Digital twin-driven equipment support saturation state verification system
The equipment support system built using digital twin technology solves the problems of high cost, long cycle, and disconnect between virtual and real systems in existing verification methods. It enables accurate identification of equipment support status and bottleneck analysis, improving the efficiency and adaptability of verification.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-25
- Publication Date
- 2026-03-31
AI Technical Summary
Existing methods for verifying the saturation state of equipment support are costly, time-consuming, and difficult to reproduce complex battlefield environments. The simulation model and the physical entity are disconnected, and the simulation model has poor versatility and scalability. It also lacks a multi-dimensional saturation index system and a virtual-physical collaborative verification mechanism.
A digital twin-driven equipment support system is constructed, comprising a physical entity layer, a data acquisition and transmission layer, a virtual twin layer, a saturation state simulation and verification layer, and an application service layer. A multi-dimensional twin model and Kalman filtering technology are used to achieve real-time collaboration between the virtual and real worlds. A multi-dimensional evaluation index system is constructed by combining discrete event simulation and multibody dynamics simulation.
It has improved the accuracy of equipment support status verification, reduced verification costs, shortened the cycle, enhanced scenario adaptability and versatility, and can quickly adapt to different equipment and mission scenarios, providing intelligent analysis capabilities to identify bottleneck resources.
Smart Images
Figure CN121766079A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment support informatization and digital twin technology, specifically to a digital twin-driven equipment support saturation state verification system. Background Technology
[0002] Equipment support saturation refers to a critical state in a specific mission scenario where equipment support resources (personnel, spare parts, tools, etc.) reach their maximum capacity, making it impossible to further improve support efficiency through optimized scheduling. Accurately verifying saturation is a core basis for equipment support system planning, resource allocation optimization, and emergency response plan development.
[0003] Existing equipment support saturation verification methods have the following main drawbacks: First, they rely on physical experiments and empirical formulas. For example, conducting physical experiments by constructing scaled-down support scenarios is not only costly and time-consuming, but also difficult to reproduce the support process in complex battlefields or extreme environments. Second, there is a "disconnect between virtual and real" problem between simulation models and physical entities. Traditional simulation systems mostly use static models, which cannot reflect the dynamic characteristics of equipment failure evolution and resource consumption fluctuations in real time, resulting in a large deviation between verification results and actual conditions. Third, the scenario coverage is insufficient. Existing systems are mostly designed for single equipment or fixed mission scenarios, making it difficult to quickly adapt to the saturation verification needs of different equipment models and mission intensities, resulting in poor versatility and scalability.
[0004] Digital twin technology, by constructing virtual mirrors of physical entities, enables real-time fusion and dynamic interaction of multi-source data, providing a technical path to solve the aforementioned problems. For example, existing technologies have applied digital twins to equipment modeling and maintenance, achieving real-time monitoring of equipment status and fault prediction. However, a dedicated verification system for equipment support saturation states has not yet been developed, lacking a complete technical solution from data acquisition and model building to saturation judgment, particularly in terms of multi-dimensional saturation indicator systems and virtual-physical collaborative verification mechanisms. Therefore, there is an urgent need to develop an equipment support saturation state verification system based on digital twins to improve the accuracy, efficiency, and versatility of verification.
[0005] To address this, a digital twin-driven equipment support saturation state verification system is proposed. Summary of the Invention
[0006] The purpose of this invention is to provide a digital twin-driven equipment support saturation state verification system to solve the problems mentioned in the background art.
[0007] To achieve the above objectives, the present invention provides the following technical solution: a digital twin-driven equipment support saturation state verification system, comprising a physical entity layer, a data acquisition and transmission layer, a virtual twin layer, a saturation state simulation and verification layer, and an application service layer, wherein each layer sequentially realizes data interaction and functional collaboration;
[0008] The physical entity layer includes a cluster of equipment to be supported, support resource units, and environmental sensing devices. The support resource units include maintenance tools, spare parts inventory, and support personnel terminals. The environmental sensing devices are used to collect environmental parameters such as temperature, humidity, and electromagnetic interference.
