Welding machine process parameter optimization method, device and equipment and storage medium
By acquiring welding condition parameters and user feedback, combined with an expert database and intelligent optimization mechanism, the problems of low efficiency and insufficient iteration in traditional welding systems have been solved. This has enabled automatic optimization and continuous improvement of welding parameters, thereby enhancing welding quality and the system's adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHENGDU CRP ROBOT TECH CO LTD
- Filing Date
- 2025-12-31
- Publication Date
- 2026-04-17
AI Technical Summary
Traditional welding process parameter adjustment relies on manual experience, which is inefficient and inconsistent. Existing intelligent welding systems are costly, susceptible to environmental interference, and lack continuous iteration capabilities, resulting in unreliable welding quality and difficulty in accumulating process knowledge.
By acquiring welding condition parameters and an expert database, welding parameters are determined using the expert database, and the expert database is updated based on user feedback. By adopting rule adjustment and intelligent optimization mechanisms, the welding parameters are automatically optimized and continuously iterated.
This improved the accuracy and reliability of welding quality labels, led to the accumulation of structured data, enhanced welding quality and system adaptability, and enabled the intelligent iteration of welding machines and the continuous accumulation of process knowledge.
Smart Images
Figure CN121870347A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of welding machine parameter technology, and more specifically, to a method, apparatus, equipment, and storage medium for optimizing welding machine process parameters. Background Technology
[0002] In traditional welding process debugging, the determination of process parameters relies heavily on manual experience, resulting in low debugging efficiency, poor consistency, and difficulty in forming a reusable knowledge system. While welding parameter recommendation systems have emerged in recent years, two major bottlenecks remain: First, data acquisition is costly and unreliable. Existing intelligent welding systems largely rely on high-cost sensors (such as vision, acoustics, and touch) for automatic weld quality detection. This not only increases equipment costs and system complexity but is also susceptible to environmental interference from smoke, noise, light, and dirt in real-world industrial scenarios, leading to unreliable detection results. If a quality label is incorrect, subsequent parameter optimization will completely deviate from its intended direction, wasting time and resources. Second, there is a lack of continuous iteration and knowledge accumulation mechanisms. Existing systems often only provide static parameter recommendations and cannot dynamically optimize or learn from on-site welding results. Parameter, operating condition, and quality label data generated during welding are not structured and fully utilized, resulting in each welding task still starting from scratch with experience-based debugging, hindering continuous improvement of welding machine performance and effective accumulation of process knowledge. Therefore, there is an urgent need for a low-cost, highly reliable welding process parameter optimization method that supports continuous iteration, enabling rapid debugging and intelligent evolution of welding parameters in real industrial environments. Summary of the Invention
[0003] The purpose of this invention is to provide a method, apparatus, equipment, and storage medium for optimizing welding machine process parameters to improve the above-mentioned problems.
[0004] To achieve the above objectives, the embodiments of this application provide the following technical solutions: On one hand, embodiments of this application provide a method for optimizing welding machine process parameters, the method comprising: Obtain welding condition parameters and expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. Based on the welding condition parameters and an expert database, welding parameters are determined; control commands are sent, including commands to control the welding equipment to perform welding using the welding parameters. Obtain welding quality tags from user feedback on welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used when the welding is completed.
[0005] Secondly, embodiments of this application provide a welding machine process parameter optimization device, the device comprising: The acquisition module is used to acquire welding condition parameters and an expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. The control module is used to determine welding parameters based on the welding condition parameters and an expert database; and to send control commands, including commands to control the welding equipment to perform welding using the welding parameters. The update module is used to obtain welding quality tags from user feedback on welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used when the welding is completed.
[0006] Thirdly, embodiments of this application provide a welding machine process parameter optimization device, the device including a memory and a processor. The memory is used to store a computer program; the processor is used to execute the computer program to implement the steps of the above-described welding machine process parameter optimization method.
[0007] Fourthly, embodiments of this application provide a readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described welding machine process parameter optimization method.
[0008] The beneficial effects of this invention are as follows: (1) This invention uses a human-computer interaction feedback mechanism to delegate the task of welding quality evaluation to on-site process personnel, avoiding the problems of high-cost sensor deployment and environmental interference, and ensuring the accuracy and reliability of welding quality labels. At the same time, the system automatically records the working conditions, welding parameters and corresponding welding quality labels for each welding operation, forming a structured and traceable data accumulation, which provides a high-quality data foundation for subsequent optimization of welding machine process parameters.
