CN115146530A - Method, apparatus, medium, and program product for constructing welding quality detection model - Google Patents
Method, apparatus, medium, and program product for constructing welding quality detection model Download PDFInfo
- Publication number
- CN115146530A CN115146530A CN202210675530.0A CN202210675530A CN115146530A CN 115146530 A CN115146530 A CN 115146530A CN 202210675530 A CN202210675530 A CN 202210675530A CN 115146530 A CN115146530 A CN 115146530A
- Authority
- CN
- China
- Prior art keywords
- welding
- data
- target
- weld
- quality detection
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Fuzzy Systems (AREA)
- Quality & Reliability (AREA)
- Resistance Welding (AREA)
- General Factory Administration (AREA)
Abstract
An object of the present application is to provide a method, an apparatus, a medium, and a program product for constructing a welding quality inspection model, the method including: responding to a welding quality detection model construction operation initiated by a target user based on a target welding task, and acquiring first welding data and first welding seam label data; determining a welding data sample set based on selection of the first welding data by the target user; extracting a plurality of welding characteristic information from a welding data sample set; determining a plurality of target welding characteristic information selected by a target user; and obtaining a welding quality detection model by utilizing automatic machine learning training according to the plurality of target welding characteristic information and the target first welding seam label data. The welding quality detection model is established based on data selection of welding process personnel, the professional knowledge of the welding process personnel is fully utilized, the welding quality detection model can be established and updated only by the welding process personnel, and the learning cost of the welding process personnel for establishing and using the welding quality detection model is reduced.
Description
Technical Field
The application relates to the technical field of welding, in particular to a technology for constructing a welding quality detection model.
Background
The welding process is accompanied with complex physical and chemical changes, and is widely applied to the industries of automobiles, pressure vessels, machinery, shipbuilding and the like. The traditional weld quality detection mode mainly comprises post-welding nondestructive detection, such as X-ray, ultrasonic, visual inspection and the like. However, the latter method has low efficiency and cannot fully cover the field, and the problem cannot be found in the first time, so that the cost is wasted. In recent years, real-time online detection of welding quality has become an important research direction in various colleges and institutions.
Disclosure of Invention
It is an object of the present application to provide a method, apparatus, medium, and program product for constructing a weld quality inspection model.
According to one aspect of the present application, there is provided a method for constructing a weld quality inspection model, the method comprising:
responding to a welding quality detection model construction operation initiated by a target user based on a target welding task, and acquiring first welding data and first welding seam label data corresponding to the first welding data from a target database;
determining a welding data sample set based on the selection operation of the target user on the first welding data;
extracting a plurality of welding characteristic information from the welding data sample set, wherein the welding characteristic information comprises basic welding characteristic information and welding mechanism characteristic information;
determining a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information;
and obtaining the welding quality detection model through automatic machine learning training according to the plurality of target welding characteristic information and the target welding seam label data corresponding to the welding data sample set.
According to one aspect of the present application, there is provided a computer apparatus for constructing a weld quality inspection model, comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of any of the methods described above.
According to an aspect of the application, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of any of the methods described above.
According to an aspect of the application, there is provided a computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of any of the methods described above.
According to an aspect of the present application, there is provided an apparatus for constructing a welding quality inspection model, the apparatus including:
the one-to-one module is used for responding to the construction operation of a welding quality detection model initiated by a target user based on a target welding task, and acquiring first welding data and first welding seam label data corresponding to the first welding data from a target database;
a second module for determining a welding data sample set based on a selection operation of the target user on the first welding data;
the three modules are used for extracting a plurality of welding characteristic information from the welding data sample set, wherein the welding characteristic information comprises basic welding characteristic information and welding mechanism characteristic information;
a fourth module, configured to determine a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information;
and the first module and the fifth module are used for obtaining the welding quality detection model through automatic machine learning training according to the target welding characteristic information and the target welding seam label data corresponding to the welding data sample set.
