Digital twin factory construction interaction method and system based on AI agent driving

Abstract

The invention relates to the technical field of data processing and analysis, in particular to a digital twinning factory construction interaction method and system based on AI agent driving, and the method comprises the steps: analyzing the disturbance degree of the insertion of an emergency order on each production line through the dynamic data of the production line, the time sequence data of equipment use and the order feature data; an order adaptation degree analysis model is constructed through the production line dynamic data and the order feature data, and the adaptation degree of the emergency order and each production line is analyzed; the disturbance degree analysis result of the insertion of the emergency order on each production line and the adaptation degree analysis result of the emergency order and each production line are imported into a production line dynamic bearing capacity evaluation model, and the dynamic bearing capacity of each production line is evaluated when the emergency order is inserted; and inserting the emergency order according to the evaluation result of the dynamic bearing capacity of each production line when the emergency order is inserted. According to the invention, productivity conflict or efficiency loss caused by blind order insertion can be avoided, the resource mismatching cost is reduced, and the emergency order delivery response speed is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and analysis, and in particular to an interactive method and system for constructing a digital twin factory driven by an AI agent. Background Art

[0002] With the advancement of Industry 4.0 and the deepening adoption of intelligent manufacturing, traditional manufacturing is undergoing unprecedented transformation. To cope with increasingly fierce market competition, traditional production plants urgently need to build highly flexible and intelligently responsive production systems. Digital twin technology, a key technology for achieving the deep integration of the physical and cyber worlds, provides a crucial path for factories to upgrade to intelligent systems by creating virtual mirrors of physical entities. Traditional digital twin factory construction is often limited to static modeling and offline analysis, making it difficult to capture dynamic changes in the production process in real time. Especially when handling emergencies like rush orders, decision-making mechanisms still rely on manual intervention or preset rules and lack autonomous learning capabilities. Furthermore, traditional digital twin systems have significant shortcomings in data integration. Multiple data points from the factory production process are often fragmented and cannot be integrated into a coherent whole. This makes them unable to cope with complex production scenarios like rush orders.

[0003] At the same time, existing interactive methods for building digital twin factories are unable to quantify in real time the cascading effects of urgent orders on production line timing conflicts and resource competition. This causes the order scheduling system to frequently fall into the dilemma of local optimization in the face of dynamic conflicts. Furthermore, existing technologies often integrate equipment capabilities and order characteristics through manually set weights, ignoring the nonlinear saturation characteristics of the production line buffer and the entropy increase effect of production change fluctuations. This results in a high misjudgment rate for highly flexible production lines during the analysis process.

[0004] In order to solve these problems, this application designs an interactive method and system for building a digital twin factory based on AI intelligent agent driving. Summary of the Invention

[0005] To overcome the defects and shortcomings of existing technologies, the present invention provides an interactive method and system for building a digital twin factory based on AI-driven agents. By analyzing the degree of disruption to each production line caused by the insertion of emergency orders and the degree of compatibility between emergency orders and each production line, the system evaluates the dynamic carrying capacity of each production line when an emergency order is inserted. Based on the evaluation results of the dynamic carrying capacity of each production line when an emergency order is inserted, the emergency order is inserted. This can avoid capacity conflicts or efficiency losses caused by blindly inserting orders, reduce resource mismatch costs, and improve the response speed of emergency order delivery.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions: In a first aspect, an embodiment of the present invention provides an interactive method for constructing a digital twin factory based on AI agent-driven operation, comprising the following steps: S1. Use AI agents to obtain production line dynamic data and equipment usage time series data for each production line, as well as order feature data for urgent orders. S2. Based on production line dynamic data, equipment usage time series data, and order feature data, a model is constructed to analyze the degree of disruption caused by the insertion of urgent orders on each production line. S3. Based on production line dynamic data and order feature data, an order adaptation analysis model is constructed to analyze the adaptability of urgent orders to each production line. S4. Build a production line capacity assessment model. The results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line are imported into the production line dynamic capacity assessment model to evaluate the dynamic capacity of each production line when the emergency order is inserted. S5. Insert the urgent order based on the evaluation results of the dynamic load-bearing capacity of each production line when the urgent order is inserted.

