Automatic welding control method and device for copper heat dissipation bottom plate

Abstract

The invention discloses an automatic welding control method and device for a copper heat dissipation bottom plate, and relates to the technical field of welding, and the method comprises the steps that data decomposition is carried out on the copper heat dissipation bottom plate, and partition welding requirements are established; and performing partition quality evaluation by using demands, constructing a quality objective function, and forming a comprehensive objective function in combination with a time and energy consumption objective function. And performing steady-state analysis based on the historical working data of the welding equipment, establishing a parameter limit interval, and performing fitness analysis to obtain a fitness result of the welding parameters. And establishing a second update constraint in combination with the number of iterations. And the initial individual set is iteratively updated through updating constraints, and automatic welding control over the copper heat dissipation bottom plate is achieved. The technical problem that the welding effect is affected due to the fact that multiple influence factors cannot be comprehensively balanced in the existing welding technology is solved, and the technical effects of optimizing the welding process and improving the overall welding effect are achieved.

Description

Technical Field

[0001] The present application relates to the field of welding technology, and in particular to an automatic welding control method and device for a copper heat dissipation base plate. Background Art

[0002] In modern welding processes, there are often contradictions between welding quality, production efficiency and energy consumption. Welding quality directly affects product performance and reliability, while production efficiency determines cost and delivery cycle. At the same time, energy consumption is a key cost factor in the welding process, especially in high-precision welding, where energy is often wasted. Existing welding technologies usually focus on optimizing a single aspect, such as improving welding quality or shortening production time, but ignore the balance between efficiency and energy consumption, resulting in low efficiency and high energy consumption. Current technology lacks a comprehensive solution that can simultaneously optimize welding quality, time efficiency and energy consumption. Therefore, there is an urgent need for a method that can optimize the time and energy consumption in the welding process while ensuring quality, thereby improving the comprehensive performance of the welding process and meeting the industrial needs of energy conservation and environmental protection.

[0003] In the current related technologies, there is a technical problem that multiple influencing factors cannot be comprehensively balanced in welding technology, which affects the welding effect. Summary of the invention

[0004] The present application solves the technical problem that the existing welding technology cannot comprehensively balance multiple influencing factors and affects the welding effect by providing an automated welding control method and device for a copper heat dissipation base plate.

[0005] The present application provides an automated welding control method for a copper heat dissipation base plate, comprising: Data decomposition is performed on the copper heat dissipation base plate to establish partition welding requirements, which include heat conduction requirements, mechanical strength requirements, welding stress requirements, and heat impact requirements; the partition quality evaluation is performed using the partition welding requirements to establish a quality objective function, and a comprehensive objective function is constructed using the quality objective function, time objective function, and energy consumption objective function; historical working data of the welding equipment is obtained, and a working steady-state analysis is performed based on the historical working data to establish a parameter limit range, an initial individual set is established within the parameter limit range, and a fitness analysis is performed on each individual in the initial individual set through the comprehensive objective function to establish a fitness calculation result, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon gas flow rate, and welding angle; distribution analysis is performed on the individuals in the initial individual set to establish distribution clustering, and a first update constraint is established through the distribution clustering and the fitness calculation result; the current number of iterations is obtained, and a second update constraint is established based on the number of iterations; the initial individual set is iteratively updated within the parameter limit range using the first update constraint and the second update constraint, and automatic welding control of the copper heat dissipation base plate is performed according to the iterative update result.

[0006] The present application also provides an automatic welding control device for a copper heat dissipation base plate, comprising: A zoned welding requirement establishment module, the zoned welding requirement establishment module is used to perform data decomposition on the copper heat dissipation base plate and establish zoned welding requirements, the zoned welding requirements include thermal conductivity requirements, mechanical strength requirements, welding stress requirements, and thermal impact requirements; a zoned quality evaluation module, the zoned quality evaluation module is used to use the zoned welding requirements to perform zoned quality evaluation, establish a quality objective function, and use the quality objective function, time objective function and energy consumption objective function to construct a comprehensive objective function; a parameter limit interval establishment module, the parameter limit interval establishment module is used to obtain historical working data of welding equipment, perform steady-state analysis based on the historical working data, establish a parameter limit interval, establish an initial individual set within the parameter limit interval, and perform the initial individual set evaluation through the comprehensive objective function. Fitness analysis of each individual is performed to establish fitness calculation results, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon gas flow rate, and welding angle; a distribution clustering establishment module is used to perform distribution analysis on individuals in the initial individual set, establish distribution clusters, and establish a first update constraint through the distribution clusters and fitness calculation results; a second update constraint establishment module is used to obtain the current number of iterations and establish a second update constraint based on the number of iterations; an automated welding control module is used to iteratively update the initial individual set within a parameter limit range using the first update constraint and the second update constraint, and perform automated welding control of the copper heat dissipation base plate according to the iterative update results.

[0007] The present application proposes an automated welding control method and device for a copper heat dissipation base plate. First, the data of the copper heat dissipation base plate is decomposed, and the zoned welding requirements are established according to the requirements of heat conduction, mechanical strength, welding stress and thermal influence. The requirements are used to evaluate the quality of the zones, construct the quality objective function, and combine the time and energy consumption objective functions to form a comprehensive objective function. A steady-state analysis is performed based on the historical working data of the welding equipment to establish a parameter limit interval, and an initial individual set is generated through the interval, and a fitness analysis is performed to obtain the fitness results of the welding parameters. Distribution analysis and distribution clustering are performed on the individuals to generate update constraints, and a second update constraint is established in combination with the number of iterations. The initial individual set is iteratively updated using the update constraints to achieve automated welding control of the copper heat dissipation base plate. By comprehensively considering multiple influencing factors such as welding quality, time efficiency and energy consumption, the technical effect of optimizing the welding process and improving the overall welding effect is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A schematic flow chart of an automated welding control method for a copper heat dissipation base plate provided in an embodiment of the present application; Figure 2 A schematic structural diagram of an automated welding control device for a copper heat dissipation base plate provided in an embodiment of the present application.

[0010] Explanation of the reference numerals: partition welding requirement establishing module 10 , partition quality evaluation module 20 , parameter limit interval establishing module 30 , distribution clustering establishing module 40 , second update constraint establishing module 50 , automated welding control module 60 . DETAILED DESCRIPTION

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0012] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0013] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0014] The present application embodiment provides an automated welding control method for a copper heat dissipation base plate, such as Figure 1 As shown, the method includes: Step S100, data decomposition of the copper heat sink base plate is performed to establish zoned welding requirements, which include thermal conduction requirements, mechanical strength requirements, welding stress requirements, and thermal impact requirements. Specifically, thermal imagers, three-dimensional laser scanners, material composition analyzers and other equipment are used to comprehensively collect data on the copper heat sink base plate, and the thermal conduction requirements are determined based on the thermal imaging data and the thermal conductivity of the material, that is, areas with large heat flow, such as the roots of the heat sink fins, require low thermal resistance welding joints, and mechanical strength requirements are evaluated based on the geometric shape and stress conditions combined with finite element analysis, such as specific tensile and shear strengths around bolt holes. Considering the thermal expansion coefficient of copper and the welding thermal cycle, the welding stress requirements are analyzed through thermal simulation, such as the need to control stress at the thickness mutation point, and the thermal impact requirements are considered based on the material composition and thermal simulation, such as controlling the thermal impact range near electronic components. Finally, these requirements are integrated to form zoned welding requirements as a basis for subsequent welding.