[0009] The data acquisition and transmission layer connects the physical entity layer and the virtual twin layer, and includes a multi-source data acquisition module, a data preprocessing module, and a secure transmission module. The multi-source data acquisition module uses sensor networks, RFID readers and writers and the OPCUA protocol to acquire equipment status, resource consumption and environmental data. The secure transmission module uses the TLS / SSL encryption protocol to realize data transmission.
[0010] The virtual twin layer is the core computing layer of the system, including a twin model construction module, a multi-source data fusion module, and a model dynamic update module. The twin model construction module uses a combination of parametric modeling and finite element analysis to construct multi-dimensional twin models of equipment, resources, and environment. The multi-source data fusion module uses the Kalman filter algorithm to eliminate data noise and achieve spatiotemporal consistency processing.
[0011] The saturation state simulation and verification layer includes a scenario configuration module, a simulation operation module, a saturation judgment module, and a result analysis module. The scenario configuration module supports customizing the guarantee task intensity, resource allocation amount, and environmental interference level. The saturation judgment module constructs a multi-dimensional evaluation index system based on guarantee resource utilization rate, task response delay, and fault handling success rate.
[0012] The application service layer includes a visualization module, a data management module, and a decision support module. The visualization module uses WebGL technology to realize the three-dimensional dynamic presentation of the verification process.
[0013] Preferably, the virtual twin layer's twin model construction module includes a geometric modeling submodule, a physical modeling submodule, and a behavioral modeling submodule;
[0014] The geometric modeling submodule uses CAD technology and point cloud scanning to achieve a 1:1 reproduction of the equipment structure with millimeter-level accuracy.
[0015] The physical modeling submodule uses finite element analysis and computational fluid dynamics to simulate the mechanical properties and heat conduction laws of equipment.
[0016] The behavioral modeling submodule combines mechanistic models with LSTM neural networks to reproduce the equipment failure evolution and support resource scheduling process.
[0017] Preferably, the simulation operation module of the saturation state simulation and verification layer adopts a combination of discrete event simulation and multibody dynamics simulation, supporting two operation modes;
[0018] The offline pre-simulation mode calculates saturation thresholds for multiple scenarios based on historical data;
[0019] The online verification mode receives physical entity data in real time, enabling saturation state simulation that synchronizes virtual and real data, with a model update delay of ≤100ms.
[0020] Preferably, the evaluation index system of the saturation judgment module includes core indicators and auxiliary indicators;
[0021] Key metrics include maintenance personnel workload, spare parts inventory turnover, and equipment repair timeliness.
[0022] The auxiliary indicators include the environmental interference intensity coefficient and the equipment failure severity coefficient, and the weight of each indicator is determined by the analytic hierarchy process.
[0023] Preferably, the preprocessing module of the data acquisition and transmission layer employs outlier detection, data interpolation, and data standardization to output structured data with a unified format, supporting seamless integration with the model parameters of the virtual twin layer.
[0024] Compared with the prior art, the beneficial effects of the present invention are:
[0025] 1. Real-time collaboration between virtual and physical models to improve verification accuracy: By using multi-dimensional twin models and Kalman filter data fusion technology, the state deviation between the virtual model and the physical entity is ≤5%, which solves the problem of "disconnect between virtual and physical" in traditional simulation and makes the saturation verification results closer to the actual protection scenario.
[0026] 2. Reduce verification costs and shorten verification cycle: Using virtual simulation to replace some physical tests can reduce the cost of physical tests by more than 70%, and shorten the saturation verification cycle of a single scenario from 15-30 days in the traditional method to 1-3 days.
[0027] 3. Strong adaptability and versatility: It supports custom scene parameters and typical scene template calls, and can be adapted to different types of equipment such as armored equipment and aero engines, as well as different mission scenarios such as peacetime operation and maintenance and wartime emergency support, without the need to reconstruct the core modules of the system.
[0028] 4. Outstanding intelligent analysis capabilities: Through a multi-dimensional indicator system and sensitivity analysis, it can not only accurately identify saturation states, but also locate bottleneck resources, providing data support for system optimization and improving the scientific nature of decision-making. Attached Figure Description
[0029] Figure 1 This is a schematic diagram of the system of the present invention. Detailed Implementation
[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.