[0007] In a preferred technical solution of the present invention, step S2 analyzes the degree of disturbance caused by the insertion of emergency orders to each production line, including the following specific steps: S21. Extract production line dynamic data, equipment usage time series data, and order feature data; S22. Based on the production line dynamic data, equipment usage time series data and order feature data, a disturbance degree analysis model for order insertion is constructed to analyze the disturbance degree of each production line caused by the insertion of emergency orders, and obtain the analysis results of the disturbance degree of each production line caused by the insertion of emergency orders.

[0008] The calculation formula for the degree of disturbance caused by the insertion of urgent orders to the current production line is: ; Where RD is the disturbance degree of the urgent order insertion on the current production line, Sc is the timing conflict degree of the urgent order insertion on the current production line, and Zz is the intensity of resource competition of the urgent order insertion on the current production line.

[0009] In the preferred technical solution of the present invention, the process of constructing the order insertion disturbance degree analysis model in step S22 includes the following specific steps: S221. Analyze the degree of timing conflict caused by the insertion of the urgent order on the current production line based on the production line dynamic data, equipment usage time series data, and order feature data, and obtain an analysis result of the degree of timing conflict caused by the insertion of the urgent order on the current production line. The calculation formula for the timing conflict degree is: ; Where Sc is the timing conflict degree of the insertion of the urgent order on the current production line, is the historical emergency order arrival factor of the current production line in the production line dynamic data, D is the number of devices required for the production of emergency orders on the current production line in the order feature data, Txd is the time required for the production of an emergency order on the d-th device to be used in the order feature data, Tyd is the idle time of the d-th device to be used for the production of an emergency order in the device usage time series data, max() is the maximum value function in the brackets, and d is any value from 1 to D; S222. Analyze the intensity of resource competition caused by the insertion of the urgent order on the current production line based on the production line dynamic data and the order characteristic data, and obtain an analysis result of the intensity of resource competition caused by the insertion of the urgent order on the current production line; The calculation formula for the intensity of resource competition is: ; Where Zz is the intensity of resource competition caused by the insertion of urgent orders on the current production line, Pj is the probability index of the use conflict of the j-th resource required by the urgent order on the current production line, Indicates the multiplication operation of the data in the brackets, n is the number of resource types required for the urgent order on the current production line in the order feature data, and j is any one from 1 to n; The calculation formula for the conflict probability index is: ; Where Pj is the usage conflict probability index of the j-th resource required for the emergency order on the current production line, rj is the demand for the j-th resource required for the emergency order on the current production line in the order feature data, Aj is the current stock of the j-th resource required for the emergency order on the current production line in the production line dynamic data, and Uj is the historical average consumption rate of the j-th resource required for the emergency order on the current production line in the production line dynamic data.

[0010] In the preferred technical solution of the present invention, the analysis of the adaptability of the emergency order to each production line in step S3 includes the following specific steps: S31, extracting production line dynamic data and order feature data; S32. Based on the production line dynamic data and order feature data, an order adaptation degree analysis model is constructed to analyze the adaptation degree between the urgent order and each production line, and obtain the adaptation degree analysis results between the urgent order and each production line; The formula for calculating the degree of compatibility between urgent orders and the current production line is: ; Where SP is the degree of adaptation between the emergency order and the current production line, Hx is the buffer absorption capacity of the current production line when the emergency order is inserted, Rh is the flexible production change capacity of the current production line when the emergency order is inserted, Rt is the total demand for all resources required for the emergency order on the current production line in the order feature data, and At is the total current stock of all resources required for the emergency order on the current production line in the production line dynamic data.

[0011] In the preferred technical solution of the present invention, the process of constructing the order adaptation degree analysis model in step S32 includes the following specific steps: S321. Analyze the buffer absorption capacity of each production line when the urgent order is inserted based on the production line dynamic data to obtain the buffer absorption capacity analysis results of each production line when the urgent order is inserted; S322. Based on the production line dynamic data and order feature data, the flexible production change capability of each production line when the emergency order is inserted is analyzed to obtain the analysis results of the flexible production change capability of each production line when the emergency order is inserted.