[0009] (2) The present invention adopts a dual path of rule adjustment and intelligent optimization. On the one hand, it achieves rapid response and transparent adjustment by pre-setting adjustment rules. On the other hand, it trains a welding quality scoring model based on historical data and combines a genetic algorithm to perform global optimization under constraints, thereby improving the diversity of user choices.
[0010] (3) This invention uses a continuous update mechanism for the expert database to automatically add each successful welding case to the expert database, enabling the system to continuously accumulate effective process knowledge during actual use. As the amount of data increases, the system's recommendation accuracy and adaptive capability continue to improve, ultimately achieving an intelligent iterative effect where the welding machine improves with each weld, significantly enhancing welding quality.
[0011] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0013] Figure 1 This is a schematic diagram of the welding machine process parameter optimization method described in the embodiments of the present invention; Figure 2 This is a schematic diagram of the welding machine process parameter optimization device described in this embodiment of the invention; Figure 3 This is a schematic diagram of the welding machine process parameter optimization equipment described in this embodiment of the invention. Detailed Implementation
[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.
[0015] It should be noted that similar reference numerals or letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0016] Example 1 like Figure 1 As shown in the figure, this embodiment provides a method for optimizing welding machine process parameters, which includes steps S1, S2 and S3.
[0017] Step S1: Obtain welding condition parameters and expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. In this step, welding parameters may include plate thickness, groove type, welding position, shielding gas, etc. Historical welding parameters may include voltage, current, pulse width, etc. Historical welding quality labels can include no defects (welds meet quality standards) and other labels. Other labels include undercut (weld edge depression), uneven weld edge (edge is not straight), insufficient penetration (penetration depth is below standard), burn-through (workpiece is burned through), false weld (surface adhesion but not fused), weld too narrow (width less than required), poor weld gloss (uneven surface gloss or severe oxidation), excessive reinforcement (weld protrusion exceeds standard), uneven weld metal (uneven microstructure distribution), porosity (porosity or slag inclusion), cracks (hot cracks or cold cracks), and excessive spatter (excessive metal spatter). Step S2: Determine welding parameters based on the expert database according to the welding condition parameters; send control commands, including commands to control the welding equipment to perform welding using the welding parameters; In this step, the specific implementation steps for determining welding parameters based on the expert database according to welding condition parameters include step S21; Step S21: Search for historical welding condition parameters that are identical to the welding condition parameters in the expert database. If a historical welding condition parameter with the same welding condition parameter is found, then the historical welding parameter corresponding to the historical welding condition parameter is used as the welding parameter corresponding to the welding condition parameter. If no historical welding condition parameter with the same welding condition parameter is found, then the historical welding condition parameters in the expert database with the historical welding quality label of "no defects" are recorded as candidate historical welding condition parameters. Calculate the similarity between each candidate historical welding condition parameter and the welding condition parameter, and record the candidate historical welding condition parameter with the highest similarity as the target historical welding condition parameter. Use the historical welding parameter corresponding to the target historical welding condition parameter as the welding parameter corresponding to the welding condition parameter.
[0018] Step S3: Obtain the welding quality label from the user's feedback on the welding quality, complete the welding based on the welding quality label, and update the expert database using the welding parameters used when the welding is completed.
[0019] The specific implementation steps of this step include step S31 and step S32; Step S31: Analyze whether the welding quality label is defect-free. If so, the welding parameters are deemed qualified, the welding is completed, and the welding condition parameters, the welding parameters corresponding to the completion of welding, and the welding quality label corresponding to the completion of welding are associated and stored in the expert database. If not, the welding parameters are automatically adjusted to generate the adjusted welding parameters. In this step, the welding parameters are automatically adjusted to generate the adjusted welding parameters, including step S311; Step S311: Adjust the welding parameters according to the welding quality label and the preset adjustment rules. The adjustment rules include a one-to-one mapping relationship between each welding quality label and the welding parameter adjustment data. Correct the welding parameters according to the welding parameter adjustment data to generate the adjusted welding parameters.
