A production line management control method, device, equipment, medium and product

Abstract

The application discloses a production line management control method, device, equipment, medium and product. The method comprises the following steps: if a product production request is received, matching is performed in a local information base according to industrial production requirements to obtain a matching result; in the case that the matching result is that there is no associated production record in the local information base, a target production line scheme is determined based on a combination of a preset large model and a small model; a simulation environment corresponding to the industrial production requirement is constructed in combination with a preset simulation tool according to the target production line scheme, and the simulation operation of the target production line scheme is performed, the optimal model parameters are determined iteratively according to the simulation operation result, and the management control of the actual production line is performed according to the optimal model parameters. The application can perform simulation iteration based on the industrial production requirement, realize self-supervised optimal production process design and model parameter determination, thereby performing automatic management control of actual industrial production, improving the production efficiency of the production line and reducing the production failure rate.

Description

Technical Field

[0001] This invention relates to the fields of artificial intelligence and industrial internet technology, and in particular to a production line management and control method, device, equipment, medium and product. Background Technology

[0002] The Industrial Internet is driving the digital transformation of the manufacturing industry and enhancing its competitiveness. Currently, the Industrial Internet has entered a new stage of large-scale development. In this process, the production line, as the core link in industrial manufacturing, is crucial for its intelligent and efficient operation. However, with the expansion of production scale and the increase in product complexity, traditional production line control models are increasingly revealing many drawbacks, such as rigid resource allocation, slow response, and poor coordination, making it difficult to meet the urgent needs of modern industry for high-precision and highly flexible production.

[0003] Therefore, how to achieve self-supervised optimal production process design and model parameter determination, so as to carry out automated management and control of actual industrial production, improve the efficiency of production line production, and reduce the production failure rate, is an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a production line management and control method, device, equipment, medium, and product to automate management and control based on industrial production needs, thereby improving production line efficiency and reducing production failure rate.

[0005] According to one aspect of the present invention, a production line management and control method is provided, comprising:

[0006] If a product manufacturing request is received, the system will match the product with the local database based on industrial production needs to obtain the matching result.

[0007] If the matching result is no related production record in the local information database, the target production line plan is determined based on a combination of preset large and small models.

[0008] Based on the target production line plan, a simulation environment corresponding to the industrial production requirements is constructed using preset simulation tools. The target production line plan is then simulated and run. Based on the simulation results, the optimal model parameters are iteratively determined, and the actual production line is managed and controlled based on these optimal model parameters.

[0009] According to another aspect of the present invention, a production line management and control device is provided, comprising:

[0010] The matching module is used to match the product production request with the local database based on the industrial production requirements and obtain the matching result.

[0011] The determination module is used to determine the target production line scheme based on a combination of preset large and small models when the matching result is no related production record in the local information database.

[0012] The simulation module is used to construct a simulation environment corresponding to the industrial production requirements based on the target production line plan and in conjunction with preset simulation tools, and to simulate the operation of the target production line plan. Based on the simulation results, the optimal model parameters are iteratively determined, so as to manage and control the actual production line according to the optimal model parameters.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the production line management and control method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the production line management and control method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer program product is also provided, which includes a computer program that, when executed by a processor, implements the production line management and control method of any embodiment of the present invention.

[0019] The technical solution of this invention, upon receiving a product production request, matches the data in a local database based on industrial production needs to obtain a matching result. If the matching result indicates no related production record in the local database, a target production line scheme is determined based on a combination of preset large and small models. Based on the target production line scheme, a simulation environment corresponding to the industrial production needs is constructed using preset simulation tools, and the target production line scheme is simulated. Based on the simulation results, the optimal model parameters are iteratively determined. Finally, based on the optimal model parameters, the actual production line is managed and controlled. This allows for iterative simulation based on industrial production needs, achieving self-supervised optimal production process design and model parameter determination, thereby enabling automated management and control of actual industrial production, improving production line efficiency, and reducing production failure rates.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart of a production line management and control method provided in an embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of a production line management and control system provided in an embodiment of the present invention;

[0024] Figure 3 This is a structural block diagram of a production line management and control device provided in an embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," "target," "candidate," "alternative," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the invention described herein can be practiced in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus. The acquisition, storage, use, and processing of data in the technical solutions of this application comply with relevant laws and regulations.

[0028] Example 1

[0029] Figure 1 This is a flowchart of a production line management and control method provided in an embodiment of the present invention. This embodiment is applicable to situations where the management and control system utilizes large and small models to perform automated management and control based on industrial production needs. This method can be executed by a production line management and control device, which can be implemented in hardware and / or software. This production line management and control device can be configured in electronic devices, such as electronic devices equipped with a production line management and control system. Figure 1 As shown, the production line management and control method includes:

[0030] S101. If a product production request is received, the system will match the product with the local database based on industrial production needs to obtain the matching result.