Compared with the prior art, the method and the device have the advantages that the first welding data and the first welding seam label data corresponding to the first welding data are obtained from the target database through the construction operation of the welding quality detection model initiated by the target user based on the target welding task; determining a welding data sample set based on the selection operation of the target user on the first welding data; extracting a plurality of weld signature information from the set of weld data samples; determining a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information; and obtaining the welding quality detection model through automatic machine learning training according to the target welding characteristic information and the target first weld label data corresponding to the welding data sample set. The welding quality detection model is established based on the data selection of the target user engaged in the welding work, the professional knowledge of welding process personnel can be fully utilized, the welding process personnel can complete the establishment and the update of the welding quality detection model only by relying on the welding process personnel, and the learning cost of the welding quality detection model established and used by the process personnel is reduced.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 illustrates a flow diagram of a method for constructing a weld quality inspection model according to one embodiment of the present application;
FIG. 2 illustrates a voltage graph according to one embodiment of the present application;
FIG. 3 shows a current profile according to an embodiment of the present application;
FIG. 4 illustrates a gas flow graph according to an embodiment of the present application;
FIG. 5 illustrates a basic weld data statistics presentation in accordance with one embodiment of the present application;
FIG. 6 illustrates a quality data correlation thermodynamic diagram according to one embodiment of the present application;
FIG. 7 illustrates a probability density distribution graph according to one embodiment of the present application;
FIG. 8 shows a schematic U-I phase diagram analysis according to an embodiment of the present application;
FIG. 9 illustrates a schematic diagram of a short circuit transition analysis according to an embodiment of the present application;
FIG. 10 illustrates an envelope traceback diagram, according to an embodiment of the present application;
FIG. 11 illustrates a weld mechanism signature configuration diagram according to one embodiment of the present application;
FIG. 12 illustrates a block diagram of an apparatus for constructing a weld quality inspection model, according to one embodiment of the present application;
FIG. 13 illustrates an exemplary system that can be used to implement the various embodiments described in this application.
The same or similar reference numbers in the drawings identify the same or similar elements.
Detailed Description
The present application is described in further detail below with reference to the attached figures.
In a typical configuration of the present application, the terminal, the device serving the network, and the trusted party each include one or more processors (e.g., central Processing Units (CPUs)), input/output interfaces, network interfaces, and memory.
The Memory may include forms of volatile Memory, random Access Memory (RAM), and/or non-volatile Memory in a computer-readable medium, such as Read Only Memory (ROM) or Flash Memory. Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement 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 (PCM), programmable Random Access 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 Disc (DVD) or other optical storage, magnetic tape 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.
The device referred to in the present application includes, but is not limited to, a user equipment, a network device, or a device formed by integrating a user equipment and a network device through a network. The user equipment includes, but is not limited to, any mobile electronic product capable of performing human-computer interaction with a user (e.g., human-computer interaction through a touch panel), such as a smart phone, a tablet computer, and the like, and the mobile electronic product may employ any operating system, such as an Android operating system, an iOS operating system, and the like. The network Device includes an electronic Device capable of automatically performing numerical calculation and information processing according to a preset or stored instruction, and the hardware includes, but is not limited to, a microprocessor, an Application Specific Integrated Circuit (ASIC), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), an embedded Device, and the like. The network device includes but is not limited to a computer, a network host, a single network server, a plurality of network server sets or a cloud of a plurality of servers; here, the Cloud is composed of a large number of computers or web servers based on Cloud Computing (Cloud Computing), which is a kind of distributed Computing, one virtual supercomputer consisting of a collection of loosely coupled computers. Including, but not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a VPN network, a wireless Ad Hoc network (Ad Hoc network), etc. Preferably, the device may also be a program running on the user device, the network device, or a device formed by integrating the user device and the network device, the touch terminal, or the network device and the touch terminal through a network.
Of course, those skilled in the art will appreciate that the foregoing is by way of example only, and that other existing or future devices, which may be suitable for use in the present application, are also encompassed within the scope of the present application and are hereby incorporated by reference.
In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Fig. 1 shows a flowchart of a method for constructing a weld quality inspection model according to an embodiment of the present application, the method including step S11, step S12, step S13, step S14, and step S15. In step S11, in response to a welding quality detection model construction operation initiated by a target user based on a target welding task, the device 1 acquires first welding data and first weld label data corresponding to the first welding data from a target database; in step S12, the device 1 determines a welding data sample set based on the selection operation of the target user on the first welding data; in step S13, the device 1 extracts a plurality of welding characteristic information from the welding data sample set, where the welding characteristic information includes basic welding characteristic information and welding mechanism characteristic information; in step S14, the device 1 determines a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information; in step S15, the device 1 obtains the welding quality detection model through automatic machine learning training according to the target welding characteristic information and the target weld label data corresponding to the welding data sample set.
In step S11, in response to a welding quality detection model construction operation initiated by a target user based on a target welding task, the device 1 obtains first welding data and first weld label data corresponding to the first welding data from a target database. In some embodiments, the apparatus 1 is an apparatus for performing training of a weld quality detection model. In some embodiments, the target database is used for storing welding data acquired by a high-frequency acquisition gateway and various sensors (e.g., a voltage sensor, a current sensor, an airflow sensor, or the like) in a production environment and weld label data corresponding to the welding data. The welding data includes, but is not limited to, voltage, current, gas flow, wire feed speed. The weld label data includes weld normality or weld abnormality. In some embodiments, the target database can be used for continuously collecting new welding data and corresponding welding seam label data from an actual welding production process, so that a target user can continuously iterate a welding quality detection model based on the newly collected data based on the current welding task requirement, and the problem of insufficient model training due to few model training samples in the prior art is solved. In some embodiments, the target user includes a user performing the target welding task, e.g., a welding production process person to whom the target welding task corresponds. The device 1 may obtain the corresponding first welding data and the first weld label data corresponding to the first welding data from the target database to construct the welding quality detection model based on the welding quality detection model constructing operation initiated by the target user. The first welding data acquired by the equipment 1 is matched with the target welding task so as to ensure the detection accuracy of the constructed welding quality detection model.