[0020] This step aims to provide a parameter adjustment mechanism that does not require complex calculations. Its core is to directly map the defect type reported by the user to a specific parameter adjustment amount. For example, for "poor weld gloss", the corresponding welding parameter adjustment data is: [reduce voltage by 1V, reduce pulse width by 5%]; the welding parameters are corrected according to the welding parameter adjustment data, and the adjusted welding parameters are obtained after correction. In step S31, the welding parameters are automatically adjusted, and the generation of the adjusted welding parameters may also include step S312; Step S312: Record each historical welding condition parameter and its corresponding historical welding parameter combination as a sample data, label the sample data, and the labeled data is the welding quality score; use the sample data and its corresponding labeled data to train the neural network model to obtain the welding quality score model, wherein the sample data is used as input and the labeled data is used as output during training; obtain the adjusted welding parameters based on the welding condition parameters, welding parameters, welding quality score model and genetic algorithm.
[0021] In this step, the sample data is labeled manually. During training, a BP neural network is used, with the sample data as input and the welding quality score as output. The mean squared error is used as the loss function, and training is performed through backpropagation and gradient descent to obtain the welding quality score model. In addition, in this step, the specific implementation steps of obtaining the adjusted welding parameters based on the welding condition parameters, welding parameters, welding quality score model and genetic algorithm include step S3121. Step S3121: Obtain the welding constraints input by the user. The welding constraints include at least one parameter among the welding condition parameters. Encode the welding parameters as chromosomes and mark the parameters corresponding to the constraints as fixed gene segments. Construct an initial population using chromosomes. Combine the constraints with each chromosome in the population and input them into the welding quality prediction model. Output the welding quality score as the fitness value. Optimize the population using a genetic algorithm based on the fitness value. The fixed gene segments do not participate in crossover and mutation operations. When the termination condition is reached, select the chromosome with the highest fitness, decode it as the optimal welding parameters, and use it as the adjusted welding parameters.
[0022] This step can be understood as, for example: I. Input Condition Definition: Complete operating parameters: [Plate thickness = 5mm, Bevel type = V-type (can also be coded as 1), Welding position = Flat weld (can also be coded as 1)] User-specified constraints: [Board thickness = 5mm, Position = Flat weld] (These two items are fixed inputs and are not involved in coding or optimization) Current welding parameters: [Voltage = 23.0V, Current = 150.0A, Pulse parameter = 50.0%]; II. Chromosome Coding and Population Initialization The chromosome encodes only welding parameters: chromosome = [voltage, current, pulse parameter], with initial values of [23.0, 150.0, 50.0]. Based on this vector, a uniform random perturbation of ±5% is applied to generate an initial population of 4 individuals. Generate 4 individuals (±5% perturbation): Individual 1: [23.0, 150.0, 50.0] Individual 2: [22.5, 155.0, 48.0] Individual 3: [24.0, 145.0, 52.0] Individual 4: [23.5, 148.0, 49.0] III. Fitness Calculation Process For each individual in the population: The chromosome (adjustable parameter) is combined with fixed constraints to form a complete input vector; this vector is then input into the welding quality scoring model to obtain a predicted score as the fitness value.
[0023] Example: Fixed working condition: [Plate thickness = 5, Bevel type = 1, Welding position = 1] Chromosome: [Voltage = 23.0, Current = 150.0, Pulse Width = 50.0] Input vector: [5, 1, 1, 23.0, 150.0, 50.0] Model output score: 0.82 (fitness) IV. Genetic Algorithm Optimization Iteration The selection process is based on fitness using a roulette wheel, and crossover and mutation are performed. Throughout the genetic iteration process, the parameters corresponding to the user constraints (plate thickness, bevel type, welding position) remain unchanged, and only the welding parameters (voltage, current, pulse parameters) in the chromosome participate in the selection, crossover and mutation.
[0024] V. Termination and Output Termination conditions: Reaching the maximum number of iterations (e.g., 100 generations) or the fitness improvement is less than 0.001 for 10 consecutive generations. Optimal chromosome decoding: Decoding the chromosome with the highest fitness into the optimal welding parameters.
[0025] Step S32: Send a command to control the welding equipment to re-execute welding based on the adjusted welding parameters, and re-acquire the welding quality label. Analyze again whether the welding quality label is defect-free. If so, determine that the welding parameters are qualified, complete the welding, and associate and store the welding condition parameters, the welding parameters corresponding to the completed welding, and the welding quality label corresponding to the completed welding in the expert database. If not, continuously acquire the adjusted welding parameters input by the user until the welding is completed, and associate and store the welding condition parameters, the welding parameters corresponding to the completed welding, and the welding quality label corresponding to the completed welding in the expert database.
