Production parameter optimization method and system for hollow glass manufacturing

Abstract

The invention discloses a production parameter optimization method and system for hollow glass manufacturing, and relates to the technical field of glass manufacturing. The method comprises the following steps: obtaining a plurality of production process nodes according to the production process of the hollow glass; performing real-time sensing acquisition based on the plurality of production process nodes, extracting real-time production control data, and determining a real-time production parameter group; constructing a control optimization channel, transmitting the real-time production parameter group to the control optimization channel, and outputting a control optimization parameter group; determining a control optimization target, and making a control optimization strategy based on the control optimization target in combination with the control optimization parameter group; and executing the control optimization strategy to perform simulation control, backtracking the control optimization parameter group according to a simulation control result, and optimizing production parameters of hollow glass manufacturing according to a backtracking result. The technical problem that the glass quality is unstable due to the fact that production parameters are not adjusted in time in the traditional hollow glass manufacturing process is solved, and the technical effect of improving the glass quality stability is achieved.

Description

Technical Field

[0001] The invention relates to the technical field of glass manufacturing, and in particular to a production parameter optimization method and system for manufacturing hollow glass. Background Art

[0002] In the growing construction industry, insulating glass has become an indispensable part of modern architecture due to its unique properties, such as excellent heat insulation, sound insulation and energy-saving characteristics. However, the production process of insulating glass involves multiple complex and interrelated process flows, such as precise cutting, efficient cleaning, precise assembly and strict glue injection. The operating parameters of each step in these process flows directly affect the final quality and performance of insulating glass. The traditional production of insulating glass mainly relies on manual experience and fixed production parameter settings, which is not only inefficient, but also difficult to ensure the stability and consistency of product quality. In addition, with the continuous changes in market demand and the diversification of product specifications, traditional production methods can no longer meet the needs of modern manufacturing for efficiency, flexibility and precise control. Summary of the invention

[0003] The embodiments of the present application provide a production parameter optimization method and system for insulating glass manufacturing, which solves the technical problem of unstable glass quality caused by untimely production parameter adjustment in the traditional insulating glass manufacturing process.

[0004] In view of the above problems, the embodiments of the present application provide a production parameter optimization method and system for insulating glass manufacturing.

[0005] In a first aspect of an embodiment of the present application, a method for optimizing production parameters for manufacturing insulating glass is provided, the method comprising:

[0006] According to the production process of insulating glass, multiple production process nodes are obtained; based on the multiple production process nodes, real-time sensing collection is performed, multiple real-time production control data are extracted, and a real-time production parameter group is determined; a control optimization channel is constructed, the real-time production parameter group is transmitted to the control optimization channel, and a control optimization parameter group is output; a control optimization target is determined, and a control optimization strategy is formulated based on the control optimization target and the control optimization parameter group; the control optimization strategy is executed to perform simulated control, the control optimization parameter group is backtracked according to the simulated control results, and the production parameters of insulating glass manufacturing are optimized according to the backtracking results.

[0007] A second aspect of the embodiment of the present application provides a production parameter optimization system for insulating glass manufacturing, the system comprising:

[0008] A node acquisition module, the node acquisition module is used to obtain multiple production process nodes according to the production process of insulating glass; a data acquisition module, the data acquisition module is used to perform real-time sensing and acquisition based on the multiple production process nodes, extract multiple real-time production control data, and determine the real-time production parameter group; a parameter optimization module, the parameter optimization module is used to build a control optimization channel, transmit the real-time production parameter group to the control optimization channel, and output the control optimization parameter group; a strategy formulation module, the strategy formulation module is used to determine the control optimization target, and formulate a control optimization strategy based on the control optimization target and the control optimization parameter group; an optimization module, the optimization module is used to execute the control optimization strategy for simulation control, backtrack the control optimization parameter group according to the simulation control results, and optimize the production parameters of insulating glass manufacturing according to the backtracking results.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, according to the production process of insulating glass, multiple production process nodes are obtained. Then, real-time sensing acquisition is performed based on multiple production process nodes, multiple real-time production control data are extracted, and a real-time production parameter group is determined. Further, a control optimization channel is constructed, the real-time production parameter group is transmitted to the control optimization channel, and the control optimization parameter group is output. By determining the control optimization target, a control optimization strategy is formulated based on the control optimization target and the control optimization parameter group. Finally, the control optimization strategy is executed to perform simulation control, and the control optimization parameter group is backtracked according to the simulation control results, and the production parameters of insulating glass manufacturing are optimized according to the backtracking results. The technical problem of unstable glass quality caused by untimely adjustment of production parameters in the traditional insulating glass manufacturing process is solved, and the technical effect of improving the stability of glass quality is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A schematic flow chart of a production parameter optimization method for manufacturing insulating glass provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a production parameter optimization system for insulating glass manufacturing provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: node acquisition module 11, data collection module 12, parameter optimization module 13, strategy formulation module 14, optimization module 15. DETAILED DESCRIPTION

