A cross-platform data collaborative optimization system based on industrial Internet

Abstract

The present invention discloses a cross-platform data collaborative optimization system based on the industrial Internet, which belongs to the field of intelligent manufacturing. The system includes: an equipment composition information acquisition module: used to interactively obtain the equipment composition information of the concept design product production line; a production control architecture acquisition module: used to configure the production control architecture according to the equipment composition information; a production control information acquisition module: used to execute production log calls on the product production line; a collaborative control parameter set acquisition module: used to execute online control collaborative optimization of the product production line across the platform production control architecture; a redistribution strategy acquisition module: used to pre-build a production task allocation model and perform production task allocation analysis; a control parameter set execution module: used to control the product production line to execute batch production of products by using an updated collaborative control parameter set. The system solves the technical problems in the prior art that the equipment data of the production line is dispersed and the collaborative optimization is difficult, resulting in low production efficiency and unstable product quality.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing, and in particular to a cross-platform data collaborative optimization system based on the industrial Internet. Background Art

[0002] In the era of Industry 4.0, the rapid development of the Industrial Internet is profoundly changing the production model of the traditional manufacturing industry. By applying advanced sensors, communication technologies and big data analysis methods to the manufacturing process, the Industrial Internet has achieved the interconnection of production equipment and systems, allowing production data to be seamlessly transmitted and shared between different devices and platforms. This cross-platform data collaboration capability not only improves production efficiency, but also provides more intelligent and automated solutions for the manufacturing industry, promoting the transformation of the manufacturing industry to intelligent manufacturing and digitalization.

[0003] However, despite the broad application prospects of the Industrial Internet in the manufacturing industry, the existing production control system still has many shortcomings. First, the data island problem between different production lines and equipment is still serious, resulting in the inability to share and integrate information, which restricts the optimization and coordination of the production process. Secondly, traditional production control systems often lack flexibility and intelligent means, and it is difficult to dynamically adjust and optimize according to real-time production data. In addition, the existing quality control methods are mostly post-detection, which cannot promptly identify and deal with defects and problems in the production process, making it difficult to ensure product quality.

[0004] In summary, the present application aims to solve the technical problems in the prior art that production line equipment data is dispersed and collaborative optimization is difficult, resulting in low production efficiency and unstable product quality. Summary of the invention

[0005] This application provides a cross-platform data collaborative optimization system based on the Industrial Internet, aiming to solve the technical problems in the prior art of low production efficiency and unstable product quality caused by the dispersion of production line equipment data and the difficulty of collaborative optimization.

[0006] In view of the above problems, the present application provides a cross-platform data collaborative optimization system based on the industrial Internet, the system comprising an equipment composition information acquisition module: used to interactively obtain multiple equipment composition information of multiple product production lines of conceptual design products; a production control architecture acquisition module: used to configure the production control architecture according to the multiple equipment composition information, and obtain multiple cross-platform production control architectures, wherein each cross-platform production control architecture is pre-built based on the industrial Internet; a production control information acquisition module: used to preset a task allocation reference window, and execute production log calls on the multiple product production lines based on the task allocation reference window to obtain multiple production control information; a collaborative control parameter set Acquisition module: used for the multiple cross-platform production control architectures to perform online control collaborative optimization of the multiple product production lines according to the multiple production control information, and obtain multiple updated collaborative control parameter sets; reallocation strategy acquisition module: used to pre-build a production task allocation model, input the multiple production control information into the production task allocation model to perform production task allocation analysis, and obtain a production task reallocation strategy; control parameter set execution module: used to use the task allocation reference window as the execution time constraint, the production task redistribution strategy as the task allocation constraint, and the multiple updated collaborative control parameter sets to control the multiple product production lines to execute batch production of the conceptual design products.

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

[0008] First, the equipment composition information of multiple production lines of the conceptual design product is obtained interactively. Then, the production control architecture is configured according to the equipment composition information to obtain multiple pre-built cross-platform production control architectures. Next, a task allocation reference window is preset, and production log calls are executed on multiple production lines based on this window to obtain multiple production control information. Using these production control information, multiple cross-platform production control architectures perform online control collaborative optimization and generate multiple updated collaborative control parameter sets. At the same time, a production task allocation model is pre-built, production control information is input, production task allocation analysis is performed, and a redistribution strategy is obtained. Finally, the task allocation reference window is used as the execution time constraint, the redistribution strategy is used as the task allocation constraint, and the updated collaborative control parameter set is used to control multiple production lines to execute batch production of the conceptual design product. The technical problems of low production efficiency and unstable product quality caused by the scattered equipment data of the production line and the difficulty of collaborative optimization in the prior art are solved, and efficient cross-platform production control is achieved.

[0009] 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

[0010] Figure 1 A structural diagram of a cross-platform data collaborative optimization system based on the Industrial Internet is provided for an embodiment of the present application.

[0011] Figure 2 A flow chart of a production control architecture acquisition module in a cross-platform data collaborative optimization system based on the Industrial Internet is provided for an embodiment of the present application.

