Welding process matching method and system, storage medium and electronic equipment

Abstract

The invention belongs to the technical field of welding, and discloses a welding process matching method and system, a storage medium and electronic equipment. Constructing a process database based on the experimental data; constructing a process library algorithm model, and training the process library algorithm model by using experimental data; and matching welding parameters for actual welding conditions through the trained process library algorithm model. According to the method, the requirement for welding operators is lowered, a large amount of debugging and testing work needed in the project implementation process is omitted, and cost is saved.

Description

Technical Field

[0001] The present invention belongs to the field of welding technology, and specifically relates to a welding process matching method and system, a storage medium, and an electronic device. Background Art

[0002] With the continuous changes in the market demand of the automotive manufacturing industry, laser welding control systems have become an indispensable product for equipment manufacturers. However, in order to ensure that the welding effect of laser welding equipment meets the needs of the project, professionals need to spend a lot of time and energy to adjust the parameters, but there is no simple and convenient way to quickly call out the corresponding parameters in the laser welding software on the market. Summary of the invention

[0003] Aiming at the deficiencies of the prior art, the present invention discloses a welding process matching method and system.

[0004] The present invention is achieved through the following technical solutions:

[0005] In a first aspect, a welding process matching method comprises:

[0006] Collect experimental data of welding process;

[0007] Building a process database based on the experimental data;

[0008] Constructing a process library algorithm model, and using the experimental data to train the process library algorithm model;

[0009] The welding parameters are matched to the actual welding conditions through the trained process library algorithm model.

[0010] In some embodiments, the experimental data includes welding conditions and welding parameters.

[0011] In some embodiments, the welding conditions include welding material, welding shape, material size, penetration depth and penetration width.

[0012] In some embodiments, the welding parameters include pattern parameters and process parameters.

[0013] In some embodiments, the graphic parameters include the shape of the welding graphic, the attributes of the graphic, whether the graphic needs to be swung, the swung mode, and the parameters under the swung mode.

[0014] In some embodiments, the process parameters include welding pen number, laser speed, DA power, frequency and duty cycle.

[0015] In some embodiments, the process database is constructed to include a welding condition table and a welding process table.

[0016] In some embodiments, the algorithm used by the process library algorithm model is a K-nearest neighbor algorithm.

[0017] In some embodiments, the distance metric of the K-nearest neighbor algorithm includes Minkowski distance, Manhattan distance, Euclidean distance, Chebyshev distance, and cosine distance.

[0018] In a second aspect, a welding process matching system includes:

[0019] Data acquisition module, used to collect experimental data related to welding;

[0020] Data processing module, used to build process database;

[0021] Model training module, used to train the process library algorithm model;

[0022] The data matching module is used to match welding parameters to welding conditions through the process library algorithm model.

[0023] In a third aspect, a computer-readable storage medium is provided, characterized in that one or more programs are stored therein, and when the one or more programs are executed, the above method can be implemented.

[0024] In a fourth aspect, an electronic device comprises a processor, a communication interface, a memory and a communication bus; the processor, the communication interface and the memory communicate with each other via the communication bus; and the processor is used for the program stored in the above-mentioned computer-readable storage medium.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] 1. Reduce the requirements for welding operators;

[0027] 2. Eliminate the need for a lot of debugging and testing work during project implementation;

[0028] 3. It has good applicability in welding tasks with less data and complex nonlinear relationships.

[0029] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the present use information. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a schematic diagram of a welding matching method of this embodiment.

[0032] Figure 2 Schematic diagram of a welding matching system of this embodiment.

[0033] Figure 3 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The drawings are only for illustrative purposes and cannot be construed as limiting the present invention. To better illustrate the present embodiment, some parts of the drawings may be omitted, enlarged, or reduced, and do not represent the size of the actual product. For those skilled in the art, it is understandable that some well-known structures and their descriptions may be omitted in the drawings. The positional relationships described in the drawings are only for illustrative purposes and cannot be construed as limiting the present invention.

[0035] like Figure 1 A welding process matching method shown includes the following steps:

[0036] S1. Collect experimental data of welding process;

[0037] Specifically, the experimental data include welding conditions and welding parameters, the welding conditions include welding materials, welding shape, material size, penetration depth and penetration width; the welding parameters include graphic parameters and process parameters, wherein the graphic parameters include the shape of the welding graphic, the attributes of the graphic, whether the graphic needs to swing, the swing mode and the parameters under the swing mode, and the attributes of the graphic include the coordinates, length, width and serial number of the graphic, and the swing mode includes spiral swing welding, elliptical swing welding, sinusoidal swing welding, vertical figure 8 swing welding and horizontal figure 8 swing welding.

[0038] Furthermore, the process parameters include welding pen number, laser speed, DA power, frequency and duty cycle.

[0039] S2. constructing a process database based on the experimental data;

[0040] Specifically, the graphic parameters are stored in a custom format document .litcad, the process parameters are stored in a custom format document .orzx, and then the above documents are stored in a project directory.

[0041] Furthermore, the welding conditions are combined into welding schemes, and a scheme ID is assigned to each of them. Then, tables are created through the database, including a welding condition table and a welding process table. The welding condition table is used to save the welding scheme and scheme ID, and the welding process table is used to save the specific directory, scheme name, scheme ID and specific process parameters of the graphic parameter document and the process parameter document.