[0015] Step S200, using the partition welding requirements to evaluate the partition quality, establish a quality objective function, and use the quality objective function, time objective function and energy consumption objective function to construct a comprehensive objective function. Specifically, based on the partition welding requirements, determine the quality evaluation indicators: for the heat conduction requirements, use the weld thermal resistance and heat conduction uniformity as key indicators, determine the range of weld thermal resistance in different partitions through theoretical and practical measurements, and use the standard deviation of temperature distribution to measure uniformity; for mechanical strength requirements, determine according to the load borne by the partition, such as the tensile strength of the tensile zone and the shear strength of the shear zone, and compare the data obtained through corresponding tests with the design requirements; considering the welding stress requirements, take the residual stress size and distribution uniformity as the key points, use specific stress measurement technology to measure the residual stress values ​​of different partitions, and strictly control in stress sensitive areas; for the heat impact requirements, pay attention to the changes in material properties in the heat affected zone, such as measuring hardness changes and observing microstructure changes. Then, evaluate each partition based on these indicators, and set corresponding weights according to the importance of each partition on the overall welding quality. , by scoring the quality evaluation indicators of each partition Perform weighted summation to obtain the partition quality evaluation score to establish the quality objective function, that is, ,in Represents the overall quality objective function value, Indicates The quality evaluation index score of each partition is Indicates The weight of the partition, Represents the total number of partitions. Then, the time objective function is constructed, considering the rationality of the total duration and the partition welding time allocation. The welding speed is determined by collecting and analyzing the operation data of the welding equipment to calculate the partition welding time and add the auxiliary time, that is, ,in represents the time objective function value, Indicates Welding time per zone, represents auxiliary time; the energy consumption objective function focuses on the energy consumption of the welding process, considers the influence of different welding parameters, and uses the power sensor to measure the power and combine the welding time to calculate the partition and total energy consumption, such as in represents the energy consumption objective function value, Indicates The power of each zone during welding, Indicates Welding time per zone, Indicates the energy consumed by the operation of other equipment except the welding process (such as cooling system, ventilation system, etc.). Finally, factors such as product quality, production efficiency and cost control are comprehensively considered to assign weights to the quality, time and energy consumption objective functions. Constructing a comprehensive objective function Used for subsequent welding parameter optimization to balance welding quality, time and energy consumption to achieve the best welding effect and economic benefits.

[0016] Step S300, obtain the historical working data of the welding equipment, perform steady-state analysis based on the historical working data, establish a parameter limit range, establish an initial individual set within the parameter limit range, and perform fitness analysis on each individual in the initial individual set through the comprehensive objective function to establish a fitness calculation result, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon flow rate, welding angle. Specifically, obtain historical working data covering different welding projects, materials and process requirements from the control system database or storage unit of the welding equipment, including information such as current, voltage, welding speed, argon flow rate, welding angle, time, energy consumption and welding quality evaluation results, and classify and organize them according to welding task type, material type and process similarity. Then, carry out steady-state analysis on the organized data, use statistical methods to calculate the mean, standard deviation, maximum value and other statistical quantities of each welding parameter under different conditions, analyze its change trend and distribution, determine the reasonable value range of each parameter when the equipment is working stably and the quality is basically qualified, and establish a multi-dimensional parameter limit range by comprehensively considering the mutual influence relationship between each parameter. Then, within the parameter limit range, random sampling or specific algorithms are used to construct the initial individual set. Each individual represents a complete welding parameter combination including current, voltage, welding speed, argon gas flow rate and welding angle. The scale depends on the complexity of the problem and computing resources. Finally, the welding parameter combination of each individual in the initial individual set is substituted into the comprehensive objective function for fitness analysis. The welding quality, time and energy consumption objective functions are comprehensively considered. The corresponding index data is obtained through simulation or small sample welding test and substituted into the function to calculate the fitness value. This value reflects the individual's quality. After analyzing all individuals, a fitness calculation result set is established to provide an evaluation basis for iterative optimization to approach the optimal welding parameter combination.

[0017] Step S400, the individuals in the initial individual set are subjected to distribution analysis, distribution clustering is established, and the first update constraint is established through the distribution clustering and fitness calculation results. Specifically, a multivariate statistical analysis method is adopted, the individuals in the initial individual set are regarded as high-dimensional space data points, each welding parameter is used as a dimension, the similarity and difference of individuals in the parameter space are measured by Euclidean or Mahalanobis distance, and clustering algorithms such as DBSCAN or K-Means are used to divide multiple distribution clusters according to the individual distance relationship. The density-based algorithm identifies the data point dense area as the cluster core and includes the surrounding connected points. The algorithm based on division allocates individuals according to preset criteria. Then, for each distribution cluster, the individual fitness calculation results are compared, and the individual with the best fitness in the cluster is determined as the center point in the cluster, which represents the individual with better comprehensive performance in the cluster parameter area. Then, all the center points in the cluster are globally analyzed to find the individual with the highest fitness value as the calibration center point, which reflects the direction of the better solution in the current parameter exploration range. Then, based on the center point in the cluster, the trend of individuals in the cluster approaching it is analyzed, and the update strategy is designed according to the difference in the dimensions of welding parameters between individuals and the center point. For example, in the current dimension, when the individual current is greatly different from the center point and the fitness is low, the adjustment ratio is determined according to the distance between the individual and the center point, the fitness difference and the preset learning rate, so that the individual approaches the better parameter combination represented by the center point. This is the first follow-up update. Based on the calibration center point, the trend of individuals in the initial individual concentration approaching it is analyzed. Similarly, the strategy is designed according to the difference in parameter dimensions. For example, in the welding speed dimension, when the individual speed is different from the center point and the fitness is low, the adjustment range is determined according to the distance between the individual and the center point, the fitness difference and the global exploration and convergence balance factor, so that the individual explores in the direction of the global optimal solution. This is the second follow-up update. Finally, the first follow-up update and the second follow-up update are jointly analyzed to construct the first update constraint. The weight distribution of the two is comprehensively considered, and the influence ratio is dynamically adjusted according to factors such as the current number of iterations, clustering stability, and the degree of individual distribution discreteness. Reasonable weights and constraints are set to balance individuals between local optimization and global exploration. The first update constraint is constructed to guide individuals to search for directions and step sizes in the parameter space to approach the optimal welding parameter combination.