[0031] A product production request is a request to simulate the production line of an industrial order to determine the optimal production process design and model parameters for actual production control. The product production request includes industrial production requirements. These requirements include at least one of the following: product type, quantity, and specifications. Specifications may include, for example, model number, customized accessories, color, and size. The local database stores historical products produced in simulation or actual production, along with their corresponding historical production lines. Matching results can be determined by whether a historical production line corresponding to the industrial product requirement exists in the local database.

[0032] Optionally, the production line management and control system can use the information receiving module to obtain multimodal industrial production needs from external systems such as cloud platforms, artificial intelligence applications, and intelligent management platforms. It can also consider that a production line management and control request has been detected when an industrial order issued by relevant personnel is detected.

[0033] Optionally, based on industrial production needs, a matching process is performed in the local information database to obtain matching results. This includes: filtering historical production products recorded in the local information database according to the product types required in the industrial production needs to obtain historical production line information for historical production products that match the product types required; and matching the historical production line information for each historical production product according to the product information required to determine whether there are historical production lines in the local information database that correspond to the industrial product needs, thereby obtaining matching results.

[0034] Optionally, after acquiring the industrial product demand, the control module of the production line management and control system can search for similar production records in the local information database according to the type of demanded products, that is, determine the historical production line information. It can further determine the similarity between the demanded product information and the historical production product information in the historical production line information. If there are historical production products with similarity that meet the threshold, such as when the similarity is greater than the preset similarity threshold, the historical plan of the historical production line can be adjusted according to the industrial production demand to obtain the subsequent target production line plan.

[0035] It should be noted that the production line should consist of multiple process links, core equipment, network equipment and computing power equipment, and the relevant distribution and connection information should be stored in a local database to form a historical production line.

[0036] For example, in a refrigerator production simulation scenario, the historical production line can include: production line 1, product 2, and production line 3. Production line 1 mainly produces single-door refrigerators, production line 2 mainly produces double-door refrigerators, and production line 3 can produce both types of refrigerators. Correspondingly, if there are associated production records in the local database, the most similar one can be matched from the historical production line, and then the relevant equipment and parameters can be adjusted according to the industrial product requirements to determine the target production line scheme.

[0037] Optionally, if the similarity between the demand product information corresponding to the industrial production demand and the historical production product information in the historical production line information is less than the preset similarity threshold, it is considered that the customization of the industrial production demand is large, that is, the matching result is that there is no related production record in the local information database. At this time, an available production line can be selected according to the product type, and then the target production line scheme can be determined based on the combination of the preset large model and small model.

[0038] S102. If the matching result is that there are no related production records in the local information database, determine the target production line scheme based on a combination of preset large and small models.

[0039] The system comprises two modules: a pre-defined large model for handling complex reasoning tasks, providing global decision support, and generating dynamic scheduling of production tasks and optimized resource allocation schemes—essentially using artificial intelligence to generate preliminary production line plans. The core function of the small model module group is to utilize machine learning models to execute lightweight, domain-specific tasks, improving response efficiency. Specifically, the small models are used to provide configuration parameters for each production stage in the production line script using machine learning models. The combination of the pre-defined large model and the small models means that the pre-defined large model is first used to determine the initial production line script, and then the small models are used at each production stage to determine the configuration parameters, thereby generating the target production line plan.

[0040] The target production line solution includes at least one production stage, and each production stage corresponds to a stage script optimized through a small model. Each production stage may include at least one piece of equipment. For example, the production stage may include loading, processing, quality inspection, unloading, and conveying. The loading, processing, quality inspection, and unloading stages may involve different types of processing equipment and part positioning sensors, while the conveying stage may involve conveyor belts, part positioning sensors, and gripping robotic arms, etc.

[0041] Optionally, the target production line scheme can be determined by combining a pre-set large model and a small model, including: processing industrial production needs based on the pre-set large model to generate a preliminary production line scheme; calling the pre-set small model for processing based on the production equipment, equipment type and production activity information involved in each production step in the preliminary production line scheme to obtain production configuration and parameter information; and adjusting the preliminary production line scheme based on the production configuration and parameter information to determine the target production line scheme.

[0042] The preliminary production line plan refers to the plan generated by the pre-set large model based on the needs of industrial production. The preliminary production line plan may include at least one production step in the production process, as well as the requirements of each production step, and indicate the main production process steps and error and exception handling methods.

[0043] Optionally, the control module in the production line management and control system can parse the initial production line plan into multiple processing step requirements of the available production line, and for each processing step, match the corresponding industrial small model of the equipment to process the processing step requirements, obtain configuration parameters, and finally summarize to obtain an executable production plan, that is, determine the target production line plan.

[0044] Optionally, the preset large-scale model in this invention is an industrial large-scale model, which generates a preliminary production line plan that is refined to a detailed plan for each production link. The production equipment matches the production line, and the equipment configuration requirements correspond to a clear operation sequence and its preliminary parameters. Based on the core equipment of different processes, corresponding small models are selected for parameter prediction, so that the generated production parameters cover the preliminary parameters, thus obtaining the target production line plan.