[0012] Explanation of the reference numerals: equipment configuration information acquisition module 11, production control architecture acquisition module 12, production control information acquisition module 13, collaborative control parameter set acquisition module 14, redistribution strategy acquisition module 15, control parameter set execution module 16. DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] An embodiment of the present application provides a cross-platform data collaborative optimization system based on the Industrial Internet. The equipment composition information of multiple product production lines is obtained interactively, and the production control architecture is configured based on this information, and pre-built through the Industrial Internet. A preset task allocation reference window is set, and the production log is called to obtain production control information. This information is used for online control collaborative optimization to generate an updated collaborative control parameter set. At the same time, a production task allocation model is pre-built, and the production control information is input into the model to perform production task allocation analysis and generate a production task redistribution strategy. Using the task allocation reference window as the execution time constraint, combined with the production task redistribution strategy, an updated collaborative control parameter set is used to control multiple product production lines to achieve mass production of conceptual design products.

[0015] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0016] Example

[0017] like Figure 1 As shown, the embodiment of the present application provides a cross-platform data collaborative optimization system based on the industrial Internet, the system comprising:

[0018] The equipment composition information acquisition module 11 is used to interactively obtain multiple equipment composition information of multiple product production lines of the conceptual design product.

[0019] Specifically, the conceptual design product refers to a product that is in the conceptual stage and has not yet entered the mass production stage. The equipment configuration of the production line needs to be determined according to its design requirements. Multiple product production lines mean not only one production line, but multiple production lines. Among them, the equipment information on each production line includes but is not limited to the type, model, configuration parameters, functional description, operating status, production capacity, etc. of the equipment. This equipment information is obtained interactively. The interactive method can be data communication between systems, human-computer interaction, or real-time collection through a sensor network. The interactive acquisition method should ensure the accuracy and timeliness of the data.

[0020] This module can accurately and comprehensively collect and manage the equipment information of multiple production lines of conceptual design products, providing necessary data support for subsequent production control architecture configuration and production optimization.

[0021] The production control architecture acquisition module 12 is used to configure the production control architecture according to the multiple equipment configuration information, and obtain multiple cross-platform production control architectures, wherein each cross-platform production control architecture is pre-built based on the industrial Internet.

[0022] Specifically, the collected equipment composition information is analyzed to determine the specific needs and characteristics of each production line. The analysis includes the type of equipment, operating parameters, data communication protocols, control requirements, etc.

[0023] Design and configure the production control architecture based on the equipment configuration information. This involves determining the production control strategy, setting the control logic, configuring the data communication method, etc. The production control architecture should ensure that the various devices can communicate and work together efficiently to achieve unified production control. Ensure that the production control architecture can run on multiple platforms, including different operating systems, network environments, and hardware devices. Use standardized data communication protocols and interfaces to ensure cross-platform compatibility and interoperability.

[0024] The production control architecture is pre-built based on the Industrial Internet technology. The Industrial Internet combines traditional industrial equipment with Internet technology to achieve data interoperability and intelligent control between devices. Pre-built means that these architectures have been designed and tested on the Industrial Internet platform and can be quickly deployed and applied.

[0025] This module uses the equipment configuration information to configure the production control architecture, and finally obtains multiple cross-platform production control architectures. These architectures are pre-built based on the industrial Internet, which can realize data interoperability and intelligent control between devices, and improve production efficiency and product quality.

[0026] The production control information acquisition module 13 is used to preset a task allocation reference window, and based on the task allocation reference window, execute production log calls on the multiple product production lines to obtain multiple production control information.

[0027] Specifically, the task allocation reference window is a time period or condition setting used to specify when or under what conditions task allocation and data collection are performed. It can be pre-set based on production plans, production rhythm, equipment status and other factors to ensure the timeliness and accuracy of data collection and task allocation.

[0028] In the preset task allocation reference window, the production logs of multiple product production lines are called. The production log call refers to obtaining detailed production data from the production line, including production progress, equipment operation status, quality inspection results, energy consumption, etc. This call can be implemented through system automation scripts, API interfaces or other data collection methods.

[0029] By calling the production log, various data generated during the production process are collected and sorted. The production control information includes but is not limited to production efficiency, product quality, equipment utilization, energy consumption, defective rate, etc. This information is of great significance for subsequent production optimization and control.

[0030] This module can obtain production quality control information of multiple product production lines through production log calls within the preset task allocation reference window. This information provides necessary data support for subsequent production control optimization and task reallocation, ensuring the efficiency and quality control of the production process.

[0031] The collaborative control parameter set acquisition module 14 is used for the multiple cross-platform production control architectures to perform online control collaborative optimization of the multiple product production lines according to the multiple product control information, and obtain multiple updated collaborative control parameter sets.

[0032] Specifically, the collected production quality control information is extracted from the data storage system. The data is ensured to be accurate and real-time, and to reflect the latest status of the production line. The production quality control information is analyzed to identify bottlenecks, inefficiencies, and quality issues in the production process.

[0033] According to the analysis results, optimization strategies are formulated. These strategies include adjusting the operating parameters of the production line, optimizing equipment configuration, improving quality control measures, etc. The optimization strategy needs to consider the collaborative work of multiple production lines to ensure the improvement of overall production efficiency and quality.

