Welding Adaptive Control Method and System for Mold Frame Production

Abstract

This application provides a welding adaptive control method and system for mold frame production, relating to the field of welding technology. It involves decomposing the mold frame components and analyzing the welding target parameters of each component according to functional requirements; optimizing process parameters based on the welding target parameters to obtain welding control strategies for each decomposed component; conducting target impact analysis based on the welding control strategies and welding target parameters to determine adaptive parameters; deploying welding monitoring equipment to collect real-time data; and adaptively adjusting the welding control strategy according to the control and adjustment relationship between the adaptive parameters and welding target parameters based on the real-time data. This application solves the technical problems of poor welding quality consistency and insufficient process adaptability in existing technologies where welding parameters rely on experience-based settings, achieving the technical effect of adaptively adjusting welding parameters, thereby improving welding quality and production efficiency.

Description

Technical Field

[0001] This application relates to the field of welding technology, specifically to a welding adaptive control method and system for mold production. Background Technology

[0002] As an important structural component in industrial manufacturing, mold frames are widely used in automobiles, daily necessities, medical products and equipment and other fields. The welding quality of the mold frames directly affects the precision, strength and service life of the final products.

[0003] Currently, welding control in mold frame production mainly relies on manually setting welding parameters. Operators select process parameters such as current, voltage, and welding speed based on experience and adjust them during the welding process by observing the molten pool and weld condition. This experience-based method is difficult to precisely adapt when welding mold frames of different materials, thicknesses, and structural forms, resulting in poor consistency in welding quality and a high likelihood of weld defects such as porosity and cracks, which in turn affect the overall performance of the mold frame. Secondly, fixed welding parameters are difficult to adapt to different mold frame structures and process requirements. When the mold frame structure changes, parameters need to be readjusted, increasing production uncertainty and debugging costs, and also limiting the stability and reliability of the welding process. Summary of the Invention

[0004] This application provides a welding adaptive control method and system for mold production, which solves the technical problem that the welding parameters in the prior art rely on experience to set, making it difficult to adapt to different welding conditions, resulting in poor welding quality consistency and insufficient process adaptability. It achieves the technical effect of adaptively adjusting welding parameters, thereby improving welding quality stability, reducing welding defects, and improving production efficiency.

[0005] In view of the above problems, this application provides a welding adaptive control method for mold frame production. The method includes: decomposing the mold frame components and analyzing the welding target parameters of each component according to the functional requirements of the decomposed components; optimizing the welding process parameters of the decomposed components with the welding target parameters as the target to obtain the welding control strategy for each decomposed component; performing target influence analysis based on the welding control strategy and the welding target parameters to determine adaptive parameters and establish the control adjustment relationship between the adaptive parameters and the welding target parameters; deploying welding monitoring equipment based on the adaptive parameters and collecting real-time monitoring data through the welding monitoring equipment; and adaptively adjusting the welding control strategy according to the control adjustment relationship based on the real-time monitoring data.

[0006] On the other hand, this application also provides a welding adaptive control system for mold frame production. The system includes: a target analysis module for decomposing the mold frame components and analyzing the welding target parameters of each component according to the functional requirements of the decomposed components; a parameter optimization module for optimizing the welding process parameters of the decomposed components with the welding target parameters as the target, and obtaining the welding control strategy for each decomposed component; an influence analysis module for performing target influence analysis based on the welding control strategy and the welding target parameters, determining adaptive parameters, and establishing the control adjustment relationship between the adaptive parameters and the welding target parameters; a welding monitoring module for deploying welding monitoring equipment based on the adaptive parameters and collecting real-time monitoring data through the welding monitoring equipment; and an adaptive adjustment module for adaptively adjusting the welding control strategy according to the control adjustment relationship based on the real-time monitoring data.

[0007] One or more technical solutions provided in this application have at least the following beneficial effects:

[0008] By decomposing the mold frame and analyzing the welding target parameters based on the functional requirements of each component, the specific goals to be achieved in welding each part can be clearly defined, providing precise guidance for subsequent process parameter optimization and control strategy formulation. Guided by the welding target parameters analyzed in the first step, welding process parameters are optimized for each decomposed component, thereby obtaining welding control strategies for each part. This step ensures that the welding process uses the optimal parameter combination to achieve the best balance between welding quality and efficiency. Target influence analysis is used to determine adaptive parameters, scientifically identifying key factors that significantly influence the welding target parameters, thus determining the adaptive parameters and making subsequent control strategy adjustments more targeted and effective. Establishing the control and adjustment relationship between adaptive parameters and welding target parameters allows the welding process to be dynamically adjusted according to actual conditions, enhancing the flexibility and adaptability of the welding process. Welding monitoring equipment is deployed based on the determined adaptive parameters, enabling real-time acquisition of monitoring data during the welding process, providing real-time data support for subsequent adaptive adjustments. Based on the real-time monitoring data, the welding control strategy is adaptively adjusted according to the pre-established control and adjustment relationship, ensuring that the welding process is always in an optimal control state, responding promptly to various changes, and ensuring stable welding quality and efficiency.

[0009] In summary, this application, through the organic combination of the above steps, forms a complete closed-loop control process, realizing adaptive parameter adjustment in the welding process, significantly improving welding quality, welding efficiency, and the stability and reliability of the welding process, making the welding control of mold production more scientific, precise, and efficient.

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating the welding adaptive control method for mold frame production provided in an embodiment of this application.

[0012] Figure 2 This is a schematic diagram illustrating the process of analyzing the welding target parameters of each component according to the functional requirements of the decomposed components in the welding adaptive control method for mold production provided in this application embodiment.

[0013] Figure 3 This is a schematic diagram of the welding adaptive control system for mold frame production provided in an embodiment of this application.

[0014] Figure labeling: Target analysis module 10, parameter optimization module 20, influence analysis module 30, welding monitoring module 40, adaptive adjustment module 50. Detailed Implementation

[0015] This application provides a welding adaptive control method and system for mold production, which solves the technical problem in the prior art that the welding parameters rely on experience to set, making it difficult to adapt to different welding conditions, resulting in poor welding quality consistency and insufficient process adaptability. It achieves the technical effect of adaptively adjusting welding parameters, thereby improving welding quality stability, reducing welding defects, and improving production efficiency.

[0016] Example 1, as Figure 1 As shown in the embodiment of this application, a welding adaptive control method for mold frame production is provided, the method comprising:

[0017] Step S1: Decompose the mold frame components and analyze the welding target parameters of each component according to the functional requirements of the decomposed components.