[0045] Optionally, after determining each production step in the initial production line plan, the optimal small model can be dynamically matched according to the task complexity and equipment type, and multiple small models can be called in parallel through the collaborative interface.

[0046] Optionally, the small model corresponding to the abnormal production process can generate improved production line script parameters based on the abnormal data and pass them to the simulation module to re-simulate the production process.

[0047] S103. Based on the target production line plan, construct a simulation environment corresponding to the industrial production requirements using preset simulation tools, and simulate the operation of the target production line plan. Based on the simulation results, iteratively determine the optimal model parameters, and manage and control the actual production line according to the optimal model parameters.

[0048] The preset simulation tools can include preset production logistics simulation tools, network simulators, and edge computing simulation toolkits. Preset production logistics simulation tools are used to build geometric / behavioral models of production equipment and simulate production processes and cycle times; examples include Plant-Simulation (digital factory simulation), DELMIA (interactive manufacturing application software for digital enterprises), and AUTOMOD (3D discrete event simulation tool). Network simulators are used to simulate network topology, latency / packet loss rate, and protocol interactions; examples include NS-3 (discrete event network simulator), OMNeT++ (object-oriented modular network simulation platform), and OPNET (Optimized Network Engineering Tool). Edge computing simulation toolkits are used to simulate edge device hardware (CPU / memory), task scheduling, and load; examples include EdgeSimPy (edge ​​computing resource management strategy modeling and simulation framework), EdgeCloudSim (a Java-based simulation framework), and OpenStack (open cloud operating system).

[0049] Optionally, based on the simulation environment, the production process can be simulated and the decision results can be predicted. The production control schemes generated by the preset large model and small model can be verified to obtain the expected execution results of the production line, thereby obtaining the optimal production process design and optimal model parameters.

[0050] Optionally, based on the target production line scheme, a simulation environment corresponding to the industrial production requirements is constructed using preset simulation tools. This includes: based on the target production line scheme and using preset simulation tools, constructing production equipment models, network models, and edge computing models respectively; and performing collaborative simulation integration of the production equipment models, network models, and edge computing models involved in the target production line scheme based on the distribution relationship between production equipment, network equipment, and edge computing equipment in the target production line scheme, so as to construct a simulation environment corresponding to the industrial production requirements.

[0051] The primary purpose of coordinated simulation integration is to achieve data synchronization across multiple tools (such as device status, network, and edge computing), which can be implemented using tools like HLA (High Level Architecture) and Docker. Distribution relationships can include information such as device spacing, connectivity, and network interconnection methods. Equipment information for production equipment can include device type and model; for example, device type could be processing equipment or conveying equipment.

[0052] Optionally, the simulation module in the production line management and control system can be used to establish a simulation environment, including equipment, network, and applications, for the target production line scheme generated by the control module. Within the simulation environment, the correctness of the production scheme can be verified using various loads, such as no-load tests, small-batch tests, and large-batch tests. The main function of the simulation module is to construct a virtual production line, simulating multiple production devices and their industrial programs, simulating the production process, and predicting the execution results.

[0053] Optionally, based on the target production line scheme and using preset simulation tools, a production equipment model, a network model, and an edge computing model are constructed respectively, including: based on a preset production logistics simulation tool, constructing a 3D model of the equipment and defining the physical attributes of the 3D model of the equipment according to the equipment information of the production equipment in the target production line scheme; based on a preset network simulator, constructing a network model and configuring the link parameters of the network model according to the network topology information in the target production line scheme; and based on a preset edge computing simulation toolkit, constructing an edge computing model according to the parameters of the edge devices in the target production line scheme and configuring the preprocessing, early warning, and control functions of the edge computing model.

[0054] The 3D model of the equipment can recreate the equipment's dimensions and moving parts (such as robotic arm joints and conveyor belt rollers). This 3D model can be imported from pre-defined 3D CAD (Computer-Aided Design) software or product model data exchange standard files. The physical attributes of the 3D model can include the machine tool's machining range (X-axis distance, Y-axis distance, Z-axis distance), AGV (Autonomous Guided Vehicle) acceleration, sensor detection range (visual camera field of view), fixture types, and more.

[0055] Optionally, the distribution of production equipment, network equipment, and edge computing equipment can be completed based on the layout of all equipment on the production line and the workshop space, so as to truly reflect the production line configuration such as equipment spacing, connection relationship, and network interconnection method, and realize the simulation of the spatial distribution of the production line.

[0056] Optionally, a 3D model of the equipment can be constructed based on the behavior and logic of different production equipment. For processing equipment, a production process script can be used to simulate the entire process of "feeding, processing, quality inspection, and unloading". Parameters such as processing time (e.g., 30 seconds for a lathe to process one part) and failure probability (e.g., one failure per day, 20 minutes of maintenance time) can be set in the script.

