Multi-protocol interworking intelligent manufacturing digital twinning practical training scene free construction method, storage medium and electronic equipment

Abstract

The invention discloses a multi-protocol interworking intelligent manufacturing digital twinning practical training scene free construction method, a storage medium and electronic equipment, and the method comprises the following steps: collecting and processing multi-modal data; constructing an intelligent manufacturing digital twin model library; carrying out multi-protocol analysis among heterogeneous industrial equipment; performing multi-protocol conversion among heterogeneous industrial equipment; and free construction of a digital twinning practical training scene: constructing a highly vivid and real-time interactive digital twinning practical training scene in a Web mode. Through application of a multi-modal data acquisition and processing technology, data comprehensiveness and accuracy are ensured, and a data basis is provided for subsequent modeling. And secondly, the digital twin model is intelligently manufactured, and a model library is constructed, so that multi-dimensional information modeling of equipment and a technological process is realized, the constructed model is more accurate and complete, and rich model resources are provided for practical training. The interoperability, the practical training effect and the development efficiency of the intelligent manufacturing system can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to a method, storage medium and electronic device for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario. Background Art

[0002] At present, digital twin technology is a virtual simulation technology that creates digital models of physical objects, systems or processes for real-time monitoring, analysis and optimization. Digital twin technology can not only reflect the actual status of objects in real time, but also predict the future behavior and performance of objects by simulating multiple operating scenarios and environmental conditions. This technology has been widely used in many fields such as manufacturing, energy, medical care and smart cities, greatly improving their operational efficiency and management level.

[0003] At present, intelligent manufacturing systems have been widely used in modern manufacturing. They combine a variety of automation equipment with information technology to make the production process more intelligent. With the development of modern science and technology and changes in market demand, the application scope of intelligent manufacturing continues to expand, so that the demand for talents in this field is also increasing. Therefore, the training of professional and technical talents close to market demand should also be paid attention to. The development of intelligent manufacturing depends on talent training and practice. Digital twin technology provides a new way for the practical training of intelligent manufacturing talents.

[0004] However, the existing intelligent manufacturing training systems have limited support for equipment layout, process simulation and real-time data integration. Many training systems can only build simple scenarios, lack support for complex process flows, and cannot accurately simulate complex situations in actual production environments. It is difficult to meet the diversified training needs of intelligent manufacturing training. This deficiency limits users' free construction and dynamic adjustment of training scenarios, making it difficult to achieve the purpose of training teaching. The main reason for the above problems is that, on the one hand, the protocol interoperability between different devices and systems varies greatly. In order to achieve data exchange and real-time communication between these devices, multiple protocol converters are usually required, which not only increases the complexity and cost of the system, but also limits the flexibility and scalability of the system; on the other hand, most of the existing digital twin platforms are client-based versions, which cannot fully utilize the lightweight and convenience brought by modern Web technology. How to solve these problems to improve the flexibility and training efficiency of the training system, provide stronger technical support and talent reserves for the digital transformation of the manufacturing industry, and solve the technical problems that urgently need to be solved in existing technologies. Summary of the invention

[0005] The purpose of the present invention is to provide a method, storage medium and electronic device for freely constructing a multi-protocol interoperable intelligent manufacturing digital twin training scenario, which can solve the problems of poor protocol interoperability between different devices and limited freedom in constructing training scenarios in existing intelligent manufacturing training systems.

[0006] The technical solution adopted by the present invention is: A method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario includes the following steps: Step 1: Multimodal data acquisition and processing: Use sensors and data acquisition equipment to collect and process multimodal data in real time; Step 2: Construction of the digital twin model library for intelligent manufacturing: Based on the multimodal data collected in step 1, digital twin models of intelligent manufacturing equipment, process flow, etc. are constructed, and a digital twin model library for intelligent manufacturing is formed; Step 3: Multi-protocol parsing between heterogeneous industrial equipment: Write a multi-protocol parsing module between heterogeneous industrial equipment to parse data packets of various protocols; Step 4: Multi-protocol conversion between heterogeneous industrial equipment: Develop multi-protocol conversion tools to ensure accurate transmission of data and control signals between different protocols; Step 5: Freely construct digital twin training scenarios: Build highly realistic, real-time interactive digital twin training scenarios via the Web.

