Automatic production control method and system for automobile skylight sealing strip

Abstract

The invention provides an automatic production control method and system for an automobile skylight sealing strip, and relates to the technical field of production control, and the method comprises the steps: receiving to-be-processed raw material data, executing a self-adaptive monitoring decision, and configuring a time period monitoring point; historical control data of extrusion forming is called, and a control parameter data set is established; establishing a raw material step grade interval, configuring a solution space, and executing control optimization: performing data cleaning to generate a cleaning parameter set, and establishing an optimization space; establishing a fitness function of quality evaluation, and establishing data mapping between a raw material step grade interval and a cleaning parameter set; an initial control result is configured, and optimization searching is executed; and generating control data, executing monitoring verification, and completing automatic production control according to a monitoring verification result. The technical problem that automatic production is abnormal due to the fact that a traditional production control method often depends on experience and manual parameter adjustment and is difficult to accurately and stably control equipment parameters is solved.

Description

Technical Field

[0001] The invention relates to the technical field of production control, and in particular to an automated production control method and system for automobile sunroof sealing strips. Background Art

[0002] The car sunroof sealing strip is an important part of the car sunroof system. It is mainly used to ensure the sealing performance between the sunroof and the car body, prevent rain, dust and other external substances from entering the car, and also play a role in reducing wind noise and improving riding comfort. In the intelligent manufacturing process of car sunroof sealing strips, rubber or silicone materials need to be used because of the need to maintain the excellent elasticity of the sealing strips. However, these materials are difficult to process, especially in the process of automated production. It is necessary to accurately control the equipment parameters to ensure the production quality of the sealing strips. However, the automated production technology for sealing strips in the existing technology is not mature enough, and there is a technical problem that the equipment parameters cannot be accurately and stably controlled, which leads to abnormal automated production. Summary of the invention

[0003] The present application provides an automated production control method for automobile sunroof sealing strips, aiming to solve the technical problem that traditional production control methods often rely on experience and manual adjustment of parameters, and it is difficult to accurately and stably control equipment parameters, which in turn leads to abnormal automated production.

[0004] In view of the above problems, the present application provides an automated production control method and system for automobile sunroof sealing strips.

[0005] In a first aspect disclosed in the present application, there is provided an automated production control method for automobile sunroof sealing strips, the method being applied to an automated production control system for automobile sunroof sealing strips, the system being communicatively connected to a first monitoring unit, a cloud processor, and a second monitoring unit, the method comprising: receiving raw material data to be processed by the first monitoring unit, and executing adaptive monitoring decisions according to the raw material data, configuring time period monitoring points, the first monitoring unit executing data monitoring after rubber mixing at the time period monitoring points, and feeding back the data monitoring results to the cloud processor; calling historical control data of extrusion molding by the cloud processor, establishing a control parameter data set, each set of data in the control parameter data set comprising raw material characteristic data, control data, and result monitoring data; executing the raw material characteristic data Clustering is performed to establish raw material step grade intervals, and a solution space corresponding to each interval in the raw material step grade interval is configured, and control optimization is performed in the corresponding solution space, and the optimization is performed as follows: A1: data cleaning is performed on the control parameter data set to generate a cleaning parameter set, and an optimization space is established with the cleaning parameter set, and the cleaning parameter set is a data set retained after data cleaning; A2: a fitness function for quality evaluation is established with the cleaning parameter set, and a data mapping between the raw material step grade interval and the cleaning parameter set is established; A3: when control optimization is performed for any raw material step grade interval, the initial control result is configured with the fitness function, and an optimization search is performed in the solution space and the optimization search space; control data is generated according to the optimization search result, and the second monitoring unit is called to perform monitoring verification, and automatic production control is completed according to the monitoring verification result.

[0006] The second aspect disclosed in the present application provides an automated production control system for automobile sunroof sealing strips, wherein the system is communicatively connected with a first monitoring unit, a cloud processor, and a second monitoring unit, and the system is used for the above-mentioned automated production control method for automobile sunroof sealing strips, and the system comprises: a time period monitoring point configuration module, wherein the time period monitoring point configuration module is used to receive raw material data to be processed with the first monitoring unit, and execute adaptive monitoring decisions according to the raw material data, and configure time period monitoring points, wherein the first monitoring unit executes data monitoring after rubber mixing at the time period monitoring points, and feeds back the data monitoring results to the cloud processor; a control parameter data set establishment module, wherein the control parameter data set establishment module is used to call the historical control data of extrusion molding with the cloud processor, and establish a control parameter data set, wherein each set of data in the control parameter data set includes raw material characteristic data, control data, and result monitoring data; control optimization Module, the control optimization module is used to perform clustering of the raw material feature data, establish raw material step grade intervals, and configure the solution space corresponding to each interval in the raw material step grade interval, and perform control optimization in the corresponding solution space, and the optimization is as follows: A1: perform data cleaning on the control parameter data set, generate a cleaning parameter set, and establish an optimization space with the cleaning parameter set, and the cleaning parameter set is the data set retained after data cleaning; A2: establish a fitness function for quality evaluation with the cleaning parameter set, and establish a data mapping between the raw material step grade interval and the cleaning parameter set; A3: when performing control optimization for any raw material step grade interval, configure the initial control result with the fitness function, and perform optimization search in the solution space and the optimization space; automated production control module, the automated production control module is used to generate control data according to the optimization search result, and call the second monitoring unit to perform monitoring verification, and complete automated production control according to the monitoring verification result.