In step S12, the device 1 determines a welding data sample set based on the selection operation of the first welding data by the target user. In some embodiments, due to the occurrence of arcing, repeated welding of the weld joint, etc. during the welding process, in order to ensure the accuracy of the subsequently determined welding characteristic information, the apparatus 1 may present a chart (for example, refer to the voltage, current, and gas flow graphs shown in fig. 2 to 4) about the first welding data to the target user, and the target user may select the better welding data by intercepting or splicing the first welding data according to the actual welding situation and by combining the statistical analysis chart, so as to determine the corresponding welding data sample set.
In some embodiments, the step S12 includes: the equipment 1 determines to form welding data sample set welding sample data based on the selection operation of the target user on the first welding data; determining and presenting statistical information corresponding to the welding sample data so that the target user can screen the welding sample data based on the statistical information; and determining the screened target welding sample data according to the screening operation of the target user on the welding sample data, and determining a welding data sample set according to the target welding sample data and the target welding seam label data corresponding to the target welding sample data. In some embodiments, the target user who performs the target welding task is used to guide the construction of the welding quality detection model, so that the welding experience and knowledge of the target user in the welding field can be fully utilized to construct a more reasonable and interpretable welding quality detection model. Meanwhile, the target user dominates model construction and model application, and the learning cost of the welding quality detection model application in a floor mode is reduced.
In some embodiments, the device 1 may perform a preprocessing of the first welding data to preliminarily determine a welding data sample set based on a selection operation of the first welding data by the target user. For example, the device 1 may preprocess the first welding data based on a preprocessing method selected by the target user for the first welding data, so as to preliminarily screen out welding sample data constituting the welding data sample set. The preprocessing methods include, but are not limited to, data cleansing, data denoising. In some embodiments, the apparatus 1 performs a descriptive analysis on the welding sample data to determine statistical information corresponding to the welding sample data, including, but not limited to, welding data base statistics (e.g., maximum, minimum, variance, etc.), quality data correlation thermodynamic diagrams, parameter distributions. Also, referring to the basic statistical data diagram of the weld data, the quality factor correlation thermodynamic diagram, the probability density distribution graph, and the weld data graphs of fig. 2-4 shown in fig. 5-7, the apparatus 1 graphically presents the relevant statistical information and the weld sample data to the target user. The device 1 may assist the target user in screening and determining the target welding sample data through the presented statistical information corresponding to the welding sample data, and further determine the welding data sample set. In some embodiments, the operation of filtering the welding sample data by the target user includes, but is not limited to, the target user intercepting or splicing the welding sample data.
It should be understood by those skilled in the art that the above statistical information is only an example, and other existing or future statistical information, such as may be applicable to the present embodiment, should be included in the scope of the present application, and is hereby incorporated by reference.
In some embodiments, the apparatus 1 may further screen the set of welding data samples for target welding sample data. The device 1 may analyze the target welding sample data by using a welding data analysis method selected by a target user, and determine and present welding analysis information about the target welding sample data. The welding data analysis method comprises a method for analyzing welding data from multiple dimensions such as welding quality, stability or normativity and the like, such as U-I phase diagram analysis, short circuit transition analysis, envelope backtracking (refer to schematic diagrams shown in figures 8-10). The target user may further screen the target welding sample data according to the welding analysis information. The device 1 may determine a welding data sample set according to the screened target welding sample data and the corresponding target weld label data.
It should be understood by those skilled in the art that the above-described weld data analysis method is merely exemplary, and other existing or future weld data analysis methods, such as those applicable to the present embodiment, are also included within the scope of the present application and are hereby incorporated by reference.
In some embodiments, the determining a welding data sample set according to the target welding sample data and target weld label data corresponding to the target welding sample data comprises: the equipment 1 determines sample classification information corresponding to the target welding sample data according to the target welding seam label data corresponding to the target welding sample data; and determining a welding data sample set according to the target welding sample data and the sample classification information corresponding to the target welding sample data. In some embodiments, the device 1 determines the positive and negative samples according to the target weld label data corresponding to the target welding sample data. For example, the apparatus 1 determines target welding data whose target bead label data includes a normal bead as a positive sample, and determines target welding data whose target bead label data includes an abnormal bead as a negative sample.