[0007] The step 1 specifically includes the following steps: Step 1.1, the data source includes sensor data and production process data, and the data acquisition equipment includes high-precision sensors, data recorders and network interface modules for capturing and transmitting multimodal data; Step 1.2, the real-time collected data is first transmitted to the central data processing unit through the network for preliminary filtering and verification to ensure the authenticity and integrity of the data; Step 1.3, then, the data enters the preprocessing stage, including data cleaning, noise reduction, missing value filling, standardization and normalization: Data cleaning improves data quality by removing noise and outliers, and further purifies data signals through noise reduction techniques such as Fourier transform and wavelet transform; Step 1.4, missing value filling, completes the missing data through interpolation, regression analysis or machine learning algorithms, and finally adjusts the data through standardization and normalization steps to eliminate the differences between data from different sources.

[0008] In step 2, the multi-dimensional information of the intelligent manufacturing equipment is modeled, and the model is adjusted and optimized according to the actual situation to ensure its accuracy and completeness; for the modeled model, a digital twin model library is established, which includes digital models of various equipment and process flows, and the models in the model library are classified and labeled to ensure that the models are easy to find and convenient for practical training.

[0009] The model in step 2 includes a geometric model, a relationship model and a production process model; the geometric model modeling specifically uses three-dimensional modeling technology to accurately reproduce the physical form of the equipment, including its internal structure, external dimensions and positional relationship, to ensure that the digital twin model is geometrically consistent with the physical equipment; in the modeling process, the physical characteristics and motion laws of the equipment, such as mass, inertia, friction, etc., are also considered to improve the accuracy of the model; Interrelationship modeling describes the interaction of each device in the production line by analyzing the physical connection and data flow relationship between the devices and using the system dynamics method; Production process modeling describes each step, process flow or manufacturing operation of production in detail according to the production process; All models are classified and labeled according to attributes, functions, uses, etc. to form a structured digital twin model library; at the same time, a model search engine is developed to quickly retrieve and locate the required models through keywords, attributes, etc.

[0010] In step 3, the protocol parsing module includes a protocol identification unit, a message parsing unit and a data mapping unit; the protocol identification unit identifies different industrial communication protocols by analyzing the characteristic information of the message; the message parsing unit deeply analyzes the message content and extracts key information; the data mapping unit maps the parsing results under different protocols to a unified standard data model. This module is highly scalable and can dynamically adapt to more industrial communication protocols according to the new protocol rules, providing accurate data support for the multi-protocol conversion in step 4.

[0011] In the step 4, a multi-protocol conversion module is developed, which is used to realize data format conversion between different industrial communication protocols, including a data parsing unit, a format mapping unit and a message generation unit. The data parsing unit is used to receive the standardized data structure output from the multi-protocol parsing module, and analyze the message content of the source protocol to determine the target protocol. The format mapping unit reorganizes the data field, converts the encoding method and converts the unit according to the data structure difference between the source protocol and the target protocol. The format mapping unit includes conversion rules corresponding to industrial protocols such as ModBusTCP protocol, S7 protocol and MQTT protocol. For example, in the conversion from ModBusTCP to S7 protocol, the unit will re-encode the register address and value to adapt to the PLC data structure requirements of the S7 protocol, and in ModBus In the conversion from sTCP to MQTT protocol, the data field needs to be rearranged into the subject and payload of the message. The message generation unit generates a complete message according to the message format of the target protocol, including adding necessary message headers, check information and structures required by other protocols. For example, when converting to the S7 protocol, the generated data frame should have the corresponding header identifier and check field. In the MQTT protocol, the message generation unit will set the QoS level and reservation flag to ensure the correct delivery of the message. Through the collaborative work of the above units, the multi-protocol conversion module can realize seamless data conversion between different industrial communication protocols. The module supports the expansion and adaptation of multiple industrial protocols, can quickly adapt to the conversion tasks of new protocols, and provide reliable technical support for data transmission and interoperability between heterogeneous industrial equipment.