[0012] In the preferred technical solution of the present invention, the production line capacity assessment model is constructed in step S4, including the following specific steps: S41. Extract and analyze the disturbance degree analysis results of the insertion of the urgent order on each production line and the adaptation degree analysis results between the urgent order and each production line; S42. Based on the results of the analysis of the degree of disturbance to each production line caused by the insertion of the emergency order and the results of the analysis of the degree of adaptation between the emergency order and each production line, the dynamic load-bearing capacity of each production line when the emergency order is inserted is evaluated to obtain an evaluation result of the dynamic load-bearing capacity of each production line when the emergency order is inserted; The evaluation formula for dynamic load-bearing capacity is: ; Where DC is the dynamic carrying capacity of the current production line when an urgent order is inserted.

[0013] In a preferred technical solution of the present invention, in step S5, the urgent order is inserted according to the evaluation result of the dynamic load capacity of each production line when the urgent order is inserted, and the following specific steps are included: S51. Obtaining the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted; S52: Extract the production line corresponding to the maximum value among the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted, and use it as the production line for inserting the urgent order.

[0014] In a second aspect, an embodiment of the present invention further provides an interactive system for building a digital twin factory based on AI-driven intelligent agents, including: The data acquisition module is used to obtain production line dynamic data and equipment usage time series data of each production line through AI agents, and also obtain order feature data of urgent orders; The order insertion disturbance degree analysis module is used to build an order insertion disturbance degree analysis model based on production line dynamic data, equipment usage time series data, and order feature data to analyze the degree of disturbance caused by the insertion of urgent orders on each production line; The order adaptation degree analysis module is used to build an order adaptation degree analysis model based on production line dynamic data and order feature data to analyze the adaptation degree of urgent orders to each production line; The production line dynamic load-bearing capacity assessment module is used to build a production line load-bearing capacity assessment model. The module imports the results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line into the production line dynamic load-bearing capacity assessment model to evaluate the dynamic load-bearing capacity of each production line when an emergency order is inserted; The urgent order insertion module is used to insert urgent orders based on the evaluation results of the dynamic load capacity of each production line at the time of urgent order insertion; The control module is used to control the operation of the data acquisition module, the order insertion disturbance degree analysis module, the order adaptation degree analysis module, the production line dynamic load-bearing capacity assessment module and the emergency order insertion module.

[0015] Compared with the prior art, the present invention has the following advantages and beneficial effects: The present invention analyzes the degree of disturbance caused by the insertion of emergency orders on each production line through production line dynamic data, equipment usage time series data, and order feature data; constructs an order adaptation degree analysis model based on production line dynamic data and order feature data to analyze the degree of adaptation between emergency orders and each production line; imports the analysis results of the degree of disturbance caused by the insertion of emergency orders on each production line and the analysis results of the degree of adaptation between emergency orders and each production line into the production line dynamic carrying capacity evaluation model to evaluate the dynamic carrying capacity of each production line when the emergency order is inserted; and inserts the emergency order based on the evaluation results of the dynamic carrying capacity of each production line when the emergency order is inserted. This can avoid capacity conflicts or efficiency losses caused by blindly inserting orders, reduce resource mismatch costs, and improve the response speed of emergency order delivery. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 This is a schematic diagram of the overall process of the interactive method for building a digital twin factory based on AI intelligent agent driving of the present invention; Figure 2This is a workflow diagram for step S2 of the interactive method for building a digital twin factory based on AI agent driving of the present invention; Figure 3 This is a workflow diagram for step S3 of the interactive method for building a digital twin factory based on AI agent driving of the present invention; Figure 4 This is a schematic diagram of the structure of the interactive system for the digital twin factory driven by AI agents in the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0018] Example 1

[0019] like Figure 1 As shown, this embodiment provides an interactive method for building a digital twin factory based on AI agent driving, which specifically includes the following steps: S1. Use AI agents to obtain production line dynamic data and equipment usage time series data for each production line, as well as order feature data for urgent orders. S2. Based on production line dynamic data, equipment usage time series data, and order feature data, a model is constructed to analyze the degree of disruption caused by the insertion of urgent orders on each production line. S3. Based on production line dynamic data and order feature data, an order adaptation analysis model is constructed to analyze the adaptability of urgent orders to each production line. S4. Build a production line capacity assessment model. The results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line are imported into the production line dynamic capacity assessment model to evaluate the dynamic capacity of each production line when the emergency order is inserted. S5. Insert the urgent order based on the evaluation results of the dynamic load-bearing capacity of each production line when the urgent order is inserted.