[0057] Optionally, for conveying equipment, such as autonomous navigation transport vehicles, it is necessary to simulate "path planning logic" (such as obstacle avoidance and priority scheduling), and for conveyor belts, it is necessary to associate the cycle time of upstream and downstream equipment (such as the conveyor belt starting to transport materials after the preceding machine tool unloads the material).

[0058] Optionally, for the simulation of the control logic of production equipment, a PLC (Programmable Logic Controller) simulation module, such as the S7-1200 interface of Plant Simulation, can be used to simulate the closed-loop control of "sensor triggering, PLC logic judgment, and equipment action" (such as part arrival sensor triggering, robotic arm grasping).

[0059] Optionally, the network topology of the target production line scheme in the physical workshop can be built in the network simulator to restore the topology. Specifically, core switches, edge switches, autonomous navigation transport vehicles / cameras and other terminal nodes can be placed, the network protocol address range of the devices can be set, and the network link bandwidth of 1Gbps and latency of 1ms, the data network link bandwidth of 100Mbps and latency of 5ms can be controlled to simulate the signal attenuation caused by workshop wall obstruction (packet loss rate of 0.5%), that is, to configure the link parameters.

[0060] Optionally, protocol and data flow simulation can be performed based on the network model. Specifically, the OPCUA (Open Platform Communications Unified Architecture) protocol can be configured between the PLC and the edge gateway, and the RTSP (Real-Time Streaming Protocol) protocol can be configured between the vision camera and the edge server to deploy an industrial protocol stack. For data flow simulation, two typical data flows can be generated. The first is a control flow, such as from the PLC or machine tool, 100 bytes / frame, sent at a frequency of 10Hz. The second is a data flow, such as from the camera or edge, 4MB / frame, sent at a frequency of 1Hz, and the network QoS (Quality of Service) can be verified to ensure it meets the requirements.

[0061] Optionally, hardware resource modeling can be performed based on edge device parameters to construct an edge computing model. The edge device parameters may include edge gateway (2 CPU cores, 4GB memory, 64GB storage), edge server (8 CPU cores, 32GB memory, 512GB storage), and resource usage thresholds (such as triggering load balancing when CPU utilization is >80%).

[0062] Optionally, different edge applications can be deployed in the edge computing model for data preprocessing (filtering sensor outliers, processing latency ≤20ms), fault early warning (predicting faults using long short-term memory networks based on equipment vibration data, processing latency ≤50ms), and real-time control (adjusting AGV speed, response latency ≤30ms).

[0063] Optionally, an edge computing model can be used to simulate task scheduling and set task priorities (control tasks > early warning tasks > statistics tasks). When the edge server is overloaded, non-real-time tasks (such as production report statistics) can be migrated to idle edge gateways.

[0064] Optionally, the target production line scheme is simulated. Based on the simulation results, the optimal model parameters are iteratively determined. The actual production line is then managed and controlled based on these optimal model parameters. This includes: simulating the control process of each production device in the target production line scheme, simulating the data flow between network devices, and simulating task scheduling between edge computing devices in the simulation environment to simulate the production process of the target production line scheme; analyzing the production line status of the target production line scheme based on the simulation data to optimize and adjust the production line script, preset large model, and small model, and iteratively determining the optimal model parameters; and finally, managing and controlling the actual production line based on the optimal model parameters.

[0065] Optionally, during the simulation operation, a monitoring module can be used to monitor abnormal events in the simulation module, review and evaluate industrial codes, equipment configurations and execution results, monitor system status in real time, evaluate performance and trigger optimization, identify production equipment parameters and results after each round of simulation, identify anomalies based on a specific classifier, adjust industrial codes and equipment configurations based on evaluation results, and after the equipment execution sequence, equipment operation and operation parameters of the entire production control scheme are correct, it is determined that the entire production process has been successfully completed in the simulation module, and the industrial codes and equipment configurations associated with the target production line scheme are sent to the corresponding equipment for actual production management and control.

[0066] For example, the steps for the simulation module to implement virtual operation of the production line can be as follows:

[0067] 1) Initialize virtual production equipment, network equipment, and edge computing facilities: Initialize the software for each production device, network device, and edge computing facility in the production line to ensure software version compatibility and applicability to the current production line scripts. This can be achieved by storing software and hardware compatibility relationships in the cloud and performing version compatibility verification on the cloud side.

[0068] 2) Single-machine simulated production line script configuration: The production line script is broken down into the configuration of each device. It is checked whether each virtual device can run its own code normally, whether the parameter settings of the device meet the software requirements, and the simulation results are fed back to the supervision module.

[0069] This includes pre-training specialized mini-models, such as a PLC mini-model trained according to the PLC code, which will generate parameters that conform to the PLC. Dedicated mini-models can be configured for commonly used equipment in industrial scenarios, and finally shared and used through the model cloud ecosystem.