[0012] The virtual simulation ecosystem running in Web mode in step 5 supports users to freely layout equipment by dragging and dropping. Users can select the commonly used industrial equipment model library in the digital twin model library provided in step 2. It also supports the import of custom models and can make the imported models into motion mechanisms. The layout of sites and equipment can be completed by dragging and dropping. It supports device coordinate setting, device rotation, translation and other position adjustments, and can build a highly realistic, real-time interactive digital twin training scene.

[0013] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the method for freely constructing multi-protocol intercommunication intelligent manufacturing digital twin training scenarios.

[0014] An electronic device comprises: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario as described above is implemented.

[0015] The present invention ensures the comprehensiveness and accuracy of data through the application of multimodal data acquisition and processing technology, and provides a data basis for subsequent modeling. Secondly, the construction of the digital twin model and model library of intelligent manufacturing realizes the multi-dimensional information modeling of equipment and process flow, making the constructed model more accurate and complete, and providing rich model resources for training. In addition, the implementation of multi-protocol parsing and multi-protocol conversion breaks the barriers between different industrial communication protocols, realizes seamless data exchange and real-time operation between devices, and enhances the flexibility and scalability of the system. Finally, the free construction of digital twin training scenarios provides users with a highly realistic, real-time interactive training environment, improves the immersion and practicality of the digital twin training of intelligent manufacturing, makes the training effect more significant, and promotes the manufacturing industry to move towards a more intelligent and digital direction, and reserves a group of compound talents with rich practical experience and solid theoretical knowledge for the high-quality development of intelligent manufacturing. The present invention can significantly improve the interoperability, training effect and development efficiency of intelligent manufacturing systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 Flowchart of the present invention Figure 2 This is a flow chart of multimodal acquisition and processing according to the present invention; Figure 3 This is a structural schematic diagram of the intelligent manufacturing digital twin model library of the present invention; Figure 4 This is a flow chart of multi-protocol conversion between heterogeneous industrial equipment according to the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The present invention provides a method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scene. Through a multi-protocol parsing and conversion module, data intercommunication between different industrial equipment is achieved, and a flexible and customizable digital twin three-dimensional training scene is constructed in combination with an intelligent manufacturing digital twin model library. Figure 1-4 Specific embodiments of the present invention are described in detail.

[0020] Step 1: Multimodal data collection and processing: Determine the data sources that need to be collected, including sensor data, equipment status data, and production process data, and collect multimodal data generated in the production process in real time by configuring corresponding sensors and data collection equipment. Preprocess the collected raw data, including data cleaning, noise reduction, missing value filling, standardization and normalization, to ensure data quality and facilitate subsequent modeling and analysis.

[0021] When implementing it, first determine the data sources that need to be collected, including sensor data (such as temperature, pressure, speed), equipment status data (such as operating status, fault information), and production process data (such as process steps, production speed). These data sources are collected in real time through sensors and data acquisition devices deployed at key locations.

[0022] The real-time collected data is first transmitted to the central data processing unit through the network (such as industrial WIFI, industrial Ethernet, fieldbus network). After the data is transmitted to the central data processing unit, it is first filtered and verified to ensure the authenticity and integrity of the data. The filtering process includes checking whether the timestamp is continuous and reasonable, removing abnormal data beyond the predetermined range, and removing duplicate data packets. The verification link ensures that the collected data of multiple devices or sensors are logical through data consistency checks, uses checksums (such as CRC) to verify whether the data packet is damaged during transmission, and identifies anomalies in the data by detecting outliers or abnormal points. Next, the data enters the preprocessing stage, including data cleaning, noise reduction, missing value filling, standardization and normalization. Data cleaning improves data quality by removing noise and outliers, and further purifies data signals through noise reduction techniques such as Fourier transform and wavelet transform.

[0023] Missing value filling uses interpolation, regression analysis or machine learning algorithms to fill in missing data, and finally adjusts the data through standardization and normalization steps to eliminate the differences between data from different sources. Through this step, the problems of incomplete, inaccurate data and difficult analysis in traditional data collection and processing can be effectively solved, the efficiency and accuracy of data collection can be improved, and a reliable data foundation can be provided for the subsequent construction of intelligent manufacturing and digital twin models.