[0026] In this step, if not, the adjusted welding parameters input by the user are continuously acquired until welding is completed. The welding condition parameters, the welding parameters corresponding to the completion of welding, and the welding quality label corresponding to the completion of welding are associated and stored in the expert database. This can be understood as: When automatic parameter adjustment fails to meet welding quality standards, the system will switch entirely to manual parameter adjustment mode. This means that if the welding quality label is still not defect-free and further adjustments to the welding parameters are needed, the system will continue to use user input to obtain the adjusted welding parameters, and will no longer use the step of automatically adjusting the welding parameters to generate the adjusted welding parameters, until the welding quality label is defect-free. Then, the welding condition parameters, the welding parameters corresponding to the completion of welding, and the welding quality label corresponding to the completion of welding will be associated and stored in the expert database.
[0027] The above steps, through the construction of a two-layer collaborative mechanism—from automated optimization attempts to human experience as a safety net—effectively solve the optimization failure problem that may occur in traditional intelligent welding systems under complex and uncertain working conditions. This design not only ensures reliable convergence of the welding debugging process in all scenarios, preventing the system from falling into an infinite loop due to algorithmic limitations, but also seamlessly integrates the deep-seated process knowledge of human experts into the iterative process as the highest-level decision-making guarantee. Simultaneously, regardless of whether the final successful parameters originate from automatic recommendations or manual input, their correspondence with the working conditions is structured and stored in an expert database. This transforms each debugging session into effective, learnable experience for the system, achieving bidirectional enhancement and continuous accumulation of tacit human knowledge and explicit machine data. This fundamentally improves the robustness, practicality, and long-term evolutionary capability of the welding process system.
[0028] Example 2 like Figure 2 As shown in the figure, this embodiment provides a welding machine process parameter optimization device, which includes an acquisition module 1, a control module 2 and an update module 3.
[0029] Module 1 is used to acquire welding condition parameters and an expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. Control module 2 is used to determine welding parameters based on the welding condition parameters and an expert database; and to send control commands, including commands to control the welding equipment to perform welding using the welding parameters. The update module 3 is used to obtain the welding quality tags from the user's feedback on the welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used when the welding is completed.
[0030] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.
[0031] Example 3 Corresponding to the above method embodiments, this disclosure also provides welding machine process parameter optimization equipment. The welding machine process parameter optimization equipment described below and the welding machine process parameter optimization method described above can be referred to in correspondence.
[0032] Figure 3 This is a block diagram illustrating a welding machine process parameter optimization device 300 according to an exemplary embodiment. (See diagram below.) Figure 3 As shown, the welding machine process parameter optimization device 300 may include: a processor 301 and a memory 302. The welding machine process parameter optimization device 300 may also include one or more of the following: a multimedia component 303, an I / O interface 304, and a communication component 305.
[0033] The processor 301 controls the overall operation of the welding machine process parameter optimization device 300 to complete all or part of the steps in the aforementioned welding machine process parameter optimization method. The memory 302 stores various types of data to support the operation of the welding machine process parameter optimization device 300. This data may include, for example, instructions for any application or method operating on the welding machine process parameter optimization device 300, as well as application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 302 can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 302 or transmitted via the communication component 305. The audio component also includes at least one speaker for outputting audio signals. I / O interface 304 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 305 is used for wired or wireless communication between the welding machine process parameter optimization device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 305 may include a Wi-Fi module, a Bluetooth module, and an NFC module.
[0034] In an exemplary embodiment, the welding machine process parameter optimization device 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the welding machine process parameter optimization method described above.
[0035] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the welding machine process parameter optimization method described above. For example, the computer-readable storage medium may be the memory 302 including program instructions described above, which may be executed by the processor 301 of the welding machine process parameter optimization device 300 to complete the welding machine process parameter optimization method described above.
[0036] Example 4 Corresponding to the above method embodiments, this disclosure also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the welding machine process parameter optimization method described above.
[0037] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the welding process parameter optimization method described in the above method embodiments.
[0038] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.
[0039] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method of optimizing welding machine process parameters, characterized by, include: Obtain welding condition parameters and expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. Based on the welding condition parameters and an expert database, welding parameters are determined; control commands are sent, including commands to control the welding equipment to perform welding using the welding parameters. Obtain welding quality tags from user feedback on welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used when the welding is completed.