[0018] In a possible implementation, the individuals in the initial individual set are subjected to distribution analysis, distribution clustering is established, and the first update constraint is established through the distribution clustering and fitness calculation results. Step S400 further includes step S410, comparing the fitness calculation results of the individuals in each clustering cluster in the distribution clustering, and establishing the center point in the cluster. Specifically, for each clustering cluster in the distribution clustering, the fitness calculation results of the individuals therein are analyzed. The fitness calculation results are obtained based on the comprehensive objective function constructed previously, which comprehensively considers multiple factors such as welding quality, time and energy consumption. By comparing the fitness value of each individual one by one, the individual with the highest fitness in the clustering cluster is accurately found. The individual is the center point in the cluster, and it shows the relatively optimal comprehensive performance in the specific parameter space area covered by the cluster, which means that its corresponding welding parameter combination can better balance the welding quality, time consumption and energy consumption level in the local area, providing a key reference benchmark for subsequent local optimization.

[0019] Step S420, based on the center point in the cluster, individual tracking analysis is performed in each cluster cluster to establish a first tracking update. Specifically, with the determined center point in the cluster as the core, a detailed tracking analysis is carried out on the individuals in each cluster cluster. The differences between each individual and the center point in the cluster in various welding parameter dimensions are analyzed, and the dimensions include current, voltage, welding speed, argon gas flow rate and welding angle. For example, in the current dimension, if the current value of an individual deviates greatly from the current value of the center point in the cluster, and the fitness value of the individual is significantly lower than that of the center point in the cluster, then a targeted update strategy needs to be formulated. According to multiple factors such as the difference in current value between the individual and the center point, the degree of difference in fitness between the two, and the pre-set learning rate, the adjustment ratio of the individual current value to the current value of the center point in the cluster when updating is determined. For other welding parameter dimensions, such as voltage, welding speed, etc., the same analysis method is also used to determine the corresponding adjustment strategy. Through analysis, each individual in the cluster is prompted to gradually move closer to the better parameter combination represented by the center point of the cluster, so as to deeply explore better welding parameter solutions in the local area. The purpose of the first follow-up update is to achieve optimal search in the local parameter space and improve the comprehensive welding performance in the local area.

[0020] Step S430, perform a global center point analysis on the center point in the cluster, establish a calibration center point, perform a follow-up analysis on each individual in the initial individual set based on the calibration center point, and establish a second follow-up update. Specifically, perform a global center point analysis on the center point in each cluster. Analyze the fitness values ​​of all the center points in the cluster, select the individual with the highest fitness, and establish it as the calibration center point. The calibration center point stands out from the entire initial individual set, representing the individual with the most outstanding performance under the comprehensive objective function evaluation, and reflects a highly potential and optimal solution direction found within the entire parameter space that has been explored. Based on this calibration center point, perform an in-depth follow-up analysis on each individual in the initial individual set. Analyze the differences between each individual and the calibration center point in each welding parameter dimension. For example, in the welding speed dimension, if there is a significant difference between the welding speed of an individual and the welding speed of the calibration center point, and the fitness value of the individual is lower than that of the calibration center point, then based on the difference in welding speed between the individual and the calibration center point, the difference in fitness, and the global exploration and convergence balance factor, determine the adjustment range of the individual welding speed to approach the welding speed of the calibration center point when updating. Similar analysis and adjustment range determination are also performed for other welding parameter dimensions. Through such operations, the individuals in the entire initial individual set are guided to explore and approach the direction of the global optimal solution to a certain extent. This process is the second follow-up update, which helps to avoid falling into the local optimal solution in the global scope and helps the entire parameter optimization process to develop in a better direction.

[0021] Step S440, performing a joint update analysis on the first follow-up update and the second follow-up update to establish a first update constraint. Specifically, performing a joint update analysis on the first follow-up update and the second follow-up update to construct a first update constraint. In the complex process of iterative update, it is necessary to carefully balance the in-depth exploration of individuals in the local clustering area and the moderate search towards the global optimal solution to prevent prematurely falling into the local optimal solution and missing the global optimal parameter combination. Therefore, when constructing the first update constraint, it is necessary to comprehensively weigh the weight distribution of the first follow-up update and the second follow-up update. The weight distribution is not fixed, but dynamically adjusted, based on factors including the current number of iterations, the stability of the clustering, and the degree of discreteness of the distribution of individuals in the parameter space. For example, in the early stage of iteration, when the clustering is not yet stable and the individual distribution is relatively discrete, the weight of the second follow-up update is appropriately increased to encourage the individual to conduct a wider exploration in the global scope; as the iteration progresses, when the clustering gradually stabilizes and the individual begins to converge to the local area, the weight of the first follow-up update can be appropriately increased to promote the individual to perform more refined optimization in the local area. By setting weights and other related constraints reasonably, we can ensure that individuals can strike a balance between local optimization and global exploration in the updating process, thus successfully establishing an effective first update constraint. This constraint will accurately guide the search direction and step size selection of individuals in a broad parameter space in the subsequent iterative update process, gradually and robustly approaching the optimal welding parameter combination, and providing a solid and reliable parameter guarantee for achieving high-quality, high-efficiency and low-energy consumption welding processes.

[0022] Step S500, obtaining the current number of iterations, and establishing a second update constraint based on the number of iterations. Specifically, the current number of iterations is accurately obtained from the iterative process of the welding parameter optimization algorithm. As a key mark, it reflects the progress stage of the algorithm when searching for the optimal welding parameter combination. The number of iterations is small at the beginning and gradually increases as the process progresses. Then, the preset iterative exploration constraint is obtained, which is based on the prior knowledge of the welding parameter optimization problem and the expected path setting, and stipulates the depth and breadth requirements of the parameter space exploration at different iteration stages. The current number of iterations is matched with it to obtain the matching result. For example, in the early iteration, the matching result will guide the algorithm to randomly select welding parameters in a large range for trial, and in the later stage, it will search in depth in a small range near the existing better solution. Then, the fitness calculation result is used to perform individual convergence analysis. By observing the changes in the fitness values ​​of individuals in multiple iterations, if most of the individual fitness values ​​change little or approach a stable value, it indicates that they may converge to the vicinity of the local or global optimal solution. Based on this, the matching result is compensated. When the convergence is too fast, the exploration range is expanded or the randomness is increased to jump out of the local optimum. When the convergence is too slow, the exploration range is reduced to increase the convergence speed, thereby obtaining the compensation exploration constraint. Finally, the individual convergence analysis results are used to create random factors. The higher the convergence degree, the greater the value range or influence, so as to increase the randomness of iterative updates and prevent falling into a fixed mode. The compensatory exploration constraint is combined with the random factor to construct the second update constraint, which acts together with the first update constraint in the iterative update process of the initial individual set. It can dynamically adjust the direction and amplitude of individual updates according to the number of iterations, individual convergence status, etc., to ensure that the algorithm converges to the optimal solution and avoids local optimality, and searches for the optimal welding parameter combination in the parameter space to help realize high-quality, high-efficiency and low-energy consumption welding processes.