[0042] S3, constructing a process library algorithm model, and using the experimental data to train the process library algorithm model;

[0043] Specifically, the process library algorithm model is constructed by combining a convolutional neural network (CNN) and a K-nearest neighbor algorithm (KNN), and the training uses CNN to extract welding parameter features.

[0044] In the first step, the experimental data set is preprocessed, and the process parameters are used as input features, while the welding conditions are used as output targets to form the data set.

[0045] Furthermore, the input features and output targets in the data set are separated, and the input features are standardized. The input features are data used to train the model, and the output targets are the results that the model needs to predict.

[0046] The dataset is split into training and test sets, and the input features are converted into 4D tensors suitable for CNN.

[0047] Furthermore, a 1D CNN model is created and trained using the mean squared error mean absolute error as the loss function. The trained CNN model is used to extract the features of the training set and the test set from the input features.

[0048] Furthermore, the extracted features are input into the KNN model for classification or regression prediction.

[0049] S4, matching welding parameters to actual welding conditions through the trained process library algorithm model;

[0050] Specifically, the algorithm is a K-nearest neighbor algorithm (KNN), which calculates the distance between the input welding conditions and the samples in the process database and selects the nearest K neighbors for category decision, wherein the methods for calculating the distance include Minkowski distance, Manhattan distance, Euclidean distance, Chebyshev distance and cosine distance.

[0051] Furthermore, five parameters of welding conditions are obtained and input into a process database, and fuzzy query in an SQL statement is used to filter out all data records that meet the requirements from the welding condition table as samples.

[0052] For the screened samples, the distance between the input welding conditions and the samples is calculated. In this embodiment, the Euclidean distance is used as the distance metric to construct the formula:

[0053]

[0054] Among them, p is the input welding condition, q is the screened sample data, (a, b, c, d, e) are the weights of the five parameters of the welding condition, and the parameters are welding material, welding shape, material size, penetration depth and penetration width, and a+b+c+d+e=5.

[0055] When D(p,q)=0, a suitable solution ID is selected from the sample, and then the welding parameters are obtained by querying the welding process table through the solution ID.

[0056] When D(p,q)≠0, it indicates that there are no suitable welding parameters in the welding process table. Then, the solution IDs of the first three values ​​with the smallest Euclidean distance are taken, and then the corresponding three groups of values ​​are queried from the process database through these three solution IDs. The average value of the three groups of values ​​is taken as the recommended parameter for output.

[0057] like Figure 2 A welding process matching system shown includes: a data acquisition module, a data processing module, a model training module and a data matching module.

[0058] Specifically, the data acquisition module is used to collect experimental data related to welding;

[0059] The data processing module is used to construct a process database;

[0060] The model training module is used to train the process library algorithm model;

[0061] The data matching module is used to match welding parameters for welding conditions through a process library algorithm model.

[0062] like Figure 3 As shown, an embodiment of the present disclosure further provides an electronic device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus.

[0063] The memory is a computer-readable storage medium for storing one or more programs.

[0064] The processor is used to execute the program stored in the computer-readable storage medium.

[0065] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or may exist independently without being assembled into the device / apparatus.

[0066] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A welding process matching method, characterized in that: include: Collect experimental data of welding process; Building a process database based on the experimental data; Constructing a process library algorithm model, and using the experimental data to train the process library algorithm model; The welding parameters are matched to the actual welding conditions through the trained process library algorithm model.

2. A welding process matching method according to claim 1, characterized in that: The experimental data include welding conditions and welding parameters.

3. A welding process matching method according to claim 2, characterized in that: The welding conditions include welding material, welding shape, material size, penetration depth and penetration width.

4. A welding process matching method according to claim 2, characterized in that: The welding parameters include pattern parameters and process parameters.

5. A welding process matching method according to claim 4, characterized in that: The graphic parameters include the shape of the welding graphic, the attributes of the graphic, whether the graphic needs to swing, the swing mode and the parameters in the swing mode.

6. A welding process matching method according to claim 4, characterized in that: The process parameters include welding pen number, laser speed, DA power, frequency and duty cycle.

7. A welding process matching method according to claim 1, characterized in that: The process database is constructed, including a welding condition table and a welding process table.

8. A welding process matching method according to claim 1, characterized in that: Training the process library algorithm model includes convolutional neural network and K-nearest neighbor algorithm; Convolutional neural network extracts effective features from welding parameters; The K-nearest neighbor algorithm uses the effective features to perform parameter matching.

9. A welding process matching method according to claim 8, characterized in that: The distance metrics of the K-nearest neighbor algorithm include Minkowski distance, Manhattan distance, Euclidean distance, Chebyshev distance and cosine distance.

10. A welding process matching system, characterized in that: include: Data acquisition module, used to collect experimental data related to welding; Data processing module, used to build process database; Model training module, used to train the process library algorithm model; The data matching module is used to match welding parameters to welding conditions through the process library algorithm model.

11. A computer-readable storage medium, characterized in that: One or more programs are stored, and when the one or more programs are executed, the method described in any one of claims 1 to 9 can be implemented.

12. An electronic device comprising a processor, a communication interface, a memory and a communication bus; the processor, the communication interface and the memory communicate with each other via the communication bus; characterized in that: The processor is used to execute the program stored in the computer-readable storage medium according to claim 10.

Images