2. The welding machine process parameter optimization method based on human-computer interaction according to claim 1, characterized in that, Welding parameters are determined based on welding condition parameters and an expert database, including: Search the expert database for historical welding condition parameters that are the same as the welding condition parameters. If a historical welding condition parameter that is the same as the welding condition parameter is found, then the historical welding parameter corresponding to the historical welding condition parameter is used as the welding parameter corresponding to the welding condition parameter. If no historical welding condition parameter with the same welding condition parameter is found, the historical welding condition parameter with the historical welding quality label of "no defects" in the expert database is recorded as the candidate historical welding condition parameter. The similarity between each candidate historical welding condition parameter and the welding condition parameter is calculated, and the candidate historical welding condition parameter with the maximum similarity is recorded as the target historical welding condition parameter. Use the historical welding parameters corresponding to the target historical welding condition parameters as the welding parameters corresponding to the welding condition parameters.
3. The welding machine process parameter optimization method based on human-computer interaction according to claim 1, characterized in that, Obtain welding quality tags from user feedback on welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used at the time of welding completion, including: Analyze whether the welding quality label is defect-free. If so, the welding parameters are deemed qualified, the welding is completed, and the welding condition parameters, the welding parameters corresponding to the completion of the welding, and the welding quality label corresponding to the completion of the welding are associated and stored in the expert database. If not, the welding parameters are automatically adjusted to generate the adjusted welding parameters. The system sends a command to control the welding equipment to re-execute the welding based on the adjusted welding parameters, and re-acquires the welding quality label. It then analyzes whether the welding quality label is defect-free. If so, the welding parameters are deemed qualified, the welding is completed, and the welding condition parameters, the welding parameters corresponding to the completed welding, and the welding quality label corresponding to the completed welding are associated and stored in the expert database. Otherwise, the system continuously acquires the adjusted welding parameters input by the user until the welding is completed, and associates and stores the welding condition parameters, the welding parameters corresponding to the completed welding, and the welding quality label corresponding to the completed welding in the expert database.
4. The welding machine process parameter optimization method based on human-computer interaction according to claim 3, characterized in that, The welding parameters are automatically adjusted to generate the adjusted welding parameters, including: The welding parameters are adjusted according to the welding quality labels and preset adjustment rules. The adjustment rules include a one-to-one mapping relationship between each welding quality label and the welding parameter adjustment data. The welding parameters are corrected according to the welding parameter adjustment data to generate the adjusted welding parameters.
5. The welding machine process parameter optimization method based on human-computer interaction according to claim 3, characterized in that, The welding parameters are automatically adjusted to generate the adjusted welding parameters, including: Each historical welding condition parameter and its corresponding historical welding parameter combination are recorded as a sample data. The sample data are labeled, and the labeled data is the welding quality score. The neural network model is trained using sample data and its corresponding labeled data to obtain a welding quality scoring model. During training, sample data is used as input and labeled data is used as output. The adjusted welding parameters are obtained based on welding condition parameters, welding parameters, welding quality scoring model, and genetic algorithm.
6. The welding machine process parameter optimization method based on human-computer interaction according to claim 5, characterized in that, The adjusted welding parameters are obtained based on welding condition parameters, welding parameters, welding quality scoring model, and genetic algorithm, including: Obtain the welding constraints input by the user, which include at least one parameter from the welding condition parameters; Welding parameters are encoded as chromosomes, and the parameters corresponding to constraints are marked as fixed gene segments; An initial population is constructed using chromosomes. The constraints are combined with each chromosome in the population and then input into the welding quality prediction model. The welding quality score is output as the fitness value. Genetic algorithm optimization is performed on the population based on fitness values, where fixed gene segments do not participate in crossover and mutation operations; When the termination condition is met, the chromosome with the highest fitness is selected as the optimal welding parameter and used as the adjusted welding parameter.
7. A welding machine process parameter optimization device, characterized in that, include: The acquisition module is used to acquire welding condition parameters and an expert database. The expert database contains each historical welding condition parameter and its corresponding historical welding parameters and historical welding quality labels. The control module is used to determine welding parameters based on the welding condition parameters and an expert database; and to send control commands, including commands to control the welding equipment to perform welding using the welding parameters. The update module is used to obtain welding quality tags from user feedback on welding quality, complete the welding based on the welding quality tags, and update the expert database using the welding parameters used when the welding is completed.
8. A welding machine process parameter optimization device, characterized in that, include: Memory, used to store computer programs; A processor for executing a computer program to implement the steps of the welding process parameter optimization method as claimed in any one of claims 1 to 6.
9. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the welding machine process parameter optimization method as described in any one of claims 1 to 6.