[0018] Specifically, a mold base is a frame structure used to support and fix the mold, typically composed of multiple parts, such as the mold plate system, guiding system, ejection mechanism, and cooling system. First, the components of the mold base are broken down in detail to clarify the specific composition of each part. Taking an injection mold base as an example, it is decomposed into the mold plate system, guiding system, ejection mechanism, and cooling system. The mold plate system includes the A-plate (fixed mold base plate), B-plate (moving mold base plate), support plate, and ejector plate; the guiding system includes guide pillars and guide sleeves; the ejection mechanism includes ejector pins and return rods; and the cooling system includes internal water channels. Next, for each decomposed component, its functional requirements in practical applications are analyzed to determine the target welding parameters for each part. For example, for the mold plate system, the functional requirement is high rigidity; therefore, the target welding parameters include welding strength and welding deformation, ensuring that it can withstand injection pressure and clamping force of 150–200 MPa after welding without deformation or damage. For the guiding system, the functional requirement is precision guiding. The welding target parameters involve the post-weld fit accuracy, ensuring the fit accuracy of the guide pillars and guide sleeves reaches ±0.01mm to guarantee a mold closing accuracy ≤0.02mm and avoid flash. The ejection mechanism's functional requirement is efficient ejection. Welding target parameters include the welding strength and positional accuracy of the ejector pins and return rods to ensure smooth ejection and return in thin-plate structures (thickness 10–30mm). The cooling system's functional requirement is efficient cooling. Welding target parameters mainly include post-weld sealing and water pressure test performance, ensuring good sealing of the internal water channels and the ability to withstand water pressure tests ≥0.6MPa, thereby shortening the molding cycle and improving production efficiency.

[0019] By decomposing the mold frame components and analyzing their functional requirements, the target welding parameters for each component can be clearly defined. This provides a precise basis for optimizing subsequent welding process parameters and formulating control strategies, ensuring that the welding process can meet the actual application requirements of the mold frame and improve welding quality and product performance.

[0020] Step S2: Using the welding target parameters as the objective, optimize the welding process parameters of the decomposed components to obtain the welding control strategy for each decomposed component.

[0021] Specifically, welding process parameters are various parameters that need to be controlled during the welding process, such as welding current, voltage, welding speed, wire diameter, and welding angle. Welding control strategies are a series of control measures and methods developed based on the optimization results of welding target parameters and process parameters. These strategies guide the welding process and ensure welding quality and efficiency. For example, different welding positions (flat welding, vertical welding, overhead welding, etc.) require different combinations of welding current, voltage, and speed; this is part of the welding control strategy.

[0022] Guided by the welding target parameters analyzed in step S1, the welding process parameters for each component of the decomposed mold frame are optimized using tools such as welding process databases, welding simulation software, and experimental design methods. For example, for welding the template system, the target parameters are high rigidity and low welding deformation. Welding simulation software (such as ANSYS, ABAQUS, etc.) can be used to simulate welding stress and deformation under different welding process parameters to find the optimal combination of welding current, voltage, and speed. Simultaneously, experimental design methods (such as orthogonal experiments, response surface methodology, etc.) are used to verify and optimize the welding process parameters in actual welding experiments. For welding the guide system, the target parameter is precision guidance, i.e., the fitting accuracy after welding. Welding deformation can be reduced by precisely controlling the welding heat input and welding sequence, thereby ensuring that the fitting accuracy of the guide post and guide sleeve reaches ±0.01mm. Furthermore, empirical data from the welding process database can be used to adjust and optimize the parameters based on actual conditions, developing welding control strategies for each decomposed component, including the specific numerical range of welding parameters, welding sequence, and welding method.

[0023] By optimizing welding process parameters and formulating welding control strategies, optimal process parameters and control methods can be provided for the welding of each component of the mold frame, ensuring that the welding process can achieve the predetermined welding target parameters, improving welding quality and production efficiency, and reducing welding defects and rework rates.

[0024] Step S3: Based on the welding control strategy and the welding target parameters, perform target influence analysis, determine adaptive parameters, and establish the control and adjustment relationship between the adaptive parameters and the welding target parameters.

[0025] Specifically, target impact analysis refers to analyzing the influence relationship between welding control strategies and welding target parameters to determine which factors or parameters have a significant impact on achieving the welding target. For example, changes in welding current and voltage may have a significant impact on weld penetration and weld formation, while changes in welding speed mainly affect welding heat input and welding deformation. Adaptive parameters are parameters that can be automatically adjusted based on real-time monitoring data during the welding process to adapt to changes in the welding environment and working conditions. For example, welding current, voltage, and speed can all be used as adaptive parameters. Control and adjustment relationships are the mathematical or logical relationships between adaptive parameters and welding target parameters, used to guide the adjustment of adaptive parameters. For example, when the weld penetration is insufficient, the welding current or voltage needs to be increased; when the welding deformation is excessive, the welding speed needs to be reduced or the welding sequence adjusted.

[0026] Based on the welding control strategy and welding target parameters established in step S2, a target impact analysis is conducted. Statistical methods such as sensitivity analysis and regression analysis can be used to determine which welding process parameters have a significant impact on the welding target parameters. For example, by analyzing the correlation between parameters such as welding current, voltage, and speed and target parameters such as weld penetration, weld deformation, and weld strength, key influencing factors are identified. Then, appropriate adaptive parameters, such as welding current, voltage, and speed, are selected from these key influencing factors. Next, the control and adjustment relationship between the adaptive parameters and the welding target parameters is established, which can be achieved through experimental data fitting, mathematical modeling, and other methods. For example, through numerous welding experiments, welding target parameter data under different welding parameters are collected, and regression analysis is used to establish a linear or nonlinear relationship model between welding current and weld penetration, or machine learning methods such as neural networks are used to establish more complex mapping relationships. In addition, existing welding process specifications and expert experience can be referenced, and adjustments and optimizations can be made in conjunction with actual conditions to ensure the accuracy and reliability of the control and adjustment relationship.

[0027] By determining adaptive parameters through target impact analysis and establishing their control and adjustment relationship with welding target parameters, welding parameters can be automatically adjusted based on real-time monitoring data during the welding process to adapt to changes in welding conditions, thereby further improving welding quality and production efficiency, and enhancing the stability and reliability of the welding process.

[0028] Step S4: Deploy welding monitoring equipment based on the adaptive parameters, and collect real-time monitoring data through the welding monitoring equipment.

[0029] Specifically, welding monitoring equipment is used to monitor various parameters and states during the welding process in real time, such as welding current sensors, voltage sensors, arc sensors, weld tracking sensors, and temperature sensors. These devices can collect real-time data during the welding process, providing a basis for adaptive control. For example, welding current sensors can monitor the magnitude and changes in welding current in real time, arc sensors can detect the stability of the welding arc, and weld tracking sensors can monitor the position and shape of the weld. Real-time monitoring data is data collected by the welding monitoring equipment during the welding process, including welding current, voltage, welding speed, weld position, and temperature. This data reflects the real-time status and quality of the welding process, providing a basis for adaptive adjustment and control.

