Analog simulation control method and system for stratospheric airship based on digital twinning

Abstract

The invention discloses a stratospheric airship analogue simulation control method and system based on digital twinning, and belongs to the technical field of aircraft digital engineering.The method comprises the following steps that stratospheric airship digital twinning bodies are constructed, and the stratospheric airship digital twinning bodies comprise online digital twinning bodies and offline digital twinning bodies; the state data of the stratospheric airship entity is obtained in real time through the online digital twinborn body, parameter setting and predictive analysis are conducted on the offline digital twinborn body, and when the predictive analysis result reaches a set value, the stratospheric airship entity is obtained. And the online digital twinborn body converts a prediction analysis result into a control instruction and sends the control instruction to the entity parameter setting device to perform parameter setting on the stratospheric airship entity. Meanwhile, the invention discloses a system based on the method, by adopting the digital twinning-based stratospheric airship analogue simulation control method and the digital twinning-based stratospheric airship analogue simulation control system, virtual-real interaction operation of a stratospheric airship system is realized, and a reliable and convenient digital means is provided for transformation and optimization of the stratospheric airship based on a digital twinning technology.

Description

Technical Field

[0001] The present invention relates to the field of aircraft digital engineering technology, and in particular to a stratospheric airship simulation control method and system based on digital twin. Background Art

[0002] Stratospheric airships are aircraft that rely on buoyancy to maintain their flight altitude and can stay in the lower stratosphere for a long time. Stratospheric airships and their applications have important industrial value. Together with aerospace and aviation equipment, they can form a high, medium and low equipment system in terms of altitude, pushing air-space integrated equipment to a higher level and truly realizing seamless integration of air-space. Stratospheric airships are usually used for tasks such as high-altitude communications, environmental monitoring, and meteorological observation, so the requirements for their performance and reliability are very high.

[0003] Existing airship simulations use integrated simulation techniques. For example, the patent with announcement number CN118780099B discloses an integrated stratospheric airship full system performance simulation platform, which centrally deploys multiple subsystem models involved in stratospheric airship simulation on the same simulation computer. The multiple subsystem models exchange data indirectly through shared memory through defined input and output interfaces, thereby improving the simulation efficiency and scalability of the simulation platform. However, there are still problems such as large time lag and data imbalance in the fusion of online airship sensor data and offline simulation data. Summary of the invention

[0004] The purpose of the present invention is to provide a stratospheric airship simulation control method and system based on digital twin to solve the above technical problems.

[0005] To achieve the above purpose, the present invention provides a stratospheric airship simulation control method based on digital twin, and the specific steps are as follows: Step S1: Acquire the physical structure data, state data and environment data of the stratospheric airship and establish a physical database; Step S2: constructing a digital twin of the stratospheric airship according to the entity database, wherein the digital twin of the stratospheric airship includes an online digital twin and an offline digital twin; Step S3: the online digital twin obtains the status data of the stratospheric airship entity in real time, and the offline digital twin keeps the status synchronized with the online digital twin; Step S4: Parameter setting and predictive analysis are performed in the offline digital twin. When the predictive analysis result reaches the set value, the online digital twin converts the predictive analysis result into a control instruction and sends it to the entity parameter setting device to perform parameter setting on the stratospheric airship entity.

[0006] Preferably, both the online digital twin and the offline digital twin include a shared parameter server, a stratospheric airship digital model and an operational function model, and both the stratospheric airship digital model and the operational function model are connected to the shared parameter server.

[0007] Preferably, a long short-term memory network prediction model for simulating a stratospheric airship entity is provided in the shared parameter server; The process of building the long short-term memory network prediction model is as follows: Step S41: combining the physical database and the simulation database to form a data set required by the long short-term memory network prediction model, and dividing the data into a training set, a test set, and a validation set; Step S42: constructing a long short-term memory network prediction model and setting its parameters, including a learning rate and number of iterations, and setting a loss function and optimizer of the long short-term memory network prediction model; Step S43: The set LSTM prediction model is trained through the training set, and after the training is completed, it is evaluated through the test set and the validation set to obtain the LSTM prediction model for simulating the stratospheric airship entity.

[0008] Preferably, during the simulation process, the long short-term memory network prediction model is regularly updated according to the feedback difference between the stratospheric airship entity and the stratospheric airship digital twin.