[0070] 3) Virtual Production Line Online Simulation: Run the entire production line script to verify the coordination and cooperation between various parts of the virtual production line, ensuring smooth and error-free transmission, conveying, and assembly actions between various devices, and feeding the simulation results back to the monitoring module. Test the connection and linkage between virtual devices, such as the conveying of virtual materials between virtual devices, ensuring that materials can smoothly move from one device to the next, and that the connections between devices are accurate and error-free. Verify whether the signal transmission between devices is timely and effective, and whether the control system can accurately control and adjust according to the operating status of the equipment.

[0071] Optionally, by identifying monitoring information, transmission conditions such as excessive time delay, spatial mismatch, excessively large parameters, and excessively small parameters can be identified.

[0072] 4) Monitor the real-time simulation results of the process: Monitor and debug each process in the production line in real time, and feed back the simulation results to the supervision module.

[0073] 5) Simulated production load: After the simulated production is successful, the production quantity is increased on the virtual production line to verify the stability and reliability of the production line, and the simulation results are fed back to the monitoring module.

[0074] 6) Simulation Process and Result Supervision and Analysis: After receiving the real-time simulation data generated in the above steps, the supervision module judges the production line status based on industry knowledge or a classifier. If the production line script is correct, the relevant configurations or codes are sent to the physical equipment. If there are errors in the relevant process and script parameters, the model tuning module processes them to obtain more suitable parameter values ​​and updates them to the production line script. If errors in the production line script cause simulation process abnormalities, the results are fed back to the control module and the large industrial model for first optimizing the large model and then regenerating the production line script.

[0075] 7) Industrial Large and Small Model Optimization: Based on the process data and simulation results of the simulated production, various aspects of the virtual production line are analyzed and evaluated to further optimize the commands, parameters, processes, and equipment of the production line script. Automated hyperparameter search is achieved based on a preset framework.

[0076] Optionally, if the simulation runs normally, there is no need to optimize the large and small models. If there is a coordination anomaly, the large model needs to be analyzed and the overall plan adjusted. If there is a equipment failure, the production equipment model needs to be adjusted. If there is a network failure, the network model needs to be adjusted. If there is insufficient computing power, the large model needs to be analyzed and the computing power allocation adjusted. If there is a performance anomaly, the corresponding small model needs to be handled.

[0077] The technical solution of this invention, upon receiving a product production request, matches the data in a local database based on industrial production needs to obtain a matching result. If the matching result indicates no associated production record in the local database, a target production line scheme is determined based on a combination of preset large and small models. Based on the target production line scheme, a simulation environment corresponding to the industrial production needs is constructed using preset simulation tools, and the target production line scheme is simulated. Based on the simulation results, the optimal model parameters are iteratively determined, and the actual production line is managed and controlled according to these optimal parameters. This allows for iterative simulation based on industrial production needs, achieving self-supervised optimal production process design and model parameter determination, thereby enabling automated management and control of actual industrial production, improving production line efficiency, and reducing production failure rates.

[0078] Preferably, in the field of smart home appliances, the production line management and control request can be a simulated production demand for a specific model of refrigerator. Specific tags include model, color, accessories, and optional functions. Parameters include adjustable data such as the quantity and size of accessories. Using a large model, available production lines can be selected based on product demand. Combining this with the latest spatiotemporal information, production lines capable of producing this type of product with relatively low workloads can be identified. Then, a production script is generated based on the number of processes in the production line structure. The production script includes time information and specific production content. The time information specifies the production start time to prevent new tasks from interfering with other production tasks.

[0079] For example, a preliminary production line scheme for manufacturing refrigerators may include the following production stages: component pretreatment, cabinet forming, refrigeration system assembly, electrical system integration, whole machine testing, and packaging. The production equipment involved in the component pretreatment stage may be a high-pressure washer, a drying oven, and a rust removal and grinding machine. The production steps involved in the component pretreatment stage may be component cleaning and component drying. The production activity information involved in the component pretreatment stage may be a cleaning pressure of 0.3-0.5 MPa and a drying temperature of 80-100℃.

[0080] Example 2

[0081] Figure 2 This is a schematic diagram of a production line management and control system provided in an embodiment of the present invention. Based on the above embodiments, this embodiment provides a preferred example of how the various modules in the production line management and control system interact to achieve automated management and control of industrial production needs.

[0082] like Figure 2 As shown, the production line management and control system includes: an information receiving module, a simulation module, a control module, an event module, a monitoring module, a large model module, a small model module group, a model optimization module, a local information database, and a control information distribution module.

[0083] Optionally, the information receiving module is used to acquire multimodal input information or obtain industrial orders from the management platform of artificial intelligence applications or intelligent agents; the simulation module may include equipment simulation, topology simulation, and link simulation. The control information dissemination module is used to interact with the managed equipment and transmit the target production line plan.

[0084] Optionally, the information receiving module may include multiple input sources such as natural language descriptions, structured parameter tables, sensor data streams, and image information, and can automatically identify the demand intent and production goals through the semantic parsing module.