[0030] Based on the adaptive parameters determined in step S3, select and deploy appropriate welding monitoring equipment. For example, if the adaptive parameters include welding current and voltage, welding current sensors and voltage sensors need to be installed to monitor the real-time values ​​of welding current and voltage, respectively. If the adaptive parameters include weld position, weld tracking sensors, such as laser vision sensors or capacitive sensors, need to be installed to monitor the position and shape of the weld in real time. The deployment of monitoring equipment should be rationally arranged according to the welding process and mold structure to ensure accurate acquisition of the required monitoring data. For example, in the welding of a mold system, welding current and voltage sensors can be installed at the output end of the welding power source, while the weld tracking sensor is installed on the welding torch, moving with the torch to monitor the weld position in real time.

[0031] By rationally deploying welding monitoring equipment, various data during the welding process can be collected in real time, providing accurate information support for subsequent adaptive adjustment and control. This ensures real-time monitoring and dynamic adjustment of the welding process, further improving welding quality and production efficiency, and reducing welding defects and rework rates.

[0032] Step S5: Based on the real-time monitoring data, adaptively adjust the welding control strategy according to the control adjustment relationship.

[0033] Specifically, the system receives the monitoring data collected in step S4 and performs data analysis and processing based on the control and adjustment relationship established in step S3. For example, when the welding current is detected to be lower than the set value, the required increase in welding current is calculated based on the control and adjustment relationship, and a corresponding control signal is sent to the welding power source to adjust the welding current. If a deviation in the weld position is detected, the position and angle that the welding torch needs to be adjusted are calculated based on the data from the weld tracking sensor and the control and adjustment relationship. Then, a control command is sent to the welding robot or the drive device of the welding torch to adjust the position and angle of the welding torch, ensuring the accuracy and quality of the weld. In addition, advanced control methods such as PID controllers and fuzzy control algorithms can be used to adjust welding parameters more precisely to adapt to complex welding environments and changes in working conditions. For example, during the welding process, when changes in ambient temperature cause unstable welding heat input, the PID controller can automatically adjust the welding speed and current based on real-time monitored temperature data to maintain stable welding heat input, thereby ensuring consistent welding quality.

[0034] By adaptively adjusting the welding control strategy based on real-time monitoring data, it is possible to respond promptly to changes in the welding environment and working conditions, maintain the stability of the welding process and the consistency of welding quality, further improve welding efficiency and product quality, reduce manual intervention and debugging time, and realize the automation and intelligence of the welding process.

[0035] Furthermore, in step S1 of this application embodiment, the composition of the mold frame is decomposed, including:

[0036] Step S11: Disassemble the design drawings of the mold frame to obtain the component disassembly structure and welding mark points.

[0037] Step S12: Obtain the workflow of the injection mold base and analyze the workflow function of each component.

[0038] Step S13: Perform functional clustering based on the process functions of each component to obtain the decomposed composition.

[0039] Specifically, the first step is to obtain the complete design drawings of the mold base and view and analyze them using CAD software (such as AutoCAD or SolidWorks). Using the exploded view function of the software, the mold base is decomposed into independent components, resulting in the component disassembly structure, i.e., the disassembled mold base parts and their connection relationships, such as templates, guide pillars, and ejection mechanisms. Based on the annotations and symbols on the drawings, the welding positions and requirements are identified, and welding markings are recorded. For example, in the injection mold base design drawings, the welding markings for the template system (A plate, B plate, support plate, ejector plate) include the welding positions and welding methods (such as butt welds, fillet welds, etc.) between the plates. For the guide system (guide pillars, guide sleeves), the markings indicate the welding positions and accuracy requirements (such as a fit accuracy of ±0.01mm) between the guide pillars and guide sleeves.

[0040] By consulting injection molding process data and equipment manuals, and combining this with actual production experience, the workflow of the injection mold base was determined, namely, the working sequence and coordination of each part of the injection mold base during the injection molding process. For example, the workflow includes: In the mold closing stage, the mold platen system provides sufficient clamping force, and the guiding system ensures precise alignment of the moving and fixed molds; in the injection stage, the mold platen system resists injection pressure, and the guiding system maintains the stability of the mold core; in the cooling stage, the cooling system removes heat from the mold through water circulation, shortening the molding cycle; and in the ejection stage, the ejection mechanism ejects the molded product from the mold. Based on the workflow, the process function of each component was analyzed: the mold platen system provides high rigidity support during mold closing and injection, resisting injection pressure of 150–200 MPa; the guiding system provides precision guidance during mold closing and opening, ensuring mold closing accuracy ≤0.02 mm; the cooling system provides efficient cooling during the cooling stage, with a water pressure test ≥0.6 MPa, shortening the molding cycle; and the ejection mechanism provides stable ejection force during the ejection stage, ensuring complete demolding of the product.

[0041] Based on the analyzed functions of each component, cluster analysis is used to perform functional clustering. For example, the A-plate, B-plate, and support plate, which provide support and resist injection pressure, are grouped into the template system; the guide pillars and guide sleeves, responsible for core alignment and motion guidance, are grouped into the guiding system; the ejector pins and reset rods, used for product demolding, are grouped into the ejection mechanism; and the built-in water channels, responsible for mold cooling, are grouped into the cooling system. Data analysis software (such as Excel and SPSS) can be used to quantify and classify the component functions, and the clustering results are determined by calculating functional similarity or correlation. For example, in Excel, weights and scores can be set for the function of each component, and the K-means clustering algorithm can be used for classification. The final decomposed components include the template system, guiding system, ejection mechanism, and cooling system. The functions of the components within each part are closely related, working together to complete the overall function of the mold base.

[0042] Functional clustering decomposes the mold frame into several functionally related components, providing a reasonable object classification for setting welding target parameters for different components. This helps improve the scientificity and rationality of welding parameter settings, thereby improving the welding quality and overall performance of the mold frame.

[0043] Furthermore, step S13 includes:

[0044] Step S131: Configure the functional clustering center, including template frame, guidance coefficient, ejection mechanism, and cooling system.

[0045] Step S132: Perform process function clustering according to the functional response relationship between each component and the functional clustering center to determine the functional category of each component.

[0046] Step S133: Decompose each component according to the functional category to obtain the decomposed components, each decomposed component including functional labels and soldering marks.

[0047] Specifically, functional cluster centers are pre-defined core concepts representing different functional types, used as reference standards for clustering. Based on the functional requirements of the injection mold base, four functional cluster centers are set: template frame, guiding system, ejection mechanism, and cooling system.