[0015] The embodiments of the present application provide a production parameter optimization method and system for insulating glass manufacturing, thereby solving the technical problem of unstable glass quality caused by untimely production parameter adjustment in the traditional insulating glass manufacturing process.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the embodiment of the present application provides a production parameter optimization method for insulating glass manufacturing, wherein the method comprises:

[0020] According to the production process of insulating glass, multiple production process nodes are obtained.

[0021] The production process of insulating glass includes raw material preparation, cutting, cleaning, assembly, glue injection, edge sealing, inspection, etc. According to the production process of insulating glass, identify and determine multiple key production process nodes.

[0022] Based on the multiple production process nodes, real-time sensing collection is performed, multiple real-time production control data are extracted, and a real-time production parameter group is determined.

[0023] Real-time sensing and collection are performed at multiple production process nodes of insulating glass to obtain multiple real-time production control data. Specifically, sensors are installed at appropriate locations according to the characteristics and requirements of the production process nodes. Sensors can monitor and record various parameter changes in the production process in real time, such as temperature, pressure, speed, position, flow, etc. For example, position sensors and speed sensors are installed on cutting equipment to monitor the cutting position and speed in real time; pressure sensors and flow sensors are installed on glue injection machines to monitor glue injection pressure and flow, etc. Key production control data, such as cutting speed, glue injection pressure, temperature, etc., are extracted from the collected data, and integrated to form a real-time production parameter group, which reflects the real-time status of the current production process.

[0024] Furthermore, based on the multiple production process nodes, real-time sensing acquisition is performed to extract multiple real-time production control data and determine the real-time production parameter group, the method includes:

[0025] The multiple production process nodes are sorted in chronological order according to the production cycle to generate a production process sequence; the multiple production process nodes are traversed to match with the production process sequence, and real-time sensing collection is performed according to the matching results to obtain multiple real-time production control data, wherein the multiple real-time production control data include first real-time production control data, second real-time production control data...Nth real-time production control data, where N is the total number of multiple production process nodes; the first real-time production control data, the second real-time production control data...the Nth real-time production control data are added to the real-time production parameter group.

[0026] According to the production cycle of insulating glass, multiple production process nodes are sorted in chronological order, such as raw material preparation, cutting, cleaning, lamination, glue injection, edge sealing, quality inspection, etc. The sorted production process nodes constitute a production process sequence, which represents the entire production process from raw materials to finished products. Multiple production process nodes are matched with the production process sequence, and real-time sensing acquisition is performed on each matched node according to the characteristics and requirements of the node, such as monitoring real-time production control data such as temperature, pressure, speed, position, flow, etc. through different types of sensors. For each production process node, the sensor will capture and record the corresponding real-time production control data, which reflects the real-time status and operating parameters of the node during the production process. These real-time production control data are marked and classified in the order of the production process sequence, for example, the first real-time production control data corresponds to the first production process node, the second real-time production control data corresponds to the second node, and so on, until the Nth real-time production control data, where N is the total number of production process nodes. The obtained real-time production control data (i.e., the first real-time production control data, the second real-time production control data...the Nth real-time production control data) are integrated into a real-time production parameter group. The real-time production parameter group is a collection of the real-time status and operating parameters of all production process nodes, reflecting the real-time status of the entire production process.