[0023] In a possible implementation, the current number of iterations is obtained, and a second update constraint is established based on the number of iterations. Step S500 further includes step S510, obtaining a preset iterative exploration constraint, performing iterative exploration constraint matching through the number of iterations, and establishing a matching result. Specifically, the preset iterative exploration constraint is obtained. The preset constraint is determined during the entire welding parameter optimization scheme design phase after comprehensive consideration of multiple factors such as welding process characteristics, parameter relationships, and past similar optimization experience. The specific depth and breadth requirements for exploring the welding parameter space at different stages of the optimization algorithm iteration process are specified in detail. For example, it is stipulated that in the early stage of iteration, the current parameter should be widely explored in a larger range (such as [100A~200A]), the voltage parameter should be in a wider range (such as [15V~25V]), and the corresponding wide range of other welding parameters to ensure that the possible high-quality parameter combination area will not be missed; in the later stage of iteration, as the high-quality parameter area is gradually locked, it is required to narrow the current exploration range to [130A~170A], the voltage range to [18V~22V], etc., for more detailed local exploration. Then, the currently obtained number of iterations is matched with this preset iterative exploration constraint. Through a specific matching algorithm or rule, it is determined which stage range of the current number of iterations in the preset constraint is determined, so as to determine the corresponding exploration depth and breadth requirements, and finally establish a matching result. For example, if the current number of iterations is 10, and the preset constraint stipulates that the first 20 iterations are the extensive exploration stage, then the matching result is to set the value range and exploration method of the welding parameters according to the requirements of the extensive exploration stage.

[0024] Step S520, use the fitness calculation results to perform individual convergence analysis, compensate the matching results based on the individual convergence analysis results, and establish compensatory exploration constraints. Specifically, use the fitness calculation results previously calculated by the comprehensive objective function to carry out individual convergence analysis. Detailed review of the fitness value change trajectory of each individual during multiple iterations. For example, draw a curve chart of each individual fitness value as the number of iterations changes, and observe the trend of the curve. If it is found that the fitness value curves of a large number of individuals gradually tend to be flat in recent iterations, that is, the change in fitness value is extremely small, such as in 5 consecutive iterations, the rate of change of individual fitness value is less than 0.1%, indicating that the individual has begun to converge to a local optimal solution or a region close to the global optimal solution. Based on the individual convergence analysis results, the matching results obtained previously are compensated and adjusted. If it is judged that the individual convergence speed is too fast, it reflects that the algorithm has fallen into the trap of local optimal solution. At this time, the matching result needs to be corrected. For example, the narrow parameter exploration range originally specified in the current iteration stage can be appropriately expanded, such as widening the current parameter exploration range from [130A~150A] to [120A~160A]. At the same time, the randomness of the exploration can be increased, such as randomly selecting parameter values ​​with a certain probability within the new exploration range, rather than selecting them according to the conventional order or rules, so as to jump out of the limitation of the local optimal solution; on the contrary, if the individual convergence is too slow, it may be necessary to tighten the exploration range appropriately and speed up the convergence speed, such as narrowing the voltage parameter exploration range from [18V~22V] to [19V~21V], so as to obtain the optimized compensation exploration constraint, which provides a basis for the subsequent construction of more reasonable update constraints.

[0025] Step S530, using the individual convergence analysis results to create a random factor, and establishing a second update constraint based on the random factor and the compensatory exploration constraint. Specifically, the random factor is created based on the individual convergence analysis results. When the individual convergence is more significant, such as the fitness values ​​of multiple individuals stagnate for a long time or fluctuate within a very small range, it indicates that the algorithm is hovering near the local optimal solution and is difficult to break through. At this time, a random factor is created, and the value range or influence of the random factor is closely related to the degree of convergence of the individual. The higher the degree of convergence, the larger the value range of the random factor or the higher the weight of its influence on parameter update. For example, if the individual fitness value has almost no change for 8 consecutive iterations, the value range of the random factor can be set to [0.5~1.5], which will change the original update direction or step size by a large margin when the parameters are updated; and if the degree of convergence is relatively light, the value range of the random factor can be reduced to [0.8~1.2]. The created random factor is combined with the previously obtained compensatory exploration constraint to construct the second update constraint. During the iterative update process, the second update constraint will flexibly and dynamically adjust the update direction and amplitude of the individual according to multiple factors such as the optimization stage reflected by the current number of iterations and the optimization state reflected by the individual convergence. For example, in a certain iteration, the current number of iterations is in the mid-term stage, the individual has a certain degree of convergence, the current parameter update step size determined by the compensation exploration constraint is 5A, and the random factor value is 1.3, then the actual current parameter update step size will become 5A*1.3=6.5A. In this way, it can ensure that the algorithm can continue to converge steadily towards the optimal solution, and effectively avoid falling into the dilemma of local optimal solution, so as to more efficiently search for the optimal welding parameter combination in the entire welding parameter space, and lay a solid foundation for parameter optimization to achieve high-quality, high-precision and low-energy consumption welding processes.

[0026] Step S600, iteratively update the initial individual set within the parameter limit interval using the first update constraint and the second update constraint, and perform automatic welding control of the copper heat dissipation base plate according to the iterative update result. Specifically, the initial individual set within the parameter limit interval is iteratively updated according to the first update constraint and the second update constraint. For each individual in the individual set in each iteration, the parameters such as welding current, voltage, welding speed, argon gas flow rate and welding angle are adjusted according to the two constraints. For the first update constraint, the local optimization of the center point in the cluster is combined with the global exploration information of the calibration center point. For example, for the current parameter adjustment, the current value of the center point in the cluster where the individual is located is 150A, and the individual current value is 130A. When the adjustment ratio is 0.2 calculated according to the cluster following update rule, the individual current value is updated to 134A; the second update constraint introduces random factors and compensation exploration constraints according to the number of iterations and the convergence of the individual. For example, the individual has a convergence trend in the middle of the iteration, and the compensation exploration constraint narrows the voltage adjustment range. The random factor is 1.1. When the original voltage adjustment range of the individual is 2V, the actual adjustment range becomes 2.2V and is within the parameter limit range. In this way, the individual updates the parameters in the iteration and moves to a better area. After multiple rounds of iterative updates, the optimal welding parameter combination of individuals at different stages is obtained. When performing automated welding control of copper heat dissipation baseplates, first select the parameter combination suitable for the current task from the iteration results according to the partition welding requirements and the previous quality, time, and energy consumption objective functions. For example, when the thermal conduction requirements in the welding area are high, select a combination with excellent thermal conduction indicators and balanced time and energy consumption. The selected parameters are then transmitted to the automated welding equipment control system, which precisely regulates the welding parameters and welds according to the predetermined process and sequence. During welding, the equipment operating status and welding quality indicators, such as weld appearance, heat-affected zone size, joint strength, etc., are continuously monitored to ensure that welding is performed according to the selected parameters and that the expected quality requirements are met. If there are abnormalities such as welding parameters deviating from the set values ​​or quality degradation, the automated welding control system will adjust according to the preset error correction mechanism, such as suspending calibration parameters or adjusting speed, current, etc. to compensate for abnormal effects, to ensure that the entire welding process is completed efficiently, stably, and with high quality.