[0007] According to a third aspect disclosed in the present application, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any step of the first aspect disclosed in the present application is implemented.

[0008] The fourth aspect disclosed in the present application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements any step of the first aspect disclosed in the present application.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: By executing adaptive monitoring decisions through the first monitoring unit, the raw material data can be processed and analyzed in real time, which improves the stability and controllability of the production process; the cloud processor is used to establish a control parameter data set for grading and adaptive optimization. Through the grading of raw materials, the excessive amount of calculation caused by overly detailed raw material parameter matching each time can be avoided, and the control deviation and unstable quality caused by not performing raw material detection can be avoided, and the amount of calculation and quality can be balanced. Through adaptive optimization processing, the control parameters corresponding to the raw material grade can be better matched, thereby providing support for intelligent and accurate automated production; combined with the monitoring verification of the second monitoring unit, real-time monitoring and verification of the production process can be achieved, problems in the production process can be discovered and solved in a timely manner, and the reliability and efficiency of the production process can be improved. In summary, the automated production control method of the automotive sunroof sealing strip achieves technical effects such as improving production efficiency, reducing production costs, and improving product quality by introducing technical means such as adaptive monitoring, automated optimization, and real-time monitoring verification.

[0010] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of an automated production control method for a car sunroof sealing strip provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of an automated production control system for a car sunroof sealing strip provided in an embodiment of the present application; Figure 3 This is a diagram of the internal structure of a computer device provided in an embodiment of the present application.

[0012] Description of the accompanying drawings: time period monitoring point configuration module 10, control parameter data set establishment module 20, control optimization module 30, automated production control module 40. DETAILED DESCRIPTION

[0013] The embodiment of the present application provides an automated production control method for automobile sunroof sealing strips, thereby solving the technical problem that traditional production control methods often rely on experience and manual adjustment of parameters, making it difficult to accurately and stably control equipment parameters, which in turn leads to abnormal automated production.

[0014] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0015] like Figure 1 As shown, an embodiment of the present application provides an automated production control method for a car sunroof sealing strip, the method is applied to an automated production control system for a car sunroof sealing strip, the system is communicatively connected with a first monitoring unit, a cloud processor, and a second monitoring unit, and the method includes: The first monitoring unit receives the raw material data to be processed, performs adaptive monitoring decisions according to the raw material data, configures time period monitoring points, and the first monitoring unit performs data monitoring after rubber mixing at the time period monitoring points, and feeds back the data monitoring results to the cloud processor; The automated production control method of an automobile sunroof sealing strip provided in the embodiment of the present application is applied to an automated production control system of an automobile sunroof sealing strip, wherein the system is connected in communication with a first monitoring unit, a cloud processor, and a second monitoring unit, wherein the first monitoring unit is used to monitor the raw material data of the production process, and to perform adaptive monitoring decisions and configure time period monitoring points based on these data; the cloud processor is the central processing unit in the system, which receives data from the first monitoring unit and performs a series of data processing and analysis operations, such as clustering and division of raw material feature data, optimization of control parameters, etc.; the second monitoring unit performs monitoring verification based on the control data generated by the cloud processor, and according to the monitoring verification results, the system can make further adjustments to ensure that the production process of the automobile sunroof sealing strip meets the expected standards. In this way, the entire system obtains data through the first monitoring unit, the cloud processor performs data processing and analysis, and the second monitoring unit performs actual monitoring verification, thereby realizing the automated control of the production process of the automobile sunroof sealing strip.

[0016] First, the first monitoring unit receives data from the raw material supply chain. These data include the composition, quality, supplier information, etc. of the raw materials. The first monitoring unit performs adaptive monitoring decisions based on the received raw material data, including analyzing the characteristics, quality and supply of the raw materials, and dynamically adjusting the monitoring strategy based on the real-time situation. For example, if the quality of a batch of raw materials is abnormal, the monitoring frequency is increased to ensure that the problem is discovered in time. According to the adaptive monitoring decision, time period monitoring points are configured. These time periods are usually key stages in the production process. During these time periods, monitoring points are set to monitor the data after rubber mixing. These data include parameters such as temperature, pressure, and rubber mixing ratio.