[0031] Please see Figure 1 The present invention provides a technical solution: a digital twin-driven equipment support saturation state verification system, comprising a physical entity layer, a data acquisition and transmission layer, a virtual twin layer, a saturation state simulation and verification layer, and an application service layer. Each layer achieves data interaction and functional linkage through standardized interfaces, forming a closed-loop system.
[0032] The physical entity layer serves as the real-world foundation for verification, encompassing the equipment clusters to be supported (such as armored vehicles and aircraft engines), support resource units (maintenance tool vehicles, intelligent spare parts warehouses, and intelligent terminals worn by support personnel), and environmental sensing equipment (temperature and humidity sensors, vibration sensors, and electromagnetic interference monitors). The intelligent spare parts warehouse uses RFID tags to automatically record the entry and exit of spare parts, while the support personnel terminals use BeiDou positioning and 4G / 5G communication to report their location and operational status in real time.
[0033] The data acquisition and transmission layer acts as a "data bridge," comprising a multi-source data acquisition module, a data preprocessing module, and a secure transmission module. The multi-source data acquisition module employs a hybrid acquisition method combining sensors, industrial protocols, and manual input: it collects equipment fault characteristic parameters through sensors such as vibration and temperature sensors; it obtains resource consumption data from the intelligent spare parts warehouse and tool management system via the OPC UA protocol; it collects task execution status data through personnel terminals; and it achieves full coverage acquisition of environmental parameters through a distributed sensor network. The data preprocessing module uses... Outliers are removed using criteria, missing data is interpolated using a cubic spline function, and all data is standardized to JSON format. The secure transmission module employs TLS / SSL encryption protocols and edge computing nodes to achieve encrypted data transmission and local caching, reducing network latency and the risk of data leakage.
[0034] The virtual twin layer is the core computing unit of the system, comprising a twin model construction module, a multi-source data fusion module, and a model dynamic update module. The twin model construction module employs multi-dimensional modeling methods encompassing geometry, physics, and behavior: the geometric model is built using SolidWorks and point cloud scanning technology to achieve millimeter-level reconstruction of equipment and resources; the physical model uses finite element analysis (FEA) to simulate equipment structural stress and thermal conductivity characteristics, and computational fluid dynamics (CFD) to simulate the impact of the environment on the support process; the behavioral model combines mechanistic models (such as equipment fault propagation models) with LSTM neural networks, using historical support data for training to accurately reproduce fault evolution and resource scheduling processes. The multi-source data fusion module uses a Kalman filter algorithm to fuse real-time data and model prediction data, eliminating measurement noise and ensuring spatiotemporal consistency of the data. The model dynamic update module is based on a collaborative architecture of edge computing and cloud computing. Real-time data (such as equipment vibration data) is updated with model parameters within 100ms via edge nodes, while historical statistical data is processed in the cloud to complete model optimization iterations.
[0035] The saturation state simulation and verification layer implements core verification functions, including a scenario configuration module, a simulation operation module, a saturation judgment module, and a result analysis module. The scenario configuration module provides a visual scenario editing interface, supporting user-defined parameters such as equipment quantity, fault type, task intensity (e.g., number of faulty equipment per hour), resource allocation, and environmental interference level. It also includes built-in typical scenario templates such as armored equipment cluster support and aero-engine maintenance. The simulation operation module combines discrete event simulation and multibody dynamics simulation. Discrete event simulation is used to simulate the triggering and execution process of support tasks, while multibody dynamics simulation is used to simulate the physical operations (e.g., component disassembly and installation) during equipment maintenance. The two are synchronized through a data interface. The saturation judgment module constructs a multi-dimensional evaluation index system. Core indicators include maintenance personnel workload rate (actual workload / maximum working capacity), spare parts inventory turnover rate (number of spare parts consumed / total inventory), and equipment repair timeliness rate (number of equipment repaired on time / total number of faulty equipment). Auxiliary indicators include environmental interference intensity coefficient (calculated based on temperature, humidity, and electromagnetic interference) and fault severity coefficient (based on fault impact range scoring). The weight of each indicator is determined using the analytic hierarchy process (AHP). When the comprehensive score reaches a preset threshold (e.g., 85 points) or any core indicator exceeds a critical value (e.g., personnel workload rate ≥ 90%), the system is judged to have reached saturation. The results analysis module uses a sensitivity analysis algorithm to identify key bottleneck resources affecting the saturation state (e.g., specific spare parts models, senior maintenance personnel) and calculates the saturation critical value under different scenarios.