[0024] Step 2: Construction of the digital twin model library for intelligent manufacturing: Based on the multimodal data collected in step 1, the geometric model, mutual relationship, production process and other multidimensional information of intelligent manufacturing equipment are modeled, and the model is adjusted and optimized in combination with the actual situation to ensure the accuracy and completeness of the model. Subsequently, a digital twin model library is established for the model obtained after modeling, which includes digital models of various equipment and process flows, and the models in the model library are classified and labeled to ensure that the models are easy to find and convenient for use in practical training.

[0025] In specific implementation, based on the multimodal data collected and processed in step 1, the present invention establishes a detailed geometric model, a relationship model and a production process model of the equipment. Geometric model modeling uses three-dimensional modeling technology to accurately reproduce the physical form of the equipment, including its internal structure, external dimensions and positional relationship, to ensure that the digital twin model is geometrically consistent with the physical equipment. In the modeling process, the physical characteristics and motion laws of the equipment, such as mass, inertia, and friction, are also considered to improve the accuracy of the model. Relationship modeling uses the system dynamics method to describe the interaction of each device in the production line by analyzing the physical connection and data flow relationship between the devices. Production process modeling describes each step, process flow or manufacturing operation of the production in detail according to the production process. All models are classified and labeled according to attributes, functions, uses, etc. to form a structured digital twin model library. At the same time, a model search engine is developed to quickly retrieve and locate the required models by keywords, attributes, etc. This model library is not only easy to find and retrieve, but also can provide customized solutions for different application scenarios, solving the problem of single model and difficulty in fully reflecting equipment and production processes in traditional manufacturing processes, and improving the flexibility and scalability of intelligent manufacturing systems.

[0026] Step 3: Multi-protocol parsing between heterogeneous industrial devices: A multi-protocol parsing module was developed to parse the message formats of various industrial communication protocols. Different industrial communication protocols include ModBusTCP, S7, and MQTT. By analyzing different industrial communication protocols, we can understand their characteristics such as message format, transmission method, and control signal, which facilitates the conversion of multiple protocols between heterogeneous industrial devices in step 4.

[0027] In specific implementation, the developed multi-protocol parsing module contains multiple functional units, which can effectively parse the message structure of various industrial communication protocols. First, when the data is transmitted to the parsing module, the protocol identification unit will identify the communication protocol used based on the characteristic information of the message. Take several common protocols as examples: the message of the ModBusTCP protocol consists of three parts: message header, function code, and data. The function code is used to indicate the specific operation type (such as reading and writing registers), and the data part contains the specific register address and value; the S7 protocol message contains data area identification, data length field and other parts; and the message structure of the MQTT protocol covers fixed header, variable header and payload, where the variable header contains the topic name and message ID, and the payload is the message content. By accurately identifying the header structure and specific composition of different protocol messages, the parsing module can accurately determine the type of protocol currently used.

[0028] After the protocol identification is completed, the data is immediately passed to the message parsing unit, which performs in-depth parsing according to the specific format of the protocol. For the ModBusTCP protocol, the parsing unit extracts the function code, data address, and register value to determine whether it is a read operation or a write operation; when processing the S7 protocol, the parsing unit extracts device status information and diagnostic data; for the MQTT protocol, the parsing unit decomposes the message type, QoS level, reserved flag, and remaining length in the fixed header, and parses the topic name and message ID (if any) in the variable header, and extracts the message content in the payload. This process enables the parsing unit to convert the data content of various protocols into a format that the system can understand.

[0029] Afterwards, the data enters the data mapping unit, whose task is to map the parsing results under different protocols into a unified standard data model to ensure smooth subsequent processing. For example, the register values ​​in the ModBusTCP protocol will be mapped to specific device parameters, while the messages in the MQTT protocol are mapped to corresponding device operation instructions or status updates according to their topics. With this mapping mechanism, the system can ensure that the parsed data can be seamlessly integrated into other system modules, realizing unified management and efficient use of data.

[0030] Step 4: Multi-protocol conversion between heterogeneous industrial equipment: Based on the multi-protocol analysis in step 3, a protocol conversion module is further designed and developed to realize detailed data format conversion between different industrial communication protocols.