[0027] In a possible implementation, the first update constraint and the second update constraint are used to iteratively update the initial individual set within the parameter limit range, and the automatic welding control of the copper heat dissipation base plate is performed according to the iterative update result. Step S600 further includes step S610, using the first update constraint and the second update constraint to perform position update analysis on each individual in the initial individual set to create a pre-update result. Specifically, for each individual in the initial individual set, a position update analysis is performed based on the first update constraint and the second update constraint. The first update constraint integrates the local optimization information based on the center point within the cluster and the global exploration information based on the calibrated center point. For example, when analyzing the update of welding current parameters, if the current value of the center point of the cluster where an individual is located is 160A, and the current value of the individual is 140A, according to the individual following update rule in the cluster, the adjustment amplitude to approach the center point in the cluster is calculated to be 5A. At the same time, considering the number of iterations in the second update constraint, the random factor determined by the individual convergence (assuming it is 1.05) and the compensation exploration constraint, the update amount of the individual current value is finally determined to be 5A*1.05=5.25A, and the updated current value is 145.25A. Similar calculations and analyses based on two constraints are performed on the welding voltage, welding speed, argon gas flow rate and welding angle parameters of each individual, so as to obtain the pre-update results of each individual in this iteration, which represent the new position information that the individual is about to move to in the parameter space according to the constraints.

[0028] Step S620, perform a neighboring interference analysis on the pre-update result and establish an interference mark. Specifically, after obtaining the pre-update result, perform a neighboring interference analysis on the result. Each pre-update individual is regarded as a point in the parameter space, and the distance relationship between the pre-update individuals is calculated. For example, the Euclidean distance formula is used to calculate the distance between two individuals in the space composed of multi-dimensional parameters such as current, voltage, welding speed, argon gas flow rate and welding angle. If it is found that some individuals are too close to other individuals after the pre-update, for example, the number of individuals within a certain parameter range (such as the current value difference is less than 3A, the voltage value difference is less than 0.5V, etc.) exceeds the preset interference threshold (assuming 5), it is considered that there is neighboring interference between the individuals. For individuals with neighboring interference, an interference mark is established, which records the information of the interfered individual and the degree of interference, such as the number of the interfering individual and the average distance between the interfering individual and the neighboring individual, so as to carry out targeted processing later.

[0029] Step S630, performing center search avoidance on the pre-update result through the interference identifier, and establishing a center search avoidance result. Specifically, according to the established interference identifier, a center search avoidance operation is performed on the pre-update result. For individuals identified as having adjacent interference, their positions in the parameter space are recalculated to keep them away from the area that may currently cause interference. For example, taking the center point of the cluster in which the individual is located as a reference, if the individual is too close to other individuals after the pre-update and causes interference, then it is moved a certain distance in the direction away from the interference area. The specific moving distance and direction can be determined according to factors such as the degree of interference, the shape and distribution of the cluster, etc. For example, by calculating the line vector connecting the interfering individual and the center point in the cluster, and then determining an offset vector in a direction perpendicular to the vector, and determining the length of the offset vector according to the degree of interference, new position information is obtained, thereby establishing a center search avoidance result. For individuals that are not identified as having interference, their pre-update results are directly used as center search avoidance results and remain unchanged.

[0030] Step S640, using the center search avoidance result to complete the iterative update. Specifically, the center search avoidance result is used to complete this iterative update. The parameter values ​​in the center search avoidance result of each individual, such as the updated current, voltage, welding speed, argon flow rate, welding angle and other parameters, are formally applied to the individual parameter settings to replace the original parameter information of the individual. The initial individual set has completed an iterative update process, the position of the individual in the parameter space has been updated and optimized, and the adverse effects that may be caused by excessive proximity between individuals have been avoided, laying a better foundation for the next iterative update, and gradually promoting the entire welding parameter optimization process to develop in a better direction, so as to finally obtain the best welding parameter combination that meets the welding requirements of the copper heat dissipation base plate.

[0031] In a possible implementation, the iterative update is completed using the center search avoidance result, and step S640 further includes step S641, executing individual iteration records and generating continuous iteration evaluation. Specifically, in the entire iterative process of welding parameter optimization, the system will perform individual iteration recording operations for each individual. The recorded content covers the various parameter information of the individual at each iteration, including the specific values ​​of parameters such as welding current, voltage, welding speed, argon gas flow rate and welding angle, and also records the fitness value calculated by the individual according to the comprehensive objective function after each iteration. Based on these rich iterative record data, a continuous iteration evaluation is further generated. The calculation method of the continuous iteration evaluation is to analyze the fitness value change trend, parameter fluctuation range and relative advantages and disadvantages relationship between the individual and other individuals in the process of several consecutive iterations, and use a specific evaluation algorithm for comprehensive evaluation. For example, if the fitness value of an individual increases very little in five consecutive iterations and always fluctuates within a narrow range, and its comprehensive performance (taking into account aspects such as welding quality, time and energy consumption) continues to be at a lower level compared with other individuals in the group, then its continuous iteration evaluation will be low; on the contrary, if the fitness value of the individual shows a stable upward trend in continuous iterations, the parameter changes are reasonable, and the comprehensive performance gradually approaches or surpasses the excellent individuals in the group, then the continuous iteration evaluation will be high.

[0032] Step S642, if the continuous iteration evaluation is lower than the preset threshold, an elimination instruction is generated, the corresponding individual is eliminated according to the elimination instruction, and the newly added individual is reconstructed within the parameter limit range, and the newly added individual is added to the corresponding individual set. Specifically, when the calculated continuous iteration evaluation is lower than the preset threshold, the system will automatically generate an elimination instruction. The preset threshold is a critical value set at the beginning of the entire optimization scheme design based on the accuracy requirements of the welding parameter optimization target, the limitation of computing resources, and the expectation of the algorithm convergence speed. Once the continuous iteration evaluation of an individual is lower than the threshold, it reflects that the individual has fallen into a local optimal solution or its optimization progress is extremely slow in the current iteration process, and the contribution to the exploration of the entire group towards the global optimal solution is small, and it may even interfere with the overall optimization process. According to the generated elimination instruction, the system will accurately eliminate the corresponding individual, remove it from the current individual set, thereby reducing unnecessary waste of computing resources and making room for the introduction of more potential individuals. After eliminating the individual, in order to maintain the diversity and exploration ability of the individual set, it is necessary to reconstruct the newly added individual within the parameter limit range. The process of reconstructing the newly added individuals is to determine the welding parameters of the newly added individuals by random generation or based on a specific distribution model (such as normal distribution, uniform distribution, etc.) within the previously determined parameter limit range. For example, a current value can be randomly generated according to a uniform distribution within the limit range of the current parameter, and then the corresponding parameter values ​​are randomly generated within the limit range of parameters such as voltage, welding speed, argon flow rate and welding angle, thereby forming a new individual. The newly added individuals generated by the reconstruction are added to the corresponding individual set, so that the individual set can continue to maintain the ability to explore the entire parameter space, avoid the reduction of the search range due to the elimination of individuals, and help the entire optimization algorithm to jump out of the local optimal solution in the subsequent iteration process, and continue to explore and optimize in the direction of the global optimal welding parameter combination, thereby increasing the probability of finally obtaining a high-quality, high-efficiency and low-energy consumption welding parameter combination.

