Smart factory management method based on digital twinning

Abstract

The invention relates to the technical field of factory management. The intelligent factory management method based on digital twinning comprises the following steps: performing dynamic identification and analysis processing on a multi-source heterogeneous communication protocol of factory equipment to obtain a standardized data stream; constructing a three-dimensional digital twinborn model comprising an equipment state and a technological process; generating a virtual control instruction according to an analog control strategy in the three-dimensional digital twin model; sandbox security verification processing is carried out on the virtual control instruction, and a compliance instruction set is screened out; converting the compliance instruction set into a protocol format supported by the target equipment, generating a reverse control instruction and issuing the reverse control instruction to the physical equipment; performing closed-loop feedback optimization processing according to the difference between the execution result of the physical equipment and the prediction result of the three-dimensional digital twinborn model, so as to solve the problem that the digital twinborn model lacks real-time sensor data injection and dynamic behavior constraint embedding, ensure that the model can reflect the real state of the equipment, and improve the real-time performance of the equipment. And the reliability and the execution security of the virtual control instruction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of factory management, and particularly to a digital-twin-based intelligent factory management method. Background Art

[0002] With the deep integration of industry and digital twin technology, real-time control and equipment collaborative management of intelligent factories have become the core requirements for improving production efficiency and safety. In complex industrial scenarios, factory equipment usually adopts multiple heterogeneous communication protocols (such as Modbus, Profinet, OPC UA), and a closed-loop control for virtual-real interaction needs to be realized through a digital twin system.

[0003] However, the related technologies have problems that the digital twin model lacks real-time sensor data injection and dynamic behavior constraint embedding, resulting in the model being unable to reflect the true state of the equipment, and further reducing the reliability of virtual control instructions. Summary of the Invention

[0004] Based on this, it is necessary to provide a digital-twin-based intelligent factory management method for the above technical problems, so as to solve the problems that the digital twin model lacks real-time sensor data injection and dynamic behavior constraint embedding, ensure that the model can reflect the true state of the equipment, and improve the reliability and execution safety of virtual control instructions.

[0005] The present application provides a digital-twin-based intelligent factory management method, and the method includes: Dynamically identify and parse the multi-source heterogeneous communication protocols of factory equipment to obtain a standardized data stream; Construct a three-dimensional digital twin model including equipment status and process flow based on the standardized data stream; Generate virtual control instructions according to the simulation control strategy in the three-dimensional digital twin model; Perform sandbox security verification processing on the virtual control instructions to screen out a compliant instruction set; Convert the compliant instruction set into a protocol format supported by the target device, generate a reverse control instruction and send it to the physical device; Perform closed-loop feedback optimization processing according to the difference between the execution result of the physical device and the prediction result of the three-dimensional digital twin model.

[0006] Further, constructing a three-dimensional digital twin model including equipment status and process flow based on the standardized data stream includes: Perform dynamic association processing on the equipment status data and process flow data in the standardized data stream to generate a multi-source data fusion model; Perform three-dimensional geometric topology modeling processing based on the multi-source data fusion model to generate an initial three-dimensional model framework; Inject real-time sensor data and process logic constraints into the initial 3D model framework to generate a dynamic and interactive 3D digital twin model; Perform real-time status update processing on the 3D digital twin model through the virtual-real synchronization engine to ensure the behavioral consistency between the model and the physical device.

[0007] Further, injecting real-time sensor data and process logic constraints into the initial 3D model framework to generate a dynamic and interactive 3D digital twin model includes: Perform dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial 3D model framework to generate the binding relationship between the device state and the model parameters; Perform rule engine embedding processing on the device motion trajectory and the process flow based on the process logic constraints to generate dynamic behavior constraint rules; Perform real-time fusion processing on the binding relationship and the dynamic behavior constraint rules through the virtual-real synchronization engine to generate a synchronization parameter set; Load the synchronization parameter set into the initial 3D model framework to generate a dynamic and interactive 3D digital twin model.

[0008] Further, performing dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial 3D model framework to generate the binding relationship between the device state and the model parameters includes: Perform multi-dimensional feature analysis processing on the real-time sensor data to extract the device state feature vector; Perform semantic topology analysis processing on the geometric parameters of the initial 3D model framework to generate model parameter semantic labels; Perform correlation mapping processing on the device state feature vector and the model parameter semantic labels based on the dynamic semantic matching algorithm to generate a parameter mapping rule set; Perform dynamic binding processing on the device state and the model parameters according to the parameter mapping rule set to generate the binding relationship between the device state and the model parameters.

[0009] Further, performing real-time fusion processing on the binding relationship and the dynamic behavior constraint rules through the virtual-real synchronization engine to generate a synchronization parameter set includes: Perform multi-source data acquisition processing on the device state parameters in the binding relationship and the process logic parameters in the dynamic behavior constraint rules to generate a fusion input data stream; Perform conflict detection processing on the real-time parameters and the historical parameters in the fusion input data stream based on the dynamic priority scheduling algorithm to generate a conflict resolution parameter set; Perform dynamic matching processing on the conflict resolution parameter set and the dynamic behavior constraint rules through a rule-driven fusion strategy to generate a candidate synchronization parameter set; Perform incremental optimization processing on the candidate synchronization parameter set according to the virtual-real interaction scenario to generate a synchronization parameter set.