[0017] At the configured time period monitoring point, the first monitoring unit monitors the data after rubber mixing, such as using temperature sensors, pressure sensors, etc. to obtain data in real time. When the data monitoring is completed, the monitoring results are fed back to the cloud processor, which will perform further processing and analysis based on the data, as well as subsequent production process control and optimization.

[0018] Using the cloud processor to call historical control data of extrusion molding to establish a control parameter data set, each set of data in the control parameter data set includes raw material feature data, control data and result monitoring data; The cloud processor first accesses the historical data of the extrusion molding process stored in the system. These data include records of various parameters and variables in the extrusion molding process, such as temperature, pressure, speed, etc., and establishes a control parameter data set based on the historical control data. Each set of data includes three main parts: raw material characteristic data, control data and result monitoring data. Among them, the raw material characteristic data describes the characteristics of the raw materials used in each production process, including the composition of the raw materials, supplier information, quality grade, etc.; the control data records the control strategy and parameter settings adopted in the extrusion molding process, including temperature setting, pressure setting, speed setting, etc.; the result monitoring data is the actual monitoring results generated during the extrusion molding process, including the actual values ​​of various parameters and variables in the production process, such as actual temperature, actual pressure, actual speed, etc.

[0019] By establishing a control parameter data set, the extrusion molding process can be analyzed and optimized using historical data, which serves as an important basis for control parameter optimization and production process control in subsequent steps.

[0020] Execute clustering of the raw material feature data, establish raw material ladder grade intervals, configure the solution space corresponding to each interval in the raw material ladder grade interval, and perform control optimization in the corresponding solution space. The optimization is as follows: Cluster analysis is performed on the characteristic data of raw materials. Clustering algorithms such as K-means clustering and hierarchical clustering can be used. The purpose of clustering is to divide the raw materials into different categories or clusters according to their characteristics for subsequent analysis and processing. According to the clustering results, the raw materials are divided into different ladder-level intervals. Each ladder-level interval represents a group of raw materials with similar characteristics. The division of these level intervals can be determined based on the quality, composition, supplier and other characteristics of the raw materials.

[0021] For each raw material grade interval, a corresponding solution space is configured. The solution space is a set of possible control parameter values, which is used to optimize the control parameters. In each grade interval, the configuration of the solution space can be adjusted according to the characteristics of the interval. In each raw material grade interval, the control parameters are optimized for the configured solution space. The specific optimization process is described in detail in the subsequent steps, so I will not go into details here. The optimal control parameter combination is searched in the solution space through control optimization.

[0022] Through this process, control parameters can be optimized for raw materials in different grade ranges to ensure that the production process can achieve the best effect and performance with raw materials of different quality and characteristics. Such an optimization strategy can improve the stability of the production process and thus improve the quality of the product.

[0023] A1: Perform data cleaning on the control parameter data set to generate a cleaning parameter set, and establish an optimization space with the cleaning parameter set, where the cleaning parameter set is the data set retained after data cleaning; First, the control parameter data set is cleaned. The purpose of data cleaning is to deal with possible errors, anomalies or missing values ​​in the data set to ensure the quality and integrity of the data. The specific cleaning steps include deduplication of data, processing of outliers, filling of missing values, etc. After the cleaning is completed, a cleaning parameter set is generated. The cleaning parameter set is a subset of the data retained after data cleaning, which does not contain data with errors, anomalies or missing values. These data serve as the basis for the subsequent optimization space.

[0024] Statistical analysis is performed on the data in the cleaning parameter set to determine the parameter value range and distribution, so as to establish the optimization space. The optimization space is a set of possible control parameter values ​​used to optimize the control parameters. The optimization space should conform to the limitations of the actual production process, while taking into account factors such as raw material characteristics and equipment performance. This ensures that the control parameter combination generated in the optimization process can be effectively applied in actual production and can meet the stability and controllability requirements of the production process.

[0025] A2: Establishing a fitness function for quality evaluation with the cleaning parameter set, and establishing a data mapping between the raw material grade interval and the cleaning parameter set; Using the data in the cleaning parameter set, a fitness function is established to evaluate the quality of each set of control parameters, and used as the evaluation criterion for the optimization algorithm. The establishment of the fitness function involves the objectives and constraints of the production process, as well as the optimization indicators. The optimization indicators can be determined based on the characteristics and needs of the production process, such as maximizing production efficiency, minimizing production costs, optimizing product quality, etc.

[0026] According to the data characteristics in the cleaning parameter set and the division of the raw material grade intervals, the data in the cleaning parameter set are matched with the raw material grade intervals to establish a mapping relationship. By establishing such a mapping relationship, the data in the cleaning parameter set can be matched with raw materials of different grades, providing a basis for subsequent optimization and control.