[0031] In the specific implementation, based on the multi-protocol parsing in step 3, a multi-protocol conversion module is developed to realize the data format conversion between different industrial communication protocols. The module includes a data parsing unit, a format mapping unit and a message generation unit. Through the collaborative work of these functional units, the conversion from the source protocol to the target protocol is realized.

[0032] First, the data parsing unit receives the standardized data structure output from the multi-protocol parsing module, analyzes the message content of the source protocol, and determines the target protocol to be converted. For example, the received register data of the ModBusTCP protocol will need to be converted into the data frame of the S7 protocol.

[0033] Next, the data enters the format mapping unit, which is responsible for mapping the data fields of the source protocol to the data format of the target protocol. There are differences in the data structures between different industrial protocols. For example, the register data of ModBusTCP is different from the PLC data format of the S7 protocol. The mapping unit rearranges the data fields through the configured conversion rules to meet the requirements of the target protocol. The mapping process includes the reorganization of data fields, the conversion of data encoding methods, and the conversion of units. For example, in the conversion from ModBusTCP to S7 protocol, the register address and value need to be re-encoded to adapt to the data format and data domain requirements of S7.

[0034] Finally, the converted data enters the message generation unit, which generates a complete target protocol data message according to the message format of the target protocol. For example, when converting to the S7 protocol, the message generation unit will rearrange the data fields according to the message structure of the S7 protocol, and add the necessary message header and verification information to ensure that the data can be correctly identified and processed by the target device. Similarly, when converting to the MQTT protocol, the message generation unit will encapsulate the data into an MQTT message and set the corresponding topic so that the target device can correctly parse and execute it after receiving it.

[0035] Through the collaborative work of the above units, the protocol conversion module can achieve seamless data conversion between different industrial communication protocols. The flexible design of this module enables it to quickly adapt to new protocol conversion tasks according to needs, thereby providing technical support for data transmission and interoperability between heterogeneous industrial equipment.

[0036] Step 5: Free construction of digital twin training scenarios: Build a virtual simulation ecosystem that runs in a Web-based manner. Users can select the commonly used industrial equipment model library in the digital twin model library provided in Step 2. It also supports the import of custom models and can make the imported models into motion structures. The site and equipment layout can be completed by dragging and dropping. It supports device coordinate setting, device rotation, translation and other position adjustments to build a highly realistic, real-time interactive digital twin training scenario.

[0037] During the specific implementation, a web-based virtual simulation ecosystem was built, and users can access and operate the system through a browser. The platform allows users to select existing industrial equipment models from the intelligent manufacturing digital twin model library built in step 2. In addition, the platform supports users to customize the import of new model files, such as CAD format, further broadening the boundaries of scene construction. The system user interface is intuitively designed, providing drag-and-drop site and equipment layout tools, and supports the precise positioning and rotation angle settings of equipment. It also supports users to move interactive components of components in the simulation scene. Users can add models to the three-dimensional scene construction area by simply dragging and dropping, and freely adjust their position, angle and size to achieve rapid construction and precise layout of the scene. Each device and component in the scene can dynamically adjust its properties, such as appearance, material, animation, etc., to simulate different production environments and conditions. The system also supports real-time data integration. Users can connect field sensor data streams to virtual scenes. Users can access the context and API of the simulation environment through JavaScript scripting, obtain real-time information such as the operating status and production data of the equipment, and display them intuitively in the three-dimensional scene, so that users can monitor equipment information in real time and accurately. It also provides users with rich view operations and interactive functions to gain in-depth understanding of the production environment from different angles. Through this freely constructed and highly simulated virtual scene, users can understand and manage the intelligent manufacturing process in an intuitive and comprehensive way, which enhances the immersion and participation of user training.

[0038] The present invention provides an innovative solution that is significantly superior to the existing technology through a multi-protocol intercommunication intelligent manufacturing digital twin training scenario free construction method. First, the implementation of multimodal data acquisition and processing ensures the comprehensiveness and accuracy of the data, providing a reliable foundation for the construction of subsequent models. This not only solves the problem of insufficient or incomplete data in traditional training systems, but also improves the accuracy of the model through data preprocessing (such as noise reduction, standardization, etc.).