[0048] Functional response relationships refer to the degree to which each component responds to the function represented by the functional cluster center during the workflow; that is, to what extent does the component undertake the function represented by that functional cluster center. For each component, its function in the injection mold base workflow is analyzed, and then the functional relationships between each component and the four functional cluster centers (template frame, guiding system, ejection mechanism, and cooling system) are compared. For example, the reset rod mainly participates in the reset operation of the ejection mechanism during injection molding, so it has a functional response relationship with the ejection mechanism functional cluster center, thus classifying it into the ejection mechanism functional category. Tools such as functional analysis matrices or correlation diagrams can be used to quantify and visualize the relationships between each component and the functional cluster centers, thereby enabling more accurate functional clustering.

[0049] Based on the determined functional categories of each component, components belonging to the same functional category are grouped together to form decomposed components. Each decomposed component is then assigned a corresponding functional label, and welding markers are recorded. For example, components such as plate A, plate B, and support plate, classified as part of the template frame functional category, are grouped into a template frame decomposed component, labeled "template frame," and the welding markers for each component are recorded. Similarly, guide pillars and guide sleeves, classified as part of the guide coefficient functional category, are grouped into a guide coefficient decomposed component, labeled "guide coefficient," and the welding markers are recorded. Likewise, decomposed components for the ejector mechanism and cooling system are formed, each labeled with its corresponding functional label, and the welding markers are recorded. The assembly and annotation functions of CAD software can be used to assist this process, ensuring the accuracy and completeness of the decomposed components.

[0050] By analyzing the functional response relationship between each component and the functional cluster center, the components are accurately classified into their corresponding functional categories, resulting in a decomposed composition with clear functional labels and welding markers. This provides a clear structure and basis for subsequent analysis of welding target parameters and optimization of process parameters, which helps to improve the pertinence and efficiency of the welding process and ensures that the welding quality meets the functional requirements of the mold frame.

[0051] Furthermore, such as Figure 2 As shown, step S1 involves analyzing the welding target parameters of each component according to the functional requirements of the decomposed components, including:

[0052] Step S14: Construct a working simulation model of the injection mold base. The working simulation model includes the three-dimensional model and material properties of the mold base, and defines boundary conditions and load data.

[0053] Step S15: Simulate the injection molding process using the aforementioned work simulation model, and monitor the working status and stress data of each component in the process.

[0054] Step S16: Perform forward functional condition analysis based on the working state, and perform reverse compensation analysis based on the force data to obtain the welding target parameters of each component.

[0055] Specifically, a working simulation model is a computer model used to simulate the behavior and performance of an injection mold base under actual working conditions. It can predict the stress, deformation, and temperature distribution of the mold base during the injection molding process. Boundary conditions are the constraints set in the simulation, such as the injection pressure, holding pressure, and mold opening speed of the injection molding machine. Load data are the various forces that the mold base may experience during the injection molding process, such as the extrusion of liquid plastic and the weight of the mold itself. A working simulation model of the injection mold base is constructed using professional injection molding simulation software (such as Autodesk Moldflow and SolidWorks Simulation). First, based on the mold base design drawings, a three-dimensional model of the mold base is created in the software, including all components such as the moving mold plate, fixed mold plate, core, cavity, and cooling system. Then, corresponding material properties are specified for each component in the model, such as the elastic modulus and thermal conductivity of the mold base material, and the flowability and coefficient of thermal expansion of the plastic raw material. Next, boundary conditions and load data are defined, such as the injection pressure (150-200 MPa), holding pressure, and mold opening speed of the injection molding machine, as well as the extrusion pressure of the liquid plastic and the weight of the mold itself that the mold base may experience during injection molding. Through these settings, a simulation model that can accurately reflect the actual working conditions of the mold base is established.

[0056] Using a constructed simulation model, the injection mold base is simulated at various stages of the injection molding process, including mold closing, injection, holding pressure, cooling, mold opening, and ejection. Simulation parameters, such as injection time, holding pressure time, and cooling time, are set, and the simulation is run. During the simulation, the working status and stress data of each component are monitored. The working status refers to the operation of each component in the injection molding process, such as position, speed, and temperature; the stress data refers to the magnitude and direction of various forces acting on each component during injection, such as injection pressure, holding pressure, and thermal stress in the cooling water channels. For example, the deformation of the mold plate system during the injection stage, the alignment and smoothness of the guiding system during mold closing and opening, the stress on the ejection mechanism during the ejection stage, and the temperature distribution of the cooling system during the cooling stage can be monitored. Monitoring tools and data logging functions in the simulation software can be used to obtain detailed data for each component at different stages.

[0057] Based on the working status of each component in the injection molding process, a forward functional condition analysis is performed to analyze the functional conditions that each component needs to meet, such as high rigidity, precision guidance, and efficient cooling. This determines the relevant welding target parameters, such as weld strength and weld position accuracy. For example, the template system needs to withstand injection pressure of 150–200 MPa during the injection stage, therefore it needs high rigidity and strength to resist deformation and damage caused by pressure. The core welding target parameter is set as: flatness error ≤ 0.03 mm / m. 2 Residual stress ≤ 100MPa; weld strength ≥ 90% of base material; the guiding system needs to maintain precise alignment during mold closing and opening, therefore requiring micron-level precision and wear resistance. The core welding target parameters are: guide post perpendicularity ≤ 0.01mm / m; heat-affected zone (HIAZ) width ≤ 0.3mm; surface hardness ≥ HRC55; the cooling system needs to efficiently remove heat during the cooling stage, therefore requiring good sealing and corrosion resistance. The core welding target parameters are: penetration depth ≥ 1.1 times plate thickness; leakage rate ≤ 1x10⁻⁶. -9 Pam 2 / s; Salt spray corrosion resistance ≥500h. Then, based on the forces and stresses experienced by each component during injection molding, reverse compensation analysis is performed to analyze the necessary compensation measures, such as structural reinforcement and dimensional adjustments. Based on the previously determined welding target parameters, adjustments are made to generate the final welding target parameters for each component to meet functional requirements. For example, if the template system exhibits excessive deformation in the simulation, compensation is needed by increasing welding strength or adjusting the welding sequence to reduce deformation; if the guide system experiences centering deviation during mold closing, compensation is needed by precisely controlling the welding position and dimensions to ensure fitting accuracy. Finally, combining the results of forward functional condition analysis and reverse compensation analysis, the welding target parameters for each component are determined, such as the welding strength requirements for the template system, the welding accuracy requirements for the guide system, and the welding sealing requirements for the cooling system.

[0058] By constructing a working simulation model of the injection mold frame, the injection molding process was simulated. The positive functional condition analysis and reverse compensation analysis were completed. The actual needs and stress conditions of each component in the injection molding process were comprehensively considered. The welding target parameters of each component were accurately determined, which provided a scientific basis for subsequent optimization of welding process parameters and formulation of control strategies. This ensured that the welding process could meet the functional and quality requirements of the mold frame.