[0033] In a possible implementation, the initial individual set is iteratively updated within the parameter limit interval using the first update constraint and the second update constraint, and the automated welding control of the copper heat dissipation base plate is performed according to the iterative update result. Step S600 further includes step S650, configuring a sensor group, wherein the sensor group includes a thermal imager and a laser rangefinder. Specifically, the sensor group is configured, and a thermal imager and a laser rangefinder are selected as core monitoring equipment. The thermal imager can accurately capture the temperature distribution of the copper heat dissipation base plate during the welding process. Its working principle is based on the infrared radiation characteristics of the object. By detecting and analyzing the infrared intensity radiated from different areas, it is converted into a visual thermal image, thereby clearly presenting the temperature change details of the welding area and the surrounding areas, including the degree of heat concentration at the weld, the temperature diffusion range of the heat-affected zone and other information. The laser rangefinder is used to measure the shape changes of various parts of the base plate during the welding process and the relative position relationship between the welded parts. It uses the reflection time of the laser beam to calculate the distance and can monitor the deformation of the base plate under the action of welding thermal stress with high precision, such as measuring the degree of bulge or depression in the area near the welding point, as well as the changes in spacing between different welded parts, providing key geometric shape data support for subsequent welding quality evaluation and parameter adjustment.

[0034] Step S660, using the sensor group to perform real-time welding monitoring of the copper heat dissipation base plate, and establish real-time welding monitoring feedback. Specifically, the configured sensor group is used to perform all-round real-time monitoring of the welding process of the copper heat dissipation base plate. The thermal imager continuously collects thermal image data of the welding area, and each thermal image contains a large number of temperature information points, which form a detailed data matrix about the welding temperature field. By analyzing and processing the data matrix, important parameters related to heat conduction such as the real-time thermal resistance of the weld (calculated according to the temperature gradient and the law of heat conduction) and the temperature change rate of the heat-affected zone are obtained. The laser rangefinder performs distance measurement according to the set time interval or trigger condition, obtains the shape and position data of the base plate at different welding stages, for example, records the initial flatness of the base plate and the relative position of each component at the beginning of welding, and continuously monitors the shape and position changes caused by thermal deformation during the welding process. The temperature data and shape and position data collected by the thermal imager and the laser rangefinder are integrated and analyzed to establish real-time welding monitoring feedback. This feedback includes a variety of information such as the thermal behavior characteristics and geometric structure change characteristics of the copper heat sink during the welding process. It is a comprehensive and real-time description of the welding process status and provides a basic data source for subsequent optimization control.

[0035] Step S670, the real-time welding monitoring feedback and the iterative update result are synchronized to the feedback optimization network to generate a closed-loop control feedback. Specifically, the real-time welding monitoring feedback data and the iterative update result of the welding parameters obtained by the previous iterative update are synchronously transmitted to the feedback optimization network. The feedback optimization network is an intelligent system that integrates data processing, model analysis and decision-making functions. In this network, the real-time welding monitoring feedback data is first cleaned and feature extracted to remove noise data and extract key features that can reflect welding quality and process stability, such as abnormal temperature fluctuation points and areas with excessive shape deformation; at the same time, the welding parameter information in the iterative update result is sorted and analyzed to clarify the influence trend of different parameter combinations on the welding process. Then, the processed monitoring feedback data and iterative update result data are input into the pre-established welding process model, which is a thermal-mechanical coupling model based on physical principles, or a machine learning model trained based on a large amount of experimental data. Through the calculation and analysis of the model, the welding quality target (such as weld strength, heat conduction efficiency), time target (total welding time) and energy consumption target (total energy consumption of the welding process) are comprehensively considered to generate a closed-loop control feedback. This closed-loop control feedback is a comprehensive information set that includes an evaluation of the current welding process and suggestions for the next step of welding parameter adjustment. It can not only point out the problems in the current welding process (such as excessive temperature may cause the heat affected zone to be too large, deformation beyond the allowable range, etc.), but also propose specific welding parameter adjustment directions and amplitudes based on model prediction and optimization algorithms (such as reducing current to reduce heat input, adjusting welding speed to control heat affected time, etc.).

[0036] Step S680, optimizing the welding of the copper heat dissipation base plate according to the closed-loop control feedback. Specifically, optimizing the welding process of the copper heat dissipation base plate according to the generated closed-loop control feedback. If the closed-loop control feedback indicates that the temperature of a certain area in the current welding process is too high and the heat-affected zone has a tendency to expand, then according to the parameter adjustment suggestions in the feedback, reduce the welding current or increase the welding speed to reduce the welding heat input, thereby controlling the temperature rise and the range of the heat-affected zone. If the feedback shows that the base plate has a large deformation during the welding process, the welding sequence may be adjusted or process measures such as pre-deformation may be adopted, and the welding parameters may be adjusted accordingly, such as reducing the welding heat input in the deformation-sensitive area, increasing the rigid support for the deformation area or adopting a pre-processing method of reverse deformation. During the entire welding process, the above-mentioned closed-loop control process of real-time monitoring, feedback generation and optimization adjustment is continuously repeated, and the welding parameters are adjusted in time according to each closed-loop control feedback to ensure that the welding process always moves towards the goal of optimizing welding quality, shortening welding time and reducing welding energy consumption, and finally achieving the optimization effect of high quality, high efficiency and low energy consumption of copper heat dissipation base plate welding.

[0037] In a possible implementation, the sensor group is used to perform real-time welding monitoring of the copper heat dissipation base plate, and real-time welding monitoring feedback is established. Step S660 further includes step S661, which performs joint authentication of feedback frequency and feedback strength on the real-time welding monitoring feedback, and establishes a joint authentication result. Specifically, the joint authentication of feedback frequency and feedback strength is carried out for the real-time welding monitoring feedback. For the authentication of feedback frequency, it is necessary to determine whether the number of welding monitoring feedback data received per unit time meets the preset frequency range. For example, if it is preset that 10 temperature monitoring data and 5 shape monitoring data should be received per second, the system will count the actual receiving frequency and analyze its deviation from the preset frequency. If the receiving frequency of temperature monitoring data is only 6 times per second within a certain period of time, this indicates that the feedback frequency is abnormal. For the authentication of feedback strength, it is necessary to evaluate the amplitude of the change of physical quantity in the welding process reflected by the monitoring feedback data. Taking the temperature data fed back by the thermal imager as an example, if during normal welding, the temperature fluctuation range of the weld area should be between 500°C and 800°C, when the monitored temperature data shows that the weld temperature suddenly soars to 1200°C at a certain moment, this indicates that the feedback intensity has changed abnormally. By comprehensively analyzing the certification results of feedback frequency and feedback intensity, a joint certification result is established. For example, if the feedback frequency is lower than the preset value and the feedback intensity exceeds the normal range, the joint certification result will be marked as a high-risk abnormal state; if the feedback frequency is normal but the feedback intensity fluctuates slightly, it will be marked as a low-risk warning state, etc.