[0027] A control optimization channel is constructed, the real-time production parameter group is transmitted to the control optimization channel, and the control optimization parameter group is output.

[0028] The control optimization channel is used to optimize the real-time production parameter group. By inputting the real-time production parameter group into the control optimization channel, the control optimization parameter group can be output.

[0029] Further, a control optimization channel is constructed, the real-time production parameter group is transmitted to the control optimization channel, and the control optimization parameter group is output, and the method includes:

[0030] Construct production optimization fitness function;

[0031]

[0032] Among them, f(x j ) is the production optimization fitness of the jth initial solution, c represents the production cost, h represents the production loss, d represents the production parameter, x j represents the jth initial solution, q represents x j The qth production process node of , Q represents the total number of power supply production process nodes of the jth initial solution, w c 、w h 、w d are the weights of c, h, and d respectively, and w c 、wh 、w d The sum of the weights is 1; the production optimization fitness function is introduced to construct the control optimization channel; the first real-time production control data, the second real-time production control data...the Nth real-time production control data are transmitted to the control optimization channel, and the production optimization fitness is calculated according to the production optimization fitness function to obtain the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness; based on the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness, the first real-time production control data, the second real-time production control data...the Nth real-time production control data are evaluated, control optimization is performed according to multiple evaluation results, and multiple production control optimization results are obtained; the multiple production control optimization results are added to the control optimization parameter group.

[0033] The production optimization fitness function comprehensively considers the production cost c, production loss h and production parameter d to evaluate the quality of the parameters in the production plan. j represents the jth initial solution, q represents x j The qth production process node of , Q represents the total number of power supply production process nodes of the jth initial solution, w c 、w h 、w d are the weights of c, h, and d respectively, and w c 、w h 、w d The sum of the weights is 1. A control optimization channel is constructed through the production optimization fitness function to evaluate the current production status. The first real-time production control data, the second real-time production control data...the Nth real-time production control data are transmitted to the control optimization channel. In the control optimization channel, according to the real-time data of each production process node, the production optimization fitness function is used to calculate multiple production optimization fitnesses, namely the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness. The first real-time production control data, the second real-time production control data...the Nth real-time production control data are evaluated according to the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness to obtain multiple evaluation results. Control optimization is performed based on multiple evaluation results. By comparing the fitness values ​​of different production states, it can be determined which production states are better and which need to be adjusted, thereby obtaining multiple production control optimization results. The production control optimization results obtained after optimization evaluation and control optimization are used as the control optimization parameter group.

[0034] Further, based on the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness, the first real-time production control data, the second real-time production control data...the Nth real-time production control data are optimized and evaluated, and control optimization is performed according to multiple evaluation results to obtain multiple production control optimization results. The method includes:

[0035] The multiple evaluation results are screened for maximum values ​​to obtain the i-th production optimization fitness; the i-th production optimization fitness is added to the first real-time production control data, the second real-time production control data...the N-th real-time production control data, the first real-time production control data, the second real-time production control data...the N-th real-time production control data are screened for the maximum value of production optimization fitness to determine global optimization control data; based on the i-th production optimization fitness, the i-th real-time production control data is obtained, and the i-th production process node is expanded with the i-th real-time production control data and the global optimization control data to produce The production control data expansion result of the i-th production process node is formed, and the production control data expansion result of the i-th production process node is added to the first real-time production control data, the second real-time production control data... the N-th real-time production control data, and the first node control data expansion result, the second node control data expansion result... the N-th node control data expansion result are output; according to the first node control data expansion result, the second node control data expansion result... the N-th node control data expansion result, it is repeatedly iterated m times to obtain m global optimal solutions, which are set as the control optimization parameter group, wherein m is an integer greater than or equal to 2.