[0059] Furthermore, step S2 in this embodiment includes:

[0060] Step S21: Based on the functional labels, extract the component structures of each decomposed component, and identify the welding distribution of the component structures according to the welding mark points.

[0061] Step S22: With the goal of maximizing the welding target parameters, optimize the welding method, welding path, and welding parameters according to the component structure and welding distribution of the decomposed components. When the search target is reached, obtain the welding control strategy for each decomposed component. The search target includes the number of searches and the target parameter threshold.

[0062] Specifically, based on functional labels, the component structures of each decomposed component are extracted from design drawings or 3D models. For example, for the decomposed components of the template frame functional category, the 3D models and material properties of components such as plate A, plate B, and support plate are extracted. Then, based on the identified welding markers, the welding distribution of each component structure is determined. For example, the butt weld positions between plate A and plate B, and the fillet weld positions between the support plate and plates A and B.

[0063] The goal is to maximize the welding target parameters, i.e., to optimize the welding process parameters to achieve the optimal state of these parameters, such as highest welding strength, minimum welding deformation, and highest welding precision. Based on the component structure and welding distribution, an optimization search is performed on the welding method, welding path, and welding parameters. The search objective, i.e., the termination condition of the optimization search, includes reaching a set number of search iterations or a set threshold for the target parameters. First, a suitable welding method is selected; for example, gas shielded welding is chosen for thick plate welding of the template frame, and laser welding is chosen for precision welding of the guide system. Then, the welding path is planned; for example, for complex welding distributions, segmented welding or symmetrical welding paths are used to reduce welding stress and deformation. Next, an initial range of welding parameters is set, such as welding current, voltage, and speed, and an optimization algorithm (such as a genetic algorithm or simulated annealing algorithm) is used for the optimization search. For example, using a genetic algorithm, within the set welding parameter range, through multiple generations of crossover, mutation, and selection operations, the optimal combination of parameters (such as welding strength and welding deformation) is found. During the search process, the target welding parameter values ​​under the current welding parameter combination are continuously evaluated. When the search target is reached (such as the number of searches reaching 100 or the target welding parameter reaching a set threshold), the search stops, and the welding control strategies for each decomposed component are obtained, including the optimal welding method, welding path, and welding parameters.

[0064] By optimizing the welding target parameters, the optimal welding method, welding path and welding parameters were determined for each decomposed component, forming a specific welding control strategy. This not only improved welding quality and efficiency, but also reduced welding defects and rework rate, ensuring the performance and reliability of the mold frame.

[0065] Furthermore, step S22 includes:

[0066] Step S221: Establish a welding process database, including preset welding methods, welding path planning strategies, welding parameter ranges, and welding effects, where welding effects include welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration.

[0067] Step S222: Taking the welding target parameters as the target, establish a target evaluation function based on the influence relationship between the welding method, welding path, welding parameters and welding target parameters. The influence relationship between the welding method and welding target parameters is expressed by the welding stress distribution, welding deformation, welding heat input, welding strength and weld penetration.

[0068] Step S223: Use the target evaluation function to evaluate the welding method, welding path, and welding parameters to perform welding control strategy evaluation, and search for the welding control strategy with the best evaluation value as the optimization result.

[0069] Specifically, a comprehensive welding process database should be established, covering different welding methods, path planning strategies, parameter ranges, and their corresponding welding effects. Welding methods refer to the welding techniques used, such as manual arc welding, gas shielded welding, and laser welding; welding path planning strategies refer to the methods for planning the trajectory and sequence of the welding torch during the welding process, such as segmented symmetrical welding, skip welding, and back-welding; welding parameter ranges refer to the possible values ​​of each parameter during the welding process, such as welding current, voltage, and speed; and welding effects are the quality and performance indicators of the weld after welding, including welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration. For example, for welding template frames, the database could include methods such as segmented symmetrical welding, anti-deformation pre-setting technology, and dynamic heat input control, along with their parameter ranges and effect data. For welding guide systems, it could include methods such as high-energy beam welding technology and precision fixture and positioning systems, along with their parameter ranges and effect data. This data can be obtained through experiments, literature review, and accumulation of practical production experience. A database management system (such as MySQL or Excel) can be used to organize and store this data for easy subsequent querying and retrieval. By establishing a welding process database, abundant reference data is provided for subsequent optimization of welding process parameters, ensuring the scientific nature and practicality of the optimization process and improving the reliability of welding control strategies.

[0070] With the goal of maximizing welding target parameters, an influence model is established based on data from the welding process database, relating welding method, welding path, welding parameters, and welding target parameters. The influence of welding method on welding target parameters is represented by the relationships between welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration. For example, for welding template frames, relationship functions can be established between welding current, voltage, speed, welding strength, and welding deformation, and these functions can be fitted using experimental data or simulation results. For welding guide systems, relationship functions can be established between laser power, welding speed, welding accuracy, and welding strength. These relationship functions can be expressed as linear or nonlinear equations. Finally, these relationship functions are integrated into a target evaluation function to assess different welding control strategies. For example, the optimization objective may be to maximize weld quality (such as strength and penetration) while minimizing deformation and stress concentration. The objective function can be expressed as: J = w1S + w2D + w3H + w4T, where: S represents weld strength (the higher the better); D represents deformation (the smaller the better); H represents penetration depth (needs to be greater than the threshold); T represents heat input (needs to be moderate); and w1, w2, w3, and w4 are weighting coefficients, adjusted through experiments or optimization algorithms. The objective evaluation function provides a quantitative standard for evaluating welding control strategies. Through this function, different welding methods, paths, and parameters can be transformed into a comparable evaluation value, enabling a more scientific and accurate evaluation of various possible welding control strategies, which is beneficial for finding the optimal welding control strategy.

[0071] Using the established objective evaluation function, welding control strategies consisting of various possible welding methods, welding paths, and combinations of welding parameters are evaluated. For example, for welding the template frame, different segmented symmetrical welding sequences and different combinations of welding current and voltage are tried. The welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration under each combination are calculated, and their merits are evaluated using the objective evaluation function. For welding the guide system, different combinations of laser power and welding speed can be tried. Optimization algorithms (such as genetic algorithms and simulated annealing algorithms) can be used to search the welding process database to find the welding control strategy with the best evaluation value. For example, a genetic algorithm can be used to gradually approach the optimal solution through multiple generations of crossover, mutation, and selection operations. Finally, the welding control strategy with the best evaluation value is taken as the optimization result, including the optimal welding method, path, and welding parameters.

[0072] Furthermore, step S3 in this embodiment includes:

[0073] Step S31: Analyze the adjustable parameters of the welding control strategy to obtain the adjustable parameters and the control range.

