually provided with a plurality of group control devices, and the group control devices are used for controlling each welding device for realizing welding, so that not only actual welding data but also corresponding station information can be obtained from the group control devices so as to distinguish which station the group control device belongs to, and similarly, which station the welding data corresponds to. In addition, a station display screen is also usually arranged at a station of the production workshop and used for providing some necessary information for a worker to check, so that the station corresponding to the welding parameters can be determined through the station information and then sent to the station display screen at the corresponding station to pertinently guide technicians at the corresponding station to perform welding operation.
It should be noted that, in the welding manufacturing process of the vehicle body in white, the welding operation is performed with the welding spot as a basic unit, and the welding spot is uniquely represented by the welding spot identification number (ID), so that the correspondence relationship between the data such as each welding parameter can be simply realized by the welding spot ID.
According to the preferred scheme provided by the embodiment, the station display screens arranged at all stations in the existing workshop are utilized to respectively send and display the welding data corresponding to different stations, so that guidance is provided for the welding operation of all stations in a targeted manner, and the improvement of the welding efficiency and the welding quality is facilitated.
Because the working conditions in the actual manufacturing process are constantly changed, the welding process may be changed, and thus a part of welding points are newly added, for the insufficient sample historical data of the newly added welding points, the welding parameters predicted by the prediction model are not predicted accurately or cannot be predicted to obtain the welding parameters meeting the preset quality standard, at this time, in order to ensure the guiding function of the method, as shown in fig. 2, the embodiment further provides a preferred embodiment:
s15: and if the welding parameters meeting the preset quality standard are not obtained, returning to the preset default welding parameters and giving an alarm.
At this time, if the preferred solution of step S14 is established, the welding parameters sent to the display screen of the corresponding station in step S14 for display are the default welding parameters determined in step S15.
In fact, step S14 and step S15 may also be implemented separately, which is only one possible implementation, and when step S14 and step S15 are implemented separately and do not affect each other, they have no precedence relationship with each other.
When the welding parameters meeting the quality standard can be acquired, the probability indicates that sample data in the prediction model data set is not enough, the prediction capability of the newly added working condition is still to be improved, at the moment, the default welding parameters which are recorded in advance can be returned, the default welding parameters can be realized through a group of basic welding parameters summarized in the actual welding process, and can also be realized through other modes, but because the default welding parameters are not as guaranteed in the welding quality as the welding parameters obtained in the above mode, an alarm needs to be given to prompt technical staff to carry out differentiation processing on the welding points. In addition, the alarm information is also helpful for prompting related personnel to collect the actual welding data of the welding spot, and enriches the data set of the prediction model so as to optimize the mechanism of the prediction model and improve the effective prediction range.
In the above embodiments, a welding parameter determination method is described in detail, and the present application also provides an embodiment corresponding to a welding parameter determination apparatus. It should be noted that the present application describes the embodiments of the apparatus portion from two perspectives, one is from the perspective of the function module, and the other is from the perspective of the hardware.
Based on the angle of the function module, as shown in fig. 3, the present embodiment provides a welding parameter determination apparatus, including:
an information acquisition module 21, configured to acquire welding material information;
a model calling module 22 for calling the prediction model; the prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning frame;
and the parameter prediction module 23 is used for inputting the welding material information into the prediction model so as to obtain the welding parameters meeting the preset quality standard.
Preferably, the welding parameter determination device further includes:
and the data processing module is used for carrying out regularization processing on the material information.
And the model optimization module is used for periodically acquiring welding material data, welding parameter data and corresponding quality parameter data in the actual welding process, and updating the data set so as to optimize the prediction model.
And the parameter display module is used for acquiring the station information and sending the welding parameters to the corresponding station display screen according to the station information.
And the abnormity warning module is used for returning to preset default welding parameters and giving a warning if the welding parameters meeting the preset quality standard are not obtained.
Since the embodiments of the apparatus portion and the method portion correspond to each other, please refer to the description of the embodiments of the method portion for the embodiments of the apparatus portion, which is not repeated here.
In the welding parameter determination device provided by the embodiment, the information acquisition module is used for acquiring the welding material information in the welding process; furthermore, through the model calling module and the parameter prediction module, the corresponding welding parameters are reversely deduced by the pre-trained prediction model according to the output quality parameters meeting the preset standard, so that the welding parameters with the expected welding quality meeting the actual engineering requirements are determined and recommended to each welding station as the optimal welding parameters, guidance is provided for the actual welding process, and the improvement of the welding quality is facilitated. Simultaneously, this device need not to rely on technical staff's manual debugging repeatedly, and the requirement to technical staff also reduces by a wide margin when efficiency is higher, also need not to produce a large amount of unqualified products because of repeated trial production, has avoided the unnecessary loss, has satisfied actual welding production's requirement better.