[0036] The multiple evaluation results are screened for maximum values ​​respectively to find the real-time production control data with the highest production optimization fitness, that is, the i-th production optimization fitness corresponding to the i-th real-time production control data. The screened i-th real-time production control data and its corresponding i-th production optimization fitness are added to all real-time production control data. Then, all real-time production control data are screened for the maximum value of production optimization fitness to determine the global optimization control data. The i-th real-time production control data is obtained based on the i-th production optimization fitness, and the i-th real-time production control data and the global optimization control data are used to expand the production control data of the i-th production process node to generate the production control data expansion result of the i-th production process node. The production control data expansion result of the i-th production process node is added to the original real-time production control data set to update all real-time production control data. For each production process node, its control data expansion result is output, that is, the control data expansion result of the first node, the control data expansion result of the second node...the control data expansion result of the Nth node. The node control data expansion results are used as new real-time production control data. The above evaluation, screening and expansion process is repeated for m iterations. The best global optimization control data obtained in each iteration is selected as the global optimal solution of this iteration. The global optimal solutions of m iterations are combined to form a control optimization parameter group.

[0037] Further, based on the i-th production optimization fitness, the i-th real-time production control data is obtained, the i-th real-time production control data and the global optimization control data are used to expand the production control data of the i-th production process node, and the production control data expansion result of the i-th production process node is generated. The method includes:

[0038] Perform feature analysis on the i-th real-time production control data to generate an i-th real-time production control feature; use the i-th real-time production control feature as index data, traverse the global optimization control data to extract optimization control data, and there is a corresponding relationship between the optimization control data and the i-th real-time production control feature; merge the i-th real-time production control feature with the optimization control data, expand and update the production control data of the i-th production process node, and generate a production control data expansion result for the i-th production process node.

[0039] Perform feature analysis on the i-th real-time production control data to extract key production features, which can reflect the status and performance of the current production process, including indicators of various aspects such as production efficiency, energy consumption, and product quality. Generate the i-th real-time production control feature based on the results of feature analysis. Use the i-th real-time production control feature as index data to traverse the global optimization control data so as to extract the optimization control data that corresponds to the i-th real-time production control feature from the global optimization control data. Fuse the i-th real-time production control feature with the extracted optimization control data, and generate the best control data suitable for the current production environment through weighted averaging. Use the fused data to expand and update the production control data of the i-th production process node. After expansion and updating, generate the expansion result of the production control data of the i-th production process node. Apply the above process to all production process nodes, and perform feature analysis, optimization control data extraction, data fusion, and production control data expansion and update on the real-time production control data of each node.

[0040] Determine a control optimization target, and formulate a control optimization strategy based on the control optimization target and the control optimization parameter group;

[0041] Control optimization objectives include improving production efficiency, reducing production costs, improving product quality, reducing energy consumption, shortening production cycles, etc. Determine control optimization objectives based on actual needs. After determining the optimization objectives, it is necessary to conduct an in-depth analysis of the control optimization parameter group. The control optimization parameter group contains the best production control data obtained through the iterative optimization process, which reflects the optimal control parameters under different production conditions. By analyzing the parameter group, we can understand the degree of influence of different parameters on production performance and the interaction between them. Based on the analysis results of the control optimization objectives and parameter groups, formulate a control optimization strategy.

[0042] The control optimization strategy is executed to perform simulation control, the control optimization parameter group is backtracked according to the simulation control result, and the production parameters of insulating glass manufacturing are optimized according to the backtracking result.

[0043] The control optimization parameter group is imported into the simulation control system. The simulation control system executes the control optimization strategy based on these parameters, simulates the entire insulating glass manufacturing process, monitors and records the changes in various parameters, key indicators such as production efficiency and product quality during the simulation process, and generates simulation control results. The simulation control results are analyzed with the expected goals. When the simulation control results fail to achieve the expected goals, the control optimization parameter group needs to be backtracked to find out the control parameters that lead to undesirable results. Based on the backtracking results, the production parameters of insulating glass manufacturing are optimized.

[0044] Furthermore, executing the control optimization strategy to perform simulation control and generate simulation control results, the method includes:

[0045] Retrieve the historical manufacturing data record log of insulating glass, and construct the production simulation environment information based on the historical manufacturing data record log; based on the production simulation environment information, import the control optimization parameter group, execute the control optimization strategy to perform dynamic simulation recording, and generate a dynamic simulation parameter set; synchronize the dynamic simulation parameter set to the simulation control unit, and output a simulation control signal; perform simulated production control adjustment according to the simulation control signal to obtain a feedback signal; and add the feedback signal to the simulation control result.