[0074] Step S32: Establish the controllable response relationship between the adjustable parameters and the welding target parameters.

[0075] Step S33: Obtain regulation benefit data based on the regulation range and regulation response relationship.

[0076] Step S34: Filter the regulation response relationship and the regulation benefit data according to the preset adaptive filtering rules to determine the adaptive parameters.

[0077] Specifically, adjustable parameters are those that can be adjusted and controlled during the welding process, such as welding current, voltage, speed, segment length, and interpass temperature. Analyzing the welding method, welding path, and welding parameters in the welding control strategy identifies adjustable parameters and their permissible range of variation (adjustment range) during welding. For example, for welding template frames, adjustable parameters include welding current (I), welding speed (V), segment length (L), and interpass temperature (T). The adjustment range of these parameters is determined by consulting welding process specifications and actual production experience. For example, the adjustment range of welding current is 150A to 250A, and the adjustment range of welding speed is 0.5m / min to 2.0m / min. Parametric analysis tools (such as Excel and MATLAB) can be used to organize and analyze these adjustable parameters and their ranges. Analyzing the adjustable parameters and their adjustment ranges in the welding control strategy provides a foundation for establishing subsequent control response relationships and adaptive parameter selection, ensuring the flexibility and controllability of the welding process.

[0078] Using sensitivity analysis (such as the Sobol index) and orthogonal experimental design (DOE), combined with simulation and experimental data, the controllable response relationship between adjustable parameters and welding target parameters is established. For example, for welding a template frame, the target parameter is the flatness error Δ, and the adjustable parameters include welding current (I), welding speed (v), segment length (L), and interpass temperature (T). Sensitivity analysis is used to calculate the contribution of each parameter to the flatness error. Assuming the welding current contributes 40%, welding speed 30%, segment length 20%, and interpass temperature 10%, this indicates that welding current and welding speed are the main control parameters for flatness. Mathematical models between these parameters and the flatness error can be established using regression analysis or neural networks. For example, the flatness error Δ can be expressed as: Δ = aI + bv + cL + dT + e, where a, b, c, d, and e are coefficients obtained by fitting experimental data. By establishing the controllable response relationship between adjustable parameters and welding target parameters, the influence of each parameter on the target parameter was quantified, providing a scientific basis for subsequent adaptive parameter selection and control adjustment relationship establishment, and improving the controllability and precision of the welding process.

[0079] Based on the determined control range and control-response relationship, the control benefits of adjusting the controllable parameters within the control range are calculated. For example, for welding a template frame, the control range of the welding current is 150A to 250A, and the control range of the welding speed is 0.5m / min to 2.0m / min. Using a control-response relationship model, the degree of improvement in flatness error Δ when adjusting the welding current and speed within these ranges is calculated. For example, when the welding current increases from 150A to 250A, the flatness error Δ decreases by 20%; when the welding speed increases from 0.5m / min to 2.0m / min, the flatness error Δ decreases by 15%. These improvement data constitute the control benefit data. Virtual experiments can be conducted using simulation software (such as ANSYS or ABAQUS), or data can be collected in actual welding experiments to obtain the control benefit data. By calculating the control benefit data, the improvement effect of adjusting the controllable parameters within the control range on the welding target parameters is quantified, providing data support for subsequent adaptive parameter selection, helping to select the optimal adaptive parameters, and improving welding quality and efficiency.

[0080] According to preset adaptive screening rules, the control response relationship and control benefit data are screened to determine adaptive parameters. For example, the following screening rules are set: High sensitivity: Select process parameters with an influence weight greater than 20% on the target parameter. Adjustability: Parameters must be able to be monitored and dynamically adjusted in real time (e.g., current, speed). Engineering feasibility: Adjustment should not significantly increase cost or complexity. Taking the welding of the template frame as an example, according to the sensitivity analysis results, the contribution of welding current (I) is 40%, welding speed (v) is 30%, segment length (L) is 20%, and interpass temperature (T) is 10%. According to screening rule 1, the influence weights of welding current and welding speed are greater than 20%, which meets the requirements; according to screening rule 2, welding current and welding speed can be monitored and dynamically adjusted in real time through the welding power supply and control system; according to screening rule 3, adjusting welding current and speed will not significantly increase cost or complexity. Therefore, welding current and welding speed are determined as adaptive parameters. By filtering the control response relationship and control benefit data according to the preset adaptive screening rules, the optimal adaptive parameters were determined, ensuring that the adaptive control of the welding process is both effective and feasible, improving welding quality and production efficiency, and reducing costs and complexity.

[0081] Furthermore, the adjustable parameters in step S31 include: direct adjustable parameters and indirect adjustable parameters; when the adjustable parameter is a direct adjustable parameter, the adjustment range is the numerical adjustment range of the direct adjustable parameter; when the adjustable parameter is an indirect adjustable parameter, the adjustment range is a conversion relationship expression with the direct control parameters in the welding control strategy, wherein the indirect adjustable parameter is a parameter that needs to be affected by the synergistic effect of the direct control parameters.

[0082] Specifically, controllable parameters include directly controllable parameters and indirectly controllable parameters. Directly controllable parameters are process parameters that can be directly set or adjusted by the equipment, such as welding current, welding speed, laser power, wire feed speed, and argon flow rate. Indirectly controllable parameters are derivative parameters that cannot be directly set and require the synergistic effect of direct parameters. Examples include heat input, cooling rate, heat-affected zone (HAZ) width, and weld pool depth.

[0083] Extract directly settable or adjustable parameters from the welding control strategy to determine directly controllable parameters, such as welding current, welding speed, and laser power. For example, examine the control panel of the welding equipment; it will have knobs or digital input areas specifically for adjusting parameters such as welding current (I) and welding speed (V). Then, based on the welding process specifications and the characteristics of the workpiece material, determine the numerical adjustment range for each directly controllable parameter.

[0084] Next, the derived parameters that need to be affected by the synergistic effect of direct parameters, i.e., indirect control parameters, such as heat input and cooling rate, are identified. Through experimental data and theoretical models, the mathematical relationship between indirect and direct control parameters is established. For example, for heat input, based on the law of conservation of energy and the principle of heat transfer in the welding process, its conversion relationship with welding current, welding voltage, and welding speed is derived: Q = I × U / V, where I is welding current, U is welding voltage, and V is welding speed. The direct control parameters and their numerical control ranges, as well as the indirect control parameters and their conversion relationship expressions, are integrated into the analytical results of the controllable parameters.

[0085] This paper provides a detailed analysis of the adjustable parameters and their control range in welding control strategies, clarifies the classification and adjustment methods of direct and indirect control parameters, and lays the foundation for establishing subsequent control-response relationships and adaptive parameter selection. This ensures the flexibility and controllability of the welding process and improves welding quality and production efficiency.