[0010] Further, based on the dynamic priority scheduling algorithm, conflict detection processing is performed on the real-time parameters and historical parameters in the fused input data stream to generate a conflict resolution parameter set, including: Perform timeliness weight classification processing on the real-time parameters and historical parameters to generate real-time parameter categories and historical parameter categories; Based on the device operation scenario, perform dynamic weight allocation processing on the real-time parameter categories to generate a real-time priority list; Perform scenario adaptation coefficient matching processing on the historical parameter categories to generate a historical priority list; Through the conflict detection engine, perform cross-comparison processing on the real-time priority list and the historical priority list to generate a conflict event set; Based on the dynamic conflict resolution strategy, perform parameter replacement or logical overwrite processing on the conflict event set to generate a conflict resolution parameter set.

[0011] Further, through a rule-driven fusion strategy, perform dynamic matching processing on the conflict resolution parameter set and the dynamic behavior constraint rules to generate a candidate synchronization parameter set, including: Perform multi-dimensional feature extraction processing on the device status parameters in the conflict resolution parameter set and the process logic parameters in the dynamic behavior constraint rules to generate a rule matching feature vector; Based on the dynamic scenario adaptation algorithm, perform similarity comparison processing on the rule matching feature vector and the behavior constraint template in the preset rule library to generate a rule matching priority list; According to the device real-time operation model, perform dynamic weight allocation processing on the rule matching priority list to generate a scenario-based rule weight set; Through the rule engine, perform logical superposition processing on the scenario-based rule weight set and the conflict resolution parameter set to generate a candidate synchronization parameter set.

[0012] Further, convert the compliance instruction set into a protocol format supported by the target device, generate a reverse control instruction, and send it to the physical device, including: Perform dynamic protocol matching processing on the communication protocol type of the target device to generate a target protocol feature identifier; Based on the target protocol feature identifier, perform protocol semantic mapping processing on the compliance instruction set to generate an intermediate instruction set compatible across protocols; Through the instruction encapsulation engine, perform instruction encapsulation processing with device status awareness on the intermediate instruction set to generate a protocol adaptation instruction; Based on the real-time load status of the physical device, perform dynamic priority scheduling processing on the protocol adaptation instruction to generate a time-sequence optimized instruction sequence for sending; Through the edge node, perform redundancy check and conflict resolution processing on the instruction sequence for sending to generate a reverse control instruction and push it to the physical device.

[0013] Further, based on the real-time load status of physical devices, perform dynamic scheduling and processing on the protocol adaptation instructions to generate a sequence of issued instructions with optimized timing, including: Perform multi-dimensional data acquisition and processing on the real-time load status of physical devices to generate device load characteristic parameters; Based on the device operation scenario, perform dynamic evaluation and processing on the device load characteristic parameters to generate a load type identifier and a priority weight; According to the load type identifier and the priority weight, perform dynamic classification and processing on the protocol adaptation instructions to generate an instruction priority allocation strategy; Through a timing optimization algorithm, perform dynamic matching and processing on the instruction priority allocation strategy and the real-time response ability of the device to generate a timing adjustment strategy; Based on the timing adjustment strategy, perform logical recombination and conflict resolution processing on the protocol adaptation instructions to generate a sequence of issued instructions with optimized timing.

[0014] Further, perform dynamic identification and parsing processing on the multi-source heterogeneous communication protocols of factory devices to obtain a standardized data stream, including: Perform dynamic protocol feature matching and processing on the communication protocol features of the target device to generate a protocol type identifier; Based on the protocol type identifier, perform dynamic segmentation and protocol frame extraction processing on the original communication data stream to generate a structured protocol data block; Through an adaptive parsing engine, perform semantic analysis and data bit mapping processing on the structured protocol data block to generate intermediate parsed data; Based on a preset unified data model, perform format conversion and semantic calibration processing on the intermediate parsed data to generate a standardized data stream.

[0015] The technical solutions provided in this application include the following technical effects: By providing a digital twin-based intelligent factory management method, including: performing dynamic identification and parsing processing on the multi-source heterogeneous communication protocols of factory devices to obtain a standardized data stream; constructing a three-dimensional digital twin model including device status and process flow; generating virtual control instructions in the simulated control strategy in the three-dimensional digital twin model; performing sandbox security verification processing on the virtual control instructions to screen out a compliant instruction set; converting the compliant instruction set into a protocol format supported by the target device, generating a reverse control instruction and issuing it to the physical device; performing closed-loop feedback optimization processing based on the difference between the execution result of the physical device and the prediction result of the three-dimensional digital twin model to solve the problem that the digital twin model lacks real-time sensor data injection and dynamic behavior constraint embedding, ensuring that the model can reflect the true state of the device, and improving the reliability and execution security of virtual control instructions. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a flowchart of a digital twin-based intelligent factory management method in an embodiment of the present invention; Figure 2 It is a flowchart of constructing a three-dimensional digital twin model including equipment status and process flow based on standardized data streams in an embodiment of the present invention. Detailed implementation manners

[0018] In order to make the above objects, features, and advantages of the present application more obvious and understandable, the following will describe the specific implementation manners of the present application in detail with reference to the drawings. Many specific details are set forth in the following description in order to fully understand the present application. However, the present application can be implemented in many other ways different from those described herein. Those skilled in the art can make similar improvements without departing from the connotation of the application. Therefore, the present application is not limited by the specific embodiments disclosed below.

[0019] As Figure 1 shown, the present application provides a digital twin-based intelligent factory management method, which includes: S101: Dynamically identify and parse the multi-source heterogeneous communication protocols of factory equipment to obtain standardized data streams.