[0046] The historical manufacturing data record log of insulating glass is retrieved from big data. The historical manufacturing data record log contains detailed information such as various parameters, conditions, and results in the past production process. The production simulation environment information is constructed based on the historical manufacturing data record log. The production simulation environment information can simulate various conditions and parameter changes in the actual production process. The control optimization parameter group is imported into the production simulation environment, and the control optimization strategy is executed in the simulation environment to simulate the production process under different parameter combinations. The various parameter changes, production results, and performance indicators in the simulation process are recorded to generate a dynamic simulation parameter set. The dynamic simulation parameter set is synchronized to the simulation control unit. The simulation control unit is used to receive simulation parameters and generate simulation control signals. The simulation control unit outputs simulation control signals according to the dynamic simulation parameter set. In the simulation environment, simulated production control adjustments are made according to the simulation control signals, including adjusting various production parameters, changing production conditions, etc. The simulated production process generates feedback signals, which reflect various responses and results in the simulated production process, and the obtained feedback signals are added to the simulation control results. In summary, building a production simulation environment based on historical manufacturing data record logs and using control optimization parameter groups and control optimization strategies for dynamic simulation to optimize production control can help predict and evaluate the effects of different control strategies before actual production, thereby reducing production costs, improving production efficiency and product quality.

[0047] Furthermore, the control optimization parameter group is backtracked according to the simulation control result, and the method includes:

[0048] A control expectation value is set based on the feedback signal; whether the control optimization parameter group reaches the control expectation value is determined; if the control optimization parameter group does not reach the control expectation value, a parameter backtracking unit is activated, and the control optimization parameter group is analyzed and identified by the parameter backtracking unit to determine a backtracking control data source; optimization and adjustment are performed based on the backtracking control data source, and the control optimization parameter group is updated according to the adjustment result, and secondary simulation control is performed based on the update result to generate a simulation control optimization result; and the simulation control optimization result is added to the backtracking result.

[0049] The control expectation value is set according to the feedback signal, and the control expectation value is used to measure whether the control optimization parameter group achieves the expected production effect. The feedback signal after the simulation production control adjustment is compared with the control expectation value. If the feedback signal indicates that the actual production effect is consistent with or close to the control expectation value, it is considered that the control optimization parameter group has achieved the expected effect. If the feedback signal indicates that there is a significant difference between the actual production effect and the control expectation value, the control optimization parameter group needs to be further adjusted. If the control optimization parameter group does not reach the control expectation value, the parameter backtracking unit is activated. The parameter backtracking unit is used to analyze and identify the problems in the control optimization parameter group and determine the backtracking control data source. The control optimization parameter group is analyzed by the parameter backtracking unit to identify the key parameters that cause the control expectation value not to be achieved, and then the backtracking control data source is determined, that is, the specific reasons for the poor control effect. According to the backtracking control data source, the current control optimization parameter group is optimized and adjusted, including modifying the values ​​of key parameters, adjusting parameter combinations, or introducing new control strategies. The adjusted control optimization parameter group is imported into the simulation environment, and secondary simulation control is performed. The parameter changes, production results, and performance indicators during the secondary simulation process are recorded to generate simulation control optimization results. The simulation control optimization results obtained by the secondary simulation control are added to the backtracking results.

[0050] In summary, the embodiments of the present application have at least the following technical effects:

[0051] First, according to the production process of insulating glass, multiple production process nodes are obtained. Then, real-time sensing acquisition is performed based on multiple production process nodes, multiple real-time production control data are extracted, and a real-time production parameter group is determined. Further, a control optimization channel is constructed, the real-time production parameter group is transmitted to the control optimization channel, and the control optimization parameter group is output. By determining the control optimization target, a control optimization strategy is formulated based on the control optimization target and the control optimization parameter group. Finally, the control optimization strategy is executed to perform simulation control, and the control optimization parameter group is backtracked according to the simulation control results, and the production parameters of insulating glass manufacturing are optimized according to the backtracking results. The technical problem of unstable glass quality caused by untimely adjustment of production parameters in the traditional insulating glass manufacturing process is solved, and the technical effect of improving the stability of glass quality is achieved.