[0086] Furthermore, step S32 includes:

[0087] Step S321: Calculate the contribution of the adjustable parameters to the welding target parameters through orthogonal experiments.

[0088] Step S322: Convert the contribution into a response weight, and establish the controllable response relationship between the adjustable parameter and the welding target parameter based on the response weight.

[0089] Specifically, orthogonal experiments are an experimental design method for studying multiple factors and levels. By rationally arranging experimental factors and levels, the experimental points are evenly distributed and representative within the experimental range. This allows for the acquisition of comprehensive experimental information with fewer experiments, enabling the analysis of the influence of each factor (in this case, the adjustable parameters) on the target (in this case, the welding target parameters). The contribution rate indicates the degree of influence of the adjustable parameters on the welding target parameters.

[0090] Adjustable parameters are used as experimental factors, and appropriate numerical ranges within their controllable ranges are selected as the number of levels. For example, welding current is set to three levels: 150A, 200A, and 250A; welding speed is set to three levels: 0.5m / min, 1.25m / min, and 2.0m / min. Based on the number of factors and levels, a suitable orthogonal array is selected to arrange the experiment. Welding experiments are conducted according to the orthogonal experimental design, and the welding target parameter values ​​under each experimental condition are recorded. Statistical methods such as analysis of variance are used to calculate the contribution of each adjustable parameter to the welding target parameter. Orthogonal experimental design software (such as the orthogonal design module in SPSS) can be used to arrange the experiment, measuring instruments (such as strain gauges to measure welding deformation, tensile testing machines to measure welding strength, etc.) can be used to measure the welding target parameters, and statistical analysis software (such as data analysis tools in Excel, SPSS, etc.) can be used for data processing and contribution calculation.

[0091] Response weights are values ​​obtained by converting contribution values ​​and are used to represent the relative importance of adjustable parameters in controlling welding target parameters. The control-response relationship describes the relationship between adjustable parameters and welding target parameters, and the degree of quantification of this relationship is reflected by response weights. The calculated contribution values ​​are normalized and then converted into response weights. For example, if the contribution of welding current is 40%, welding speed is 30%, segment length is 20%, and interpass temperature is 10%, these contribution values ​​can be normalized to obtain response weights. Assuming a total contribution of 100%, then the response weight for welding current is 0.4, the response weight for welding speed is 0.3, the response weight for segment length is 0.2, and the response weight for interpass temperature is 0.1. Then, based on these response weights and combined with experimental data or simulation results, the control-response relationship between adjustable parameters and welding target parameters is established. For example, if the target welding parameter is welding strength, and the adjustable parameters are welding current (I), welding speed (v), segment length (L), and interpass temperature (T), a simple linear control response relationship model can be established: welding strength = 0.4×I + 0.3×v + 0.2×L + 0.1×T.

[0092] By converting contribution values ​​into response weights and establishing a control-response relationship, the influence of controllable parameters on welding target parameters can be clearly defined in a quantitative manner. This relationship can be used to predict the changing trend of welding target parameters when controllable parameters are changed, providing a theoretical basis for optimizing welding control strategies.

[0093] In summary, the welding adaptive control method for mold frame production provided in this application has the following beneficial effects:

[0094] This application's embodiments, through the organic combination of the above steps, form a complete closed-loop control process, realizing the automation, intelligence, and adaptive control of the welding process. Its technical effects are mainly reflected in the following aspects: Through precise target parameter analysis, systematic process parameter optimization, and real-time adaptive adjustment control, welding defects are effectively reduced, significantly improving the consistency and reliability of welding quality; Automated control of the welding process reduces manual intervention and debugging time, while optimized welding parameters make the welding process smoother and more efficient, greatly improving production efficiency; Adaptive parameters determined based on target influence analysis and corresponding control adjustment relationships enable the welding control system to better adapt to different mold compositions and working condition changes, enhancing the adaptability of the welding process.

[0095] Overall, the embodiments of this application realize adaptive parameter adjustment of the welding process, which significantly improves welding quality, welding efficiency, and the stability and reliability of the welding process, making the welding control of mold production more scientific, precise and efficient.

[0096] Example 2, as Figure 3 As shown, based on the same inventive concept as in Embodiment 1 above, this application provides a welding adaptive control system for mold frame production, the system comprising:

[0097] The target analysis module 10 is used to decompose the mold frame components and analyze the welding target parameters of each component according to the functional requirements of the decomposed components.

[0098] The parameter optimization module 20 is used to optimize the welding process parameters of the decomposed components with the welding target parameters as the target, and obtain the welding control strategy for each decomposed component.

[0099] The impact analysis module 30 is used to perform target impact analysis based on the welding control strategy and the welding target parameters, determine adaptive parameters, and establish the control and adjustment relationship between the adaptive parameters and the welding target parameters.

[0100] The welding monitoring module 40 is used to deploy welding monitoring equipment based on the adaptive parameters and collect real-time monitoring data through the welding monitoring equipment.

[0101] The adaptive adjustment module 50 is used to adaptively adjust the welding control strategy according to the real-time monitoring data and the control adjustment relationship.

[0102] Furthermore, in this embodiment of the application, the target parsing module 10 is also used to perform the following steps:

[0103] The design drawings of the mold base are structurally disassembled to obtain the component disassembly structure and welding mark points; the workflow of the injection mold base is obtained, and the workflow function of each component is analyzed; based on the workflow function of each component, functional clustering is performed to obtain the decomposed composition.

[0104] Furthermore, in this embodiment of the application, the target parsing module 10 is also used to perform the following steps:

[0105] Configure a functional clustering center, including a template frame, a guiding coefficient, an ejection mechanism, and a cooling system; perform process function clustering according to the functional response relationship between each component and the functional clustering center to determine the functional category of each component; decompose each component according to the functional category to obtain the decomposed components, each decomposed component including a functional label and welding mark points.

[0106] Furthermore, in this embodiment of the application, the target parsing module 10 is also used to perform the following steps:

[0107] A working simulation model of the injection mold frame is constructed. The working simulation model includes a three-dimensional model of the mold frame and material properties, and defines boundary conditions and load data. The injection molding process is simulated through the working simulation model, and the working status and stress data of each component in the process are monitored. Based on the working status, forward functional condition analysis is performed, and based on the stress data, reverse compensation analysis is performed to obtain the welding target parameters of each component.

[0108] Furthermore, in this embodiment of the application, the parameter optimization module 20 is also used to perform the following steps:

[0109] Based on functional labels, the component structures of each decomposed component are extracted, and the welding distribution of the component structures is identified according to the welding markers. With the goal of maximizing the welding target parameters, the welding method, welding path, and welding parameters are optimized based on the component structures and welding distribution of the decomposed components. When the search target is reached, the welding control strategy of each decomposed component is obtained. The search target includes the number of searches and the target parameter threshold.