[0034] Online control collaborative optimization refers to the use of production control information in real time to control and optimize the production line during the production process. The optimization strategy is implemented in real time through a cross-platform production control architecture. The architecture dynamically adjusts control parameters through communication with production line equipment and control systems. The continuity and real-time nature of the optimization process are ensured, so that the production line can maintain efficient operation during the optimization process.

[0035] After implementing the optimization strategy, the production control architecture generates a new set of collaborative control parameters to adjust the operation of the production line to make it more efficient and reliable. It reflects the optimal operating state of the production line for subsequent production control.

[0036] This module implements online control collaborative optimization based on production control information, dynamically adjusts multiple product production lines across the platform production control architecture, and finally obtains updated collaborative control parameter sets. These parameter sets are used to optimize the operation of the production line and improve production efficiency and product quality.

[0037] The reallocation strategy acquisition module 15 is used to pre-build a production task allocation model, input the multiple production control information into the production task allocation model to perform production task allocation analysis, and obtain a production task reallocation strategy.

[0038] Specifically, the production task allocation model is a mathematical model or algorithm framework for analyzing and optimizing production task allocation. The model takes into account multiple factors such as production line capacity, equipment status, production demand, etc. Pre-built means that the model has been designed and tested before actual use to ensure that it is suitable for the actual production environment.

[0039] Input multiple production control information into the production task allocation model. Ensure the integrity and accuracy of the data to provide a reliable data basis for model analysis. The production task allocation model performs analysis to evaluate the current load and capacity of each production line. Use optimization algorithms to calculate the best task allocation plan, taking into account factors such as production efficiency, equipment utilization, and product quality.

[0040] Based on the analysis results, a production task reallocation strategy is generated. The strategy includes specific task allocation details, such as the allocation of production tasks, production line priorities and time arrangements. The reallocation strategy aims to balance the production load, improve production efficiency, reduce production costs, and ensure product quality.

[0041] This module realizes the generation of optimized production task redistribution strategy by pre-building production task allocation model and analyzing production control information. This strategy can effectively improve production efficiency, balance production load and ensure product quality.

[0042] Control parameter set execution module 16: used to use the task allocation reference window as the execution time constraint, the production task reallocation strategy as the task allocation constraint, and adopt the multiple updated collaborative control parameter sets to control the multiple product production lines to execute batch production of the conceptual design products.

[0043] Specifically, determine the task allocation reference window as the execution time constraint. Ensure that all production tasks are executed within the specified time window. According to the production task redistribution strategy, the production tasks are allocated to each production line. Task allocation should take into account the load and production capacity of the production line to ensure balanced production. Use the updated collaborative control parameter set to adjust the operating parameters of the production line. The control parameters include equipment operating speed, production process parameters, quality control standards, etc.

[0044] Start mass production of conceptual design products under time and task allocation constraints. Monitor the production process to ensure that the production line operates according to the optimized control parameters and task allocation strategy.

[0045] This module realizes the control of multiple product production lines to efficiently execute batch production of conceptual design products under the constraints of the task allocation reference window and production task redistribution strategy, using the updated collaborative control parameter set. This not only optimizes the production process, improves production efficiency and product quality, but also ensures the on-time completion of production tasks.

[0046] Further, such as Figure 2 As shown, the system is also used to perform the following steps:

[0047] Interactively obtain the first equipment composition information of the first product production line of the conceptual design product, wherein the first equipment composition information includes multiple production and processing equipment; pre-build multiple equipment control edge platforms, and connect the multiple production and processing equipment and the multiple equipment control edge platforms based on the industrial Internet; pre-build a first cross-platform production control cloud, wherein the first cross-platform production control cloud includes a cascaded production defect identifier and a production equipment optimizer; communicatively connect the first cross-platform production control cloud and the multiple equipment control edge platforms to obtain a first cross-platform production control architecture; and so on, configure the production control architecture according to the multiple equipment composition information to obtain the multiple cross-platform production control architectures.

[0048] Specifically, the equipment composition information of the first product production line is obtained through interactive methods (such as data request, sensor data collection, etc.). This information includes detailed data of multiple production and processing equipment, such as equipment type, model, configuration parameters, function description, etc.

[0049] Pre-design and build multiple equipment control edge platforms to manage and control production and processing equipment. Based on industrial Internet technology, multiple production and processing equipment are connected to the equipment control edge platform to achieve data interoperability and real-time control.

[0050] Among them, build an equipment control edge platform, and design the overall architecture of the edge platform according to the needs of the production line and the equipment composition information. Determine the hardware configuration, network connection method and software system of the edge platform. Select hardware devices suitable for edge computing, such as industrial-grade computers, routers, gateways, etc. Ensure that the hardware equipment has sufficient computing power and reliability to cope with the demanding requirements of the production environment. Develop an edge computing software system, including data acquisition modules, real-time processing modules, control algorithms, etc. Deploy edge computing software to hardware devices to ensure that the system can run stably. Connect the edge platform with multiple production and processing equipment to establish a data communication channel. Ensure that the edge platform can obtain the operating data of the equipment in real time and control and optimize the equipment.