[0039] Secondly, the establishment of the digital twin model library for intelligent manufacturing breaks the limitation of the existing training system model being single and difficult to expand. By introducing a multi-dimensional modeling method of geometric models, relationship models, and production process models, the authenticity and integrity of the twin model are ensured. The flexibility and scalability of this model library allow users to freely call and adjust according to actual needs, greatly improving the customization of the scene.

[0040] Compared with existing methods, the most significant innovation of the present invention is the development of a multi-protocol parsing and conversion module between heterogeneous industrial devices. Traditional training systems are usually limited by protocol incompatibility, making it difficult to achieve seamless communication between devices. By supporting multiple industrial protocols (such as ModBusTCP, S7, MQTT) and providing automatic parsing and conversion functions, the present invention ensures smooth data exchange and real-time operation between devices with different protocols, significantly improving the interoperability and flexibility of the system.

[0041] In addition, the Web-based training scene construction platform allows users to achieve device layout and real-time interaction through simple drag-and-drop operations, and supports the import of custom models and dynamic adjustment of scenes. This high-degree-of-freedom construction method not only enhances the immersiveness of training, but also greatly simplifies the operation process in complex environments.

[0042] Compared with the existing system, the present invention freely constructs digital twin training scenarios by comprehensively utilizing multi-protocol parsing and conversion, flexible model libraries, and a Web-based training environment, which significantly improves the practicality and scalability of the system and provides strong technical support for talent training and digital transformation in the field of intelligent manufacturing.

[0043] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the device where the computer-readable storage medium is located executes the method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario as described above. The computer program includes a computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory, and other memories.

[0044] An electronic device comprises: a memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, the method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario as described above is implemented.

[0045] If the module / unit integrated in the electronic device described in this application is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware devices through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented.

[0046] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0047] Computer-readable instructions are stored in a computer-readable storage medium, and the computer-readable instructions are executed by a processor in an electronic device to implement the method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario as described in any of the above embodiments.

[0048] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0049] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0050] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

[0051] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or are inherent to these processes, methods, products or apparatuses.

[0052] Note that the above are only preferred embodiments of the present invention and the principles of the application technology. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention is described in more detail through the above embodiments, the present invention is not limited to the specific embodiments described herein, and may include more other effective embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario, characterized in that: The following steps are included: Step 1: Multimodal data acquisition and processing: Use sensors and data acquisition equipment to collect and process multimodal data in real time; Step 2: Construction of the digital twin model library for intelligent manufacturing: Based on the multimodal data collected in step 1, digital twin models of intelligent manufacturing equipment, process flow, etc. are constructed, and a digital twin model library for intelligent manufacturing is formed; Step 3: Multi-protocol parsing between heterogeneous industrial equipment: Write a multi-protocol parsing module between heterogeneous industrial equipment to parse data packets of various protocols; Step 4: Multi-protocol conversion between heterogeneous industrial equipment: Develop multi-protocol conversion tools to ensure accurate transmission of data and control signals between different protocols; Step 5: Freely construct digital twin training scenarios: Build highly realistic, real-time interactive digital twin training scenarios via the Web.

2. According to claim 1, the method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario is characterized in that: The step 1 specifically includes the following steps: Step 1.1, the data source includes sensor data and production process data, and the data acquisition equipment includes high-precision sensors, data recorders and network interface modules for capturing and transmitting multimodal data; Step 1.2, the real-time collected data is first transmitted to the central data processing unit through the network for preliminary filtering and verification to ensure the authenticity and integrity of the data; Step 1.3, then, the data enters the preprocessing stage, including data cleaning, noise reduction, missing value filling, standardization and normalization: Data cleaning improves data quality by removing noise and outliers, and further purifies data signals through noise reduction techniques such as Fourier transform and wavelet transform; Step 1.4, missing value filling, completes the missing data through interpolation, regression analysis or machine learning algorithms, and finally adjusts the data through standardization and normalization steps to eliminate the differences between data from different sources.