[0052] Embodiment 2

[0053] Based on the same inventive concept as the production parameter optimization method for hollow glass manufacturing in the aforementioned embodiment, Figure 2 As shown, the present application provides a production parameter optimization system for insulating glass manufacturing, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0054] A node acquisition module 11, the node acquisition module 11 is used to obtain multiple production process nodes according to the production process of insulating glass; a data acquisition module 12, the data acquisition module 12 is used to perform real-time sensing and acquisition based on the multiple production process nodes, extract multiple real-time production control data, and determine the real-time production parameter group; a parameter optimization module 13, the parameter optimization module 13 is used to build a control optimization channel, transmit the real-time production parameter group to the control optimization channel, and output the control optimization parameter group; a strategy formulation module 14, the strategy formulation module 14 is used to determine the control optimization target, and formulate a control optimization strategy based on the control optimization target and the control optimization parameter group; an optimization module 15, the optimization module 15 is used to execute the control optimization strategy for simulation control, backtrack the control optimization parameter group according to the simulation control results, and optimize the production parameters of insulating glass manufacturing according to the backtracking results.

[0055] Furthermore, the data acquisition module 12 is used to perform the following method:

[0056] The multiple production process nodes are sorted in chronological order according to the production cycle to generate a production process sequence; the multiple production process nodes are traversed to match with the production process sequence, and real-time sensing collection is performed according to the matching results to obtain multiple real-time production control data, wherein the multiple real-time production control data include first real-time production control data, second real-time production control data...Nth real-time production control data, where N is the total number of multiple production process nodes; the first real-time production control data, the second real-time production control data...the Nth real-time production control data are added to the real-time production parameter group.

[0057] Furthermore, the parameter optimization module 13 is used to perform the following method:

[0058] Construct production optimization fitness function;

[0059]

[0060] Among them, f(x j ) is the production optimization fitness of the jth initial solution, c represents the production cost, h represents the production loss, d represents the production parameter, x j represents the jth initial solution, q represents x j The qth production process node of , Q represents the total number of power supply production process nodes of the jth initial solution, w c 、w h 、w d are the weights of c, h, and d respectively, and w c 、w h 、w dThe sum of the weights is 1; the production optimization fitness function is introduced to construct the control optimization channel; the first real-time production control data, the second real-time production control data...the Nth real-time production control data are transmitted to the control optimization channel, and the production optimization fitness is calculated according to the production optimization fitness function to obtain the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness; based on the first production optimization fitness, the second production optimization fitness...the Nth production optimization fitness, the first real-time production control data, the second real-time production control data...the Nth real-time production control data are evaluated, control optimization is performed according to multiple evaluation results, and multiple production control optimization results are obtained; the multiple production control optimization results are added to the control optimization parameter group.

[0061] Furthermore, the parameter optimization module 13 is used to perform the following method:

[0062] The multiple evaluation results are screened for maximum values ​​to obtain the i-th production optimization fitness; the i-th production optimization fitness is added to the first real-time production control data, the second real-time production control data...the N-th real-time production control data, the first real-time production control data, the second real-time production control data...the N-th real-time production control data are screened for the maximum value of production optimization fitness to determine global optimization control data; based on the i-th production optimization fitness, the i-th real-time production control data is obtained, and the i-th production process node is expanded with the i-th real-time production control data and the global optimization control data to produce The production control data expansion result of the i-th production process node is formed, and the production control data expansion result of the i-th production process node is added to the first real-time production control data, the second real-time production control data... the N-th real-time production control data, and the first node control data expansion result, the second node control data expansion result... the N-th node control data expansion result are output; according to the first node control data expansion result, the second node control data expansion result... the N-th node control data expansion result, it is repeatedly iterated m times to obtain m global optimal solutions, which are set as the control optimization parameter group, wherein m is an integer greater than or equal to 2.

[0063] Furthermore, the parameter optimization module 13 is used to perform the following method:

[0064] Perform feature analysis on the i-th real-time production control data to generate an i-th real-time production control feature; use the i-th real-time production control feature as index data, traverse the global optimization control data to extract optimization control data, and there is a corresponding relationship between the optimization control data and the i-th real-time production control feature; merge the i-th real-time production control feature with the optimization control data, expand and update the production control data of the i-th production process node, and generate a production control data expansion result for the i-th production process node.