[0038] Step S662, trigger analysis of welding anomalies is performed through the joint authentication results, and anomalies are reported according to the trigger analysis results. Specifically, trigger analysis of welding anomalies is performed according to the joint authentication results. When the joint authentication results show a high-risk abnormal state, the system will immediately conduct an in-depth analysis of the possible causes of this anomaly. For example, if the feedback frequency is too low and the temperature feedback intensity is too high, it may be that the thermal imager has failed or that there is a serious thermal runaway phenomenon during the welding process, such as the welding current is too large and the duration is too long. The system will investigate and judge these possible causes according to the preset abnormal trigger rules. Once it is determined that there is a welding abnormality, an abnormality is reported according to the trigger analysis results. Abnormalities can be reported in many forms, such as displaying a striking red alarm message on the operation panel of the welding equipment, prompting the operator that "the welding temperature has risen abnormally and the monitoring data feedback is abnormal, please check immediately"; at the same time, an alarm signal can be sent to the remote monitoring center, containing detailed information about the abnormality, such as the time when the abnormality occurred, the type of abnormality (too high temperature, missing monitoring data, etc.) and possible causes of the abnormality, so that relevant technical personnel can take timely measures to deal with it, avoid the occurrence of welding defects or further damage to the equipment, and ensure the safety and quality stability of the copper heat dissipation base plate welding process.

[0039] The embodiment of the present application adopts data decomposition of the copper heat dissipation base plate, and establishes the zoned welding requirements according to the requirements of heat conduction, mechanical strength, welding stress and thermal influence. The requirements are used to evaluate the quality of the zones, construct the quality objective function, and combine the time and energy consumption objective functions to form a comprehensive objective function. A steady-state analysis is performed based on the historical working data of the welding equipment, and the parameter limit interval is established. The initial individual set is generated through the interval, and the fitness analysis is performed to obtain the fitness results of the welding parameters. The individuals are subjected to distribution analysis and distribution clustering, and an update constraint is generated, and a second update constraint is established in combination with the number of iterations. The initial individual set is iteratively updated using the update constraint to realize the automatic welding control of the copper heat dissipation base plate. By comprehensively considering multiple influencing factors such as welding quality, time efficiency and energy consumption, the technical effect of optimizing the welding process and improving the overall welding effect is achieved.

[0040] In the above, refer to Figure 1 The present invention describes in detail an automatic welding control method of a copper heat dissipation base plate according to an embodiment of the present invention. Figure 2 An automatic welding control device for a copper heat dissipation base plate according to an embodiment of the present invention is described.

[0041] An automatic welding control device for a copper heat dissipation base plate according to an embodiment of the present invention is used to solve the technical problem that the existing welding technology cannot comprehensively balance multiple influencing factors and affect the welding effect. By comprehensively considering multiple influencing factors such as welding quality, time efficiency and energy consumption, the technical effect of optimizing the welding process and improving the overall welding effect is achieved. An automatic welding control device for a copper heat dissipation base plate includes: a partition welding demand establishment module 10, a partition quality evaluation module 20, a parameter limit interval establishment module 30, a distribution cluster establishment module 40, a second update constraint establishment module 50, and an automatic welding control module 60.

[0042] The zoned welding requirement establishment module 10 is used to perform data decomposition on the copper heat dissipation base plate and establish zoned welding requirements, which include thermal conductivity requirements, mechanical strength requirements, welding stress requirements, and thermal impact requirements.

[0043] The partition quality evaluation module 20 is used to perform partition quality evaluation using the partition welding requirements, establish a quality objective function, and construct a comprehensive objective function using the quality objective function, time objective function and energy consumption objective function.

[0044] The parameter limit interval establishment module 30 is used to obtain the historical working data of the welding equipment, perform a steady-state analysis based on the historical working data, establish a parameter limit interval, establish an initial individual set within the parameter limit interval, and perform a fitness analysis of each individual in the initial individual set through the comprehensive objective function to establish a fitness calculation result, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon gas flow rate, and welding angle.

[0045] The distribution clustering establishment module 40 is used to perform distribution analysis on the individuals in the initial individual set, establish distribution clustering, and establish a first update constraint through the distribution clustering and fitness calculation results.

[0046] The second update constraint establishing module 50 is used to obtain the current number of iterations and establish a second update constraint based on the number of iterations.

[0047] The automatic welding control module 60 is used to iteratively update the initial individual set within the parameter limit range using the first update constraint and the second update constraint, and perform automatic welding control of the copper heat dissipation base plate according to the iterative update result.

[0048] The specific configuration of the distribution clustering establishment module 40 will be described in detail below. As described above, the individuals in the initial individual set are subjected to distribution analysis, distribution clustering is established, and the first update constraint is established through the distribution clustering and fitness calculation results. The distribution clustering establishment module 40 further includes: a calculation result comparison unit, the calculation result comparison unit is used to compare the fitness calculation results of the individuals in each clustering cluster in the distribution clustering, and establish the center point in the cluster; an individual following analysis unit, the individual following analysis unit is used to perform individual following analysis in each clustering cluster based on the center point in the cluster, and establish a first following update; a calibration center point establishment unit, the calibration center point establishment unit is used to perform global center point analysis on the center point in the cluster, establish a calibration center point, and perform following analysis on each individual in the initial individual set based on the calibration center point, and establish a second following update; a joint update analysis unit, the joint update analysis unit is used to perform joint update analysis on the first following update and the second following update, and establish a first update constraint.

[0049] The specific configuration of the second update constraint establishment module 50 will be described in detail below. As described above, the current number of iterations is obtained, and the second update constraint is established based on the number of iterations. The second update constraint establishment module 50 further includes: a matching result establishment unit, the matching result establishment unit is used to obtain a preset iterative exploration constraint, perform iterative exploration constraint matching through the number of iterations, and establish a matching result; an individual convergence analysis unit, the individual convergence analysis unit is used to perform individual convergence analysis using the fitness calculation result, compensate the matching result based on the individual convergence analysis result, and establish a compensation exploration constraint; a random factor creation unit, the random factor creation unit is used to create a random factor using the individual convergence analysis result, and establish a second update constraint based on the random factor and the compensation exploration constraint.

[0050] The specific configuration of the automated welding control module 60 will be described in detail below. As described above, the initial individual set is iteratively updated within the parameter limit interval using the first update constraint and the second update constraint, and the automated welding control of the copper heat dissipation base plate is performed according to the iterative update result. The automated welding control module 60 further includes: a position update analysis unit, which is used to perform position update analysis on each individual in the initial individual set using the first update constraint and the second update constraint to create a pre-update result; an interference identification establishment unit, which is used to perform adjacent interference analysis on the pre-update result and establish an interference identification; a center search avoidance unit, which is used to perform center search avoidance on the pre-update result through the interference identification and establish a center search avoidance result; and an iterative update unit, which is used to complete the iterative update using the center search avoidance result.

[0051] Among them, the iterative update is completed using the center search avoidance result, and the iterative update unit further includes: a continuous iteration evaluation generation subunit, the continuous iteration evaluation generation subunit is used to execute the iteration record of the individual and generate a continuous iteration evaluation; the elimination instruction generation subunit, the elimination instruction generation subunit is used to generate an elimination instruction if the continuous iteration evaluation is lower than a preset threshold, eliminate the corresponding individual according to the elimination instruction, reconstruct the newly added individual within the parameter limit range, and add the newly added individual to the corresponding individual set.