[0027] A3: When performing optimization of any raw material step-level interval control, the initial control result is configured with the fitness function, and the optimization search is performed in the solution space and the optimization space; When optimizing the control parameters for any raw material step level interval, the current control parameters are evaluated according to the fitness function, and the initial parameter control results are configured according to the evaluation results. These initial results can be based on historical data or randomly generated initial parameters to perform optimization searches in the solution space and the optimization space. The solution space is a set of possible control parameter values, and the optimization space is the range for performing optimization searches in the solution space. Various optimization algorithms, such as genetic algorithms, particle swarm optimization algorithms, etc., can be used to search the optimization space to find the optimal control parameter combination.

[0028] By executing the optimization search process, the control parameters for any raw material grade interval can be optimized to improve the efficiency and performance of the production process while ensuring the quality of the product.

[0029] The control data is generated according to the optimization search results, and the second monitoring unit is called to perform monitoring verification, and the automated production control is completed according to the monitoring verification results.

[0030] According to the results of the optimization search, the optimal control data is generated for production control. The second monitoring unit is called, which is used for monitoring and verifying the actual production process, including monitoring various parameters and indicators of the production process. The monitoring and verification results are analyzed, and the control parameters are adjusted according to the actual situation to ensure that the production process achieves the expected results, including adjusting the parameter settings of the production equipment, modifying the control strategy of the production process, etc., to maintain the stability of the production process, thereby ensuring that the automated production process of the automotive sunroof sealing strips meets the expected quality standards.

[0031] Furthermore, the A3 includes: Reading device attribute information of the extrusion molding device, and configuring a minimum adaptive step size constraint with the device attribute information; Configure the random selection probability of the solution space and the optimization space, and search for control parameters in the corresponding space with the random selection result and the minimum adaptive step size constraint; Evaluate the control parameter search results according to the fitness function, and update the initial control results with the evaluation results; Continue to perform search iterations, and when the iteration results meet the preset results, the optimal search is completed.

[0032] Obtain the device attribute information of the extrusion molding equipment, including the model, specifications, performance parameters, working status, etc. of the equipment, which is usually stored in the control system of the equipment. Analyze the read device attribute information, such as evaluating the working characteristics, working range, response speed, etc. of the equipment, to determine the working status and performance characteristics of the extrusion molding equipment.

[0033] Configure the minimum adaptive step size constraint according to the working status and performance characteristics of the device. The minimum adaptive step size constraint refers to the minimum step size or change amount of the control parameter adjustment in the optimization algorithm. The purpose of this constraint is to ensure that the response speed and stability of the device are taken into account when adjusting the control parameters, and to avoid frequent adjustments that cause fluctuations in device performance.

[0034] According to the needs of the optimization algorithm, the random selection probability of the solution space and the optimization space is configured. This probability determines the possibility of randomly selecting parameters during the search process. Usually, the random selection probability of the solution space and the optimization space is adjusted according to the characteristics of the optimization algorithm and the optimization goal.

[0035] According to the configured random selection probability, control parameters are randomly selected in the solution space and the optimization space. These randomly selected parameters are used as the initial control parameter combination. According to the randomly selected initial control parameter combination, the control parameter search is performed in the corresponding solution space and the optimization space. When performing the control parameter search, the minimum adaptive step size constraint is combined. This constraint stipulates the minimum step size of the control parameter adjustment. During the search process, the adjustment of the control parameters will not be less than the minimum adaptive step size constraint. The control parameters are continuously adjusted and optimized during the search process to find the optimal control parameter combination.

[0036] The previously defined fitness function is used to evaluate each set of control parameter search results. The fitness function evaluates the quality of the control parameter combination according to the optimization objectives and constraints, and obtains an evaluation score. Based on the evaluation results, the initial control results are updated, including retaining the control parameter combination with the highest evaluation score. The updated control parameter results will be used as the initial values ​​for the next round of optimization search, thereby gradually optimizing the control parameter combination to achieve the optimization objectives and improve production efficiency.

[0037] Set the preset termination conditions according to specific needs and optimization goals, including reaching the maximum number of iterations, reaching a certain optimization goal, and the evaluation function converging to a stable value. According to the set termination conditions, search iterations are performed. After each iteration, check whether the preset termination conditions are met. If the conditions are met, the search iteration is terminated, otherwise the next round of iterations is continued. When the search iteration meets the preset termination conditions, the optimization search is completed, and the optimal control parameter combination is obtained, which is used to optimize the production process to improve product quality and production efficiency.