[0020] Specifically, perform dynamic protocol feature matching on the communication protocol features of the target device to generate a protocol type identifier; then, based on the protocol type identifier, dynamically segment the original communication data stream and extract protocol frames to generate a structured protocol data block; then, perform semantic analysis and data bit mapping on the structured protocol data block through an adaptive parsing engine to generate intermediate parsed data; then, perform format conversion and semantic calibration on the intermediate parsed data based on a preset unified data model to obtain standardized data streams. The above process ensures that data with different communication protocols can be uniformly identified and parsed, providing a standardized data basis for subsequent digital twin model construction and control strategy simulation.

[0021] S102: Construct a three-dimensional digital twin model including equipment status and process flow based on the standardized data stream.

[0022] Specifically, perform dynamic association processing on the device status data and process flow data in the standardized data stream to generate a multi-source data fusion model. This step ensures that data from different sources can be integrated together, providing a basis for subsequent modeling. Based on the multi-source data fusion model, perform three-dimensional geometric topology modeling processing to generate an initial three-dimensional model framework. This step uses geometric topology technology to convert the data into the basic structure of a three-dimensional model. Inject real-time sensor data and process logic constraints into the initial three-dimensional model framework to generate a dynamic and interactive three-dimensional digital twin model. This step enables the model to dynamically reflect the real state and behavior of the device through real-time data updates and the application of logic constraints. Through the virtual-real synchronization engine, perform real-time status update processing on the three-dimensional digital twin model to ensure the behavioral consistency between the model and the physical device. This step ensures that the digital twin model can be updated in real time as the physical device changes, thereby providing more accurate device status information.

[0023] S103: In the three-dimensional digital twin model, generate virtual control instructions based on the simulation control strategy.

[0024] Specifically, perform rule engine embedding processing on the device movement trajectory and process flow based on process logic constraints to generate dynamic behavior constraint rules. This step ensures that the device behavior in the model complies with actual process requirements and logic constraints. In the three-dimensional digital twin model, simulate different control strategies based on the embedded dynamic behavior constraint rules and real-time sensor data. This step improves the reliability and effectiveness of the control strategy by testing and optimizing the control strategy in a virtual environment. Generate corresponding virtual control instructions according to the simulated control strategy. The above instructions will be used to guide the operation of the physical device to ensure that it operates in the expected manner.

[0025] S104: Perform sandbox security verification processing on the virtual control instructions to screen out a compliant instruction set.

[0026] Specifically, create an isolated sandbox environment for safely executing and validating virtual control instructions. This environment is isolated from the actual production environment to ensure that the verification process will not affect the actual device. In the sandbox environment, perform compliance checks on the virtual control instructions. This includes checking whether the instructions comply with preset security rules, logic constraints, and device operation specifications. Perform conflict detection on the virtual control instructions to identify instruction conflicts that may cause device failures or inconsistent behaviors. Resolve the above conflicts through conflict resolution strategies such as parameter replacement or logic override to ensure the consistency and reliability of the instruction set. After the above verification steps, screen out virtual control instructions that meet all security and logic requirements to form a compliant instruction set. The above instruction set can be safely applied to the control of actual physical devices.

[0027] S105: Convert the compliance instruction set into a protocol format supported by the target device, generate reverse control instructions, and send them to the physical device.

[0028] Specifically, perform dynamic protocol matching on the communication protocol type of the target device to generate a target protocol feature identifier. This step ensures that the instructions can adapt to the communication protocol of the target device. Based on the target protocol feature identifier, perform protocol semantic mapping on the compliance instruction set to generate an intermediate instruction set compatible across protocols. This step converts the instructions into a format compatible with the target device protocol. Through the instruction encapsulation engine, perform instruction encapsulation processing with device status awareness on the intermediate instruction set to generate protocol adaptation instructions. This step ensures that the instructions can be correctly parsed and executed by the target device. Based on the real-time load status of the physical device, perform dynamic priority scheduling on the protocol adaptation instructions to generate a sequence of issued instructions with optimized timing. This step ensures that the instructions are sent in the optimal timing to avoid resource conflicts. Through the edge node, perform redundant verification and conflict resolution on the sequence of issued instructions to generate reverse control instructions and push them to the physical device. This step ensures the reliability of the instructions and the security of execution.

[0029] S106: Perform closed-loop feedback optimization processing based on the difference between the execution result of the physical device and the prediction result of the 3D digital twin model.

[0030] Specifically, collect the execution result data of the physical device in real time and synchronously compare it with the prediction result of the 3D digital twin model. This step ensures the real-time and accuracy of the data, providing a basis for subsequent difference analysis. By comparing the actual execution result of the physical device with the prediction result of the digital twin model, identify the difference between the two. This step uses data analysis techniques to find the deviation between the model prediction and the actual execution. According to the identified difference, adjust the 3D digital twin model. This includes updating model parameters, adjusting algorithm logic, etc., to improve the prediction accuracy of the model. Based on the adjusted model, generate a new optimization strategy. The above strategy aims to reduce the difference between the future execution result and the prediction result and improve the overall performance. Apply the new optimization strategy to the physical device and compare the execution result with the model prediction result again. If the difference still exists, repeat the above steps until the prediction result of the model and the execution result of the physical device reach the expected consistency. This step ensures the continuity and effectiveness of the optimization process. Through this closed-loop feedback mechanism, the accuracy and reliability of the digital twin model can be continuously improved, ensuring that it can truly reflect the state and behavior of the physical device, thus supporting more effective control and decision-making.