In step S13, the device 1 extracts a plurality of welding characteristic information from the welding data sample set, wherein the welding characteristic information includes basic welding characteristic information and welding mechanism characteristic information. In some embodiments, the base weld signature information includes, but is not limited to, time domain signature information, frequency domain signature information, or time-frequency domain signature information extracted from the weld data sample set, such as a rectified mean, a significant value, a coefficient of variation, a frequency, an energy, an amplitude, or an energy concentration, among others. The characteristic information of the welding mechanism comprises but is not limited to characteristic information determined based on welding professional knowledge, such as U-I phase diagram area, track repeatability and the like.
In some embodiments, the step S13 includes: the device 1 determines basic welding characteristic information corresponding to the welding data sample set based on a preset characteristic algorithm; determining welding mechanism characteristic information corresponding to the welding data sample set according to the function and the parameter selected by the target user; and determining a plurality of welding characteristic information according to the welding mechanism characteristic information and the basic welding characteristic information.
In some embodiments, the feature algorithm for extracting the basic weld feature information is already set, and after determining the weld data sample set, the device 1 may determine the corresponding basic weld feature information from the weld data sample set directly according to the corresponding feature algorithm. The device 1 may also present the basic welding characteristics information, selected by the target user based on model building requirements. In some embodiments, referring to the welding mechanism characterization configuration diagram shown in fig. 11, after determining the welding data sample set, the apparatus 1 presents a corresponding attribute generation interface for the target user to select corresponding functions and parameters based on his own welding knowledge and welding experience. The device 1 extracts welding mechanism characteristic information from the welding data sample set according to the selected function and parameters. The device 1 may determine a plurality of corresponding welding characteristic information according to the basic welding characteristic information selected by the target user and the welding mechanism characteristic information.
In step S14, the apparatus 1 determines a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information. In some embodiments, in order to improve the model training speed, the training effect, and the interpretability of the trained welding quality detection model, the apparatus 1 may screen out a plurality of target welding characteristic information related to the model training from the plurality of welding characteristic information based on the selection of the target user. In some embodiments, device 1 may determine an importance ranking of the plurality of weld signature information based on a selection by a target user, and determine a plurality of target weld signature information from the plurality of weld signature information based on the importance ranking. For example, the apparatus 1 may present a list containing the plurality of welding characteristic information, which is ranked in importance by the target user based on his welding field experience to select a plurality of target welding characteristic information.
In some embodiments, the step S14 includes: the device 1 determines a target welding characteristic selection method in response to the setting operation of the target user; and determining a plurality of target welding characteristic information from the plurality of welding characteristic information according to the target welding characteristic selection method. In some embodiments, the device 1 may perform welding characteristic selection by using a target welding characteristic selection method, where the target welding characteristic selection method includes a characteristic selection method such as an F test, a fisher test, or a mutual information method. The device 1 determines the verification result information (for example, a P value determined based on the F test or the fisher test, or a mutual information amount of the welding characteristic information determined based on the mutual information method and the target) corresponding to the plurality of welding characteristic information according to the target welding characteristic selection method selected by the target user. The apparatus 1 may determine a plurality of target welding characteristic information from the plurality of welding characteristic information based on the inspection result information. For example, among the plurality of welding characteristic information, welding characteristic information having a P value smaller than a certain threshold or having a mutual information amount larger than a certain threshold is determined as target welding characteristic information.
In step S15, the device 1 obtains the welding quality detection model through automatic machine learning training according to the multiple pieces of target welding feature information and the target weld label data corresponding to the welding data sample set. In some embodiments, in response to a triggering operation of a target user on a model training control in the apparatus 1, the apparatus 1 obtains the welding quality detection model by training with an automatic machine learning engine according to the plurality of target welding feature information and target weld label data corresponding to the welding data sample set. The automatic machine learning engine includes, but is not limited to, auto-Sklearn, TPOT (Tree-based Pipeline Optimization Tool), auto-ViML. For example, taking TPOT as an example to perform automatic training of a welding quality detection model, the device 1 imports the multiple pieces of target welding characteristic information and target weld label data corresponding to the welding data sample set into TPOT based on a trigger operation of a target user on a model training control, divides the imported data, and determines a corresponding training set and a corresponding test set. The device 1 performs model construction, fitting, and scoring based on TPOT, outputs an optimal welding quality detection model and parameters, and can export the optimal welding quality detection model and parameters to a relevant file. And relevant information about the welding quality detection model can be acquired through the analysis of the file, so that automatic modeling is realized. The scheme presents a visual welding quality detection model construction process to a target user through the equipment 1. The target user can participate in the whole process of model construction, the target user can conveniently apply the welding experience of the target user to the model construction, and the learning cost of constructing and using the welding quality detection model by the target user is reduced.