[0038] Furthermore, the method comprises: Configure a search step size, wherein the search step size is constructed by a minimum adaptive step size constraint, and the search step size includes an initial search step size, a mid-term search step size, and a steady-state search step size; After the random selection result is determined, the search step size is matched according to the iteration state to search for the control parameters in the corresponding space.

[0039] The search step is constructed through the minimum adaptive step constraint. This constraint stipulates the minimum step size of the control parameter adjustment to ensure that the search step size will not be less than the minimum adaptive step size constraint. The search step size includes the initial search step size, the mid-term search step size and the steady-state search step size.

[0040] Specifically, at the beginning of the search, the control parameters are adjusted using an initial search step size, which is set to a larger value so that a potential optimization direction can be quickly found in the search space; as the search proceeds, the search step size is gradually reduced so that the control parameters can be adjusted more finely, and the mid-term search step size is set to a value between the initial search step size and the steady-state search step size to balance the search speed and search accuracy; when the system is close to the optimal solution, the control parameters are fine-tuned using a steady-state search step size, which is set to a smaller value to ensure finer adjustments near the optimal solution while avoiding performance fluctuations caused by excessive adjustments.

[0041] According to the configured random selection probability, random selection is performed in the solution space and optimization space to obtain the initial control parameter combination and record the current iteration status, including the number of iterations, convergence status, search direction and other information. This information can help the system determine the current search status and optimization process.

[0042] According to the current iteration state, the corresponding search step size is matched, that is, according to different iteration states, the size of the search step size is adjusted to adapt to the current search situation. For example, a larger search step size is used in the initial iteration stage, and a smaller search step size is used in the stable state. According to the matched search step size, the control parameter search is performed in the corresponding space to find the optimal control parameter combination.

[0043] By matching the search step size according to the iteration status, the search step size can be dynamically adjusted according to the current search situation and optimization process, and the control parameters can be fine-tuned, thereby more effectively searching for control parameters and improving the search efficiency and the quality of the optimization results.

[0044] Furthermore, matching the search step size according to the iteration state to search for control parameters in the corresponding space includes: Determine whether the iteration state is an initial iteration state, and if it is an initial iteration state, determine whether a local loop is trapped according to the continuous iteration results; When the judgment is passed, the current iteration result is sealed as the mid-term iteration result, and a single step size update is generated; An iterative search is performed with the single step size update, and the initial search step size search is restored in the next iteration to complete the control parameter search.

[0045] Check the current iteration status, including the number of iterations, convergence status, search direction and other information to determine whether it is in the initial iteration stage. If it is currently in the initial iteration state, then make a local loop trap judgment, that is, check the continuous iteration results, and determine whether it is trapped in the local optimal solution according to the change trend of the parameters and the change of the optimization target, that is, the search process stays at the local optimal solution and cannot continue to evolve to the global optimal solution.

[0046] When the judgment is passed, that is, it is found that the current initial iteration state has fallen into the local optimal solution, the current iteration result will be sealed as the mid-term iteration result, which means that the current control parameter combination will be saved as a reference point for the mid-term state for subsequent optimization processes. According to the judgment of falling into the local loop, a single step size update will be generated, that is, the current search step size will be adjusted to try to jump out of the local optimal solution and continue to search for the global optimal solution.

[0047] Using the generated single step size update, an iterative search is performed on the current control parameter combination, that is, the control parameters are adjusted according to the single step size update, and the adjusted results are evaluated to find a better control parameter combination. In the next round of iterations, the search is resumed using the initial search step size, which means relaxing the step size constraint to search for possible solutions more widely in the search space. By resuming the initial search step size search, you can try to jump out of the local optimal solution and continue to search for the global optimal solution.

[0048] According to the above steps, the control parameter search is repeatedly performed until the preset termination condition is met. Once the termination condition is met, the control parameter search will be completed and the optimal control parameter combination and the corresponding optimization result will be obtained. In this way, the search strategy can be adjusted in time when a local optimal solution is found to continue the optimization search process, thereby improving the search efficiency and the quality of the optimization results.

[0049] Furthermore, the method comprises: Determine whether the uneliminated storage results meet the preset quantity threshold or the number of iterations meets the preset requirements; When any condition is triggered, the initial iteration state is determined to be ended, and the mid-term search step is called to continue the iterative search to complete the control parameter search.

[0050] Check the sealed mid-term iteration results, that is, the results that have not been eliminated. These results are the local optimal solutions found in the initial iteration state and are sealed for subsequent reference control parameter combinations. Check whether the number of sealed results that have not been eliminated has reached the preset number threshold. This threshold is determined based on actual needs and optimization goals and is used to control the number of sealed results; at the same time, check whether the number of iterations has reached the preset requirements, that is, the preset number of iterations. The preset number of iterations is also determined based on actual needs and optimization goals and is used to control the number of iterations.