[0031] An embodiment of the present application provides a digital-twin-based intelligent factory management method, including: dynamically identifying and parsing multi-source heterogeneous communication protocols of factory equipment to obtain standardized data streams; constructing a three-dimensional digital-twin model including equipment status and process flows; simulating control strategies in the three-dimensional digital-twin model to generate virtual control instructions; performing sandbox security verification processing on the virtual control instructions to screen out a compliant instruction set; converting the compliant instruction set into a protocol format supported by target devices, generating reverse control instructions and sending them to physical devices; and performing closed-loop feedback optimization processing based on the difference between the execution results of physical devices and the prediction results of the three-dimensional digital-twin model to solve the problem that the digital-twin model lacks real-time sensor data injection and dynamic behavior constraint embedding, ensuring that the model can reflect the true state of the device and improving the reliability and execution security of virtual control instructions.

[0032] As Figure 2 shown, constructing a three-dimensional digital-twin model including equipment status and process flows based on the standardized data stream includes: S201: Dynamically associating the equipment status data and process flow data in the standardized data stream to generate a multi-source data fusion model; S202: Performing three-dimensional geometric topology modeling processing based on the multi-source data fusion model to generate an initial three-dimensional model framework; S203: Injecting real-time sensor data and process logic constraints into the initial three-dimensional model framework to generate a dynamically interactive three-dimensional digital-twin model; S204: Performing real-time status update processing on the three-dimensional digital-twin model through a virtual-real synchronization engine to ensure the behavioral consistency between the model and physical devices.

[0033] Specifically, extract the operating status data of the equipment from the standardized data stream, including real-time parameters such as temperature, pressure, and vibration. Extract process flow data, such as production plans, process logics, and equipment linkage relationships. Dynamically associate the equipment status data and process flow data through semantic analysis and feature matching algorithms to generate a multi-source data fusion model. Extract the geometric parameters of the equipment, such as dimensions, shapes, and positions, from the multi-source data fusion model. Analyze the connection relationships and spatial layouts between the equipment to generate the topological structure of the equipment. Based on the geometric parameters and topological relationships, use a three-dimensional modeling tool to generate an initial three-dimensional model framework. Dynamically map the real-time sensor data to the geometric parameters of the three-dimensional model framework to generate a binding relationship between the equipment status and model parameters. Based on the process logic constraints, embed a rule engine into the motion trajectories and process flows of the equipment to generate dynamic behavior constraint rules.

[0034] Through the virtual-real synchronization engine, real-time data and constraint rules are loaded into the 3D model framework to generate a dynamic and interactive 3D digital twin model. Through the virtual-real synchronization engine, the real-time state parameters of physical devices are collected and compared with the predicted states of the digital twin model. The state differences between the model and the physical devices are detected, and parameter replacement or logical override is performed through the conflict detection engine to generate a conflict resolution parameter set. Based on the conflict resolution parameter set, incremental optimization is performed on the digital twin model to ensure the behavioral consistency between the model and the physical devices. Through the above steps, the 3D digital twin model constructed based on the standardized data stream can reflect the states and behaviors of physical devices in real time, providing accurate virtual control and optimization support for the management of smart factories.

[0035] Further, real-time sensor data and process logic constraints are injected into the initial 3D model framework to generate a dynamic and interactive 3D digital twin model, including: Perform dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial 3D model framework to generate the binding relationship between the device state and the model parameters; Perform rule engine embedding processing on the device motion trajectory and process flow based on the process logic constraints to generate dynamic behavior constraint rules; Perform real-time fusion processing on the binding relationship and the dynamic behavior constraint rules through the virtual-real synchronization engine to generate a synchronization parameter set; Load the synchronization parameter set into the initial 3D model framework to generate a dynamic and interactive 3D digital twin model.

[0036] Specifically, obtain the real-time state data of the device, such as temperature, pressure, vibration, etc., from the sensor. Extract the geometric parameters of the device, such as position, size, shape, etc., from the initial 3D model framework. Through the dynamic semantic matching algorithm, associate and map the real-time sensor data with the geometric parameters to generate the binding relationship between the device state and the model parameters. Extract the motion trajectory of the device and the logical constraints of the process flow from the process flow data. Based on the process logic constraints, perform rule engine embedding on the motion trajectory and process flow of the device to generate dynamic behavior constraint rules. Generate the dynamic behavior constraint rules of the device through the rule engine to ensure that the device behavior conforms to the process logic. Collect the device state parameters in the binding relationship and the process logic parameters in the dynamic behavior constraint rules to generate a fusion input data stream. Through the conflict detection engine, perform conflict detection on the real-time parameters and historical parameters to generate a conflict event set; through the dynamic conflict resolution strategy, perform parameter replacement or logical override on the conflict event set to generate a conflict resolution parameter set.

[0037] Through a rule-driven fusion strategy, dynamically match the conflict resolution parameter set with the dynamic behavior constraint rules to generate a candidate synchronization parameter set; incrementally optimize the candidate synchronization parameter set through the virtual-real interaction scenario to generate a synchronization parameter set. Load the synchronization parameter set into the initial 3D model framework to update the geometric parameters and behavior constraints of the model. Through the virtual-real synchronization engine, update the model state in real time to ensure the behavioral consistency between the model and the physical device, and generate a dynamically interactive 3D digital twin model. Support users to perform real-time interactions through the model, such as viewing the device status, adjusting process parameters, simulating device behavior, etc. Through steps such as dynamic data mapping, rule engine embedding, virtual-real synchronization fusion, and model loading, the generated dynamically interactive 3D digital twin model can reflect the state and behavior of the physical device in real time, providing accurate virtual control and optimization support for the management of smart factories.

[0038] Furthermore, perform dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial 3D model framework to generate the binding relationship between the device state and the model parameters, including: Perform multi-dimensional feature analysis processing on the real-time sensor data to extract the device state feature vector; Perform semantic topology analysis processing on the geometric parameters of the initial 3D model framework to generate model parameter semantic labels; Based on the dynamic semantic matching algorithm, perform correlation mapping processing on the device state feature vector and the model parameter semantic labels to generate a parameter mapping rule set; According to the parameter mapping rule set, perform dynamic binding processing on the device state and the model parameters to generate the binding relationship between the device state and the model parameters.