[0085] Optionally, the core function of the control module is to dynamically schedule production tasks and optimize resource allocation. Based on intelligent algorithms such as genetic algorithms and simulated annealing algorithms, it completes the scheduling of all processes on the entire production line. The core function of the large model module is to handle complex reasoning tasks, provide global decision support, and generate schemes for dynamically scheduling production tasks and optimizing resource allocation, i.e., the initial production line script. The core function of the small model module group is to use machine learning models to provide the parameters configured for each step in the production line script.

[0086] Optionally, the control module can determine whether to generate a new production control scheme based on the matching of the local information database, thus determining the final generated control scheme. Specifically, if the local information database contains historical production records for the product, it triggers a "macro-micro" dual-model collaborative process, calling the algorithm in the small model module group to adjust the parameters of the existing scheme, and automatically fine-tuning the execution strategy based on the current equipment operating status and process cycle time. Then, the production line script is transmitted to the production equipment through the control information distribution module. If the local information database does not contain historical production records for the product, the control module calls the industry large model and the dedicated small model sequentially to generate the production line script. The simulation module is used to build a simulation verification environment, simulating the spatial layout of the production line, equipment hardware and software, network type and connection relationships. The environment parameters are dynamically adjusted based on simulation feedback to keep the simulation state consistent with the actual production constraints, thereby obtaining predictive operating results. During the timer cycle, the simulation module executes the production line script generated by the large and small models on the virtual production line, forming a spatiotemporally consistent predictive environment for the production line, and simulating the product production process.

[0087] The core function of the simulation module is to construct a virtual production line, simulating multiple production devices and their industrial programs, simulating the production process, and predicting the execution results. During the timer cycle, the simulation module executes the production line script generated by the large and small models on the virtual production line, forming a spatiotemporally consistent prediction environment for the production line, and simulating the product production process.

[0088] The performance indicators, abnormal events, and equipment response data during the simulation process will be captured in real time by the event module and summarized to the supervision module.

[0089] The core function of the event module is to monitor abnormal events in the simulation module. The core function of the monitoring module is to analyze faults, anomalies, or problems in the events, evaluate the performance of the current simulation scheme, provide optimization suggestions, and trigger optimizations. For example, if parameters such as equipment current or shaft temperature are detected to be too high, the module compares them with rules to identify the cause.

[0090] The core function of the model tuning module is to continuously optimize model parameters and improve prediction accuracy. The core function of the local database is to store localized data, supporting fast access and privacy protection. For example, storing sensitive data such as device status and work orders on edge devices. The core function of the information receiving module is to collect and preprocess external data. For example, acquiring physical signals such as temperature and pressure through multimodal sensors, or receiving user text / voice commands. The core function of the control information dissemination module is to send decision commands to actuators to achieve closed-loop control. For example, controlling the insertion depth and speed of the dummy bar in a continuous casting machine system.

[0091] It should be noted that as production lines become increasingly intelligent, various production equipment, edge computing devices, cloud services, and network devices require coordinated control. Previously, intelligent agent-related work focused on auxiliary management, requiring manual intervention for joint debugging and final parameter determination, with a high degree of professional involvement. This invention addresses the real-time, close collaborative relationships in industrial production processes by constructing an intelligent agent production line simulation module. This module provides unified simulation and supervision of different equipment and their collaborative processes, ultimately forming an intelligent management, operation, and dynamic optimization solution. It can fill the gap in the modulation work between large-scale production schemes and execution code, gradually replacing manual debugging and error correction.

[0092] Preferably, the production line management and control system may further include a task perception and computing network collaborative scheduling module. This module is used to allocate tasks and coordinate resources among different computing nodes, network links, and production equipment, ensuring the real-time performance and execution consistency of the production control scheme. The task perception and computing network collaborative scheduling module may include: a task perception unit, a scheduling decision unit, and a collaborative control unit. The task perception unit monitors the execution progress, equipment load, and network communication status of each stage of the production line, forming a quantifiable resource status matrix. The scheduling decision unit, based on the task priorities, execution order, and data dependencies generated by the large model, performs task mapping and path planning for each computing node (cloud, edge, terminal), ensuring that critical tasks are executed first. When the collaborative control unit detects network congestion, computing power occupancy, or equipment timing conflicts, it can automatically adjust the task allocation ratio and communication channels to maintain the timing consistency and transmission reliability of control commands.

[0093] Optionally, the task awareness and computing network collaborative scheduling module has network link prediction and computing power assessment functions. It can predict communication latency and processing load before task execution and dynamically adjust scheduling parameters. The scheduling results are summarized by the control module to form an integrated execution plan for "control-network-computing" and fed back to the simulation module for verification and the monitoring module for performance checking. By introducing the task awareness and computing network collaborative scheduling module, task-level resource collaboration and dynamic scheduling can be realized in complex computing network environments, improving the execution accuracy and system stability of production control schemes under multi-device and multi-network conditions.