[0051] Design and build the first cross-platform production control cloud as the core of the entire control architecture. The cloud system includes two main modules: production defect identifier and production equipment optimizer. The production defect identifier is used to detect and identify defects and problems that occur during the production process. The production equipment optimizer is used to optimize and adjust the operating parameters of the production equipment based on the identified defect information.

[0052] Among them, pre-build the first cross-platform production control cloud, and design the overall architecture of the cloud system according to the needs of production control. Determine the functional modules and data flows of the cloud system. Select a suitable cloud service platform, such as AWS, Azure, GoogleCloud, etc., to provide computing, storage and network resources. Ensure that the selected platform can support cross-platform operations and real-time data processing. Develop algorithms and software modules for detecting and identifying defects in the production process. The defect identifier identifies abnormal conditions of products or equipment by analyzing data from the production line. Develop algorithms and software modules for optimizing the operation of production equipment. The optimizer adjusts the operating parameters of the equipment based on real-time data and analysis results to improve production efficiency and product quality.

[0053] Through communication technologies (such as IoT protocols, wireless networks, etc.), the first cross-platform production control cloud is connected to multiple device control edge platforms. Ensure real-time transmission and interaction of data between the cloud and edge platforms, thus forming a complete production control architecture.

[0054] The same method and process are used to collect equipment information, build edge platforms, build cloud platforms, and connect communications for other production lines. Finally, multiple cross-platform production control architectures are configured to achieve unified management and collaborative optimization of the entire production system.

[0055] This step describes in detail how to gradually build and configure a cross-platform production control architecture based on the equipment configuration information, including obtaining equipment information, building edge platforms and cloud systems, and achieving communication connections. Through these steps, unified control and collaborative optimization of multiple production lines can be achieved to improve production efficiency and product quality.

[0056] Furthermore, the system is also used to perform the following steps:

[0057] Interactively obtain multiple groups of sample processing defect images of the multiple production and processing equipment; preset defect feature parameter labels, and identify the multiple groups of sample processing defect images based on the defect feature parameter labels to obtain multiple groups of sample defect identification images; construct multiple defect recognition mark branches of the multiple production and processing equipment based on the mapping of the multiple groups of sample processing defect images and the multiple groups of sample defect identification images; connect the multiple defect recognition mark branches in parallel to generate the production defect identifier.

[0058] Specifically, multiple sets of sample processing defect images are obtained from multiple production and processing equipment through interactive methods (such as manual collection, automatic collection, etc.). The multiple sets of sample processing defect images cover various possible processing defects and provide a data basis for subsequent identification and labeling.

[0059] Define the characteristic parameter labels of various defects, such as size, shape, color, etc. Use the preset defect characteristic parameter labels to annotate the sample processing defect image and generate an identification image. Each sample image corresponds to an identification image to identify the defective part in the image.

[0060] Map the sample processing defect image and the corresponding identification image to train the defect recognition model. Establish an identification tag branch for each production and processing equipment to specifically identify the specific defects of the equipment.

[0061] All defect identification marking branches are connected in parallel to form a complete defect identifier. The defect identifier is an integrated system that can identify all preset types of defects and is used for real-time monitoring and detection during the production process.

[0062] For example, in an electronic product manufacturing plant: sample images containing defects such as poor welding and uneven spraying are collected from different production equipment (such as welding equipment and spraying equipment). Defect feature parameters (such as hole size of poor welding and color difference of uneven spraying) are preset, sample images are annotated, and identification images are generated. Using sample images and identification images, defect recognition models for welding equipment and spraying equipment are constructed to form two identification mark branches. The identification mark branches of welding and spraying are connected in parallel to generate a unified defect identifier that can identify and alarm problems such as poor welding and uneven spraying in real time during the production process.

[0063] This step builds an efficient production defect identification system, realizes real-time monitoring and detection of multiple devices and multiple types of defects, and improves the quality control level of the production process.

[0064] Furthermore, the system is also used to perform the following steps:

[0065] Preset standard defect feature parameters, standard parameter adjustment step and standard parameter adjustment frequency, and construct a collaborative optimization parameter adjustment layer based on the standard defect feature parameters, standard parameter adjustment step and standard parameter adjustment frequency; interactively obtain multiple groups of sample control parameters and multiple sample production feature images, wherein each group of sample control parameters includes multiple sample control parameters of the multiple production and processing equipment; train the production collaborative optimization fitting layer according to the multiple groups of sample control parameters and the multiple sample production feature images; preset qualified defect constraints, and synchronize the qualified defect constraints to the collaborative optimization fitting layer; cascade the collaborative optimization parameter adjustment layer and the collaborative optimization fitting layer to generate the production equipment optimizer.