[0036] The application service layer provides users with interactive and decision support, including a visualization module, a data management module, and a decision support module. The visualization module uses WebGL technology to construct a 3D scene, presenting a real-time synchronized virtual and real-world support process. It uses color coding (green - normal, yellow - alert, red - saturation) to display resource and task status and supports data drill-down (e.g., clicking on a piece of equipment to view detailed fault and maintenance records). The data management module stores historical verification data, model parameters, and scenario configuration files in a distributed database, supporting data querying, exporting, and version management. The decision support module generates resource optimization suggestions based on the verification results, such as "When the task intensity reaches 15 faulty pieces of equipment per hour, 2 additional senior maintenance personnel and 5 sets of specialized tools are required," and outputs a standardized verification report.
[0037] Example 1
[0038] This embodiment uses the saturation state verification of an armored equipment cluster in a field support scenario as an example to illustrate the specific application process of the system.
[0039] Step 1: System Deployment and Initialization. The physical layer deploys 10 armored vehicles (including key components such as engines and transmission systems), 2 maintenance tool vehicles, 1 intelligent spare parts warehouse (containing 50 commonly used spare parts), 5 support personnel (wearing smart wristbands), and 10 environmental sensors (deployed in the support area). The data acquisition and transmission layer connects to the equipment sensors via a CAN bus, to the intelligent spare parts warehouse via RFID readers, and to the support personnel's wristbands via a 4G network, completing equipment communication testing and parameter configuration.
[0040] Step 2: Twin Model Construction and Calibration. The twin model construction module of the virtual twin layer constructs a geometric model based on armored equipment CAD drawings and point cloud scan data, achieving an accuracy of 0.1mm. The physical model uses ANSYS software to construct an engine thermodynamic model, setting the normal operating temperature threshold to 80-100℃. The behavioral model trains an LSTM neural network using 500 sets of historical maintenance data, achieving a fault type identification accuracy of ≥95%. The multi-source data fusion module incorporates initial data (such as equipment idling vibration values and initial spare parts inventory quantities) to complete the calibration of the virtual model and physical entity, ensuring that the initial state deviation is ≤3%.
[0041] Step 3: Scenario Configuration and Simulation Execution. In the saturation state simulation and verification layer, the scenario configuration module selects the "Field Emergency Support" template and sets the task parameters: trigger random failures of 2 pieces of equipment per hour, environmental interference level is "moderate rain + electromagnetic interference," and spare parts replenishment delay is 2 hours. After the simulation execution module starts, the discrete event simulation module triggers equipment failure events (such as engine overheating of equipment No. 3 and transmission system jamming of equipment No. 7), and the multibody dynamics simulation module simulates the physical process of maintenance personnel disassembling engine components. Both are synchronized, with the simulation time step set to 1 second.
[0042] Step 4: Saturation State Judgment and Analysis. The saturation judgment module collects simulation data in real time: when the system reaches the 4th hour of operation, the maintenance personnel load rate reaches 92% (exceeding the 90% critical value), the spare parts inventory turnover rate drops to 12% (below the 15% critical value), the equipment repair timeliness rate drops to 78% (below the 80% critical value), and the comprehensive score reaches 88 points. The system determines that it has reached the saturation state and triggers an early warning. The results analysis module, through sensitivity analysis, finds that "the number of senior maintenance personnel" and "critical spare parts inventory" are the main bottleneck resources.