[0110] Furthermore, in this embodiment of the application, the parameter optimization module 20 is also used to perform the following steps:

[0111] A welding process database is established, including preset welding methods, welding path planning strategies, welding parameter ranges, and welding effects. The welding effects include welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration. Using the welding target parameters as the objective, a target evaluation function is established based on the influence relationship between the welding method, welding path, welding parameters, and welding target parameters. The influence relationship between the welding method and welding target parameters is represented by the welding stress distribution, welding deformation, welding heat input, welding strength, and weld penetration. The welding control strategy is evaluated using the target evaluation function, and the welding control strategy with the best evaluation value is selected as the optimization result.

[0112] Furthermore, in this embodiment of the application, the impact analysis module 30 is also used to perform the following steps:

[0113] The welding control strategy is analyzed for adjustable parameters to obtain adjustable parameters and adjustment ranges; the adjustment response relationship between the adjustable parameters and the welding target parameters is established; adjustment benefit data is obtained based on the adjustment range and adjustment response relationship; the adjustment response relationship and the adjustment benefit data are filtered according to preset adaptive screening rules to determine the adaptive parameters.

[0114] Furthermore, the adjustable parameters include: direct adjustable parameters and indirect adjustable parameters; when the adjustable parameter is a direct adjustable parameter, the adjustment range is the numerical adjustment range of the direct adjustable parameter; when the adjustable parameter is an indirect adjustable parameter, the adjustment range is a conversion relationship expression with the direct control parameters in the welding control strategy, wherein the indirect adjustable parameter is a parameter that needs to be affected by the synergistic effect of the direct control parameters.

[0115] Furthermore, in this embodiment of the application, the impact analysis module 30 is also used to perform the following steps:

[0116] Through orthogonal experiments, the contribution of the adjustable parameter to the welding target parameter is calculated; the contribution is converted into a response weight, and the controllability-response relationship between the adjustable parameter and the welding target parameter is established based on the response weight.

[0117] Through the foregoing detailed description of the welding adaptive control method for mold frame production, those skilled in the art can clearly understand that the welding adaptive control system for mold frame production in this embodiment, as disclosed in Embodiment 2, corresponds to the method disclosed in Embodiment 1, and has corresponding functional modules and beneficial effects. For relevant details, please refer to the method section.

[0118] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A welding adaptive control method for mold frame production, characterized in that, include: S1: Decompose the mold base components, disassemble the mold base design drawings to obtain the component disassembly structure and welding mark points; obtain the injection mold base workflow, analyze the workflow function of each component; perform functional clustering based on the workflow function of each component to obtain the decomposed components, configure functional clustering centers, including template frame, guide coefficient, ejection mechanism, and cooling system; perform workflow function clustering according to the functional response relationship between each component and the functional clustering center to determine the functional category of each component; decompose each component according to the functional category to obtain the decomposed components, each decomposed component including functional labels and welding mark points; analyze the welding target parameters of each component according to the functional requirements of the decomposed components, and construct a working simulation model of the injection mold base. The working simulation model has a built-in three-dimensional model and material properties of the mold base and defines boundary conditions and load data. The injection molding process is simulated using the aforementioned simulation model, and the working status and stress data of each component in the process are monitored. Based on the working status, forward functional condition analysis is performed, and based on the stress data, reverse compensation analysis is performed to obtain the welding target parameters of each component. S2: Using the target welding parameters as the objective, optimize the welding process parameters for the decomposed components to obtain welding control strategies for each component. Based on functional tags, extract the component structures of each component and identify the welding distribution of the component structures according to the welding markers. With the goal of maximizing the target welding parameters, optimize the welding methods, welding paths, and welding parameters based on the component structures and welding distribution of the decomposed components. Establish a welding process database, including preset welding methods, welding path planning strategies, welding parameter ranges, and welding effects. The welding effects include welding stress distribution, welding deformation, welding heat input, and welding strength.

1. Weld penetration depth; 2. Taking the welding target parameters as the objective, a target evaluation function is established based on the influence relationship between the welding method, welding path, welding parameters and welding target parameters. The influence relationship between the welding method and welding target parameters is represented by the welding stress distribution, welding deformation, welding heat input, welding strength and weld penetration depth. The welding control strategy is evaluated using the target evaluation function, and the welding control strategy with the best evaluation value is searched as the optimization result. When the search objective is reached, the welding control strategy of each decomposed component is obtained. The search objective includes the number of searches and the target parameter threshold. S3: Based on the welding control strategy and the welding target parameters, perform target impact analysis to determine adaptive parameters. Analyze the adjustable parameters of the welding control strategy to obtain adjustable parameters and their controllable ranges. The adjustable parameters include: direct controllable parameters and indirect controllable parameters. When the adjustable parameter is a direct controllable parameter, the controllable range is the numerical control range of the direct controllable parameter. When the adjustable parameter is an indirect controllable parameter, the controllable range is a conversion relationship expression with the direct controllable parameters in the welding control strategy, where the indirect controllable parameter is a parameter that needs to be affected by the synergistic effect of the direct controllable parameters. Establish the controllable response relationship between the adjustable parameters and the welding target parameters. Calculate the contribution of the adjustable parameters to the welding target parameters through orthogonal experiments. Convert the contribution to response weights and establish the controllable response relationship between the adjustable parameters and the welding target parameters based on the response weights. Obtain control benefit data based on the controllable range and controllable response relationship. Filter the controllable response relationship and the control benefit data according to preset adaptive screening rules to determine the adaptive parameters and establish the control adjustment relationship between the adaptive parameters and the welding target parameters. S4: Deploy welding monitoring equipment based on the adaptive parameters, and collect real-time monitoring data through the welding monitoring equipment; S5: Based on the real-time monitoring data, the welding control strategy is adaptively adjusted according to the control adjustment relationship.

2. A welding adaptive control system for mold frame production, characterized in that, The system is used to execute the welding adaptive control method for mold production as described in claim 1, including: The target analysis module is used to decompose the mold frame components and analyze the welding target parameters of each component according to the functional requirements of the decomposed components. The parameter optimization module is used to optimize the welding process parameters of the decomposed components with the welding target parameters as the target, and obtain the welding control strategy for each decomposed component. The impact analysis module is used to perform target impact analysis based on the welding control strategy and the welding target parameters, determine adaptive parameters, and establish the control adjustment relationship between the adaptive parameters and the welding target parameters. The welding monitoring module is used to deploy welding monitoring equipment based on the adaptive parameters and collect real-time monitoring data through the welding monitoring equipment. The adaptive adjustment module is used to adaptively adjust the welding control strategy according to the real-time monitoring data and the control adjustment relationship.

Images