In some embodiments, the step S15 includes: the equipment 1 determines a training set and a testing set for training a welding quality detection model based on the target welding characteristic information and target weld joint label data corresponding to the welding data sample set; and obtaining the welding quality detection model by utilizing automatic machine learning training. In some embodiments, the apparatus 1 determines a training set and a testing set for training the welding quality detection model from the target welding characteristic information and the target weld label data corresponding to the welding data sample set based on a training set and testing set ratio set by a target user. And the equipment 1 obtains the welding quality detection model by utilizing automatic machine learning training according to the training set.
In some embodiments, the method further comprises: step S16 (not shown), the device 1 issues the welding quality detection model to a target gateway for detecting the welding quality in the welding process. For example, after completing the training of the welding quality detection model, the device 1 may issue the trained welding quality detection model to a target gateway of the welding production field, so as to detect the welding quality in real time during the welding process.
In some embodiments, the step S15 further includes: the equipment 1 determines detection accuracy rate information corresponding to the welding quality detection model according to the test set and the welding quality detection model; and determining whether to issue the welding quality detection model or not according to the detection accuracy information. In some embodiments, the apparatus 1 inputs the test set into a trained welding quality detection model, obtains welding quality detection result information about the test set, and determines corresponding detection accuracy information based on the welding quality detection result information. If the detection accuracy information is greater than or equal to the preset accuracy threshold, the device 1 may issue the welding quality detection model to a target gateway to perform actual welding quality detection. Or, the device 1 presents the detection accuracy information, and the target user may determine whether to issue the welding quality detection model based on the detection accuracy information. The device 1 may issue the welding quality detection model to a target gateway based on an issue operation of a target user.
In some embodiments, without issuing the weld quality detection model, the method further comprises: step S17 (not shown), the device 1 obtains second welding data and second weld label data corresponding to the second welding data from the target database; and updating the welding quality detection model based on the second welding data and second welding seam label data corresponding to the second welding data. For example, if the determined detection accuracy information is lower than a preset accuracy threshold, or the target user does not agree to issue the welding quality detection model, the device 1 may continue to acquire the second welding data and the second weld label data corresponding to the second welding data from the target database, and continue to train the welding quality detection model based on the newly acquired second welding data and the second weld label data corresponding to the second welding data, so as to acquire a new welding quality detection model. Here, the processing of the second welding data and the second weld label data and the training of the welding quality detection model are the same as or similar to the foregoing steps S11 to S15, and therefore, the description is omitted here for brevity and is included herein by way of reference.
In some embodiments, the method further comprises: step S18 (not shown), the apparatus 1 updates the welding quality detection model based on the update of the target welding task. For example, if a welding production environment or a welding production mode changes, the welding quality detection model does not adapt to a new target welding task any more, the device 1 may obtain, according to a model update operation initiated by a target user, third welding data matched with the updated target welding task and third weld label data corresponding to the third welding data from a target database, and update the welding quality detection model based on the third welding data and the third weld label data corresponding to the third welding data, thereby solving the problems of short life cycle and unstable generalization of the welding quality detection model. The target user can automatically complete the updating of the welding quality detection model by combining the actual execution time change of the target welding task, and the generalization of the welding quality detection model is ensured. Here, the updating method of the welding quality detection model is the same as or similar to that of the step S17, and therefore, the description is omitted, and the updating method is included herein by reference.
Fig. 12 shows a block diagram of an apparatus for constructing a welding quality inspection model according to an embodiment of the present application, where the apparatus 1 includes a one-module 11, a two-module 12, a three-module 13, a four-module 14, and a five-module 15. A module 11, in response to a welding quality detection model construction operation initiated by a target user based on a target welding task, acquires first welding data and first weld label data corresponding to the first welding data from a target database; a second module 12 determines a welding data sample set based on the selection operation of the target user on the first welding data; a third module 13 extracts a plurality of welding characteristic information from the welding data sample set, wherein the welding characteristic information includes basic welding characteristic information and welding mechanism characteristic information; a fourth module 14 for determining a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information; and a fifth module 15 obtains the welding quality detection model through automatic machine learning training according to the target welding characteristic information and the welding seam label data corresponding to the welding data sample set. Here, the specific embodiments of the one-to-one module 11, the two-to-two module 12, the one-to-three module 13, the one-to-four module 14, and the one-to-five module 15 shown in fig. 12 are the same as or similar to the specific embodiments of the step S11, the step S12, the step S13, the step S14, and the step S15, respectively, and are not repeated herein and are included herein by reference.
In some embodiments, the apparatus 1 further comprises a six-module 16 (not shown). The first six modules 16 issue the welding quality detection model to a target gateway for detecting the welding quality in the welding process. Here, the embodiment of the six modules 16 is the same as or similar to the embodiment of the step S16, and therefore, the description thereof is omitted here for brevity.
