CN-121999147-A - Digital twin-driven multi-model synchronous teaching method, system, terminal and medium

CN121999147ACN 121999147 ACN121999147 ACN 121999147ACN-121999147-A

Abstract

The invention belongs to the technical field of model teaching, and particularly discloses a digital twin-driven multi-model synchronous teaching method, a system, a terminal and a medium. The method comprises the steps of obtaining modeling information of target equipment, constructing a three-dimensional geometric model behavior model and a signal model based on the modeling information, establishing a mapping relation between the behavior model and corresponding parts in the three-dimensional geometric model, establishing an association relation between the signal model and the behavior model, driving the behavior model to change state according to instructions in a teaching process, synchronously triggering state updating of the three-dimensional geometric model and the signal model, determining a signal flow path in a current working state, mapping the signal flow path to the corresponding parts of the three-dimensional geometric model, and realizing collaborative teaching output of the equipment. By taking the behavior state as a unified control core, synchronous updating and consistent running of multiple models under the same working state are realized. The structure form, the working logic and the signal processing process of the equipment can be kept consistent and corresponding under any working state.

Inventors

Cao Silei
MENG HAO
XU HUIQI
ZENG WEIGUI
LIU MINGGANG
LIANG YUFENG

Assignees

中国人民解放军海军航空大学

Dates

Publication Date: 20260508
Application Date: 20260410

Claims (10)