[0009] A system based on the above-mentioned stratospheric airship simulation control method based on digital twin includes: The data acquisition device is used to collect the actual parameter status of the stratospheric airship entity, and the data acquisition device is arranged on the stratospheric airship entity; The data communication processing device connected to the data acquisition device is used to send and receive the actual parameter status and control instructions collected, and the data communication processing device processes the actual parameter status and sends it to the online digital twin; The online digital twin is used to simulate the actual state of the stratospheric airship entity and convert the prediction results into control instructions sent to the stratospheric airship entity; The offline digital twin is used for parameter setting and predictive analysis. The offline digital twin is connected to the online digital twin through a state synchronization device.

[0010] Preferably, a three-dimensional digital model of a stratospheric airship is constructed based on the entity structure data, and the digital model of the stratospheric airship includes a structural subsystem, an energy subsystem, a power subsystem, an avionics subsystem, a flight control subsystem, a measurement and control subsystem, and a load subsystem, and the structural subsystem, the energy subsystem, the power subsystem, the avionics subsystem, the flight control subsystem, the measurement and control subsystem, and the load subsystem are all connected to a shared parameter server.

[0011] Preferably, the running function model includes a virtual-reality interaction module, a shared parameter server, a data storage module, a data management module, a simulation scheduling module and a visualization module; the virtual-reality interaction module, the data storage module, the data management module, the simulation scheduling module and the visualization module are all connected to the shared parameter server; the virtual-reality interaction module, the data storage module, the data management module and the visualization module are all connected to the simulation scheduling module.

[0012] Preferably, the structure subsystem, energy subsystem, power subsystem, avionics subsystem, flight control subsystem, measurement and control subsystem and load subsystem are all connected to the simulation scheduling module.

[0013] Therefore, the present invention adopts the above-mentioned stratospheric airship simulation control method and system based on digital twin, which has the following beneficial effects: (1) The online digital twin can simulate, monitor and reflect the stratospheric airship entity in the physical space in real time based on the three-dimensional visual model and the actual collected data. The structure, state, performance and behavior of the stratospheric airship entity are mapped to the virtual world, providing a reliable and convenient digital means for observing, recognizing, understanding, controlling and transforming the stratospheric airship entity.

[0014] (2) The virtual-real interaction technology of the stratospheric airship based on the dynamic scale of online-offline time series data realizes the virtual-real interactive operation of the stratospheric airship system in two aspects: "virtual mirroring the real" and "virtual controlling the real". In terms of "virtual mirroring the real", based on deep learning technology and historical data in the actual physical environment, through continuous iterative updates, the difference between the digital twin and the stratospheric airship entity is reduced, and the authenticity and accuracy of the simulation is improved. In terms of "virtual controlling the real", the parameters of the real object are adjusted automatically / interactively based on the offline digital twin. The parameter adjustment is based on the "one-to-many" characteristics of the digital twin. Through the state synchronization of the online-offline digital twin and the adjustment of the parameters in the offline digital twin, the state of the stratospheric airship that needs to be controlled is predicted and analyzed. After achieving the expected control effect, the online digital twin converts it into the corresponding control instructions, and the real object is effectively controlled through the online digital twin automatic / interactive mode.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a stratospheric airship simulation control method based on digital twins of the present invention; Figure 2 This is a schematic diagram of the application of a stratospheric airship simulation control method based on digital twins in the present invention; Figure 3It is a schematic diagram of the structure of the digital twin of the stratospheric airship of the present invention. DETAILED DESCRIPTION

[0017] In the description of the present invention, it should be noted that the terms "upper", "lower", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the invented product is usually placed when in use. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of the present invention, it should also be noted that, unless otherwise clearly specified and limited, the terms "setting", "installation", and "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0018] The embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0019] like Figure 1 As shown, a stratospheric airship simulation control method based on digital twin is shown, and the specific steps are as follows: Step S1: Obtain the physical structure data, state data and environment data of the stratospheric airship and establish a physical database. The structural data includes physical dimensions, data of key components and the layout of corresponding components, etc., to facilitate the subsequent establishment of a three-dimensional model. The state data includes flight parameters (altitude, speed, heading, attitude and acceleration, etc.) and system status (the status of each sensor, engine status, energy status and communication status, etc.), and the meteorological data includes temperature and humidity, air pressure, wind speed and direction, etc.

[0020] Step S2: constructing a digital twin of the stratospheric airship according to the entity database, the digital twin of the stratospheric airship includes an online digital twin and an offline digital twin. Both the online digital twin and the offline digital twin include a shared parameter server, a digital model of the stratospheric airship and an operation function model, and both the digital model of the stratospheric airship and the operation function model are connected to the shared parameter server.