[0051] According to the above two conditions, if the number of sealed results that have not been eliminated reaches the preset threshold, or the preset number of iterations has been reached, when any of the conditions is triggered, it is determined that the current initial iteration state is terminated, which means ending the search process of the initial iteration stage and entering the next stage of mid-term iteration state, that is, calling the mid-term search step to continue the iterative search until the preset termination condition is met. The mid-term search step is small, and optimization can be performed in a more refined search space to further find the optimal control parameter combination.

[0052] Furthermore, the method comprises: Determine whether the random selection result meets the selection threshold of the continuous solution space; If the continuous solution space selection threshold is met, then the selected result is optimized and evaluated; Matching additional weights according to the optimization evaluation results, and optimizing the random selection probability for the next round with the additional weights; Continue to control parameter search based on the optimization results.

[0053] The continuous solution space selection threshold is determined according to actual needs and optimization goals, and is used to control the quality of the selected results. It is judged whether the random selection result meets the continuous solution space selection threshold. If the threshold is met, it means that the selected result has a certain degree of continuity and stability. When it is judged that the random selection result meets the continuous solution space selection threshold, the selected result is evaluated, that is, the fitness function or other evaluation indicators are used to evaluate the selected results and obtain the fitness value of each result.

[0054] According to the optimization evaluation results, additional weights are matched for each selected result. These additional weights can be determined according to the fitness value and are used to adjust the weights of each result in the next round of random selection. According to the matched additional weights, the probability of random selection in the next round is optimized, which means that according to the additional weights of each result, its probability distribution in random selection is adjusted, so that the results with higher scores have a higher selection probability, which can guide the search process more effectively and increase the probability of high-quality solutions being selected, thereby accelerating the optimization process and improving search efficiency.

[0055] According to the optimization results, the control parameter search continues, including evaluation based on the optimization results of each round, and continuously updating the current best parameter combination, performing optimization iterations multiple times until the preset termination conditions are reached. The final parameter combination is regarded as the optimal solution for subsequent applications of the system.

[0056] Furthermore, the automated production control is completed according to the monitoring and verification results, including: Determining whether the monitoring verification result meets the consistency threshold; If the consistency threshold cannot be met, an alternative search result is selected based on the optimal search result, and the automated production control is completed with the alternative search result.

[0057] Obtain the monitoring verification results returned from the second monitoring unit, which include various monitoring data of the automotive sunroof sealing strip production process. Define the consistency threshold in advance. This threshold is determined based on production requirements, quality standards and other related factors to evaluate the consistency between the monitoring verification results and the expected goals.

[0058] The acquired monitoring verification results are compared with the expected targets to determine whether the consistency threshold is met. If the difference between the monitoring verification results and the expected targets is within the consistency threshold, the results are considered qualified; otherwise, the results are considered unqualified.

[0059] If the monitoring verification result cannot meet the consistency threshold, the previous optimization search process is reviewed to obtain alternative search results, which are alternative parameter combinations generated in the previous optimization process. The alternative search results are used as new control parameter combinations for automated production control.

[0060] In summary, the automated production control method for a car sunroof sealing strip provided in the embodiment of the present application has the following technical effects: 1. The first monitoring unit performs adaptive monitoring decisions, which can process and analyze raw material data in real time, thus improving the stability and controllability of the production process; 2. Use cloud processors to establish control parameter data sets, perform grading and adaptive optimization. Through raw material grading, the excessive amount of calculation caused by overly detailed raw material parameter matching each time can be avoided, and the control deviation and unstable quality caused by not performing raw material testing can be avoided. The amount of calculation and quality are balanced. Through adaptive optimization processing, the control parameters corresponding to the raw material grade can be better matched, thereby providing support for intelligent and accurate automated production; 3. Combined with the monitoring and verification of the second monitoring unit, real-time monitoring and verification of the production process can be achieved, problems in the production process can be discovered and solved in a timely manner, and the reliability and efficiency of the production process can be improved.

[0061] In summary, the automated production control method of the automobile sunroof sealing strip achieves technical effects such as improving production efficiency, reducing production costs, and improving product quality by introducing technical means such as adaptive monitoring, automated optimization, and real-time monitoring verification.