[0066] Specifically, the preset standard defect characteristic parameters refer to the standard characteristics that define common defects in products or processing processes, such as size, shape, color, etc. The standard parameter adjustment step size is the amplitude of each adjustment when adjusting the operating parameters of the production equipment. The step size setting needs to take into account the sensitivity of the equipment and the requirements of the production process to ensure that the adjusted parameters can significantly affect the production results but not too drastically. For example, the step size when adjusting the temperature can be set to 0.5°C, and the step size when adjusting the pressure can be set to 5Pa. The standard parameter adjustment frequency refers to the frequency of adjusting the parameters of the production equipment, that is, how often the parameters are adjusted. The frequency setting should take into account the dynamics and stability of the production process to ensure that the adjustment frequency can respond to production changes and will not be too frequent to cause system instability. For example, the parameter adjustment frequency can be set to once an hour or once after each batch of products is produced. Based on the above standard parameters, a hierarchical structure for real-time adjustment and optimization of production equipment parameters is constructed.

[0067] Collect control parameters of different production and processing equipment under various operating conditions. Obtain production feature images corresponding to these control parameters to reflect the production process and product quality. Collect these sample data through interaction with equipment and production lines to provide a basis for model training.

[0068] Using sample control parameters and production feature images, a fitting layer model is trained to simulate and optimize parameter adjustments during the production process. The fitting layer can predict production results based on the input control parameters and guide the optimization adjustment of equipment parameters.

[0069] Define the product's qualification standards and defect tolerance range, such as the maximum size of defects, the allowed number, etc. Synchronize these qualification standards to the collaborative optimization fitting layer to ensure that the production results meet the quality requirements during the optimization process.

[0070] The collaborative optimization parameter adjustment layer and the fitting layer are combined to form a comprehensive optimization system. The comprehensive system can adjust the production equipment parameters in real time to improve production efficiency and product quality.

[0071] Based on this step, intelligent control and optimization of the production process can be achieved, production efficiency can be improved, and stable product quality can be ensured.

[0072] Furthermore, the system is also used to perform the following steps:

[0073] The production control information of each product includes production energy consumption, production efficiency parameters, production defect rate and defect image set.

[0074] Specifically, production control information refers to the various key indicators and data collected and recorded during the production process, which are used to monitor and optimize the production process.

[0075] Production energy consumption refers to the total amount of energy consumed during the production process, including the use of electricity, gas, water and other energy sources. Monitor and manage energy efficiency to reduce waste, lower production costs and reduce environmental impact. Energy consumption data can be recorded and analyzed in real time through energy metering devices installed on equipment and production lines.

[0076] Production efficiency parameters refer to the operating efficiency of a production line or equipment, including production speed, equipment utilization, production time, etc. Evaluate the working efficiency of production lines and equipment, identify bottlenecks and inefficient links, and optimize production processes. Obtain production efficiency-related data in real time through production management systems and equipment monitoring systems.

[0077] The defective rate of production refers to the proportion of defective products produced in the production process to the total output. Evaluate product quality and the stability of the production process, discover and solve quality problems in the production process. Through the quality inspection system and production records, count the number of defective products and total output in the production process, and calculate the defective rate.

[0078] Defective product image set refers to the image collection of defective product samples recorded during the production process. These images are used to analyze and identify the characteristics and causes of defective products. Through image analysis, the types and causes of defective products can be identified and classified to improve production processes and quality control measures. The images of defective product samples are captured and recorded in real time through the camera equipment installed on the production line and saved as an image set.

[0079] By collecting and analyzing this production control information, the factory can fully understand all aspects of the production process, so as to effectively optimize and improve it, improve production efficiency, reduce costs and improve product quality.

[0080] Furthermore, the system is also used to perform the following steps:

[0081] The first product image set of the first product production line is obtained from the multiple production control information; the first product image set is input into the first cross-platform production control cloud in the first cross-platform production control architecture; equipment positioning is performed via the production defect identifier of the first cross-platform production control cloud to obtain deviation equipment and deviation defect characteristic parameters; the deviation operation parameter set of the deviation equipment is interactively obtained, and the production equipment optimizer of the first cross-platform production control cloud performs online control collaborative optimization according to the deviation operation parameter set and deviation defect characteristic parameters to obtain a first updated collaborative control parameter set; and so on, the multiple cross-platform production control architectures perform online control collaborative optimization of the multiple product production lines according to the multiple production control information to obtain the multiple updated collaborative control parameter sets.

[0082] Specifically, a defective image set of the first product production line is retrieved from a database or storage system. The defective image set is input into a cloud system of a first cross-platform production control architecture. The defective image is analyzed using a defect identifier in the production control cloud. The defect type and features are identified, and the specific equipment causing the defect is located.

[0083] Obtain the operating parameter set from the deviation equipment, including the current operating conditions. Perform online control collaborative optimization by combining the deviation operating parameters and defect characteristic parameters through the production equipment optimizer. Generate an updated control parameter set based on the optimization results.

[0084] Apply the above process to other production lines, repeat the acquisition of defective product image sets, defect identification, equipment positioning, acquisition of operating parameters, and optimization. Generate an updated set of collaborative control parameters for each production line.

[0085] Based on this step, cross-platform online control collaborative optimization can be achieved to improve the operating efficiency and product quality of the production line.