[0020] In this embodiment, if Figure 2 As shown, step S2 analyzes the degree of disturbance caused by the insertion of urgent orders to each production line, including the following specific steps: S21. Extract production line dynamic data, equipment usage time series data, and order feature data; S22. Based on the production line dynamic data, equipment usage time series data and order feature data, a disturbance degree analysis model for order insertion is constructed to analyze the disturbance degree of each production line caused by the insertion of emergency orders, and obtain the analysis results of the disturbance degree of each production line caused by the insertion of emergency orders.

[0021] The calculation formula for the degree of disturbance caused by the insertion of urgent orders to the current production line is: ; Where RD is the disturbance degree of the urgent order insertion on the current production line, Sc is the timing conflict degree of the urgent order insertion on the current production line, and Zz is the intensity of resource competition of the urgent order insertion on the current production line.

[0022] For example, this embodiment solves the fundamental defect of the existing technology of evaluating the two types of disturbances separately by constructing a dual disturbance coupling model of timing conflict and resource competition. Accurately captures the synergistic deterioration effect of "equipment congestion causing resource retention"; square root term The Euclidean norm is used to ensure that the high risk of a single dimension is not evenly distributed. Specifically, when conflicts on a certain device surge, the degree of disturbance can still be accurately captured even if resource competition is mild.

[0023] In this embodiment, the process of constructing the order insertion disturbance degree analysis model in step S22 includes the following specific steps: S221. Analyze the degree of timing conflict caused by the insertion of the urgent order on the current production line based on the production line dynamic data, equipment usage time series data, and order feature data, and obtain an analysis result of the degree of timing conflict caused by the insertion of the urgent order on the current production line. The calculation formula for the timing conflict degree is: ; Where Sc is the timing conflict degree of the insertion of the urgent order on the current production line, is the historical emergency order arrival factor of the current production line in the production line dynamic data, D is the number of devices required for the production of emergency orders on the current production line in the order feature data, Txd is the time required for the production of an emergency order on the d-th device to be used in the order feature data, Tyd is the idle time of the d-th device to be used for the production of an emergency order in the device usage time series data, max() is the maximum value function in the brackets, and d is any value from 1 to D; Among them, the historical emergency order arrival factor of the current production line , where N is the number of urgent orders received by the current production line during the operation cycle in the production line dynamic data, and T is the operation cycle length of the current production line in the production line dynamic data; For example, this embodiment is used to quantify the intensity of production line timing conflicts caused by the insertion of urgent orders. Through in-depth analysis of time window conflicts in multi-device collaborative production, this embodiment uses an exponential decay function structure to ensure that the output value can not only keenly capture high conflict risks, but also avoid the problem of extreme value distortion. Calculations are performed to quantify the positive gap between the equipment demand time of an order and the available time of the equipment, thereby filtering out the interference of invalid negative values ​​on the calculation results; at the same time, the influence of differences in equipment scale is eliminated through the idle time of the equipment. Specifically, this embodiment uses the historical emergency order arrival factor of the production line as the weight coefficient of the conflict probability, which can accurately describe the actual production situation where the production line with high-frequency emergency order insertion is more sensitive to the degree of timing conflict caused by new orders. Furthermore, this embodiment aggregates the conflict of the insertion of emergency orders on discrete equipment into the degree of timing conflict of the insertion of emergency orders on the production line, breaking through the limitation of traditional scheduling systems that only focus on conflicts of a single device, and providing a decision-making basis for dynamically adjusting the equipment time window and optimizing the production rhythm. It can drive the digital twin system to re-plan the schedule and avoid production interruptions.