1. The digital twin-driven multi-model synchronous teaching method is characterized by comprising the following steps of: Obtaining modeling information of target equipment, wherein the modeling information comprises structure information, workflow information and signal processing information; constructing a three-dimensional geometric model for representing the outline structure of the equipment and the hierarchical relationship of the components based on the structure information; Constructing a behavior model for representing the running state of the target equipment and the state change sequence and state conversion relation of the target equipment in different working phases based on the workflow information; constructing a signal model for representing the signal generation, transmission and processing processes of the equipment in different working modes based on the signal processing information; establishing a mapping relation between corresponding parts in the behavior model and the three-dimensional geometric model; establishing an association relation between a signal model and a behavior model; In the teaching process, receiving an instruction aiming at target equipment, driving a behavior model to change the state according to the instruction, wherein the change of the state is used for representing the change of the running state of the target equipment, and synchronously triggering the corresponding state updating of a three-dimensional geometric model and a signal model; Determining a signal flow path of the target equipment in the current working state based on the updated signal model, and mapping the signal flow path to a part or structure position corresponding to the three-dimensional geometric model; And according to the mapping relation between the signal flow path and the three-dimensional geometric model, carrying out cooperative teaching output on the structural state, the working principle and the signal processing process of the target equipment.
2. The digital twin driven multi-model synchronous teaching method according to claim 1, wherein establishing a mapping relation between corresponding components in the behavior model and the three-dimensional geometric model and establishing an association relation between the signal model and the behavior model comprises: defining each working stage or working state in the behavior model as a behavior state node; Configuring at least one corresponding structure part identification set for each behavior state node, wherein the structure part identification set is used for indicating three-dimensional geometric model parts participating in work under the behavior state; when the behavior model is subjected to state switching, determining a three-dimensional geometric model component which needs to be activated, displayed or participate in teaching based on a structural component identification set corresponding to a current behavior state node; configuring a signal processing mode or a signal flow identifier corresponding to each behavior state node; When the behavior model is switched, a signal flow path or a signal processing unit which needs to be started in the signal model is determined based on a signal processing mode or a signal flow identifier corresponding to the current behavior state node, and an association relation between the signal model and the behavior model is established.
3. The digital twinned driven multimodal synchronous teaching method of claim 2, wherein, when the behavior state nodes in the behavior model are associated with the three-dimensional geometric model and the signal model, the generating of the set of structural component identifiers and the set of signal processing elements comprises at least one of: Based on a manual configuration mode, pre-configuring a structural component identification set corresponding to each behavior state node in the behavior model and a signal processing mode or a signal flow identification corresponding to the behavior state node according to design data or teaching requirements of target equipment; Analyzing a structural component identifier associated with a current behavior state node in a component hierarchy relation or an assembly relation of a three-dimensional geometric model based on an automatic analysis mode, generating a corresponding structural component identifier set, synchronously analyzing a signal interface relation or a signal connection relation corresponding to the structural component identifier, and determining a signal processing element associated with the behavior state node; Based on a rule generation mode, according to a preset component participation rule and a signal processing rule and according to a working mode, a working stage or a functional type corresponding to a behavior state node, structural component identifiers meeting rule conditions are screened from a component set of a three-dimensional geometric model to generate a corresponding structural component identifier set, and a signal processing unit or a signal flow path matched with the structural component identifier set is screened from a signal model.
4. The digital twin-driven multi-model synchronous teaching method according to claim 3, wherein the generating of the structural component identification set and the signal processing element set is based on an automatic analysis mode, when the behavior model is switched, the behavior state nodes are analyzed and inferred based on an inference model, and the motion actions of the structural components corresponding to the current behavior state are determined by combining the structural component identification set and the signal processing element set, and the method specifically comprises the following steps: inputting behavior state nodes with state switching in the behavior model into an inference model, and analyzing the behavior state nodes to obtain behavior semantic information representing the behavior state; Based on the behavior semantic information, the action type and the action constraint information corresponding to the behavior state are obtained through reasoning by an inference model, and the signal processing mode or the signal flow type corresponding to the behavior state is obtained through synchronous reasoning; for each structural component in the structural component identification set, determining a corresponding motion action of each structural component in the current behavior state by combining the component hierarchical relation or the assembly relation of each structural component in the three-dimensional geometric model; Determining a signal processing unit or a signal flow path which needs to be started in the current behavior state in a signal processing element set based on a signal processing mode or a signal flow type, and establishing an association relation between a signal model and a behavior model; And outputting motion descriptions or motion parameters corresponding to the structural components to drive the corresponding structural components in the three-dimensional geometric model to generate motion changes consistent with the behavior states, and synchronously driving the signal model to execute signal processing teaching according to the determined signal flow path.
5. The digital twin-driven multi-model synchronous teaching method according to claim 4, wherein the inference model is a model obtained through training, and the action association relationship between the behavior model and the three-dimensional geometric model and the signal association relationship between the behavior model and the signal model are established in the course of analyzing and reasoning behavior state nodes through the inference model, and specifically comprising: In a model training stage, a training data set containing a behavior state description sample and corresponding semantic annotations is obtained, the semantic annotations at least comprise behavior semantic annotations and signal semantic annotations, the behavior semantic annotations at least comprise action types, action object types and action constraint information, and the signal semantic annotations at least comprise signal processing modes or signal flow types; Training the inference model based on the training data set to enable the inference model to establish a corresponding relation between the behavior state description and the behavior semantic annotation and between the behavior semantic annotation and the signal semantic annotation, so as to obtain a trained inference model; When the behavior model is subjected to state switching, inputting a state description corresponding to the behavior state node into a trained reasoning model; The trained reasoning model receives the state description in the operation stage, and identifies the action type, the action object type and the action constraint information corresponding to the behavior state by extracting semantic elements from the state description, and synchronously identifies the signal processing mode or the signal flow type corresponding to the behavior state; combining and standardizing the extracted behavior semantic elements to obtain structural action semantic information for representing behavior states, wherein the structural action semantic information is used for indicating movement actions of structural components in the three-dimensional geometric model; Combining and standardizing the extracted signal semantic elements to obtain signal semantic information for representing the behavior state, wherein the signal semantic information is used for indicating a signal processing unit or a signal flow path which needs to be started in the signal model, and an action association relationship between the behavior model and the three-dimensional geometric model and a signal association relationship between the behavior model and the signal model are respectively established.
6. The digital twin driven multi-model synchronous teaching method according to claim 4 or 5, wherein the signal flow path or the signal processing unit corresponding to the current behavior state is selected and started in the signal model based on the signal semantic information output by the inference model, and the linkage operation of the signal model and the behavior model is realized, and the method comprises the following steps: Pre-constructing a plurality of signal flow paths or a plurality of signal processing unit combinations in a signal model, and configuring corresponding flow identifiers or mode identifiers for each signal flow path or signal processing unit; After the behavior model is subjected to state switching, signal semantic information is obtained, and a signal flow identifier or a mode identifier matched with the current behavior state is determined according to the signal semantic information; selecting a corresponding signal flow path or signal processing unit from a plurality of signal flow paths or signal processing unit combinations in the signal model based on the signal flow identification or the mode identification; And enabling the selected signal flow path or the signal processing unit to enable the signal model to execute signal generation, transmission or processing processes according to the determined signal flow path, so as to realize signal processing teaching consistent with the current behavior state.
7. The digital twin-driven multi-model synchronous teaching method according to any of claims 1-5, wherein when the behavior model changes state, the behavior state node is used as a unified trigger source, and synchronous update control is performed on the three-dimensional geometric model and the signal model to realize the consistent operation of the multiple models in the current behavior state, and the method specifically comprises: When the behavior model changes state, generating a corresponding state change event, and taking the state change event as a triggering condition for multi-model synchronous update; based on the state change event, synchronously triggering the movement of a structural component corresponding to the current behavior state node in the three-dimensional geometric model to update the starting or switching of a signal flow path or a signal processing unit corresponding to the current behavior state in the trigger signal model.
8. A digital twinned multi-model synchronous teaching system for implementing the digital twinned multi-model synchronous teaching method according to claim 1, characterized in that the system comprises: The modeling module is used for acquiring modeling information of the target equipment, wherein the modeling information comprises structure information, workflow information and signal processing information, a three-dimensional geometric model for representing the appearance structure and the part hierarchical relation of the equipment is constructed based on the structure information, a behavior model for representing the state change sequence and the state conversion relation of the equipment in different working phases is constructed based on the workflow information, and a signal model for representing the signal generation, transmission and processing processes of the equipment in different working modes is constructed based on the signal processing information; The model association module is used for establishing a mapping relation between the corresponding parts in the behavior model and the three-dimensional geometric model and establishing an association relation between the signal model and the behavior model; the element analysis module is used for generating a structural component identification set and a signal processing element set based on an automatic analysis mode when the behavior state nodes in the behavior model are associated with the three-dimensional geometric model and the signal model; The reasoning module is used for analyzing and reasoning the behavior state nodes when the behavior model is subjected to state switching, and outputting structural action semantic information and signal semantic information for representing the current behavior state; The structure driving module is used for determining corresponding motion actions of each structural component in the current behavior state based on the structural action semantic information and combining the structural component identification set and the component hierarchical relation or the assembly relation in the three-dimensional geometric model, and driving the corresponding structural components in the three-dimensional geometric model to perform motion update; The signal driving module is used for selecting and starting a signal flow path or a signal processing unit corresponding to the current behavior state in the signal model based on the signal semantic information, so that the signal model executes signal generation, transmission or processing according to the determined signal flow path; The synchronous control module is used for synchronously triggering the structure update of the three-dimensional geometric model and the signal flow switching of the signal model by taking the behavior state node as a unified triggering source when the behavior model is subjected to state change, and carrying out consistency control on the running states of the multiple models; the teaching output module is used for carrying out cooperative teaching output on the structural state, the working principle and the signal processing process of the target equipment based on the synchronous updating result of the three-dimensional geometric model and the signal model.
9. A terminal, comprising: the memory is used for storing a multi-model synchronous teaching program of the digital twin drive; a processor for implementing the steps of the digital twinned multi-model synchronous teaching method according to claim 1 when executing the digital twinned multi-model synchronous teaching system.
10. A computer readable storage medium storing computer instructions that when read by a computer, the computer performs the digital twinned driven multimodal synchronous teaching method of claim 1.