[0086] Furthermore, the system is also used to perform the following steps:

[0087] Based on the Euclidean distance calculation, the deviation coefficient of the deviation defect feature parameter and the standard defect feature parameter is obtained, and the standard parameter adjustment step and the standard parameter adjustment frequency are updated according to the deviation coefficient to obtain the updated parameter adjustment step and the updated parameter adjustment frequency; in the collaborative optimization parameter adjustment layer, the deviation operation parameter set is adjusted with the updated parameter adjustment step and the updated parameter adjustment frequency as constraints to obtain multiple updated operation parameter sets; the multiple updated operation parameter sets are input into the collaborative optimization fitting layer to obtain multiple updated production feature images, wherein the multiple updated production feature image mappings have multiple updated defect feature parameter identifiers; the multiple updated defect feature parameters are traversed to screen and obtain K updated defect feature parameters that fall within the qualified defect constraints; the K updated defect feature parameters and the K defect similarity coefficients of the qualified defect constraints are calculated, and based on the extreme values ​​of the K defect similarity coefficients, the multiple updated operation parameter sets are mapped and called to obtain the first updated collaborative control parameter set.

[0088] Specifically, the deviation defect characteristic parameter refers to the actual defect characteristic parameter obtained from the production process. The standard defect characteristic parameter refers to the preset ideal or qualified defect characteristic parameter. The Euclidean distance between the actual defect characteristic parameter and the standard defect characteristic parameter is calculated to obtain the deviation coefficient. Euclidean distance formula:

[0089]

[0090] Among them, x i and i Represent the i-th value of the deviation defect characteristic parameter and the standard defect characteristic parameter respectively. Use the calculated deviation coefficient to update the parameter adjustment step size and parameter adjustment frequency. If the deviation coefficient is large, the parameter adjustment step size may need to be increased and the parameter adjustment frequency may need to be increased. If the deviation coefficient is small, the parameter adjustment step size may need to be reduced and the parameter adjustment frequency may need to be reduced.

[0091] In the collaborative optimization parameter adjustment layer, the deviation operating parameters are adjusted using the updated parameter adjustment step size and frequency to generate multiple updated operating parameter sets. The adjusted operating parameter sets are input into the collaborative optimization fitting layer for further processing. The collaborative optimization fitting layer generates corresponding production feature images based on the input updated operating parameter sets. These feature images contain updated defect feature parameters.

[0092] Traverse all updated defect feature parameters. Filter K updated defect feature parameters that meet the qualified standards: Filter out the defect feature parameters that meet the preset qualified standards. Calculate the similarity coefficient between the K updated defect feature parameters and the qualified defect constraints. According to the extreme value of the similarity coefficient, select the optimal operating parameter set from the updated operating parameter set. The selected optimal operating parameter set is used as the first updated collaborative control parameter set and applied to the production process.

[0093] Based on this step, production equipment can continuously optimize operating parameters, improve production efficiency and product quality, and ensure the stability and reliability of the production process.

[0094] Furthermore, the system is also used to perform the following steps:

[0095] The production task allocation model includes a production reliability evaluation layer and a production task allocation layer; a production reliability evaluation function is introduced into the production reliability evaluation layer to evaluate the multiple production control information to obtain multiple production reliability coefficients; real-time production tasks are obtained interactively, and the multiple production reliability coefficients and the real-time production tasks are synchronized to the production task allocation layer to execute production task weight allocation to obtain the production task redistribution strategy.

[0096] Specifically, the production task allocation model is used to analyze and optimize the allocation strategy of production tasks to improve production efficiency and quality. It includes a production reliability evaluation layer and a production task allocation layer.

[0097] Based on the production control information, the reliability of each production line and equipment is evaluated using an evaluation function. The evaluation function takes into account factors such as production efficiency, defective rate, and equipment operating status to calculate the production reliability coefficient. Multiple production reliability coefficients are calculated through the evaluation function, which reflect the operating reliability of each production line and equipment.

[0098] Through the interaction between the system and the production management system (such as the MES system), the current production tasks can be obtained in real time, including specific task information such as production orders and production demand adjustments.

[0099] Input the production reliability coefficient and real-time production tasks into the production task allocation layer. According to the production reliability coefficient and real-time production tasks, calculate the weight distribution of each production task to optimize the utilization of production resources. Based on the task weight distribution results, generate a production task redistribution strategy to ensure reasonable and efficient task allocation.

[0100] Based on this step, dynamic production task allocation based on production reliability and real-time task requirements can be achieved, which can improve the flexibility and efficiency of the production process and ensure product quality and delivery time.

[0101] Furthermore, the system is also used to perform the following steps:

[0102] The production reliability evaluation function is as follows:

[0103]

[0104] Among them, R is the production reliability coefficient, E is the production energy consumption, P is the production efficiency parameter, D is the production defective rate, k and n are the first weight parameter group of the production defective rate, m is the second weight parameter of the production defective rate, and k+n+m=1.

[0105] Specifically, the production quality control information of each production line is collected, including the production efficiency parameter P, the production energy consumption E, and the production defect rate D. The production reliability coefficient R of each production line is calculated according to the weight parameters k, n, m and the above formula.