[0039] Specifically, obtain the real-time state data of the device from the sensor, such as temperature, pressure, vibration, etc. Perform multi-dimensional feature analysis processing on the real-time sensor data to extract the device state feature vector, including key features such as the operating state and performance indicators of the device. Extract the geometric parameters of the device from the initial 3D model framework, such as position, size, shape, etc. Perform semantic topology analysis processing on the geometric parameters to generate model parameter semantic labels, providing a basis for subsequent semantic matching. Based on the dynamic semantic matching algorithm, perform correlation mapping processing on the device state feature vector and the model parameter semantic labels to generate a parameter mapping rule set. Through algorithm calculation, generate the mapping rules between the device state and the model parameters to ensure their accurate correspondence. According to the parameter mapping rule set, perform dynamic binding processing on the device state and the model parameters to generate the binding relationship between the device state and the model parameters. During the operation of the device, update the binding relationship between the device state and the model parameters in real time to ensure that the model can accurately reflect the real-time state of the device.

[0040] Furthermore, the virtual-real synchronization engine performs real-time fusion processing on the binding relationship and the dynamic behavior constraint rules to generate a synchronization parameter set, including: Perform multi-source data acquisition processing on the device state parameters in the binding relationship and the process logic parameters in the dynamic behavior constraint rules to generate a fused input data stream; Based on the dynamic priority scheduling algorithm, perform conflict detection processing on the real-time parameters and historical parameters in the fused input data stream to generate a conflict resolution parameter set; Perform dynamic matching processing on the conflict resolution parameter set and the dynamic behavior constraint rules through a rule-driven fusion strategy to generate a candidate synchronization parameter set; Perform incremental optimization processing on the candidate synchronization parameter set according to the virtual-real interaction scenario to generate a synchronization parameter set.

[0041] Specifically, extract the device state parameters from the binding relationship and the process logic parameters from the dynamic behavior constraint rules. Integrate the collected device state parameters and process logic parameters into a fused input data stream to provide a basis for subsequent processing. Classify the real-time parameters and historical parameters according to their timeliness weights to generate real-time parameter categories and historical parameter categories. Based on the device operation scenario, dynamically allocate weights to the real-time parameter categories to generate a real-time priority list; match the scene adaptation coefficients for the historical parameter categories to generate a historical priority list. Through the conflict detection engine, cross-compare the real-time priority list and the historical priority list to generate a conflict event set. Based on the dynamic conflict resolution strategy, perform parameter replacement or logical overwrite on the conflict event set to generate a conflict resolution parameter set. Perform multi-dimensional feature extraction on the device state parameters in the conflict resolution parameter set and the process logic parameters in the dynamic behavior constraint rules to generate a rule matching feature vector. Based on the dynamic scene adaptation algorithm, compare the similarity between the rule matching feature vector and the behavior constraint template in the preset rule library to generate a rule matching priority list.

[0042] According to the device real-time operation model, dynamically allocate weights to the rule matching priority list to generate a scene-based rule weight set. Through the rule engine, logically superimpose the scene-based rule weight set and the conflict resolution parameter set to generate a candidate synchronization parameter set. According to the virtual-real interaction scenario, analyze the applicability and optimization direction of the candidate synchronization parameter set. Perform incremental optimization on the candidate synchronization parameter set, adjust the parameters to improve the consistency between the model and the physical device. After optimization, generate a synchronization parameter set to ensure that the model can accurately reflect the state and behavior of the physical device. Through the above steps, the virtual-real synchronization engine can fuse the binding relationship and the dynamic behavior constraint rules in real time to generate a synchronization parameter set, ensuring the behavioral consistency between the digital twin model and the physical device.

[0043] Further, based on the dynamic priority scheduling algorithm, conflict detection processing is performed on the real-time parameters and historical parameters in the fused input data stream to generate a conflict resolution parameter set, including: Perform timeliness weight classification processing on the real-time parameters and historical parameters to generate real-time parameter categories and historical parameter categories; Based on the device operation scenario, perform dynamic weight allocation processing on the real-time parameter categories to generate a real-time priority list; Perform scenario adaptation coefficient matching processing on the historical parameter categories to generate a historical priority list; Through the conflict detection engine, perform cross-comparison processing on the real-time priority list and the historical priority list to generate a conflict event set; Based on the dynamic conflict resolution strategy, perform parameter replacement or logical overwrite processing on the conflict event set to generate a conflict resolution parameter set.

[0044] Specifically, extract real-time parameters from the fused input data stream, classify them according to their timeliness to generate real-time parameter categories. Extract historical parameters from the fused input data stream, classify them according to their timeliness to generate historical parameter categories. Based on the device operation scenario, perform dynamic weight allocation processing on the real-time parameter categories to generate a real-time priority list. Perform scenario adaptation coefficient matching processing on the historical parameter categories to generate a historical priority list. For example, for historical parameters in a stable operation scenario, assign a lower weight. Through the conflict detection engine, perform cross-comparison processing on the real-time priority list and the historical priority list to identify conflicts between parameters. For conflicting parameters, according to the information in the conflict event set, adopt the method of parameter replacement, and replace the parameter with lower timeliness with the parameter with higher timeliness. For parameters that cannot be directly replaced, adopt the method of logical overwrite, and select appropriate parameters for overwrite according to the device operation scenario and task priority to generate a conflict resolution parameter set. Through the above steps, conflict detection processing is performed on the real-time parameters and historical parameters in the fused input data stream based on the dynamic priority scheduling algorithm, which can effectively solve the parameter conflict problem and ensure stability and consistency.