3. The method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario according to claim 2 is characterized in that: In the step 2, the multidimensional information of the intelligent manufacturing equipment is modeled, and the model is adjusted and optimized according to the actual situation to ensure its accuracy and completeness; for the modeled model, a digital twin model library is established, which includes digital models of various equipment and process flows, and the models in the model library are classified and labeled to ensure that the model is easy to find and convenient for practical training; The model in step 2 includes a geometric model, a relationship model and a production process model; the geometric model modeling specifically uses three-dimensional modeling technology to accurately reproduce the physical form of the equipment, including its internal structure, external dimensions and positional relationship, to ensure that the digital twin model is geometrically consistent with the physical equipment; in the modeling process, the physical characteristics and motion laws of the equipment, such as mass, inertia, friction, etc., are also considered to improve the accuracy of the model; Interrelationship modeling describes the interaction of each device in the production line by analyzing the physical connection and data flow relationship between the devices and using the system dynamics method; Production process modeling describes each step, process flow or manufacturing operation of production in detail according to the production process; All models are classified and labeled according to attributes, functions, uses, etc. to form a structured digital twin model library; at the same time, a model search engine is developed to quickly retrieve and locate the required models through keywords, attributes, etc.

4. The method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario according to any one of claims 1 to 3, characterized in that: In step 3, the protocol parsing module includes a protocol identification unit, a message parsing unit and a data mapping unit; the protocol identification unit identifies different industrial communication protocols by analyzing the characteristic information of the message; the message parsing unit deeply analyzes the message content and extracts key information; the data mapping unit maps the parsing results under different protocols to a unified standard data model.

5. The module is highly scalable and can dynamically adapt to more industrial communication protocols according to new protocol rules, providing accurate data support for multi-protocol conversion in step 4.

6. The method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario according to any one of claims 1 to 4, characterized in that: In the step 4, a multi-protocol conversion module is developed, which is used to realize data format conversion between different industrial communication protocols, including a data parsing unit, a format mapping unit and a message generation unit. The data parsing unit is used to receive the standardized data structure output from the multi-protocol parsing module, and analyze the message content of the source protocol to determine the target protocol. The format mapping unit reorganizes the data field, converts the encoding method and converts the unit according to the data structure difference between the source protocol and the target protocol. The format mapping unit includes conversion rules corresponding to industrial protocols such as ModBusTCP protocol, S7 protocol and MQTT protocol. For example, in the conversion from ModBusTCP to S7 protocol, the unit will re-encode the register address and value to adapt to the PLC data structure requirements of the S7 protocol, and in ModBus In the conversion from sTCP to MQTT protocol, the data field needs to be rearranged into the subject and payload of the message. The message generation unit generates a complete message according to the message format of the target protocol, including adding necessary message headers, check information and structures required by other protocols. For example, when converting to the S7 protocol, the generated data frame should have the corresponding header identifier and check field. In the MQTT protocol, the message generation unit will set the QoS level and reservation flag to ensure the correct delivery of the message. Through the collaborative work of the above units, the multi-protocol conversion module can realize seamless data conversion between different industrial communication protocols. The module supports the expansion and adaptation of multiple industrial protocols, can quickly adapt to the conversion tasks of new protocols, and provide reliable technical support for data transmission and interoperability between heterogeneous industrial equipment.

7. The method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario according to any one of claims 1 to 5, characterized in that: The virtual simulation ecosystem running in Web mode in step 5 supports users to freely layout equipment by dragging and dropping. Users can select the commonly used industrial equipment model library in the digital twin model library provided in step 2. It also supports the import of custom models and can make the imported models into motion mechanisms. The layout of sites and equipment can be completed by dragging and dropping. It supports device coordinate setting, device rotation, translation and other position adjustments, and can build a highly realistic, real-time interactive digital twin training scene.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the device where the computer-readable storage medium is located executes the method for freely constructing multi-protocol intercommunication intelligent manufacturing digital twin training scenarios as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a program that can be run on the processor, and when the processor executes the program, a method for freely constructing a multi-protocol intercommunication intelligent manufacturing digital twin training scenario as described in any one of claims 1-7 is implemented.

Images