[0106] Obtain real-time production tasks through the system, including production requirements and order information. Calculate the production reliability coefficients of multiple production lines, calculate the weight distribution of multiple production lines based on multiple production reliability coefficients, and then multiply the multiple weight distributions by the total production volume required by the real-time task to obtain the production volume of each production line as a production task redistribution strategy

[0107] This step can realize cross-platform data collaborative optimization based on the Industrial Internet, improve the flexibility and efficiency of the production process, and ensure product quality and delivery time.

[0108] In summary, the cross-platform data collaborative optimization system based on the industrial Internet provided by the embodiment of the present application has the following technical effects:

[0109] 1. Obtain the equipment composition information of the production line through interaction, configure the production control architecture based on the industrial Internet, preset the task allocation reference window, call the production log to obtain production control information, perform online control collaborative optimization, pre-build the production task allocation model, analyze the production tasks and generate the redistribution strategy, and finally control the production line for batch production with the updated collaborative control parameter set. It realizes the unified management and optimization of multiple production lines and improves production efficiency and product quality.

[0110] 2. Obtain sample processing defect images of the equipment through interaction, preset defect feature parameter labels, and build multiple defect recognition tag branches based on these images and tags, and finally connect these branches in parallel to generate a production defect identifier. By building a defect identifier, the accuracy and efficiency of defect detection in the production process are improved. The preset of multiple sets of sample processing defect images and feature labels ensures the comprehensiveness and accuracy of defect identification. Connecting multiple identification tag branches in parallel enhances the recognition ability of the system, enabling real-time monitoring and detection of various defects in the production process and improving product quality.

[0111] 3. Through the presetting and acquisition of standard parameters and sample data, combined with the training of the fitting layer and the synchronization of qualified constraints, the collaborative optimization of production equipment is achieved. The cascade of the parameter adjustment layer and the fitting layer forms a complete optimizer that can adjust the parameters of production equipment according to real-time data, improve production efficiency and quality, and ensure that the product meets the qualified standards.

[0112] 4. By defining the content of production control information in detail, comprehensive monitoring and analysis of the production process is ensured. Monitoring of production energy consumption and efficiency parameters helps to optimize energy use and improve production efficiency; recording of production defective rate and defective image set helps defect detection and quality control, providing comprehensive production process data support.

[0113] 5. Through the pre-construction of the production task allocation model and the introduction of the reliability evaluation layer, the scientific allocation and dynamic adjustment of production tasks are realized. The calculation of the production reliability coefficient provides the basis for task allocation and ensures the rational use and optimal configuration of production resources. The generation of task weight allocation and redistribution strategy improves the efficiency and flexibility of the production process and ensures the efficient execution of production tasks.

[0114] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0115] Furthermore, the first or second mentioned above may represent an order relationship, or may represent a specific concept, and / or may refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art may make various changes and modifications 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 cross-platform data collaborative optimization system based on the industrial Internet, characterized in that: The system comprises: Equipment composition information acquisition module: used to interactively obtain multiple equipment composition information of multiple product production lines of conceptual design products; A production control architecture acquisition module: configured to configure a production control architecture according to the plurality of equipment configuration information, and obtain a plurality of cross-platform production control architectures, wherein each cross-platform production control architecture is pre-built based on the industrial Internet; A production control information acquisition module is used to preset a task allocation reference window, and based on the task allocation reference window, perform production log calls on the multiple product production lines to obtain multiple production control information; A collaborative control parameter set acquisition module: used for the multiple cross-platform production control architectures to perform online control collaborative optimization of the multiple product production lines according to the multiple product control information, and obtain multiple updated collaborative control parameter sets; A redistribution strategy acquisition module is used to pre-build a production task allocation model, input the plurality of production control information into the production task allocation model to perform production task allocation analysis, and obtain a production task redistribution strategy; A control parameter set execution module: used to use the task allocation reference window as an execution time constraint, the production task reallocation strategy as a task allocation constraint, and use the multiple updated collaborative control parameter sets to control the multiple product production lines to execute batch production of the conceptual design products; The production control architecture is configured according to the plurality of equipment configuration information to obtain a plurality of cross-platform production control architectures, wherein each cross-platform production control architecture is pre-built based on the industrial Internet, and the production control architecture acquisition module further includes the following execution steps: Interactively obtaining first equipment configuration information of a first product production line of the conceptual design product, wherein the first equipment configuration information includes a plurality of production and processing equipment; Pre-build multiple equipment control edge platforms, and connect the multiple production and processing equipment and the multiple equipment control edge platforms based on the industrial Internet; Pre-building a first cross-platform production control cloud, wherein the first cross-platform production control cloud includes a cascaded production defect identifier and a production equipment optimizer; Communicating and connecting the first cross-platform production control cloud and the plurality of device control edge platforms to obtain a first cross-platform production control architecture; Similarly, the production control architecture is configured according to the plurality of equipment configuration information to obtain the plurality of cross-platform production control architectures; The system further comprises the following execution steps: Interactively obtaining multiple groups of sample processing defect images of the multiple production and processing equipment; Presetting defect feature parameter labels, and identifying the plurality of groups of sample processing defect images based on the defect feature parameter labels, to obtain a plurality of groups of sample defect identification images; Constructing a plurality of defect identification marking branches for the plurality of production and processing equipment based on the plurality of groups of sample processing defect images and the plurality of groups of sample defect identification image mappings; connecting the plurality of defect identification mark branches in parallel to generate the production defect identifier; The system further comprises the following execution steps: Preset standard defect characteristic parameters, standard parameter adjustment step length, and standard parameter adjustment frequency, and construct a collaborative optimization parameter adjustment layer based on the standard defect characteristic parameters, standard parameter adjustment step length, and standard parameter adjustment frequency; Interactively obtaining multiple groups of sample control parameters and multiple sample production characteristic images, wherein each group of sample control parameters includes multiple sample control parameters of the multiple production and processing equipment; Training and producing collaborative optimization fitting layers according to the multiple groups of sample control parameters and multiple sample production feature images; Presetting qualified defect constraints, and synchronizing the qualified defect constraints to the collaborative optimization fitting layer; The collaborative optimization parameter adjustment layer and the collaborative optimization fitting layer are cascaded to generate the production equipment optimizer.