In some embodiments, the apparatus 1 further comprises a seven module 17 (not shown). The seventh module 17 obtains second welding data and second weld label data corresponding to the second welding data from the target database; and updating the welding quality detection model based on the second welding data and second welding seam label data corresponding to the second welding data. Here, the embodiment of the seventh module 17 is the same as or similar to the embodiment of the step S17, and therefore, the detailed description is omitted, and the detailed description is incorporated herein by reference.
In some embodiments, the apparatus 1 further comprises an eight module 18 (not shown). The eight module 18 updates the weld quality detection model based on the update of the target weld task. Here, the embodiment of the eight modules 18 is the same as or similar to the embodiment of the step S18, and therefore, the detailed description is omitted, and the detailed description is included herein by reference.
FIG. 13 illustrates an exemplary system that can be used to implement the various embodiments described in this application;
in some embodiments, as shown in FIG. 13, the system 300 can be implemented as any of the devices in the various embodiments described. In some embodiments, system 300 may include one or more computer-readable media (e.g., system memory or NVM/storage 320) having instructions and one or more processors (e.g., processor(s) 305) coupled with the one or more computer-readable media and configured to execute the instructions to implement modules to perform the actions described herein.
For one embodiment, system control module 310 may include any suitable interface controllers to provide any suitable interface to at least one of processor(s) 305 and/or any suitable device or component in communication with system control module 310.
The system control module 310 may include a memory controller module 330 to provide an interface to the system memory 315. Memory controller module 330 may be a hardware module, a software module, and/or a firmware module.
For one embodiment, system control module 310 may include one or more input/output (I/O) controllers to provide an interface to NVM/storage 320 and communication interface(s) 325.
For example, NVM/storage 320 may be used to store data and/or instructions. NVM/storage 320 may include any suitable non-volatile memory (e.g., flash memory) and/or may include any suitable non-volatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).
NVM/storage 320 may include storage resources that are physically part of the device on which system 300 is installed or may be accessed by the device and not necessarily part of the device. For example, NVM/storage 320 may be accessible over a network via communication interface(s) 325.
Communication interface(s) 325 may provide an interface for system 300 to communicate over one or more networks and/or with any other suitable device. System 300 may wirelessly communicate with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols.
For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) of the system control module 310, such as memory controller module 330. For one embodiment, at least one of the processor(s) 305 may be packaged together with logic for one or more controller(s) of the system control module 310 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310. For one embodiment, at least one of the processor(s) 305 may be integrated on the same die with logic for one or more controller(s) of the system control module 310 to form a system on chip (SoC).
In various embodiments, system 300 may be, but is not limited to being: a server, a workstation, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.). In various embodiments, system 300 may have more or fewer components and/or different architectures. For example, in some embodiments, system 300 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and speakers.
In addition to the methods and apparatus described in the embodiments above, the present application also provides a computer readable storage medium storing computer code that, when executed, performs the method as described in any of the preceding claims.
The present application also provides a computer program product, which when executed by a computer device, performs the method of any of the preceding claims.
The present application further provides a computer device, comprising:
one or more processors;
a memory for storing one or more computer programs;
the one or more computer programs, when executed by the one or more processors, cause the one or more processors to implement the method of any preceding claim.
It should be noted that the present application may be implemented in software and/or a combination of software and hardware, for example, implemented using Application Specific Integrated Circuits (ASICs), general purpose computers or any other similar hardware devices. In one embodiment, the software programs of the present application may be executed by a processor to implement the steps or functions described above. As such, the software programs (including associated data structures) of the present application can be stored in a computer readable recording medium, such as RAM memory, magnetic or optical drive or diskette and the like. Additionally, some of the steps or functions of the present application may be implemented in hardware, for example, as circuitry that cooperates with the processor to perform various steps or functions.
In addition, some of the present application may be implemented as a computer program product, such as computer program instructions, which when executed by a computer, may invoke or provide methods and/or techniques in accordance with the present application through the operation of the computer. Those skilled in the art will appreciate that the form in which the computer program instructions reside on a computer-readable medium includes, but is not limited to, source files, executable files, installation package files, and the like, and that the manner in which the computer program instructions are executed by a computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Computer-readable media herein can be any available computer-readable storage media or communication media that can be accessed by a computer.
Communication media includes media whereby communication signals, including, for example, computer readable instructions, data structures, program modules, or other data, are transmitted from one system to another. Communication media may include conductive transmission media such as cables and wires (e.g., fiber optics, coaxial, etc.) and wireless (non-conductive transmission) media capable of propagating energy waves such as acoustic, electromagnetic, RF, microwave, and infrared. Computer readable instructions, data structures, program modules, or other data may be embodied in a modulated data signal, for example, in a wireless medium such as a carrier wave or similar mechanism such as is embodied as part of spread spectrum techniques. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. The modulation may be analog, digital or hybrid modulation techniques.