[0045] Further, through the rule-driven fusion strategy, perform dynamic matching processing on the conflict resolution parameter set and the dynamic behavior constraint rules to generate a candidate synchronization parameter set, including: Perform multi-dimensional feature extraction processing on the device status parameters in the conflict resolution parameter set and the process logic parameters in the dynamic behavior constraint rules to generate a rule matching feature vector; Based on the dynamic scenario adaptation algorithm, perform similarity comparison processing on the rule matching feature vector and the behavior constraint template in the preset rule library to generate a rule matching priority list; According to the device real-time operation model, perform dynamic weight allocation processing on the rule matching priority list to generate a scenario-based rule weight set; The rule engine performs logical superposition processing on the scenario-based rule weight set and the conflict resolution parameter set to generate a candidate synchronization parameter set.

[0046] Specifically, device status parameters are extracted from the conflict resolution parameter set, including key indicators such as temperature, pressure, and vibration. Process logic parameters are extracted from the dynamic behavior constraint rules, such as the device movement trajectory and the process flow logic. Through the feature extraction algorithm, the device status parameters and the process logic parameters are converted into rule matching feature vectors, providing a basis for subsequent similarity comparison. Based on the dynamic scenario adaptation algorithm, the rule matching feature vectors are compared with the behavior constraint templates in the preset rule library for similarity. According to the similarity comparison results, a rule matching priority list is generated, recording the matching degree and priority of each rule template. According to the real-time operation model of the device, the current device operation scenario is analyzed, such as emergency tasks and stable operation. Based on the scenario analysis results, dynamic weight allocation is performed on the rules in the rule matching priority list to generate a scenario-based rule weight set. Through the rule engine, logical superposition processing is performed on the scenario-based rule weight set and the conflict resolution parameter set. After the logical superposition processing, a candidate synchronization parameter set is generated to ensure that the parameter set can accurately reflect the real-time status and behavior constraints of the device. Through the above steps, the rule-driven fusion strategy can perform dynamic matching processing on the conflict resolution parameter set and the dynamic behavior constraint rules to generate a candidate synchronization parameter set, providing support for subsequent model optimization and control instruction generation.

[0047] Furthermore, the compliance instruction set is converted into a protocol format supported by the target device, generating a reverse control instruction and sending it to the physical device, including: Perform dynamic protocol matching processing on the communication protocol type of the target device to generate a target protocol feature identifier; Perform protocol semantic mapping processing on the compliance instruction set based on the target protocol feature identifier to generate an intermediate instruction set compatible across protocols; Perform instruction encapsulation processing for device status perception on the intermediate instruction set through the instruction encapsulation engine to generate a protocol adaptation instruction; Perform priority dynamic scheduling processing on the protocol adaptation instruction based on the real-time load status of the physical device to generate a time-sequence optimized instruction sequence for sending; Perform redundancy check and conflict resolution processing on the instruction sequence for sending through the edge node to generate a reverse control instruction and push it to the physical device.

[0048] Specifically, read the communication protocol type from the configuration information of the target device, such as Modbus, Profinet, OPCUA, etc. Obtain the protocol library object that matches the target protocol type. Generate the target protocol feature identifier based on the matched protocol library object for subsequent protocol semantic mapping. Parse the compliance instruction set to extract the semantic information and execution parameters of the instructions. Based on the target protocol feature identifier, map the semantic information of the compliance instruction set to the semantics of the target protocol. Generate an intermediate instruction set that is cross-protocol compatible to ensure seamless conversion of instructions between different protocols. Obtain the current status information of the target device, such as load, connection status, etc. Adapt the intermediate instruction set according to the device status information to generate protocol adaptation instructions that conform to the communication protocol of the target device. Package the protocol adaptation instructions into an executable instruction packet through the instruction packaging engine.

[0049] Monitor the load status of the physical device in real time, including CPU usage, memory occupancy, etc. Allocate priorities to the protocol adaptation instructions according to the device load status to ensure that high-priority instructions are executed first. Generate a sequence of issued instructions with optimized timing to ensure that the instructions are issued in the optimal order. Perform redundancy verification on the sequence of issued instructions to ensure the integrity and correctness of the instructions. Detect potential conflicts in the instruction sequence, such as resource competition, logical contradictions, etc. Solve the instruction conflict problem through conflict resolution strategies, such as parameter adjustment, logical coverage, etc. Push the reverse control instructions that have been verified and resolved to the physical device to ensure reliable execution of the instructions. Through the above steps, efficient conversion of the compliance instruction set to the communication protocol of the target device can be achieved, ensuring the accuracy and execution efficiency of the instructions.

[0050] Furthermore, perform dynamic scheduling and processing of the priorities of the protocol adaptation instructions based on the real-time load status of the physical device to generate a sequence of issued instructions with optimized timing, including: Perform multi-dimensional data acquisition and processing on the real-time load status of the physical device to generate device load characteristic parameters; Perform dynamic evaluation and processing on the device load characteristic parameters based on the device operating scenario to generate a load type identifier and a priority weight; Perform dynamic classification and processing on the protocol adaptation instructions according to the load type identifier and the priority weight to generate an instruction priority allocation strategy; Perform dynamic matching and processing on the instruction priority allocation strategy and the real-time response ability of the device through a timing optimization algorithm to generate a timing adjustment strategy; Perform logical reorganization and conflict resolution processing on the protocol adaptation instructions based on the timing adjustment strategy to generate a sequence of issued instructions with optimized timing.