Description

Digital twin-driven multi-model synchronous teaching method, system, terminal and medium Technical Field The invention belongs to the technical field of model teaching, and particularly relates to a digital twin-driven multi-model synchronous teaching method, a system, a terminal and a medium. Background With the continuous improvement of the integration level and the functional complexity of a complex device system, the structural composition, the workflow and the signal processing mechanism of the device increasingly show the characteristics of multiple layers, multiple modes and strong coupling. In order to meet the demands of principle understanding, operation training and maintenance teaching in the process of equipment research, use and guarantee, the digital teaching technology gradually develops from a traditional two-dimensional drawing and static three-dimensional model to a digital twin-driven multi-model collaborative teaching direction. In the prior art, aiming at the equipment teaching and simulation requirements, a three-dimensional geometric model is generally adopted to express the appearance structure and the component level of the equipment, and the operation sequence and the state change process of the equipment in different working phases are described by combining a flow chart, a state machine or a script mode, and in a scene related to signal processing, the signal generating, transmitting and processing processes can be modeled through a signal flow chart or a signal simulation module. However, the prior art still has certain defects in practical application, on one hand, the existing teaching mode takes the pre-fabricated video, moving pictures or script driven animation demonstration as a core, the teaching process essentially belongs to pre-recorded or pre-arranged demonstration content, dynamic deduction and real-time response are difficult to carry out according to the current working state or user operation behavior of the equipment, linkage update among the structural state, the behavior state and the signal processing process cannot be realized in the teaching process, and the interactivity and the expandability of the teaching system are limited. On the other hand, when the structure display and the signal flow switching are realized in the prior art, a large amount of manual preset mapping relations, fixed rules or script configurations are generally relied on to specify the participation parts and the signal flow under different working states, and when the equipment model, the working mode or the teaching requirement changes, the manual configuration or the scene manufacturing is required to be carried out again, so that the implementation cost is high, the maintenance workload is large, and the teaching requirement under multiple states and modes of complex equipment is difficult to adapt. Disclosure of Invention Aiming at the problems in the prior art, the invention provides a digital twin-driven multi-model synchronous teaching method, a system, a terminal and a medium, which are used for solving the problems that prerecording or prerecording display content in the background art is difficult to dynamically deduct and respond in real time according to the current working state or user operation behavior of equipment, the linkage update among the structural state, the behavior state and the signal processing process cannot be realized in the teaching process, the interactivity and the expandability of a teaching system are limited, and meanwhile, the problems that the prior art generally depends on a large number of manual preset mapping relations, fixed rules or script configuration to specify the participation parts and the signal flow under different working states when the structural display and the signal flow switching are realized, and the teaching requirements of complex equipment under multi-state and multi-mode are difficult to adapt. The technical scheme adopted by the invention is as follows: in a first aspect, the present application provides a digital twin driven multi-model synchronous teaching method comprising the steps of: Obtaining modeling information of target equipment, wherein the modeling information comprises structure information, workflow information and signal processing information; constructing a three-dimensional geometric model for representing the outline structure of the equipment and the hierarchical relationship of the components based on the structure information; Constructing a behavior model for representing the running state of the target equipment and the state change sequence and state conversion relation of the target equipment in different working phases based on the workflow information; constructing a signal model for representing the signal generation, transmission and processing processes of the equipment in different working modes based on the signal processing information; establishing a mapping relation between correspo