[0021] The online digital twin can simulate, monitor and reflect the stratospheric airship entity in the physical space in real time based on the three-dimensional visual model and the actual collected data. The structure, state, performance and behavior of the stratospheric airship entity are mapped to the virtual world, providing a reliable and convenient digital means for observing, recognizing, understanding, controlling and transforming the stratospheric airship entity.

[0022] The offline digital twin analyzes, evaluates, predicts, manages, and optimizes parameters of the stratospheric airship based on deep learning technology.

[0023] Step S3: The online digital twin obtains the status data of the stratospheric airship entity in real time, and the offline digital twin keeps the status synchronized with the online digital twin.

[0024] Step S4: Parameter setting and predictive analysis are performed in the offline digital twin. When the predictive analysis result reaches the set value, the online digital twin converts the predictive analysis result into a control instruction and sends it to the entity parameter setting device to set the parameters of the stratospheric airship entity. The ultra-real-time simulation rate is not less than 50:1.

[0025] A long short-term memory network prediction model for simulating a stratospheric airship entity is provided in the shared parameter server; The process of building the long short-term memory network prediction model is as follows: Step S41: Combine the physical database and the simulation database to form a data set required by the long short-term memory network prediction model, and divide the data into a training set, a test set, and a validation set.

[0026] Step S42: Build a long short-term memory network prediction model and set its parameters, including learning rate and number of iterations. Set the initial learning rate, and use the learning rate scheduler to dynamically adjust the learning rate. Set the loss function and optimizer of the long short-term memory network prediction model.

[0027] Step S43: The set LSTM prediction model is trained through the training set. After the training is completed, it is evaluated through the test set and the validation set. The performance of the model is evaluated on the test set, and evaluation indicators such as mean square error (MSE), root mean square error (RMSE), determination coefficient (R²) and the like are calculated to obtain the LSTM prediction model for simulating the stratospheric airship entity.

[0028] During the simulation process, the long short-term memory network prediction model is regularly updated according to the feedback difference between the stratospheric airship entity and the stratospheric airship digital twin. By regularly updating the long short-term memory network prediction model based on feedback, the difference between the digital twin and the stratospheric airship entity is reduced, and the authenticity and accuracy of the simulation are improved.

[0029] The stratospheric airship virtual-reality interaction technology based on dynamically scaled online-offline time series data realizes the virtual-reality interaction operation of the stratospheric airship system in two aspects: "reflecting the real with the virtual" and "controlling the real with the virtual".

[0030] In terms of "using virtual to reflect reality", based on deep learning technology and historical data in the actual physical environment, through continuous iterative updates, the differences between digital twins and stratospheric airship entities are reduced, thereby improving the authenticity and accuracy of the simulation.

[0031] In terms of "controlling the real with the virtual", the offline digital twin can realize the parameter setting of the real object through automatic / interactive methods. The parameter setting is based on the "one-to-many" characteristics of the digital twin. Through the online-offline digital twin state synchronization and parameter adjustment in the offline digital twin, the control state of the stratospheric airship is predicted and analyzed. After achieving the expected control effect, the online digital twin converts it into corresponding control instructions, and the effective control of the real object is realized through the online digital twin automatic / interactive methods.

[0032] Based on the above-mentioned system of a stratospheric airship simulation control method based on digital twin, such as Figure 2 As shown, including: The data acquisition device is used to collect the actual parameter status (status data and environmental data) of the stratospheric airship entity, and the data acquisition device is arranged on the stratospheric airship entity.

[0033] The data communication processing device connected to the data acquisition device is used to send and receive the collected actual parameter status and control instructions. At the same time, the data communication processing device processes the actual parameter status and sends it to the online digital twin. The data processing includes removing outliers and normalization processing.

[0034] The online digital twin is used to simulate the actual state of the stratospheric airship entity and convert the prediction results into control instructions sent to the stratospheric airship entity.

[0035] The offline digital twin is used for parameter setting and predictive analysis. The offline digital twin is connected to the online digital twin through a state synchronization device.