[0094] Example 3

[0095] Figure 3 This is a structural block diagram of a production line management and control device provided in an embodiment of the present invention. This embodiment is applicable to situations where the management and control system utilizes large and small models to perform automated management and control based on industrial production needs. The production line management and control device provided by the present invention can execute the production line management and control method provided in any embodiment of the present invention, possessing the corresponding functional modules and beneficial effects of the execution method. This production line management and control device can be implemented in hardware and / or software and configured in an electronic device with production line management and control functions, such as... Figure 3 As shown, the production line management and control device may specifically include:

[0096] The matching module 301 is used to match the product production request in the local database according to the industrial production requirements and obtain the matching result.

[0097] The determination module 302 is used to determine the target production line scheme based on a combination of preset large and small models when the matching result is no related production record in the local information database.

[0098] The simulation module 303 is used to construct a simulation environment corresponding to the industrial production requirements based on the target production line scheme and in conjunction with preset simulation tools, and to simulate the operation of the target production line scheme. Based on the simulation results, the optimal model parameters are iteratively determined so as to manage and control the actual production line according to the optimal model parameters.

[0099] The technical solution of this invention, upon receiving a product production request, matches the data in a local database based on industrial production needs to obtain a matching result. If the matching result indicates no associated production record in the local database, a target production line scheme is determined based on a combination of preset large and small models. Based on the target production line scheme, a simulation environment corresponding to the industrial production needs is constructed using preset simulation tools, and the target production line scheme is simulated. Based on the simulation results, optimal model parameters are iteratively determined, and the actual production line is managed and controlled according to these optimal parameters. This invention can perform simulation iterations based on industrial production needs, achieving self-supervised optimal production process design and model parameter determination, thereby enabling automated management and control of actual industrial production, improving production line efficiency, and reducing production failure rates.

[0100] Furthermore, the matching module 301 is specifically used for:

[0101] Based on the product types required in industrial production, the historical production products recorded in the local database are filtered to obtain historical production line information for historical production products that match the product types required.

[0102] Based on the demand product information, the historical production line information of each historically produced product is matched to determine whether there is a historical production line in the local information database that corresponds to the industrial product demand, and the matching result is obtained.

[0103] Furthermore, module 302 is specifically used for:

[0104] The industrial production demand is processed based on a pre-set large model to generate a preliminary production line plan; the preliminary production line plan includes at least one production step in the production process.

[0105] Based on the production equipment, equipment type and production activity information involved in each production step in the preliminary production line plan, the preset small model is called for processing to obtain production configuration and parameter information.

[0106] The initial production line plan is adjusted based on production configuration and parameter information to determine the target production line plan.

[0107] Furthermore, the simulation module 303 is specifically used for:

[0108] Based on the target production line plan, and using pre-set simulation tools, production equipment models, network models, and edge computing models are constructed respectively.

[0109] Based on the distribution relationship between production equipment, network equipment and edge computing equipment in the target production line scheme, the production equipment model, network model and edge computing model involved in the target production line scheme are integrated through collaborative simulation to construct a simulation environment corresponding to industrial production needs.

[0110] Furthermore, the simulation module 303 is also used for:

[0111] Based on the preset production logistics simulation tool, and according to the equipment information of the production equipment in the target production line plan, a three-dimensional model of the equipment is constructed and the physical properties of the three-dimensional model of the equipment are defined.

[0112] Based on a preset network simulator, a network model is constructed and the link parameters of the network model are configured according to the network topology information in the target production line plan.

[0113] Based on a pre-set edge computing simulation toolkit, an edge computing model is constructed according to the parameters of the edge devices in the target production line scheme, and the preprocessing, early warning and control functions of the edge computing model are configured.

[0114] Furthermore, the simulation module 303 is also used for:

[0115] The simulation environment simulates the control process of each production equipment in the target production line scheme, the data flow between network devices, and the task scheduling between edge computing devices, so as to realize the simulation of the production process of the target production line scheme.

[0116] Based on simulation data, the production line status of the target production line scheme is analyzed to obtain management and control results. This allows for the optimization and adjustment of production line scripts, preset large models, and small models, and iterative determination of the optimal model parameters.

[0117] Based on the optimal model parameters, manage and control the actual production line.

[0118] Example 4

[0119] Figure 4 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0120] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.

[0121] Multiple components in electronic device 10 are connected to input / output 15, including: input unit 16, such as a keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as a disk, optical disk, etc.; and communication unit 19, such as a network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0122] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as production line management control methods.

[0123] In some embodiments, the production line management control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the production line management control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the production line management control method by any other suitable means (e.g., by means of firmware).

[0124] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), system-on-a-chip (SoCs), complex programmable logic devices (PLCs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0126] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (e.g., voice input, speech input, or tactile input).

[0128] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0129] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system to address the shortcomings of traditional physical hosts and virtual reality services, such as high management difficulty and weak business scalability.

[0130] In one embodiment, the present invention further includes a computer program product, which includes a computer program that, when executed by a processor, implements the production line management and control method of any embodiment of the present invention.