[0043] Step 5: Results Output and Decision Support. The application service layer's visualization module presents the saturation state in a 3D scene: red highlights indicate overloaded maintenance personnel and insufficient spare parts, while yellow highlights equipment with delayed repairs. The data management module stores the verification data (including 1200 real-time data points and 20 event records). The decision support module outputs suggestions: adding 2 senior maintenance personnel and supplementing 10 types of key spare parts can raise the saturation threshold to 3 faulty pieces of equipment per hour.
[0044] This embodiment, through system operation verification, achieves accurate identification and bottleneck analysis of the saturation state of armored equipment support. The verification cycle is only 2 days, which is 90% shorter than traditional physical tests, providing effective support for the optimization of support resources.
[0045] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A digital twin-driven equipment support saturation state verification system, characterized in that: It includes a physical entity layer, a data acquisition and transmission layer, a virtual twin layer, a saturation state simulation and verification layer, and an application service layer, with each layer sequentially realizing data interaction and functional collaboration; The physical entity layer includes a cluster of equipment to be supported, support resource units, and environmental sensing devices. The support resource units include maintenance tools, spare parts inventory, and support personnel terminals. The environmental sensing devices are used to collect environmental parameters such as temperature, humidity, and electromagnetic interference. The data acquisition and transmission layer connects the physical entity layer and the virtual twin layer, and includes a multi-source data acquisition module, a data preprocessing module, and a secure transmission module. The multi-source data acquisition module uses sensor networks, RFID readers and writers, and OPC UA protocol to acquire equipment status, resource consumption, and environmental data. The secure transmission module uses TLS / SSL encryption protocol to realize data transmission. The virtual twin layer is the core computing layer of the system, including a twin model construction module, a multi-source data fusion module, and a model dynamic update module. The twin model construction module uses a combination of parametric modeling and finite element analysis to construct multi-dimensional twin models of equipment, resources, and environment. The multi-source data fusion module uses the Kalman filter algorithm to eliminate data noise and achieve spatiotemporal consistency processing. The saturation state simulation and verification layer includes a scenario configuration module, a simulation operation module, a saturation judgment module, and a result analysis module. The scenario configuration module supports customizing the guarantee task intensity, resource allocation amount, and environmental interference level. The saturation judgment module constructs a multi-dimensional evaluation index system based on guarantee resource utilization rate, task response delay, and fault handling success rate. The application service layer includes a visualization module, a data management module, and a decision support module. The visualization module uses WebGL technology to realize the three-dimensional dynamic presentation of the verification process.
2. The digital twin-driven equipment support saturation state verification system according to claim 1, characterized in that: The virtual twin layer's twin model construction module includes a geometric modeling submodule, a physical modeling submodule, and a behavioral modeling submodule; The geometric modeling submodule uses CAD technology and point cloud scanning to achieve a 1:1 reproduction of the equipment structure with millimeter-level accuracy. The physical modeling submodule uses finite element analysis and computational fluid dynamics to simulate the mechanical properties and heat conduction laws of equipment. The behavioral modeling submodule combines mechanistic models with LSTM neural networks to reproduce the equipment failure evolution and support resource scheduling process.
3. The digital twin-driven equipment support saturation state verification system according to claim 1, characterized in that: The simulation operation module of the saturation state simulation and verification layer adopts a combination of discrete event simulation and multibody dynamics simulation, supporting two operation modes. The offline pre-simulation mode calculates saturation thresholds for multiple scenarios based on historical data; The online verification mode receives physical entity data in real time, enabling saturation state simulation that synchronizes virtual and real data, with a model update delay of ≤100ms.
4. The digital twin-driven equipment support saturation state verification system according to claim 1, characterized in that: The evaluation index system of the saturation judgment module includes core indicators and auxiliary indicators; Key metrics include maintenance personnel workload, spare parts inventory turnover, and equipment repair timeliness. The auxiliary indicators include the environmental interference intensity coefficient and the equipment failure severity coefficient, and the weight of each indicator is determined by the analytic hierarchy process.
5. The digital twin-driven equipment support saturation state verification system according to claim 1, characterized in that: The preprocessing module of the data acquisition and transmission layer employs outlier detection, data interpolation, and data standardization to output structured data with a unified format, supporting seamless integration with the model parameters of the virtual twin layer.