Fig. 4 is a structural diagram of a welding parameter determination apparatus according to another embodiment of the present application, and as shown in fig. 4, a welding parameter determination apparatus includes: a memory 30 for storing a computer program;
a processor 31 for implementing the steps of a welding parameter determination method as described in the above embodiments when executing a computer program.
The welding parameter determination device provided by the embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, or a desktop computer.
The processor 31 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The Processor 31 may be implemented in hardware using at least one of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), and a Programmable Logic Array (PLA). The processor 31 may also include a main processor and a coprocessor, where the main processor is a processor for Processing data in a wake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 31 may be integrated with a Graphics Processing Unit (GPU) which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, processor 31 may further include an Artificial Intelligence (AI) processor for processing computational operations related to machine learning.
Memory 30 may include one or more computer-readable storage media, which may be non-transitory. Memory 30 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 30 is at least used for storing a computer program 301, wherein after being loaded and executed by the processor 31, the computer program can implement the relevant steps of a welding parameter determination method disclosed in any one of the foregoing embodiments. In addition, the resources stored in the memory 30 may also include an operating system 302, data 303, and the like, and the storage may be transient storage or permanent storage. Operating system 302 may include Windows, unix, linux, and the like. Data 303 may include, but is not limited to, a welding parameter determination method, and the like.
In some embodiments, a welding parameter determination device may also include a display screen 32, an input-output interface 33, a communication interface 34, a power source 35, and a communication bus 36.
Those skilled in the art will appreciate that the configuration shown in FIG. 4 does not constitute a limitation of a welding parameter determination device and may include more or fewer components than those shown.
The welding parameter determining device provided by the embodiment of the application comprises a memory and a processor, wherein when the processor executes a program stored in the memory, the following method can be realized: a welding parameter determination method.
According to the welding parameter determination device provided by the embodiment, the processor executes the computer program stored in the memory, so that the acquired material information is input into the prediction model through the pre-trained prediction model, the welding parameters with the expected quality meeting the preset standard can be determined according to the output, and are recommended to each welding station as the optimal welding parameters, guidance is provided for the actual welding process, and the improvement of the welding quality of the actual welding production is facilitated. Simultaneously, this device need not to rely on technical staff's manual debugging repeatedly, and the requirement to technical staff also reduces by a wide margin when efficiency is higher, also need not to produce a large amount of unqualified products because of repeated trial production, has avoided the unnecessary loss, has satisfied actual welding production's requirement better.
Finally, the application also provides a corresponding embodiment of the computer readable storage medium. The computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps as set forth in the above-mentioned method embodiments.
It is to be understood that if the method in the above embodiments is implemented in the form of software functional units and sold or used as a stand-alone product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, which are essential or part of the prior art, or all or part of the technical solutions may be embodied in the form of a software product, which is stored in a storage medium and executes all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In the computer-readable storage medium provided by this embodiment, when the stored computer program is executed, the obtained material information may be input into the prediction model through the pre-trained prediction model, so that the welding parameters whose expected quality meets the preset standard may be determined according to the output, and the welding parameters may be recommended to each welding station as the preferred welding parameters, thereby providing guidance for the actual welding process, and facilitating improvement of the welding quality of the actual welding production. Simultaneously, this device need not to rely on technical staff's manual debugging repeatedly, also reduces by a wide margin to technical staff's requirement when efficiency is higher, also need not to output a large amount of unqualified products because of repeated production of trying, has avoided the unnecessary loss, has satisfied actual welding production's requirement better.
The welding parameter determining method, the welding parameter determining device and the welding parameter determining medium provided by the application are described in detail above. The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed in the embodiment corresponds to the method disclosed in the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
It is further noted that, in the present specification, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, 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 like elements in a process, method, article, or apparatus that comprises the element.
Claims (10)
1. A method of determining welding parameters, comprising:
acquiring welding material information;
calling a prediction model; the prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning framework;
and inputting the welding material information into the prediction model to obtain welding parameters meeting preset quality standards.
2. The welding parameter determination method according to claim 1, wherein the welding material information includes material thickness information and material information;
correspondingly, after the acquiring the welding material information, the method further comprises the following steps:
and performing regularization processing on the material information.
3. The welding parameter determination method of claim 1, wherein the quality parameters include welding process stability, quality score, and spatter rate;
correspondingly, the preset quality standard comprises the following steps: a first threshold corresponding to a stability of the welding process, a second threshold corresponding to a quality score, and a third threshold corresponding to a spatter rate.
4. The welding parameter determination method of claim 3, wherein said inputting the welding material information into the predictive model to obtain welding parameters that meet a predetermined quality criterion comprises:
and inputting the welding material information into the prediction model as a characteristic parameter, and acquiring the welding parameters which are output by the prediction model and have the welding process stability higher than the first threshold, the quality score higher than the second threshold and the spattering rate lower than the third threshold.