By way of example, and not limitation, computer-readable storage media may include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. For example, computer-readable storage media include, but are not limited to, volatile memory such as random access memory (RAM, DRAM, SRAM); and non-volatile memory such as flash memory, various read-only memories (ROM, PROM, EPROM, EEPROM), magnetic and ferromagnetic/ferroelectric memories (MRAM, feRAM); and magnetic and optical storage devices (hard disk, tape, CD, DVD); or other now known media or later developed that can store computer-readable information/data for use by a computer system.
An embodiment according to the present application comprises an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the apparatus to perform a method and/or a solution according to the aforementioned embodiments of the present application.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the apparatus claims may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.
Claims (10)
1. A method for constructing a weld quality inspection model, wherein the method comprises:
responding to a welding quality detection model construction operation initiated by a target user based on a target welding task, and acquiring first welding data and first welding seam label data corresponding to the first welding data from a target database;
determining a welding data sample set based on the selection operation of the target user on the first welding data;
extracting a plurality of welding characteristic information from the welding data sample set, wherein the welding characteristic information comprises basic welding characteristic information and welding mechanism characteristic information;
determining a plurality of target welding characteristic information selected by the target user from the plurality of welding characteristic information;
and obtaining the welding quality detection model through automatic machine learning training according to the target welding characteristic information and the welding seam label data corresponding to the welding data sample set.
2. The method of claim 1, wherein the determining a sample set of welding data based on the selection of the first welding data by the target user comprises:
determining centralized welding sample data for forming a welding data sample set based on the selection operation of the target user on the first welding data;
determining and presenting statistical information corresponding to the welding sample data so that the target user can screen the welding sample data based on the statistical information;
and determining the screened target welding sample data according to the screening operation of the target user on the welding sample data, and determining a welding data sample set according to the target welding sample data and the target welding seam label data corresponding to the target welding sample data.
3. The method of claim 1, wherein the extracting a plurality of weld signature information from the weld data sample set, wherein the weld signature information including base weld signature information and weld mechanization signature information comprises:
determining basic welding characteristic information corresponding to the welding data sample set based on a preset characteristic algorithm;
determining welding mechanism characteristic information corresponding to the welding data sample set according to the function and the parameter selected by the target user;
and determining a plurality of welding characteristic information according to the welding mechanism characteristic information and the basic welding characteristic information.
4. The method of claim 1, wherein the determining the target user-selected plurality of weld signature information from the plurality of weld signature information comprises:
determining a target welding characteristic selection method in response to the setting operation of the target user;
and determining a plurality of target welding characteristic information from the plurality of welding characteristic information according to the target welding characteristic selection method.
5. The method of claim 1, wherein the method further comprises:
and issuing the welding quality detection model to a target gateway for detecting the welding quality in the welding process.
6. The method of claim 1, wherein the obtaining the weld quality detection model through automatic machine learning training based on the plurality of target weld signature information and weld signature data corresponding to the set of weld data samples comprises:
determining a training set and a testing set for training a welding quality detection model based on the target welding characteristic information and target weld joint label data corresponding to the welding data sample set;
and obtaining the welding quality detection model by utilizing automatic machine learning training.
7. The method of claim 6, wherein the obtaining the weld quality detection model through automatic machine learning training based on the plurality of target weld signature information and weld signature data corresponding to the set of weld data samples further comprises:
determining detection accuracy rate information corresponding to the welding quality detection model according to the test set and the welding quality detection model;
and determining whether to issue the welding quality detection model or not according to the detection accuracy information.
8. The method of claim 1, wherein the method further comprises:
updating the weld quality detection model based on the update of the target welding task.
9. A computer device for constructing a weld quality inspection model, comprising a memory, a processor and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.