[0051] Specifically, identify multiple data sources of physical devices, such as sensors, controllers, etc. Collect the load status data of the device in real time, including CPU usage, memory occupancy, network bandwidth, etc. Through data processing algorithms, convert the collected data into device load characteristic parameters, such as average load rate, peak load, etc. Analyze the current operating scenario of the device, such as normal operation, high-load operation, emergency tasks, etc. Apply a dynamic evaluation model to evaluate the device load characteristic parameters and determine the load type identifier. According to the load type and the device operating scenario, assign priority weights to different types of loads. According to the load type identifier, classify the protocol adaptation instructions into different categories, such as high-priority instructions, medium-priority instructions, low-priority instructions. Based on the priority weights, generate an instruction priority allocation strategy to ensure that high-priority instructions are executed first. Evaluate the real-time response ability of the device, including processing speed, memory availability, etc. Through a timing optimization algorithm, match the instruction priority allocation strategy with the device response ability to generate a timing adjustment strategy. According to the timing adjustment strategy, logically reorganize the protocol adaptation instructions to ensure that the instructions are sent in the optimal order. Detect potential conflicts in the instruction sequence, such as resource competition, logical contradictions, etc., and solve the above problems through a conflict resolution strategy. Generate a timing-optimized instruction sequence for sending to ensure that the instructions can be executed efficiently and accurately. Through the above steps, it is possible to achieve accurate evaluation of the real-time load status of physical devices and efficient scheduling of protocol adaptation instructions, ensuring the accuracy and execution efficiency of the instructions.

[0052] Furthermore, perform dynamic identification and parsing processing on the multi-source heterogeneous communication protocols of factory equipment to obtain standardized data streams, including: Perform dynamic protocol feature matching processing on the communication protocol features of the target device to generate a protocol type identifier; Based on the protocol type identifier, perform dynamic segmentation and protocol frame extraction processing on the original communication data stream to generate structured protocol data blocks; Through an adaptive parsing engine, perform semantic analysis and data bit mapping processing on the structured protocol data blocks to generate intermediate parsing data; Based on a preset unified data model, perform format conversion and semantic calibration processing on the intermediate parsing data to generate a standardized data stream.

[0053] Specifically, protocol features such as frame headers, frame tails, check codes, etc. are extracted from the communication data of the target device. The protocol library is queried to match the protocol features with the features of known protocols in the library. According to the matching results, protocol type identifiers such as Modbus, Profinet, OPC UA, etc. are generated. According to the protocol type identifier, the original communication data stream is dynamically segmented to extract protocol frames. The structure of the protocol frame is parsed, including the frame header, data segment, check segment, etc. The parsed protocol frame is converted into a structured protocol data block to provide a basis for subsequent processing. Through an adaptive parsing engine, semantic analysis is performed on the structured protocol data block to extract the semantic information of the data. The data bits are mapped to the semantic information of the protocol to generate intermediate parsed data, ensuring the accuracy and consistency of the data. Based on a preset unified data model, format conversion is performed on the intermediate parsed data. Semantic calibration is performed on the converted data to ensure that the semantic information of the data is consistent with the model. A standardized data stream is generated to provide a unified data input for the subsequent construction of the digital twin model. Through the above steps, efficient identification and parsing of multi-source heterogeneous communication protocols of factory equipment can be achieved, ensuring the accuracy and consistency of the data and providing reliable data support for the management of smart factories.

[0054] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0055] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can refer to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present disclosure solution. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0056] The above-described embodiments merely represent several implementation manners of the embodiments of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the embodiments of the present application.

Claims

1. A smart factory management method based on digital twin, characterized in that, The method includes: Dynamically identifying and parsing the multi-source heterogeneous communication protocols of factory equipment to obtain a standardized data stream; Constructing a three-dimensional digital twin model including equipment status and process flow based on the standardized data stream; Generating virtual control instructions based on the simulation control strategy in the three-dimensional digital twin model; Performing sandbox security verification processing on the virtual control instructions to screen out a compliant instruction set; Converting the compliant instruction set into a protocol format supported by the target device, generating reverse control instructions and sending them to the physical device; Performing closed-loop feedback optimization processing according to the difference between the execution result of the physical device and the prediction result of the three-dimensional digital twin model.

2. The intelligent factory management method based on digital twin according to claim 1, wherein The constructing a three-dimensional digital twin model including equipment status and process flow based on the standardized data stream includes: Performing dynamic association processing on the equipment status data and process flow data in the standardized data stream to generate a multi-source data fusion model; Performing three-dimensional geometric topology modeling processing based on the multi-source data fusion model to generate an initial three-dimensional model framework; Injecting real-time sensor data and process logic constraints into the initial three-dimensional model framework to generate the dynamic and interactive three-dimensional digital twin model; Performing real-time status update processing on the three-dimensional digital twin model through a virtual-real synchronization engine to ensure the behavioral consistency between the model and the physical device.

3. The intelligent factory management method based on digital twin according to claim 2, wherein, The injecting real-time sensor data and process logic constraints into the initial three-dimensional model framework to generate the dynamic and interactive three-dimensional digital twin model includes: Performing dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial three-dimensional model framework to generate a binding relationship between equipment status and model parameters; Performing rule engine embedding processing on the equipment movement trajectory and process flow based on the process logic constraints to generate dynamic behavior constraint rules; Performing real-time fusion processing on the binding relationship and the dynamic behavior constraint rules through a virtual-real synchronization engine to generate a synchronization parameter set; Loading the synchronization parameter set into the initial three-dimensional model framework to generate the dynamic and interactive three-dimensional digital twin model.