[0024] S222. Analyze the intensity of resource competition caused by the insertion of the urgent order on the current production line based on the production line dynamic data and the order characteristic data, and obtain an analysis result of the intensity of resource competition caused by the insertion of the urgent order on the current production line; The calculation formula for the intensity of resource competition is: ; Where Zz is the intensity of resource competition caused by the insertion of urgent orders on the current production line, Pj is the probability index of the use conflict of the j-th resource required by the urgent order on the current production line, Indicates the multiplication operation of the data in the brackets, n is the number of resource types required for the urgent order on the current production line in the order feature data, and j is any one from 1 to n; The calculation formula for the conflict probability index is: ; Where Pj is the usage conflict probability index of the j-th resource required for the emergency order on the current production line, rj is the demand for the j-th resource required for the emergency order on the current production line in the order feature data, Aj is the current stock of the j-th resource required for the emergency order on the current production line in the production line dynamic data, and Uj is the historical average consumption rate of the j-th resource required for the emergency order on the current production line in the production line dynamic data; The calculation formula for the historical average utilization rate is: ; Where, is the total consumption of the jth resource required for the urgent order on the current production line in the production line dynamic data during the operation cycle.

[0025] For example, this embodiment calculates the probability of occurrence of at least one resource conflict by using a calculation formula for the intensity of resource competition, thereby solving the risk of underestimation of the severity of the conflict by the traditional weighted average method. In the calculation formula using the conflict probability index provided in this embodiment, when resources are sufficient, i.e. When , the conflict probability index is 0 to avoid false alarms; when resources are scarce, that is, When, through Accurately quantify the absolute gap rate of resources and introduce Reflecting resource consumption pressure. Furthermore, in this embodiment, when the calculated resource competition intensity is low, the AI ​​agent can be prompted to prepare backup resources; when the calculated resource competition intensity is high, this embodiment can mark the risk of resource deadlock and simultaneously link the supply chain system to initiate emergency resource procurement.

[0026] In this embodiment, if Figure 3 As shown, step S3 analyzes the degree of adaptation between the urgent order and each production line, including the following specific steps: S31, extracting production line dynamic data and order feature data; S32. Based on the production line dynamic data and order feature data, an order adaptation degree analysis model is constructed to analyze the adaptation degree between the urgent order and each production line, and obtain the adaptation degree analysis results between the urgent order and each production line; The formula for calculating the degree of compatibility between urgent orders and the current production line is: ; Where SP is the degree of adaptation between the emergency order and the current production line, Hx is the buffer absorption capacity of the current production line when the emergency order is inserted, Rh is the flexible production change capacity of the current production line when the emergency order is inserted, Rt is the total demand for all resources required for the emergency order on the current production line in the order feature data, and At is the total current stock of all resources required for the emergency order on the current production line in the production line dynamic data.

[0027] For example, in the calculation formula for the degree of adaptation between the urgent order and the current production line provided in this embodiment, the resource matching item The absolute value ratio eliminates dimensional differences: when Rt = At, it reaches its maximum value of 1, indicating optimal resource matching. When Rt is significantly greater than At, the resource matching term approaches 0, indicating a severe shortage of resources for urgent orders. Furthermore, this embodiment uses the adaptation degree calculation formula to reflect the fact that a low value for any sub-item in the formula will result in a low overall adaptation degree. Specifically, when buffering capacity is weak, even sufficient resources may be unable to accommodate urgent orders.

[0028] In this embodiment, the process of constructing the order adaptation degree analysis model in step S32 includes the following specific steps: S321. Analyze the buffer absorption capacity of each production line when the urgent order is inserted based on the production line dynamic data to obtain the buffer absorption capacity analysis results of each production line when the urgent order is inserted; The calculation formula for buffer absorption capacity is: ; Where Hx is the buffer absorption capacity of the current production line when the urgent order is inserted, Q is the number of buffers in the current production line in the production line dynamic data, Bq is the maximum capacity of the qth buffer in the current production line in the production line dynamic data, and Zq is the number of work-in-progress in the qth buffer in the current production line in the production line dynamic data when the urgent order is inserted. is the turnover efficiency index of the qth buffer in the current production line when the urgent order is inserted; Among them, the turnover efficiency index , where vq is the actual turnover rate of the qth buffer in the current production line when the urgent order is inserted in the production line dynamic data, is the designed maximum turnover rate of the qth buffer zone in the current production line in the production line dynamic data; For example, this embodiment uses the hyperbolic tangent function to achieve intelligent aggregation of the multi-dimensional states of all buffers on the production line. This model characterizes the real-time free volume ratio of the buffer zone. Using the turnover efficiency index, it quantifies how quickly buffers with higher turnover rates can compensate for capacity shortfalls. Furthermore, when a buffer zone on a production line is saturated, the remaining idle buffer zones can still offload the load. Therefore, this embodiment uses a summation term to collaboratively analyze multiple buffer zones on a production line, accurately quantifying the current line's buffer absorption capacity when urgent orders are inserted. Furthermore, this embodiment also uses the tanh function to simulate the marginal effects of actual production, avoiding the overestimation risk associated with traditional linear models.