2. The cross-platform data collaborative optimization system based on the industrial Internet as claimed in claim 1, characterized in that: The production control information of each product includes production energy consumption, production efficiency parameters, production defect rate and defect image set.

3. The cross-platform data collaborative optimization system based on the industrial Internet as claimed in claim 2, characterized in that: The multiple cross-platform production control architectures perform online control collaborative optimization of the multiple product production lines according to the multiple production control information to obtain multiple updated collaborative control parameter sets, and the collaborative control parameter set acquisition module further includes the following execution steps: Obtaining a first product image set of the first product production line from the plurality of product control information; Inputting the first set of product images into the first cross-platform production control cloud in the first cross-platform production control architecture; Execute equipment positioning via the production defect identifier of the first cross-platform production control cloud to obtain deviation equipment and deviation defect feature parameters; Interactively obtain a deviation operation parameter set of the deviation equipment, and the production equipment optimizer of the first cross-platform production control cloud performs online control collaborative optimization according to the deviation operation parameter set and the deviation defect characteristic parameter to obtain a first updated collaborative control parameter set; By analogy, the multiple cross-platform production control architectures perform online control collaborative optimization of the multiple product production lines according to the multiple product control information to obtain the multiple updated collaborative control parameter sets.

4. The cross-platform data collaborative optimization system based on the industrial Internet as claimed in claim 3 is characterized in that: The deviation operation parameter set of the deviation equipment is interactively obtained, and the production equipment optimizer of the first cross-platform production control cloud performs online control collaborative optimization according to the deviation operation parameter set and the deviation defect characteristic parameter to obtain a first updated collaborative control parameter set. The system also includes the following execution steps: Obtaining a deviation coefficient of the deviation defect feature parameter and the standard defect feature parameter based on Euclidean distance calculation, and updating the standard parameter adjustment step and the standard parameter adjustment frequency according to the deviation coefficient to obtain an updated parameter adjustment step and an updated parameter adjustment frequency; In the collaborative optimization parameter adjustment layer, the deviation operating parameter set is adjusted with the update parameter adjustment step size and the update parameter adjustment frequency as constraints to obtain multiple update operating parameter sets; Inputting the multiple updated operation parameter sets into the collaborative optimization fitting layer to obtain multiple updated production feature images, wherein the multiple updated production feature image maps have multiple updated defect feature parameter identifiers; Traversing the plurality of updated defect feature parameters, and screening to obtain K updated defect feature parameters that fall within the qualified defect constraints; The K updated defect feature parameters and K defect similarity coefficients of the qualified defect constraints are calculated, and the first updated collaborative control parameter set is obtained by mapping and calling the multiple updated operating parameter sets based on extreme values ​​of the K defect similarity coefficients.

5. The cross-platform data collaborative optimization system based on the industrial Internet as claimed in claim 2, characterized in that: A production task allocation model is pre-built, and the plurality of production control information is input into the production task allocation model to perform production task allocation analysis, and obtain a production task reallocation strategy. The reallocation strategy acquisition module further includes the following execution steps: The production task allocation model includes a production reliability evaluation layer and a production task allocation layer; Introducing a production reliability evaluation function in the production reliability evaluation layer to evaluate the plurality of production control information to obtain a plurality of production reliability coefficients; Interactively obtain real-time production tasks, and synchronize the multiple production reliability coefficients and the real-time production tasks to the production task allocation layer to perform production task weight allocation, and obtain the production task reallocation strategy.

6. The cross-platform data collaborative optimization system based on the industrial Internet as claimed in claim 5, characterized in that: The production reliability evaluation function is as follows: Among them, R is the production reliability coefficient, E is the production energy consumption, P is the production efficiency parameter, D is the production defective rate, k and n are the first weight parameter group of the production defective rate, m is the second weight parameter of the production defective rate, and k+n+m=1.

Images