5. The welding parameter determination method of claim 1, further comprising:
and periodically acquiring welding material data, welding parameter data and corresponding quality parameter data in the actual welding process, and updating the data set to optimize the prediction model.
6. The welding parameter determination method of claim 1, further comprising, after said obtaining welding parameters that meet a predetermined quality criterion:
and acquiring station information, and sending the welding parameters to a corresponding station display screen according to the station information.
7. The welding parameter determination method of claim 1, further comprising:
and if the welding parameters meeting the preset quality standard are not obtained, returning to preset default welding parameters and giving an alarm.
8. A welding parameter determination device, comprising:
the information acquisition module is used for acquiring welding material information;
the model calling module is used for calling the prediction model; the prediction model is a supervised multi-output regression model obtained by taking historical data of welding material information, welding parameters and quality parameters as a data set in advance and training on the basis of a deep learning framework;
and the parameter prediction module is used for inputting the welding material information into a prediction model so as to obtain the welding parameters meeting the preset quality standard.
9. A welding parameter determination device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the welding parameter determination method according to any one of claims 1 to 7 when executing said computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the welding parameter determination method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211371227.8A CN115609112A (en) | 2022-11-03 | 2022-11-03 | Welding parameter determination method, device and medium thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211371227.8A CN115609112A (en) | 2022-11-03 | 2022-11-03 | Welding parameter determination method, device and medium thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115609112A true CN115609112A (en) | 2023-01-17 |
Family
ID=84875826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211371227.8A Pending CN115609112A (en) | 2022-11-03 | 2022-11-03 | Welding parameter determination method, device and medium thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115609112A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116984771A (en) * | 2023-08-16 | 2023-11-03 | 广州盛美电气设备有限公司 | Automatic welding control method, device, equipment and medium for power distribution cabinet |
| CN117399859A (en) * | 2023-12-15 | 2024-01-16 | 南昌佛吉亚排气控制技术有限公司 | Automobile part welding control method and device |
-
2022
- 2022-11-03 CN CN202211371227.8A patent/CN115609112A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116984771A (en) * | 2023-08-16 | 2023-11-03 | 广州盛美电气设备有限公司 | Automatic welding control method, device, equipment and medium for power distribution cabinet |
| CN117399859A (en) * | 2023-12-15 | 2024-01-16 | 南昌佛吉亚排气控制技术有限公司 | Automobile part welding control method and device |
| CN117399859B (en) * | 2023-12-15 | 2024-05-10 | 南昌佛吉亚排气控制技术有限公司 | Automobile part welding control method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115609112A (en) | Welding parameter determination method, device and medium thereof | |
| US11675649B2 (en) | Fault prediction method, apparatus and storage medium | |
| US20210166181A1 (en) | Equipment management method, device, system and storage medium | |
| CN110991495A (en) | Method, system, medium, and apparatus for predicting product quality in manufacturing process | |
| CN116184988B (en) | Multi-mode data-based fault prediction method, device, equipment and storage medium | |
| CN113361958A (en) | Defect early warning method and system | |
| CN115994308B (en) | Numerical control machine tool fault identification method, system, equipment and medium based on meta learning | |
| CN112819107A (en) | Artificial intelligence-based fault prediction method for gas pressure regulating equipment | |
| CN116184930A (en) | Fault prediction method, device, equipment and storage medium for numerical control machine tool | |
| CN113722134A (en) | Cluster fault processing method, device and equipment and readable storage medium | |
| CN110084490A (en) | The method of quality Risk-warning between a kind of volume hired car | |
| CN113312244A (en) | Fault monitoring method, equipment, program product and storage medium | |
| CN115622867A (en) | Industrial control system safety event early warning classification method and system | |
| CN113673600A (en) | Industrial signal abnormity early warning method, system, storage medium and computing equipment | |
| CN116880337A (en) | Alarm auxiliary decision-making method for centralized control center monitoring system of river basin step power plant | |
| CN114862099B (en) | Continuous casting quality prejudging model online system based on rule engine | |
| CN108737164B (en) | Method and device for filtering real-time alarm of telecommunication network | |
| CN115758269A (en) | Method and system for determining opening state of safety valve of hydraulic support | |
| CN111190401A (en) | Instruction scheduling method, hydraulic engineering control method, equipment and medium | |
| CN112863133A (en) | Alarm system, alarm method and computer readable storage medium | |
| CN115230727A (en) | Traveling deviation prediction method and device and working machine | |
| CN114399209A (en) | Drilling operation risk prediction method, system and equipment based on edge cloud integration | |
| CN112966913A (en) | Enterprise quality credit data analysis method and system | |
| KR102550417B1 (en) | Apparatus and method for notifying calibration alarms for cnc machine device | |
| CN112632281B (en) | Fusion delimitation method and device based on early warning complaint data |
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 |