[0029] S322. Analyze the flexible production change capability of each production line when the urgent order is inserted based on the production line dynamic data and the order characteristic data, and obtain the flexible production change capability analysis results of each production line when the urgent order is inserted; The calculation formula for flexible production change capability is: ; Where Rh is the flexible production change capability of the current production line when an emergency order is inserted, D is the number of devices required for the production of the emergency order on the current production line as shown in the order feature data, Std is the standard deviation of the time taken for all production switches of the dth device required for the production of the emergency order on the current production line as shown in the production line dynamic data within the current production line operation cycle, and Nfd is the number of failures of the dth device required for the production of the emergency order on the current production line as shown in the production line dynamic data within the current production line operation cycle.

[0030] For example, this embodiment quantifies the flexible production change capability of the current production line when an urgent order is inserted through an exponential decay function, reflecting the negative impact of fluctuations in equipment production switching time and equipment failure frequency on the flexible production change capability of the current production line when an urgent order is inserted; wherein, the square term It can amplify the risk of production change when the equipment switches production or fails; specifically, when the time taken for production switching of the equipment fluctuates greatly and its failures occur frequently, It will grow exponentially, which will greatly weaken the flexible production change capability of the current production line when urgent orders are inserted.

[0031] In this embodiment, the construction of the production line capacity assessment model in step S4 includes the following specific steps: S41. Extract and analyze the disturbance degree analysis results of the insertion of the urgent order on each production line and the adaptation degree analysis results between the urgent order and each production line; S42. Based on the results of the analysis of the degree of disturbance to each production line caused by the insertion of the emergency order and the results of the analysis of the degree of adaptation between the emergency order and each production line, the dynamic load-bearing capacity of each production line when the emergency order is inserted is evaluated to obtain an evaluation result of the dynamic load-bearing capacity of each production line when the emergency order is inserted; The evaluation formula for dynamic load-bearing capacity is: ; Where DC is the dynamic carrying capacity of the current production line when an urgent order is inserted.

[0032] In this embodiment, in step S5, the urgent order is inserted according to the evaluation result of the dynamic load capacity of each production line when the urgent order is inserted, and the following specific steps are included: S51. Obtaining the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted; S52: Extract the production line corresponding to the maximum value among the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted, and use it as the production line for inserting the urgent order.

[0033] Example 2

[0034] like Figure 4 As shown, this embodiment provides an interactive system for building a digital twin factory based on AI-driven intelligent agents, including: The data acquisition module is used to obtain production line dynamic data and equipment usage time series data of each production line through AI agents, and also obtain order feature data of urgent orders; The order insertion disturbance degree analysis module is used to build an order insertion disturbance degree analysis model based on production line dynamic data, equipment usage time series data, and order feature data to analyze the degree of disturbance caused by the insertion of urgent orders on each production line; The order adaptation degree analysis module is used to build an order adaptation degree analysis model based on production line dynamic data and order feature data to analyze the adaptation degree of urgent orders to each production line; The production line dynamic load-bearing capacity assessment module is used to build a production line load-bearing capacity assessment model. The module imports the results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line into the production line dynamic load-bearing capacity assessment model to evaluate the dynamic load-bearing capacity of each production line when an emergency order is inserted; The urgent order insertion module is used to insert urgent orders based on the evaluation results of the dynamic load capacity of each production line at the time of urgent order insertion; The control module is used to control the operation of the data acquisition module, the order insertion disturbance degree analysis module, the order adaptation degree analysis module, the production line dynamic load-bearing capacity assessment module and the emergency order insertion module.