[0062] Based on the same inventive concept as the automated production control method for a car sunroof sealing strip in the aforementioned embodiment, Figure 2 As shown, the present application provides an automated production control system for automobile sunroof sealing strips, the system is communicatively connected with a first monitoring unit, a cloud processor, and a second monitoring unit, and the system includes: A time period monitoring point configuration module 10, the time period monitoring point configuration module 10 is used to receive the raw material data to be processed by the first monitoring unit, and perform adaptive monitoring decisions according to the raw material data, configure the time period monitoring point, the first monitoring unit performs data monitoring after rubber mixing at the time period monitoring point, and feeds back the data monitoring results to the cloud processor; A control parameter data set establishment module 20, wherein the control parameter data set establishment module 20 is used to call the historical control data of the extrusion molding with the cloud processor to establish a control parameter data set, wherein each set of data in the control parameter data set includes raw material characteristic data, control data and result monitoring data; The control optimization module 30 is used to perform clustering of the raw material feature data, establish raw material ladder grade intervals, and configure a solution space corresponding to each interval in the raw material ladder grade interval, and perform control optimization in the corresponding solution space. The optimization is as follows: A1: Perform data cleaning on the control parameter data set to generate a cleaning parameter set, and establish an optimization space with the cleaning parameter set, where the cleaning parameter set is the data set retained after data cleaning; A2: Establishing a fitness function for quality evaluation with the cleaning parameter set, and establishing a data mapping between the raw material grade interval and the cleaning parameter set; A3: When performing optimization of any raw material step-level interval control, the initial control result is configured with the fitness function, and the optimization search is performed in the solution space and the optimization space; The automated production control module 40 is used to generate control data according to the optimization search result, call the second monitoring unit to perform monitoring verification, and complete the automated production control according to the monitoring verification result.

[0063] Furthermore, the system also includes an optimization search module to perform the following operation steps: Reading device attribute information of the extrusion molding device, and configuring a minimum adaptive step size constraint with the device attribute information; Configure the random selection probability of the solution space and the optimization space, and search for control parameters in the corresponding space with the random selection result and the minimum adaptive step size constraint; Evaluate the control parameter search results according to the fitness function, and update the initial control results with the evaluation results; Continue to perform search iterations, and when the iteration results meet the preset results, the optimal search is completed.

[0064] Furthermore, the optimization search module further includes the following operation steps: Configure a search step size, wherein the search step size is constructed by a minimum adaptive step size constraint, and the search step size includes an initial search step size, a mid-term search step size, and a steady-state search step size; After the random selection result is determined, the search step size is matched according to the iteration state to search for the control parameters in the corresponding space.

[0065] Furthermore, the optimization search module further includes the following operation steps: Determine whether the iteration state is an initial iteration state, and if it is an initial iteration state, determine whether a local loop is trapped according to the continuous iteration results; When the judgment is passed, the current iteration result is sealed as the mid-term iteration result, and a single step size update is generated; An iterative search is performed with the single step size update, and the initial search step size search is restored in the next iteration to complete the control parameter search.

[0066] Furthermore, the optimization search module further includes the following operation steps: Determine whether the uneliminated storage results meet the preset quantity threshold or the number of iterations meets the preset requirements; When any condition is triggered, the initial iteration state is determined to be ended, and the mid-term search step is called to continue the iterative search to complete the control parameter search.

[0067] Furthermore, the optimization search module further includes the following operation steps: Determine whether the random selection result meets the selection threshold of the continuous solution space; If the continuous solution space selection threshold is met, then the selected result is optimized and evaluated; Matching additional weights according to the optimization evaluation results, and optimizing the random selection probability for the next round with the additional weights; Continue to control parameter search based on the optimization results.

[0068] Furthermore, the system further includes a monitoring verification result judgment module to perform the following operation steps: Determining whether the monitoring verification result meets the consistency threshold; If the consistency threshold cannot be met, an alternative search result is selected based on the optimal search result, and the automated production control is completed with the alternative search result.

[0069] Through the above-mentioned detailed description of an automated production control method for a car sunroof sealing strip in this specification, those skilled in the art can clearly understand an automated production control system for a car sunroof sealing strip in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0070] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the processor of the computer device is used to provide computing and control capabilities; the memory of the computer device includes a non-volatile storage medium and an internal memory, wherein the non-volatile storage medium stores an operating system, a computer program and a database, and the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium; the network interface of the computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement an automated production control method for a car sunroof sealing strip.

[0071] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0072] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be 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 the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An automated production control method for automobile sunroof sealing strips, the method being applied to an automated production control system for automobile sunroof sealing strips, the system being communicatively connected with a first monitoring unit, a cloud processor, and a second monitoring unit, and characterized in that: The method comprises: The first monitoring unit receives the raw material data to be processed, performs adaptive monitoring decisions according to the raw material data, configures time period monitoring points, and the first monitoring unit performs data monitoring after rubber mixing at the time period monitoring points, and feeds back the data monitoring results to the cloud processor; Using the cloud processor to call historical control data of extrusion molding to establish a control parameter data set, each set of data in the control parameter data set includes raw material feature data, control data and result monitoring data; Execute clustering of the raw material feature data, establish raw material ladder grade intervals, configure the solution space corresponding to each interval in the raw material ladder grade interval, and perform control optimization in the corresponding solution space. The optimization is as follows: A1: Perform data cleaning on the control parameter data set to generate a cleaning parameter set, and establish an optimization space with the cleaning parameter set, where the cleaning parameter set is the data set retained after data cleaning; A2: Establishing a fitness function for quality evaluation with the cleaning parameter set, and establishing a data mapping between the raw material grade interval and the cleaning parameter set; A3: When performing optimization of any raw material step-level interval control, the initial control result is configured with the fitness function, and the optimization search is performed in the solution space and the optimization space; The control data is generated according to the optimization search results, and the second monitoring unit is called to perform monitoring verification, and the automated production control is completed according to the monitoring verification results.