[0131] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including local area networks (LANs) or wide area networks (WANs), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0132] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0133] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A production line management and control method, characterized in that, include: If a product manufacturing request is received, the system will match the product with the local database based on industrial production needs to obtain the matching result. If the matching result is no related production record in the local information database, the target production line plan is determined based on a combination of preset large and small models. Based on the target production line plan, a simulation environment corresponding to the industrial production requirements is constructed using preset simulation tools, and the target production line plan is simulated and run. Based on the simulation results, the optimal model parameters are iteratively determined, and the actual production line is managed and controlled based on the optimal model parameters. The method of determining the target production line scheme based on a combination of a pre-set large model and a small model includes: processing industrial production needs based on the pre-set large model to generate a preliminary production line scheme; the preliminary production line scheme includes at least one production step; based on the production equipment, equipment type, and production activity information involved in each production step in the preliminary production line scheme, calling the pre-set small model for processing to obtain production configuration and parameter information; and adjusting the preliminary production line scheme based on the production configuration and parameter information to determine the target production line scheme. The process involves constructing a simulation environment corresponding to industrial production needs based on the target production line plan and pre-set simulation tools. This includes: constructing production equipment models, network models, and edge computing models based on the target production line plan and pre-set simulation tools; and performing collaborative simulation integration of the production equipment models, network models, and edge computing models involved in the target production line plan based on the distribution relationship between the production equipment, network equipment, and edge computing equipment in the target production line plan, so as to construct a simulation environment corresponding to industrial production needs. Based on the target production line plan and using pre-set simulation tools, production equipment models, network models, and edge computing models are constructed, including: Based on the preset production logistics simulation tool, and according to the equipment information of the production equipment in the target production line plan, a three-dimensional model of the equipment is constructed and the physical properties of the three-dimensional model of the equipment are defined. Based on a preset network simulator, a network model is constructed and the link parameters of the network model are configured according to the network topology information in the target production line plan. Based on a pre-set edge computing simulation toolkit, an edge computing model is constructed according to the parameters of the edge devices in the target production line scheme, and the preprocessing, early warning and control functions of the edge computing model are configured.

2. The method according to claim 1, characterized in that, Based on industrial production needs, a match is performed in the local database to obtain the matching results, including: Based on the product types required in industrial production, the historical production products recorded in the local database are filtered to obtain historical production line information for historical production products that match the product types required. Based on the demand product information, the historical production line information of each historically produced product is matched to determine whether there is a historical production line in the local information database that corresponds to the industrial product demand, and the matching result is obtained.

3. The method according to claim 1, characterized in that, The target production line scheme is simulated and run. Based on the simulation results, the optimal model parameters are iteratively determined. These optimal model parameters are then used for the management and control of the actual production line, including: The simulation environment simulates the control process of each production equipment in the target production line scheme, the data flow between network devices, and the task scheduling between edge computing devices, so as to realize the simulation of the production process of the target production line scheme. Based on simulation data, analyze the production line status of the target production line scheme to optimize and adjust the production line script, preset large model and small model, and iteratively determine the optimal model parameters; Based on the optimal model parameters, manage and control the actual production line.

4. A production line management and control device, characterized in that, include: The matching module is used to match the product production request with the local database based on the industrial production requirements and obtain the matching result. The determination module is used to determine the target production line scheme based on a combination of preset large and small models when the matching result is no related production record in the local information database. The simulation module is used to construct a simulation environment corresponding to the industrial production requirements based on the target production line plan and in combination with preset simulation tools, and to simulate the operation of the target production line plan. Based on the simulation results, the optimal model parameters are iteratively determined so as to manage and control the actual production line according to the optimal model parameters. Specifically, the determination module is used to: process industrial production demands based on a preset large model to generate a preliminary production line plan; the preliminary production line plan includes at least one production step in the production process; based on the production equipment, equipment type and production activity information involved in each production step in the preliminary production line plan, call the preset small model for processing to obtain production configuration and parameter information; adjust the preliminary production line plan based on the production configuration and parameter information to determine the target production line plan; Specifically, the simulation module is used to: construct production equipment models, network models, and edge computing models based on preset simulation tools according to the target production line plan; and perform collaborative simulation integration of the production equipment models, network models, and edge computing models involved in the target production line plan according to the distribution relationship between production equipment, network equipment, and edge computing equipment in the target production line plan, so as to construct a simulation environment corresponding to industrial production needs. The simulation module is also used for: constructing a 3D model of the equipment and defining its physical properties based on the equipment information of the production equipment in the target production line scheme, using a preset production logistics simulation tool; constructing a network model and configuring its link parameters based on the network topology information in the target production line scheme, using a preset network simulator; and constructing an edge computing model and configuring its preprocessing, early warning, and control functions based on the parameters of the edge devices in the target production line scheme, using a preset edge computing simulation toolkit.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor, which enables the at least one processor to perform the production line management and control method according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the production line management and control method according to any one of claims 1-3.

7. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the production line management and control method according to any one of claims 1-3.

Images