[0035] The above-mentioned parameters and steps for each unit module to realize the corresponding functions in the interactive system of the digital twin factory driven by AI intelligent agent of the present invention can refer to the parameters and steps in the embodiment of the interactive method for constructing a digital twin factory driven by AI intelligent agent above, and will not be repeated here.

[0036] The various embodiments of the present invention are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the IoT device and medium embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0037] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0038] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0039] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0040] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0041] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0042] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0043] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology to store information. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0044] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0045] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.

Claims

1. An interactive method for building a digital twin factory based on AI-driven agents, characterized by: The steps include: S1. Use AI agents to obtain production line dynamic data and equipment usage time series data for each production line, as well as order feature data for urgent orders. S2. Based on production line dynamic data, equipment usage time series data, and order feature data, a model is constructed to analyze the degree of disruption caused by the insertion of urgent orders on each production line. S3. Based on production line dynamic data and order feature data, an order adaptation analysis model is constructed to analyze the adaptability of urgent orders to each production line. S4. Build a production line capacity assessment model. The results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line are imported into the production line dynamic capacity assessment model to evaluate the dynamic capacity of each production line when the emergency order is inserted. S5. Insert the urgent order based on the evaluation results of the dynamic load-bearing capacity of each production line when the urgent order is inserted.

2. The interactive method for building a digital twin factory based on AI agent driving according to claim 1 is characterized in that: The analysis of the degree of disturbance caused by the insertion of the emergency order on each production line in step S2 includes the following specific steps: S21. Extract production line dynamic data, equipment usage time series data, and order feature data; S22. Based on the production line dynamic data, equipment usage time series data, and order feature data, a disturbance degree analysis model for order insertion is constructed to analyze the disturbance degree of the insertion of urgent orders on each production line, and obtain the disturbance degree analysis results of the insertion of urgent orders on each production line; The calculation formula for the degree of disturbance caused by the insertion of urgent orders to the current production line is: ； Where RD is the disturbance degree of the urgent order insertion on the current production line, Sc is the timing conflict degree of the urgent order insertion on the current production line, and Zz is the intensity of resource competition of the urgent order insertion on the current production line.

3. The interactive method for building a digital twin factory based on AI agent driving according to claim 2 is characterized in that: The process of constructing the order insertion disturbance degree analysis model in step S22 includes the following specific steps: S221. Analyze the degree of timing conflict caused by the insertion of the urgent order on the current production line based on the production line dynamic data, equipment usage time series data, and order feature data, and obtain an analysis result of the degree of timing conflict caused by the insertion of the urgent order on the current production line. The calculation formula for the timing conflict degree is: ； Where Sc is the timing conflict degree of the insertion of the urgent order on the current production line, is the historical emergency order arrival factor of the current production line in the production line dynamic data, D is the number of devices required for the production of emergency orders on the current production line in the order feature data, Txd is the time required for the production of an emergency order on the d-th device to be used in the order feature data, Tyd is the idle time of the d-th device to be used for the production of an emergency order in the device usage time series data, max() is the maximum value function in the brackets, and d is any value from 1 to D; S222. Analyze the intensity of resource competition caused by the insertion of the urgent order on the current production line based on the production line dynamic data and the order characteristic data, and obtain an analysis result of the intensity of resource competition caused by the insertion of the urgent order on the current production line; The calculation formula for the intensity of resource competition is: ； Where Zz is the intensity of resource competition caused by the insertion of urgent orders on the current production line, Pj is the probability index of the use conflict of the j-th resource required by the urgent order on the current production line, Indicates the multiplication operation of the data in the brackets, n is the number of resource types required for the urgent order on the current production line in the order feature data, and j is any one from 1 to n; The calculation formula for the conflict probability index is: ； Where Pj is the usage conflict probability index of the j-th resource required for the emergency order on the current production line, rj is the demand for the j-th resource required for the emergency order on the current production line in the order feature data, Aj is the current stock of the j-th resource required for the emergency order on the current production line in the production line dynamic data, and Uj is the historical average consumption rate of the j-th resource required for the emergency order on the current production line in the production line dynamic data.