[0065] Furthermore, the optimization module 15 is used to perform the following method:

[0066] Retrieve the historical manufacturing data record log of insulating glass, and construct the production simulation environment information based on the historical manufacturing data record log; based on the production simulation environment information, import the control optimization parameter group, execute the control optimization strategy to perform dynamic simulation recording, and generate a dynamic simulation parameter set; synchronize the dynamic simulation parameter set to the simulation control unit, and output a simulation control signal; perform simulated production control adjustment according to the simulation control signal to obtain a feedback signal; and add the feedback signal to the simulation control result.

[0067] Furthermore, the optimization module 15 is used to perform the following method:

[0068] A control expectation value is set based on the feedback signal; whether the control optimization parameter group reaches the control expectation value is determined; if the control optimization parameter group does not reach the control expectation value, a parameter backtracking unit is activated, and the control optimization parameter group is analyzed and identified by the parameter backtracking unit to determine a backtracking control data source; optimization and adjustment are performed based on the backtracking control data source, and the control optimization parameter group is updated according to the adjustment result, and secondary simulation control is performed based on the update result to generate a simulation control optimization result; and the simulation control optimization result is added to the backtracking result.

[0069] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do 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.

[0070] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0071] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for optimizing production parameters for insulating glass manufacturing, characterized in that: The method comprises: According to the production process of insulating glass, multiple production process nodes are obtained; Based on the multiple production process nodes, real-time sensor collection is performed to extract multiple real-time production control data and determine a real-time production parameter group; Building a control optimization channel, transmitting the real-time production parameter group to the control optimization channel, and outputting the control optimization parameter group; Determine a control optimization target, and formulate a control optimization strategy based on the control optimization target and the control optimization parameter group; The control optimization strategy is executed to perform simulation control, the control optimization parameter group is backtracked according to the simulation control result, and the production parameters of insulating glass manufacturing are optimized according to the backtracking result.

2. The method according to claim 1, characterized in that Based on the multiple production process nodes, real-time sensing collection is performed, multiple real-time production control data are extracted, and a real-time production parameter group is determined. The method includes: Sorting the multiple production process nodes in chronological order according to the production cycle to generate a production process sequence; Traversing the multiple production process nodes to match with the production process sequence, performing real-time sensing collection according to the matching results, and obtaining multiple real-time production control data, wherein the multiple real-time production control data include first real-time production control data, second real-time production control data...Nth real-time production control data, where N is the total number of the multiple production process nodes; The first real-time production control data, the second real-time production control data, ... the Nth real-time production control data are added to the real-time production parameter group.

3. The method according to claim 2, characterized in that Constructing a control optimization channel, transmitting the real-time production parameter group to the control optimization channel, and outputting the control optimization parameter group, the method includes: Construct production optimization fitness function; Among them, f(x j ) is the production optimization fitness of the jth initial solution, c represents the production cost, h represents the production loss, d represents the production parameter, x j represents the jth initial solution, q represents x j The qth production process node of , Q represents the total number of power supply production process nodes of the jth initial solution, w c 、w h 、w d are the weights of c, h, and d respectively, and w c 、w h 、w d The sum of the weights is 1; Introducing the production optimization fitness function and constructing the control optimization channel; The first real-time production control data, the second real-time production control data, ... the Nth real-time production control data are transmitted to the control optimization channel, and the production optimization fitness is calculated according to the production optimization fitness function to obtain the first production optimization fitness, the second production optimization fitness, ... the Nth production optimization fitness; The first real-time production control data, the second real-time production control data, ... the Nth real-time production control data are evaluated based on the first production optimization fitness, the second production optimization fitness, ... the Nth production optimization fitness, and control optimization is performed according to multiple evaluation results to obtain multiple production control optimization results; The plurality of production control optimization results are added to the control optimization parameter group.