4. The intelligent factory management method based on digital twin according to claim 3, wherein, The performing dynamic data mapping processing on the real-time sensor data and the geometric parameters of the initial three-dimensional model framework to generate a binding relationship between equipment status and model parameters includes: Performing multi-dimensional feature analysis processing on the real-time sensor data to extract equipment status feature vectors; Performing semantic topology analysis processing on the geometric parameters of the initial three-dimensional model framework to generate model parameter semantic tags; Performing association mapping processing on the equipment status feature vectors and the model parameter semantic tags based on a dynamic semantic matching algorithm to generate a parameter mapping rule set; Performing dynamic binding processing on equipment status and model parameters according to the parameter mapping rule set to generate the binding relationship between equipment status and model parameters.

5. The intelligent factory management method based on digital twin according to claim 3, characterized in that, The performing real-time fusion processing on the binding relationship and the dynamic behavior constraint rules through a virtual-real synchronization engine to generate a synchronization parameter set includes: Performing multi-source data acquisition processing on the equipment status parameters in the binding relationship and the process logic parameters in the dynamic behavior constraint rules to generate a fusion input data stream; Based on a dynamic priority scheduling algorithm, conflict detection is performed on the real-time parameters and historical parameters in the fused input data stream to generate a conflict resolution parameter set; Dynamically matching the conflict resolution parameter set with the dynamic behavior constraint rule through a rule-driven fusion strategy to generate a candidate synchronization parameter set; Incremental optimization processing is performed on the candidate synchronization parameter set according to the virtual-reality interaction scenario to generate the synchronization parameter set.

6. The management method of a smart factory based on digital twin according to claim 5, wherein The method of performing conflict detection processing on the real-time parameters and historical parameters in the fused input data stream based on the dynamic priority scheduling algorithm to generate a conflict resolution parameter set includes: Performing timeliness weight classification processing on the real-time parameters and historical parameters to generate real-time parameter categories and historical parameter categories; Performing dynamic weight allocation processing on the real-time parameter categories based on the device operation scenario to generate a real-time priority list; Performing scene adaptation coefficient matching processing on the historical parameter categories to generate a historical priority list; Cross-comparison processing is performed on the real-time priority list and the historical priority list by a conflict detection engine to generate a conflict event set; The conflict resolution parameter set is generated by performing parameter replacement or logic overwriting processing on the conflict event set based on a dynamic conflict resolution strategy.

7. A method for managing an intelligent factory based on digital twins according to claim 5, characterized in that, The rule-driven fusion strategy dynamically matches the conflict resolution parameter set with the dynamic behavior constraint rule to generate a candidate synchronization parameter set, including: Performing multi-dimensional feature extraction processing on the device state parameters in the conflict resolution parameter set and the process logic parameters in the dynamic behavior constraint rule to generate a rule matching feature vector; Based on the dynamic scene adaptation algorithm, the rule matching feature vector is compared with the behavior constraint template in the preset rule library to generate a rule matching priority list; Dynamically weight the rule matching priority list according to the real-time operation model of the device to generate a scenario-based rule weight set; The scenario-based rule weight set and the conflict resolution parameter set are logically superimposed by a rule engine to generate the candidate synchronization parameter set.

8. A smart factory management method based on digital twin according to claim 1, characterized in that The step of converting the compliant instruction set into a protocol format supported by the target device, generating a reverse control instruction and sending it to the physical device includes: Perform dynamic protocol matching on the communication protocol type of the target device to generate a target protocol feature identifier; Performing protocol semantic mapping processing on the compliant instruction set based on the target protocol feature identifier to generate a cross-protocol compatible intermediate instruction set; Performing device state-aware instruction encapsulation processing on the intermediate instruction set through an instruction encapsulation engine to generate a protocol adaptation instruction; Based on the real-time load status of the physical device, the protocol adaptation instruction is dynamically scheduled with priority to generate a timing-optimized instruction sequence; The edge node performs redundancy check and conflict resolution on the issued instruction sequence, generates the reverse control instruction and pushes it to the physical device.

9. A smart factory management method based on digital twin according to claim 8, characterized in that, The method of dynamically scheduling the protocol adaptation instructions based on the real-time load status of the physical device to generate a timing-optimized instruction sequence includes: Collect and process multi-dimensional data on the real-time load status of the physical device to generate device load characteristic parameters; Based on the device operation scenario, dynamically evaluate and process the device load characteristic parameters to generate a load type identifier and a priority weight; Dynamically classify the protocol adaptation instructions according to the load type identifier and the priority weight to generate an instruction priority allocation strategy; Dynamically match the instruction priority allocation strategy with the device's real-time response ability through a timing optimization algorithm to generate a timing adjustment strategy; Based on the timing adjustment strategy, perform logical recombination and conflict resolution processing on the protocol adaptation instructions to generate the issued instruction sequence with optimized timing; 10. A smart factory management method based on digital twin according to claim 1, characterized in that, The dynamic identification and parsing process of the multi-source heterogeneous communication protocols of the factory equipment to obtain standardized data streams includes: Perform dynamic protocol feature matching on the communication protocol features of the target device to generate a protocol type identifier; Based on the protocol type identifier, perform dynamic segmentation and protocol frame extraction on the original communication data stream to generate a structured protocol data block; Through an adaptive parsing engine, perform semantic analysis and data bit mapping on the structured protocol data block to generate intermediate parsing data; Based on a preset unified data model, perform format conversion and semantic calibration on the intermediate parsing data to generate the standardized data stream.

Images