4. The interactive method for constructing a digital twin factory based on AI agent driving according to claim 3 is characterized in that: The step S3 analyzes the degree of compatibility between the urgent order and each production line, including the following specific steps: S31, extracting production line dynamic data and order feature data; S32. Based on the production line dynamic data and order feature data, an order adaptation degree analysis model is constructed to analyze the adaptation degree between the urgent order and each production line, and obtain the adaptation degree analysis results between the urgent order and each production line; The formula for calculating the degree of compatibility between urgent orders and the current production line is: ； Where SP is the degree of adaptation between the emergency order and the current production line, Hx is the buffer absorption capacity of the current production line when the emergency order is inserted, Rh is the flexible production change capacity of the current production line when the emergency order is inserted, Rt is the total demand for all resources required for the emergency order on the current production line in the order feature data, and At is the total current stock of all resources required for the emergency order on the current production line in the production line dynamic data.

5. The interactive method for constructing a digital twin factory based on AI agent driving according to claim 4 is characterized in that: The process of constructing the order adaptation degree analysis model in step S32 includes the following specific steps: S321. Analyze the buffer absorption capacity of each production line when the urgent order is inserted based on the production line dynamic data to obtain the buffer absorption capacity analysis results of each production line when the urgent order is inserted; S322. Based on the production line dynamic data and order feature data, the flexible production change capability of each production line when the emergency order is inserted is analyzed to obtain the analysis results of the flexible production change capability of each production line when the emergency order is inserted.

6. The interactive method for building a digital twin factory based on AI agent driving according to claim 5 is characterized in that: The step S4 constructs a production line capacity assessment model, including the following specific steps: S41. Extract and analyze the disturbance degree analysis results of the insertion of the urgent order on each production line and the adaptation degree analysis results between the urgent order and each production line; S42. Based on the results of the analysis of the degree of disturbance to each production line caused by the insertion of the emergency order and the results of the analysis of the degree of adaptation between the emergency order and each production line, the dynamic load-bearing capacity of each production line when the emergency order is inserted is evaluated to obtain an evaluation result of the dynamic load-bearing capacity of each production line when the emergency order is inserted; The evaluation formula for dynamic load-bearing capacity is: ； Where DC is the dynamic carrying capacity of the current production line when an urgent order is inserted.

7. The interactive method for constructing a digital twin factory based on AI agent driving according to claim 6 is characterized in that: In step S5, the urgent order is inserted according to the evaluation result of the dynamic load capacity of each production line when the urgent order is inserted, including the following specific steps: S51. Obtaining the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted; S52: Extract the production line corresponding to the maximum value among the dynamic load-bearing capacity evaluation results of all production lines when the urgent order is inserted, and use it as the production line for inserting the urgent order.

8. An interactive system for constructing a digital twin factory driven by an AI agent, which is implemented based on the interactive method for constructing a digital twin factory driven by an AI agent according to any one of claims 1 to 7, characterized in that: The system comprises: The data acquisition module is used to obtain production line dynamic data and equipment usage time series data of each production line through AI agents, and also obtain order feature data of urgent orders; The order insertion disturbance degree analysis module is used to build an order insertion disturbance degree analysis model based on production line dynamic data, equipment usage time series data, and order feature data to analyze the degree of disturbance caused by the insertion of urgent orders on each production line; The order adaptation degree analysis module is used to build an order adaptation degree analysis model based on production line dynamic data and order feature data to analyze the adaptation degree of urgent orders to each production line; The production line dynamic load-bearing capacity assessment module is used to build a production line load-bearing capacity assessment model. The module imports the results of the analysis of the degree of disturbance caused by the insertion of emergency orders on each production line and the results of the analysis of the degree of adaptation between emergency orders and each production line into the production line dynamic load-bearing capacity assessment model to evaluate the dynamic load-bearing capacity of each production line when an emergency order is inserted; The urgent order insertion module is used to insert urgent orders based on the evaluation results of the dynamic load capacity of each production line at the time of urgent order insertion; A control module is used to control the operation of the data acquisition module, the order insertion disturbance degree analysis module, the order adaptation degree analysis module, the production line dynamic load-bearing capacity assessment module and the emergency order insertion module.

Images