[0036] A three-dimensional digital model of the stratospheric airship is constructed based on the physical structure data, such as Figure 3As shown, the digital model of the stratospheric airship includes a structural subsystem, an energy subsystem, a power subsystem, an avionics subsystem, a flight control subsystem, a measurement and control subsystem, and a load subsystem, and the structural subsystem, the energy subsystem, the power subsystem, the avionics subsystem, the flight control subsystem, the measurement and control subsystem, and the load subsystem are all connected to the shared parameter server. The operation function model includes a virtual-real interaction module, a shared parameter server, a data storage module, a data management module, a simulation scheduling module, and a visualization module; the virtual-real interaction module, the data storage module, the data management module, the simulation scheduling module, and the visualization module are all connected to the shared parameter server; the virtual-real interaction module, the data storage module, the data management module, and the visualization module are all connected to the simulation scheduling module. The structural subsystem, the energy subsystem, the power subsystem, the avionics subsystem, the flight control subsystem, the measurement and control subsystem, and the load subsystem are all connected to the simulation scheduling module.

[0037] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A stratospheric airship simulation control method based on digital twin, characterized in that: The specific steps are as follows: Step S1: Acquire the physical structure data, state data and environment data of the stratospheric airship and establish a physical database; Step S2: constructing a digital twin of the stratospheric airship according to the entity database, wherein the digital twin of the stratospheric airship includes an online digital twin and an offline digital twin; Step S3: the online digital twin obtains the status data of the stratospheric airship entity in real time, and the offline digital twin keeps the status synchronized with the online digital twin; Step S4: Parameter setting and predictive analysis are performed in the offline digital twin. When the predictive analysis result reaches the set value, the online digital twin converts the predictive analysis result into a control instruction and sends it to the entity parameter setting device to perform parameter setting on the stratospheric airship entity.

2. The stratospheric airship simulation control method based on digital twin according to claim 1 is characterized in that: Both the online digital twin and the offline digital twin include a shared parameter server, a stratospheric airship digital model and an operation function model, and both the stratospheric airship digital model and the operation function model are connected to the shared parameter server.

3. The stratospheric airship simulation control method based on digital twin according to claim 2 is characterized in that: A long short-term memory network prediction model for simulating a stratospheric airship entity is provided in the shared parameter server; The process of building the long short-term memory network prediction model is as follows: Step S41: combining the physical database and the simulation database to form a data set required by the long short-term memory network prediction model, and dividing the data into a training set, a test set, and a validation set; Step S42: constructing a long short-term memory network prediction model and setting its parameters, including a learning rate and number of iterations, and setting a loss function and optimizer of the long short-term memory network prediction model; Step S43: The set LSTM prediction model is trained through the training set, and after the training is completed, it is evaluated through the test set and the validation set to obtain the LSTM prediction model for simulating the stratospheric airship entity.

4. The stratospheric airship simulation control method based on digital twin according to claim 3 is characterized in that: During the simulation process, the long short-term memory network prediction model is regularly updated according to the feedback difference between the stratospheric airship entity and the stratospheric airship digital twin.

5. A system based on a digital twin-based stratospheric airship simulation control method according to claim 4, characterized in that: include: The data acquisition device is used to collect the actual parameter status of the stratospheric airship entity, and the data acquisition device is arranged on the stratospheric airship entity; The data communication processing device connected to the data acquisition device is used to send and receive the actual parameter status and control instructions collected, and the data communication processing device processes the actual parameter status and sends it to the online digital twin; The online digital twin is used to simulate the actual state of the stratospheric airship entity and convert the prediction results into control instructions sent to the stratospheric airship entity; The offline digital twin is used for parameter setting and predictive analysis. The offline digital twin is connected to the online digital twin through a state synchronization device.

6. The system of a stratospheric airship simulation control method based on digital twin according to claim 5 is characterized in that: A three-dimensional digital model of the stratospheric airship is constructed based on the physical structure data. The digital model of the stratospheric airship includes a structural subsystem, an energy subsystem, a power subsystem, an avionics subsystem, a flight control subsystem, a measurement and control subsystem, and a load subsystem. The structural subsystem, the energy subsystem, the power subsystem, the avionics subsystem, the flight control subsystem, the measurement and control subsystem, and the load subsystem are all connected to a shared parameter server.

7. The system of a stratospheric airship simulation control method based on digital twin according to claim 6 is characterized in that: The operation function model includes a virtual-reality interaction module, a shared parameter server, a data storage module, a data management module, a simulation scheduling module and a visualization module; the virtual-reality interaction module, the data storage module, the data management module, the simulation scheduling module and the visualization module are all connected to the shared parameter server; the virtual-reality interaction module, the data storage module, the data management module and the visualization module are all connected to the simulation scheduling module.

8. The system of a stratospheric airship simulation control method based on digital twin according to claim 7, characterized in that: The structural subsystem, energy subsystem, power subsystem, avionics subsystem, flight control subsystem, measurement and control subsystem, and load subsystem are all connected to the simulation scheduling module.

Images