2. The method according to claim 1, characterized in that The A3 includes: Reading device attribute information of the extrusion molding device, and configuring a minimum adaptive step size constraint with the device attribute information; Configure the random selection probability of the solution space and the optimization space, and search for control parameters in the corresponding space with the random selection result and the minimum adaptive step size constraint; Evaluate the control parameter search results according to the fitness function, and update the initial control results with the evaluation results; Continue to perform search iterations, and when the iteration results meet the preset results, the optimal search is completed.

3. The method according to claim 2, characterized in that The method comprises: Configure a search step size, wherein the search step size is constructed by a minimum adaptive step size constraint, and the search step size includes an initial search step size, a mid-term search step size, and a steady-state search step size; After the random selection result is determined, the search step size is matched according to the iteration state to search for the control parameters in the corresponding space.

4. The method according to claim 3, characterized in that The step size of searching is matched according to the iteration state to search for control parameters in the corresponding space, including: Determine whether the iteration state is an initial iteration state, and if it is an initial iteration state, determine whether a local loop is trapped according to the continuous iteration results; When the judgment is passed, the current iteration result is sealed as the mid-term iteration result, and a single step size update is generated; An iterative search is performed with the single step size update, and the initial search step size search is restored in the next iteration to complete the control parameter search.

5. The method according to claim 4, characterized in that The method comprises: Determine whether the uneliminated storage results meet the preset quantity threshold or the number of iterations meets the preset requirements; When any condition is triggered, the initial iteration state is determined to be ended, and the mid-term search step is called to continue the iterative search to complete the control parameter search.

6. The method according to claim 2, characterized in that The method comprises: Determine whether the random selection result meets the selection threshold of the continuous solution space; If the continuous solution space selection threshold is met, then the selected result is optimized and evaluated; Matching additional weights according to the optimization evaluation results, and optimizing the random selection probability for the next round with the additional weights; Continue to control parameter search based on the optimization results.

7. The method according to claim 1, characterized in that The automated production control is completed according to the monitoring and verification results, including: Determining whether the monitoring verification result meets the consistency threshold; If the consistency threshold cannot be met, an alternative search result is selected based on the optimal search result, and the automated production control is completed with the alternative search result.

8. An automated production control system for automobile sunroof sealing strips, the system being communicatively connected with a first monitoring unit, a cloud processor, and a second monitoring unit, characterized in that: A method for implementing an automated production control method for a car sunroof sealing strip according to any one of claims 1 to 7, the system comprising: A time period monitoring point configuration module, the time period monitoring point configuration module is used to receive the raw material data to be processed by the first monitoring unit, and perform adaptive monitoring decisions according to the raw material data, configure the time period monitoring point, the first monitoring unit performs data monitoring after rubber mixing at the time period monitoring point, and feeds back the data monitoring results to the cloud processor; A control parameter data set establishment module, the control parameter data set establishment module is used to call the historical control data of the extrusion molding with the cloud processor to establish a control parameter data set, each set of data in the control parameter data set includes raw material characteristic data, control data and result monitoring data; The control optimization module is used to perform clustering of the raw material feature data, establish raw material ladder grade intervals, and configure the solution space corresponding to each interval in the raw material ladder grade interval, and perform control optimization in the corresponding solution space. The optimization is as follows: A1: Perform data cleaning on the control parameter data set to generate a cleaning parameter set, and establish an optimization space with the cleaning parameter set, where the cleaning parameter set is the data set retained after data cleaning; A2: Establishing a fitness function for quality evaluation with the cleaning parameter set, and establishing a data mapping between the raw material grade interval and the cleaning parameter set; A3: When performing optimization of any raw material step-level interval control, the initial control result is configured with the fitness function, and the optimization search is performed in the solution space and the optimization space; The automated production control module is used to generate control data according to the optimization search results, call the second monitoring unit to perform monitoring verification, and complete the automated production control according to the monitoring verification results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the automated production control method for a vehicle sunroof sealing strip according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the automated production control method for a vehicle sunroof sealing strip according to any one of claims 1 to 7 are implemented.

Images