4. The method according to claim 3, characterized in that The first real-time production control data, the second real-time production control data, and the Nth real-time production control data are evaluated based on the first production optimization fitness, the second production optimization fitness, and the Nth production optimization fitness, and control optimization is performed according to multiple evaluation results to obtain multiple production control optimization results. The method includes: Performing maximum value screening on the multiple evaluation results to obtain the i-th production optimization fitness; Add the i-th production optimization fitness to the first real-time production control data, the second real-time production control data ... the N-th real-time production control data, perform maximum value screening of the production optimization fitness on the first real-time production control data, the second real-time production control data ... the N-th real-time production control data, and determine the global optimization control data; Based on the i-th production optimization fitness, the i-th real-time production control data is acquired, the production control data of the i-th production process node is expanded using the i-th real-time production control data and the global optimization control data, and an expanded result of the production control data of the i-th production process node is generated, and the expanded result of the production control data of the i-th production process node is added to the first real-time production control data, the second real-time production control data...the N-th real-time production control data, and the first node control data expansion result, the second node control data expansion result...the N-th node control data expansion result are output; According to the first node control data expansion result, the second node control data expansion result...the Nth node control data expansion result, the control data expansion result is repeatedly iterated m times to obtain m global optimal solutions, which are set as the control optimization parameter group, wherein m is an integer greater than or equal to 2.

5. The method according to claim 4, characterized in that Based on the i-th production optimization fitness, an i-th real-time production control data is obtained, and production control data of an i-th production process node is expanded using the i-th real-time production control data and the global optimization control data to generate a production control data expansion result of the i-th production process node. The method includes: Performing feature analysis on the i-th real-time production control data to generate an i-th real-time production control feature; Taking the i-th real-time production control feature as index data, traversing the global optimization control data to extract optimization control data, wherein the optimization control data corresponds to the i-th real-time production control feature; The i-th real-time production control feature is integrated with the optimized control data, the production control data of the i-th production process node is expanded and updated, and the production control data expansion result of the i-th production process node is generated.

6. The method according to claim 1, characterized in that Executing the control optimization strategy to perform simulation control and generate simulation control results, the method includes: Retrieving historical manufacturing data record logs of insulating glass, and constructing production simulation environment information based on the historical manufacturing data record logs; Based on the production simulation environment information, the control optimization parameter group is imported, the control optimization strategy is executed to perform dynamic simulation recording, and a dynamic simulation parameter set is generated; Synchronizing the dynamic simulation parameter set to the simulation control unit and outputting a simulation control signal; Performing simulated production control adjustment according to the simulated control signal to obtain a feedback signal; The feedback signal is added to the simulated control result.

7. The method according to claim 6, characterized in that The control optimization parameter group is backtracked according to the simulation control result, and the method includes: Setting a control expectation value based on the feedback signal; Determining whether the control optimization parameter group reaches the control expected value; If the control optimization parameter group does not reach the control expected value, a parameter backtracking unit is activated, and the control optimization parameter group is analyzed and identified by the parameter backtracking unit to determine a backtracking control data source; Perform optimization adjustment based on the backtracking control data source, update the control optimization parameter group according to the adjustment result, perform secondary simulation control based on the update result, and generate simulation control optimization result; The simulation control optimization result is added to the backtracking result.

8. A production parameter optimization system for insulating glass manufacturing, characterized in that: The system is used to implement the production parameter optimization method for manufacturing insulating glass according to any one of claims 1 to 7, comprising: A node acquisition module, wherein the node acquisition module is used to obtain a plurality of production process nodes according to the production process of insulating glass; A data acquisition module, the data acquisition module is used to perform real-time sensor acquisition based on the multiple production process nodes, extract multiple real-time production control data, and determine a real-time production parameter group; A parameter optimization module, the parameter optimization module is used to construct a control optimization channel, transmit the real-time production parameter group to the control optimization channel, and output the control optimization parameter group; A strategy formulation module, the strategy formulation module is used to determine a control optimization target, and formulate a control optimization strategy based on the control optimization target and the control optimization parameter group; The optimization module is used to execute the control optimization strategy to perform simulation control, backtrack the control optimization parameter group according to the simulation control result, and optimize the production parameters of insulating glass manufacturing according to the backtracking result.

Images