[0052] Among them, the automated welding control module 60 further includes: a sensor group configuration unit, which is used to configure a sensor group, and the sensor group includes a thermal imager and a laser rangefinder; a real-time welding monitoring unit, which is used to use the sensor group to perform real-time welding monitoring of the copper heat dissipation base plate and establish real-time welding monitoring feedback; a feedback optimization network synchronization unit, which is used to synchronize the real-time welding monitoring feedback and the iterative update result to the feedback optimization network to generate a closed-loop control feedback; a welding optimization unit, which is used to optimize the welding of the copper heat dissipation base plate according to the closed-loop control feedback.

[0053] Among them, the sensor group is used to perform real-time welding monitoring of the copper heat dissipation base plate, and real-time welding monitoring feedback is established. The real-time welding monitoring unit further includes: a joint authentication result establishment subunit, which is used to jointly authenticate the feedback frequency and feedback strength of the real-time welding monitoring feedback to establish a joint authentication result; an abnormality reporting subunit, which is used to trigger analysis of welding abnormalities through the joint authentication result, and report abnormalities according to the trigger analysis result.

[0054] An automatic welding control device for a copper heat dissipation base plate provided in an embodiment of the present invention can execute an automatic welding control method for a copper heat dissipation base plate provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0055] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0056] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An automatic welding control method for a copper heat dissipation base plate, characterized in that: The method comprises: Decompose the data of the copper heat dissipation base plate and establish the zone welding requirements, which include heat conduction requirements, mechanical strength requirements, welding stress requirements, and heat impact requirements; Using the zoned welding requirements to evaluate the zoned quality, establish a quality objective function, and use the quality objective function, time objective function and energy consumption objective function to construct a comprehensive objective function; Acquire historical working data of the welding equipment, perform steady-state analysis based on the historical working data, establish a parameter limit interval, establish an initial individual set within the parameter limit interval, and perform fitness analysis on each individual in the initial individual set through the comprehensive objective function to establish a fitness calculation result, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon gas flow rate, and welding angle; Performing distribution analysis on individuals in the initial individual set, establishing distribution clustering, and establishing a first update constraint through the distribution clustering and fitness calculation results; Obtaining a current number of iterations, and establishing a second update constraint based on the number of iterations; The initial individual set is iteratively updated within a parameter limit interval using the first update constraint and the second update constraint, and automatic welding control of the copper heat dissipation base plate is performed according to the iterative update result.

2. The automatic welding control method of a copper heat dissipation base plate according to claim 1, characterized in that: The establishing of the first update constraint through the distribution clustering and fitness calculation results includes: Comparing fitness calculation results of individuals in each cluster in the distribution clustering, and establishing a center point within the cluster; Performing individual following analysis in each cluster based on the center point in the cluster to establish a first following update; Performing a global center point analysis on the center point in the cluster to establish a calibration center point, performing a follow-up analysis on each individual in the initial individual set based on the calibration center point, and establishing a second follow-up update; Perform a joint update analysis on the first follow-up update and the second follow-up update to establish a first update constraint.

3. The automatic welding control method of a copper heat dissipation base plate according to claim 1, characterized in that: The establishing a second update constraint based on the number of iterations comprises: Obtaining a preset iterative exploration constraint, performing iterative exploration constraint matching according to the number of iterations, and establishing a matching result; Using the fitness calculation result to perform individual convergence analysis, compensating the matching result based on the individual convergence analysis result, and establishing a compensatory exploration constraint; A random factor is created using the individual convergence analysis result, and a second update constraint is established based on the random factor and the compensatory exploration constraint.

4. The automatic welding control method of a copper heat dissipation base plate according to claim 1, characterized in that: The iterative updating of the initial individual set within the parameter limit interval by using the first update constraint and the second update constraint includes: Performing position update analysis on each individual in the initial individual set using the first update constraint and the second update constraint to create a pre-update result; Performing adjacent interference analysis on the pre-update result and establishing an interference identifier; Performing center search avoidance on the pre-update result by using the interference identifier to establish a center search avoidance result; The center search avoidance result is used to complete iterative updating.

5. The automatic welding control method of a copper heat dissipation base plate according to claim 4, characterized in that: The method comprises: Execute individual iteration records and generate continuous iteration evaluations; If the continuous iterative evaluation is lower than a preset threshold, an elimination instruction is generated, the corresponding individuals are eliminated according to the elimination instruction, and newly added individuals are reconstructed within the parameter limit range, and the newly added individuals are added to the corresponding individual set.

6. The automatic welding control method of a copper heat dissipation base plate according to claim 1, characterized in that: The method further comprises: Configure a sensor group, the sensor group includes a thermal imager and a laser rangefinder; Using the sensor group to perform real-time welding monitoring of the copper heat dissipation base plate and establish real-time welding monitoring feedback; Synchronizing the real-time welding monitoring feedback and the iterative update result to a feedback optimization network to generate a closed-loop control feedback; The welding optimization of the copper heat dissipation base plate is performed according to the closed-loop control feedback.

7. The automatic welding control method of a copper heat dissipation base plate according to claim 6, characterized in that: The method further comprises: Performing joint authentication of feedback frequency and feedback intensity on the real-time welding monitoring feedback, and establishing a joint authentication result; A trigger analysis of welding anomalies is performed based on the combined authentication results, and an anomaly report is performed based on the trigger analysis results.

8. An automatic welding control device for a copper heat dissipation base plate, characterized in that: The device is used to implement the automatic welding control method of a copper heat dissipation base plate according to any one of claims 1 to 7, and the device comprises: A zoned welding requirement establishment module, which is used to perform data decomposition on the copper heat dissipation base plate and establish zoned welding requirements, including heat conduction requirements, mechanical strength requirements, welding stress requirements, and heat impact requirements; A partition quality evaluation module, wherein the partition quality evaluation module is used to perform partition quality evaluation using the partition welding requirements, establish a quality objective function, and construct a comprehensive objective function using the quality objective function, a time objective function, and an energy consumption objective function; A parameter limit interval establishment module, the parameter limit interval establishment module is used to obtain historical working data of the welding equipment, perform working steady-state analysis based on the historical working data, establish a parameter limit interval, establish an initial individual set within the parameter limit interval, and perform fitness analysis of each individual in the initial individual set through the comprehensive objective function to establish a fitness calculation result, wherein each individual represents a set of welding parameters, including current, voltage, welding speed, argon gas flow rate, and welding angle; A distribution clustering establishment module, the distribution clustering establishment module is used to perform distribution analysis on individuals in the initial individual set, establish distribution clusters, and establish a first update constraint through the distribution clusters and fitness calculation results; A second update constraint establishing module, the second update constraint establishing module is used to obtain a current number of iterations and establish a second update constraint based on the number of iterations; An automated welding control module is used to iteratively update the initial individual set within a parameter limit range using the first update constraint and the second update constraint, and to perform automated welding control of the copper heat dissipation base plate according to the iterative update result.

Images