10. A computer-readable storage medium on which a computer program/instructions are stored, characterized in that the computer program/instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210675530.0A CN115146530B (en) | 2022-06-15 | 2022-06-15 | Method, apparatus, medium and program product for constructing welding quality detection model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210675530.0A CN115146530B (en) | 2022-06-15 | 2022-06-15 | Method, apparatus, medium and program product for constructing welding quality detection model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115146530A true CN115146530A (en) | 2022-10-04 |
| CN115146530B CN115146530B (en) | 2023-07-28 |
Family
ID=83408084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210675530.0A Active CN115146530B (en) | 2022-06-15 | 2022-06-15 | Method, apparatus, medium and program product for constructing welding quality detection model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115146530B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115722797A (en) * | 2022-11-03 | 2023-03-03 | 深圳市微谱感知智能科技有限公司 | Laser welding signal analysis method based on machine learning |
| CN116028481A (en) * | 2023-03-30 | 2023-04-28 | 紫金诚征信有限公司 | Data quality detection method, device, equipment and storage medium |
| CN116551263A (en) * | 2023-07-11 | 2023-08-08 | 苏州松德激光科技有限公司 | Visual control method and system for welding position selection |
| CN117094045A (en) * | 2023-10-18 | 2023-11-21 | 中国铁塔股份有限公司 | Method and equipment for obtaining three-dimensional model of single-tube tower |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202224A (en) * | 2021-12-16 | 2022-03-18 | 蕴硕物联技术(上海)有限公司 | Method, apparatus, medium, and program product for detecting weld quality in a production environment |
| CN114219306A (en) * | 2021-12-16 | 2022-03-22 | 蕴硕物联技术(上海)有限公司 | Method, apparatus, medium, and program product for creating a weld quality detection model |
-
2022
- 2022-06-15 CN CN202210675530.0A patent/CN115146530B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202224A (en) * | 2021-12-16 | 2022-03-18 | 蕴硕物联技术(上海)有限公司 | Method, apparatus, medium, and program product for detecting weld quality in a production environment |
| CN114219306A (en) * | 2021-12-16 | 2022-03-22 | 蕴硕物联技术(上海)有限公司 | Method, apparatus, medium, and program product for creating a weld quality detection model |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115722797A (en) * | 2022-11-03 | 2023-03-03 | 深圳市微谱感知智能科技有限公司 | Laser welding signal analysis method based on machine learning |
| CN116028481A (en) * | 2023-03-30 | 2023-04-28 | 紫金诚征信有限公司 | Data quality detection method, device, equipment and storage medium |
| CN116028481B (en) * | 2023-03-30 | 2023-06-27 | 紫金诚征信有限公司 | Data quality detection method, device, equipment and storage medium |
| CN116551263A (en) * | 2023-07-11 | 2023-08-08 | 苏州松德激光科技有限公司 | Visual control method and system for welding position selection |
| CN116551263B (en) * | 2023-07-11 | 2023-10-31 | 苏州松德激光科技有限公司 | Visual control method and system for welding position selection |
| CN117094045A (en) * | 2023-10-18 | 2023-11-21 | 中国铁塔股份有限公司 | Method and equipment for obtaining three-dimensional model of single-tube tower |
| CN117094045B (en) * | 2023-10-18 | 2024-01-30 | 中国铁塔股份有限公司 | Method and equipment for obtaining three-dimensional model of single-tube tower |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115146530B (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115146530B (en) | Method, apparatus, medium and program product for constructing welding quality detection model | |
| Kusiak | Convolutional and generative adversarial neural networks in manufacturing | |
| CN110334130B (en) | Transaction data anomaly detection method, medium, device and computing equipment | |
| Abell et al. | Big data-driven manufacturing—Process-monitoring-for-quality philosophy | |
| TW201734841A (en) | Reference test method and device for supervised learning algorithm in distributed environment | |
| WO2021027213A1 (en) | Detection method and apparatus, electronic device and computer-readable medium | |
| CN114219306B (en) | Method, apparatus, medium for establishing welding quality detection model | |
| CN105930257B (en) | A kind of method and device of determining target detection use-case | |
| Nkonyana et al. | Performance evaluation of data mining techniques in steel manufacturing industry | |
| CN107917341A (en) | Oil pipeline leakage detection method and device | |
| CN107942956A (en) | Information processor, information processing method, message handling program and recording medium | |
| JP2021005694A (en) | Data processing device, data processing method, and program | |
| CN114207593A (en) | Techniques for analytical instrument performance diagnostics | |
| CN115599653A (en) | Method, system and medium for constructing welding quality diagnosis model | |
| CN114202224B (en) | Method, apparatus, medium for detecting weld quality in a production environment | |
| CN105444701A (en) | Region area measuring method and apparatus | |
| CN116482460A (en) | Fault diagnosis method for power grid equipment and related equipment | |
| CN113255769B (en) | Training method of compound attribute prediction model and compound attribute prediction method | |
| US11693921B2 (en) | Data preparation for artificial intelligence models | |
| CN114638096A (en) | Method, device and equipment for displaying logic among program variables and storage medium | |
| Kulkarni et al. | Impact of gaussian noise for optimized support vector machine algorithm applied to medicare payment on raspberry pi | |
| CN115169444A (en) | Method, apparatus, medium, and program product for constructing welding quality detection model | |
| US20230350392A1 (en) | Method and system for seamless transition of runtime system from controller device to digitalization platform | |
| CN115194296A (en) | Method, apparatus, medium, and program product for determining stability of welding process | |
| TWI846887B (en) | Data processing device, data processing method and data processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |