Digital wind tunnel experiment method and device based on artificial intelligence auxiliary dynamic regulation and control

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a digital wind tunnel experiment method and device based on artificial intelligence auxiliary dynamic regulation, and the method comprises the steps: obtaining the real-time working condition data, design working condition data and offline simulation data of a target aircraft; based on a preset cold and hot wall heat flow calculation method, determining heat flow regulation and control parameters of the target aircraft according to the design working condition data and the offline simulation data, and based on the heat flow regulation and control parameters, determining an initial force thermal environment simulation result according to a pre-constructed xenon lamp array and a preset power part device; and based on a pre-established machine learning agent model, calculating the aerodynamic thermal environment of the target aircraft according to the initial force thermal environment simulation result and the real-time working condition data to obtain optimization parameters of the target aircraft, and performing a wind tunnel experiment according to the optimization parameters of the target aircraft, thereby solving the problems of relatively low experiment efficiency and relatively low experiment cost in related technologies. The wind tunnel experiment efficiency is improved, and the research and development period and cost are reduced.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a digital wind tunnel experimental method and apparatus based on artificial intelligence-assisted dynamic control. Background Technology

[0002] Wind tunnel testing, through artificially designed simulations of atmospheric flow environments, tests the aerodynamic characteristics of research objects using specified parameters. It is a commonly used technique for simulating extreme environments. Taking aerospace applications as an example, rockets experience enormous aerodynamic loads when launching and passing through the atmosphere, while spacecraft (space shuttles, reentry capsules) face extreme aerodynamic heating and complex aerothermal environments upon re-entry. Because simulation techniques, such as computational fluid dynamics, have significant errors compared to real experiments, and direct flight testing is extremely costly, time-consuming, and difficult to precisely control test conditions in advance, ground-based wind tunnel testing has become a crucial technique for verifying force loads, thermal environments, and the stability of experimental objects. Therefore, wind tunnel system design methods capable of accurately simulating aerospace thermal environments have become a key technology guiding critical thermal tests in aerospace, energy utilization, and propulsion systems.

[0003] Among related technologies, the extremely complex temporal and spatial distribution of the real aerospace thermal environment provides an extremely suitable scenario for the application of artificial intelligence technology. Due to its ability to process data quickly and efficiently, the combination of artificial intelligence technology and wind tunnel testing systems has become the main technical means.

[0004] However, for simulations of mainstream hypersonic and high-temperature scenarios, the construction cost of large wind tunnels is extremely high. At the same time, due to factors such as huge power consumption, cooling requirements, and component wear, the operation and maintenance costs of the test system are also very high. Furthermore, the preparation work and actual operation of each test are time-consuming, which limits the number and efficiency of tests, the complexity of models, and the coverage of tests, increasing the research and development cycle and costs. These issues urgently need to be addressed. Summary of the Invention

[0005] This invention provides a digital wind tunnel experiment method based on artificial intelligence-assisted dynamic control to solve the problems of low experimental efficiency, high R&D cycle and cost in related technologies, thereby improving wind tunnel experiment efficiency and reducing R&D cycle and cost.

[0006] To achieve the above objectives, a first aspect of the present invention provides a digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control, comprising the following steps: acquiring real-time operating condition data, design operating condition data, and offline simulation data of a target aircraft; determining the heat flow control parameters of the target aircraft based on a preset hot and cold wall heat flow calculation method, according to the design operating condition data and the offline simulation data, and determining the initial force and thermal environment simulation results based on the heat flow control parameters, according to a pre-constructed xenon lamp array and a preset power component device; calculating the aerodynamic thermal environment of the target aircraft based on a pre-established machine learning proxy model, according to the initial force and thermal environment simulation results and the real-time operating condition data, to obtain optimized parameters of the target aircraft, and conducting wind tunnel experiments based on the optimized parameters of the target aircraft.

[0007] Furthermore, in some embodiments, the design condition data includes thermal environment parameters of the target aircraft at multiple locations corresponding to various spatiotemporal states.

[0008] Furthermore, in some embodiments, obtaining the offline simulation data of the target aircraft includes: obtaining the actual flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meets a preset accuracy of the target aircraft; and obtaining the offline simulation data of the target aircraft based on the actual flight test data, the ground wind tunnel test data, and the aerodynamic thermal simulation data that meets the preset accuracy of the target aircraft.

[0009] Furthermore, in some embodiments, the method for calculating the heat flux of the cold and hot walls, which is based on a preset cold and hot wall heat flux, determines the heat flux control parameters of the target aircraft according to the design operating condition data and the offline simulation data, and determines the initial force and thermal environment simulation results based on the heat flux control parameters, according to the pre-constructed xenon lamp array and the preset power component device, includes: calculating the hot wall heat flux data and heat flux control parameters according to the preset cold and hot wall heat flux calculation formula based on the pre-constructed xenon lamp array and the real-time operating condition data of the target aircraft, and determining the heat flux control parameters of the target aircraft based on the hot wall heat flux data and the heat flux control parameters; decoupling and controlling the pre-constructed xenon lamp array and the preset power component device respectively based on the heat flux control parameters of the target aircraft, and obtaining the initial force and thermal environment simulation results based on the decoupling and control results using a preset force and thermal coupling method.

[0010] Furthermore, in some embodiments, each xenon lamp in the xenon lamp array is independently controlled, wherein each xenon lamp concentrates energy onto a preset heating part of the target aircraft test piece through a condenser lens.

[0011] The digital wind tunnel experiment method based on artificial intelligence-assisted dynamic control provided by the present invention acquires real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. First, based on a preset hot and cold wall heat flux calculation method, heat flux control parameters are determined in combination with design operating condition data and offline simulation data. Then, initial force and thermal environment simulation results are obtained based on the xenon lamp array and power component device. Finally, based on a machine learning proxy model, the aerodynamic thermal environment is calculated in combination with the initial simulation results and real-time operating condition data to obtain optimized parameters for wind tunnel experiments. This method solves the problems of low experimental efficiency, high R&D cycle, and high cost in related technologies, improves wind tunnel experiment efficiency, and reduces R&D cycle and cost.

[0012] To achieve the above objectives, a second aspect of the present invention provides a digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control, comprising: an acquisition module for acquiring real-time operating condition data, design operating condition data, and offline simulation data of a target aircraft; a simulation module for determining the heat flow control parameters of the target aircraft based on a preset hot and cold wall heat flow calculation method, according to the design operating condition data and the offline simulation data, and determining the initial force and thermal environment simulation results based on the heat flow control parameters, according to a pre-constructed xenon lamp array and a preset power component device; and an optimization module for calculating the aerodynamic thermal environment of the target aircraft based on a pre-established machine learning proxy model, according to the initial force and thermal environment simulation results and the real-time operating condition data, to obtain optimized parameters of the target aircraft, so as to conduct wind tunnel experiments based on the optimized parameters of the target aircraft.

[0013] Furthermore, in some embodiments, the design condition data includes thermal environment parameters of the target aircraft at multiple locations corresponding to various spatiotemporal states.

[0014] Furthermore, in some embodiments, the acquisition module is specifically used to: acquire the actual flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meet a preset accuracy of the target aircraft; and obtain the offline simulation data of the target aircraft based on the actual flight test data, the ground wind tunnel test data, and the aerodynamic thermal simulation data that meet the preset accuracy of the target aircraft.

[0015] Furthermore, in some embodiments, the simulation module is specifically used for: calculating hot wall heat flux data and heat flux control parameters based on the pre-constructed xenon lamp array and the real-time operating data of the target aircraft, according to a preset cold and hot wall heat flux calculation formula; determining the heat flux control parameters of the target aircraft based on the hot wall heat flux data and the heat flux control parameters; decoupling and controlling the pre-constructed xenon lamp array and the preset power component device based on the heat flux control parameters of the target aircraft; and obtaining the initial force and heat environment simulation results based on the decoupling and control results using a preset force-thermal coupling method.

[0016] Furthermore, in some embodiments, each xenon lamp in the xenon lamp array is independently controlled, wherein each xenon lamp concentrates energy onto a preset heating part of the target aircraft test piece through a condenser lens.

[0017] The digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control provided in this embodiment of the invention acquires real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. First, it determines the heat flow control parameters based on a preset hot and cold wall heat flow calculation method, combined with the design operating condition data and offline simulation data. Then, it obtains the initial force and thermal environment simulation results based on the xenon lamp array and power component device. Finally, it calculates the aerodynamic thermal environment based on a machine learning proxy model, combined with the initial simulation results and real-time operating condition data, to obtain optimized parameters for wind tunnel experiments. This solves the problems of low experimental efficiency, high R&D cycle, and high cost in related technologies, improves wind tunnel experimental efficiency, and reduces R&D cycle and cost.

[0018] To achieve the above objectives, a third aspect of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in the above embodiments.

[0019] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in the above embodiments.

[0020] To achieve the above objectives, a fifth aspect of the present invention provides a computer program product, including a computer program that is executed to implement the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in the above embodiments.

[0021] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0022] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 A flowchart of a digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control provided in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the coupling of simulated mechanical and thermal conditions according to a specific embodiment of the present invention; Figure 3 A schematic diagram of the coupling of an experimental, measurement, and control system according to a specific embodiment of the present invention; Figure 4 A schematic diagram of the system structure of a digital wind tunnel system according to a specific embodiment of the present invention is provided. Figure 5 This is a block diagram of a digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present invention. Detailed Implementation

[0023] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0024] The following describes the digital wind tunnel experimental method and apparatus based on artificial intelligence-assisted dynamic control according to the embodiments of the present invention with reference to the accompanying drawings. First, the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control according to the embodiments of the present invention will be described with reference to the accompanying drawings.

[0025] Figure 1 A flowchart of a digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control provided in an embodiment of the present invention.

[0026] like Figure 1 As shown, this digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control includes the following steps: In step S101, real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft are acquired.

[0027] In some embodiments, the design condition data includes thermal environment parameters of the target aircraft at multiple locations under various spatiotemporal conditions.

[0028] Among them, the spatiotemporal state of the aircraft involves a combination of time and space during flight.

[0029] Specifically, the extraction of target parameters for the aircraft includes the flight envelope and various operating points of the aircraft design. It establishes the typical thermal environment of each part of the full-scale aircraft at different times during the entire flight due to different positions and flight requirements. Then, it corresponds to the aerodynamic and thermal test conditions that need to be achieved in the simulation test. The thermal environment parameters at different locations under different spatiotemporal states are extracted from the design operating conditions of the target aircraft, including cold wall heat flow conditions and typical aerodynamic parameters, such as incoming flow Mach number, gas pressure, and mainstream total temperature.

[0030] Furthermore, in some embodiments, obtaining offline simulation data of the target aircraft includes: obtaining real flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meets a preset accuracy; and obtaining offline simulation data of the target aircraft based on the real flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meets a preset accuracy.

[0031] As one possible approach, this invention can first divide the target aircraft's flight mission specifications, aerodynamic and thermal design reports, and other technical documents from the design phase into different spatiotemporal states according to flight stages (e.g., the initial reentry phase, mid-course reentry phase, and terminal deceleration phase of the reentry capsule) and altitude ranges. Then, it selects key thermal protection components such as the center, edges, windward surfaces of the sidewalls, and the canopy. Finally, it extracts the thermal environment parameters corresponding to each "spatiotemporal state-position" combination, including cold wall heat flux conditions and typical aerodynamic parameters such as incoming Mach number, gas pressure, and mainstream total temperature, forming a correspondence between "spatiotemporal state-position-parameters." Then, it cleans, calibrates, and fuses real flight test data, ground wind tunnel test data, and aerodynamic and thermal simulation data meeting preset accuracy to obtain offline simulation data.

[0032] In step S102, based on the preset hot and cold wall heat flow calculation method, the heat flow control parameters of the target aircraft are determined according to the design working condition data and offline simulation data. Based on the heat flow control parameters, the initial force and heat environment simulation results are determined according to the pre-constructed xenon lamp array and the preset power component device.

[0033] Among them, heat flow control parameters refer to physical quantities and design parameters used to describe, control or optimize the heat transfer process, while mechanical and thermal environment simulation results refer to the quantitative distribution and mutual influence of physical quantities such as stress, strain, temperature and heat flow of various parts of the device obtained through simulation under the coupling effect of mechanical force field and thermal field.

[0034] Furthermore, in some embodiments, based on a preset cold and hot wall heat flux calculation method, the heat flux control parameters of the target aircraft are determined according to design operating condition data and offline simulation data. Based on the heat flux control parameters, the initial force and thermal environment simulation results are determined according to a pre-constructed xenon lamp array and a preset power component device. This includes: calculating hot wall heat flux data and heat flux control parameters based on a preset cold and hot wall heat flux calculation formula according to a pre-constructed xenon lamp array and real-time operating condition data of the target aircraft; determining the heat flux control parameters of the target aircraft based on the hot wall heat flux data and heat flux control parameters; decoupling and controlling the pre-constructed xenon lamp array and the preset power component device respectively based on the heat flux control parameters of the target aircraft; and obtaining the initial force and thermal environment simulation results based on the decoupling and control results according to a preset force and thermal coupling method.

[0035] Specifically, this invention uses a preset hot and cold wall heat flux calculation formula to calculate hot wall heat flux data and initial heat flux control parameters based on a pre-constructed xenon lamp array (i.e., heat source simulation device) and real-time operating data of the target aircraft (e.g., flight speed, altitude, surface temperature, power consumption). Then, combined with the target aircraft's thermal control requirements (e.g., maximum allowable temperature, heat distribution uniformity), the parameters are optimized and verified to ensure that the heat flux simulation matches the actual operating conditions, thus obtaining the target aircraft's heat flux control parameters. Next, the xenon lamp array and power components (e.g., aircraft engine, servo motors) are decoupled and controlled, outputting the heat source control results of the xenon lamp array (i.e., actual thermal environment distribution) and the mechanical force control results of the power components (i.e., actual stress state). Finally, based on a force-thermal coupling method, the heat source control results and mechanical force control results are coupled and calculated to quantify their mutual influence, obtaining the initial force-thermal environment simulation results (e.g., temperature-stress joint distribution at various locations, correlation characteristics between heat flux density and stress).

[0036] Among them, power components such as compressed fans simulate the real situation where the surface of the aircraft is covered by an outflow air film and the thermal environment of the rear area is affected by the front cooling method by changing the outflow velocity conditions. They can actively adjust the wind speed and direction and support remote control. With the help of software, they can acquire real-time data. Through different power components such as compressed fans, the outflow conditions of the aircraft can be simulated. The fans can adjust different outflow velocities and simulate the direction of the angle of attack of the flight state, which helps to simulate the coupling of internal and external flow of active cooling technology under real flight conditions.

[0037] Furthermore, the adjustment strategy of decoupling and then coupling the mechanical and thermal conditions first involves setting the initial simulation state, and then adjusting the thermal boundary in real time according to the objective conditions under different working conditions and the active cooling scheme during the test, thereby unifying the control of the radiant heating system and the compressor fan system.

[0038] Figure 2This is a schematic diagram illustrating the coupling of simulated force and heat conditions according to a specific embodiment of the present invention. Figure 3 This is a schematic diagram of the coupling of a test, measurement, and control system according to a specific embodiment of the present invention, such as... Figure 2 As shown, typical internal and external flow conditions are first decoupled, and the aerodynamic thermal conditions are decomposed into thermal environment conditions and external flow conditions, which are simulated by a real-time adjustable xenon lamp radiation heating array and a compressor fan system, respectively. Simultaneously, the internal flow conditions are developed for users, allowing them to choose various active-passive coupled thermal protection schemes. The external structure of the target aircraft must simultaneously withstand the external heating load of the top thermal environment conditions, bidirectional heat exchange with the external fluid under the external flow conditions, and heat transfer with the internal fluid under the internal flow conditions; for example... Figure 3 As shown, ground tests were conducted simulating real flight conditions. Physical quantity information from the test process was acquired in real time through various measurement sensors. The signals were then transmitted to the active cooling control system for processing. Adjustments were then made based on the environmental requirements and the determined active thermal design strategy. Figure 2 The composite thermal interaction scenario in the middle is Figure 3 The surface measurement sensors in the simulated external thermal environment of the Zhongli thermal testing system monitor the structure's state under this thermal environment. The data is then transmitted to the active cooling control module via a feedback link, which outputs signals to adjust the testing system parameters, thereby achieving [the desired effect]. Figure 2 The adaptive matching and precise control of the medium thermal environment are used to complete the testing and optimization of the structural force and thermal response.

[0039] Furthermore, in some embodiments, each xenon lamp in the xenon lamp array is independently controlled, wherein each xenon lamp concentrates energy onto a preset heating part of the target aircraft test piece through a condenser lens.

[0040] Specifically, the external thermal environment is simulated by using xenon lamps for radiant heating. To reflect the differences in thermal environment at different locations, an array of xenon lamps is built. Each xenon lamp can be independently controlled to simulate the heat flow conditions of a certain area, and the heat flow magnitude can be continuously adjusted via remote software.

[0041] It should be noted that the xenon lamp system is an external heating system adapted to the test model. It has an independent control strategy that supports remote operation. Each xenon lamp concentrates energy onto a specific heating part of the test piece through a condenser lens. The heating power and corresponding heat flux density are adjustable. The control strategy can be adjusted in real time to adapt to the actual working conditions and the requirements of the external cooling system.

[0042] In step S103, based on the pre-established machine learning agent model, the aerodynamic and thermal environment of the target aircraft is calculated according to the initial force and thermal environment simulation results and real-time operating condition data to obtain the optimized parameters of the target aircraft, so as to conduct wind tunnel experiments based on the optimized parameters of the target aircraft.

[0043] This invention combines offline data with machine learning methods to establish a proxy model, which accurately describes the quantitative relationship between internal flow, surface heat flow and external environment under different real working conditions. At the same time, it uses experimental methods such as infrared cameras, flow meters, and pressure gauges to achieve real-time acquisition and collection of data such as temperature, flow, and pressure. Based on the proxy model, it quickly calculates and adjusts the force and heat conditions in real time, realizing instant comparison of ground and air experimental conditions.

[0044] Furthermore, embodiments of the present invention can incorporate different active-passive coupled thermal design schemes for large-size thermal protection components, enabling real-time acquisition of field data on the thermal performance of different schemes, which is then simultaneously uploaded to analysis and processing software for storage and parsing. This data can be further combined with artificial intelligence algorithms, such as joint analysis, to optimize multiple factors such as quality, temperature, and processing costs.

[0045] To enable those skilled in the art to better understand the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control according to the embodiments of the present invention, the following explanation will be provided in conjunction with specific embodiments.

[0046] Figure 4 The schematic diagram of the system structure of the digital wind tunnel system provided according to a specific embodiment of the present invention includes a remotely controllable radiant heating xenon lamp system, an adjustable air volume and speed compressor system, an experimental data acquisition system for temperature field, flow rate, etc., a cooling system flow supply device, and a target test piece. The software part needs to utilize artificial intelligence algorithms to establish a machine learning proxy model that correlates the surface temperature and heat flow of the test piece with the surrounding mainstream aerodynamic and thermal conditions based on the results of previously conducted high-precision wind tunnel tests, flight tests, and aerodynamic and thermal simulation calculations. This allows for rapid calculation during the experiment and real-time adjustments on the hardware. like Figure 4As shown, this invention first proposes a flight envelope corresponding to the model design based on the target functional requirements of the aircraft, extracting the actual variable-condition flight thermal environment, including necessary parameters such as flight altitude and Mach number. Based on the parameters, the cold wall heat flux corresponding to each area of ​​the aircraft surface in the initial state is calculated. The target area is heated according to the corresponding heat flux density through a radiant heating system, while the compressor fan is simultaneously activated to control the mainstream flow velocity around the test piece. At the same time, the infrared temperature measurement system measures and feeds back the surface temperature field data of the test piece to the processing software in real time. The software can calculate the real-time hot wall heat flux based on the real-time temperature field and adjust the output energy of the radiant heating system in real time according to the machine learning proxy model obtained from the previous training, ensuring that the test can be carried out according to the mainstream conditions of the corresponding flight environment. During this process, the flow control system can also be activated simultaneously to carry out the test according to the user-designed active thermal scheme and evaluate the effect of the active thermal design. Thus, the digital wind tunnel test system of this invention can conduct thermal tests under variable thermal environments for large-scale thermal protection components of full-size aircraft, can support different thermal design schemes of active and passive thermal protection coupling, simultaneously establish a thermal test database, and combine artificial intelligence algorithms to analyze the optimal scheme under multi-objective optimization constraints for a certain flight requirement, providing thermal performance reference for design selection.

[0047] The digital wind tunnel experiment method based on artificial intelligence-assisted dynamic control provided by the present invention acquires real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. First, based on a preset hot and cold wall heat flux calculation method, heat flux control parameters are determined in combination with design operating condition data and offline simulation data. Then, initial force and thermal environment simulation results are obtained based on the xenon lamp array and power component device. Finally, based on a machine learning proxy model, the aerodynamic thermal environment is calculated in combination with the initial simulation results and real-time operating condition data to obtain optimized parameters for wind tunnel experiments. This method solves the problems of low experimental efficiency, high R&D cycle, and high cost in related technologies, improves wind tunnel experiment efficiency, and reduces R&D cycle and cost.

[0048] Next, the digital wind tunnel experimental apparatus based on artificial intelligence-assisted dynamic control according to an embodiment of the present invention is described with reference to the accompanying drawings.

[0049] Figure 5 A block diagram of a digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control provided in an embodiment of the present invention.

[0050] like Figure 5 As shown, the digital wind tunnel experimental device 10 based on artificial intelligence-assisted dynamic control includes: an acquisition module 100, a simulation module 200, and an optimization module 300.

[0051] The acquisition module 100 is used to acquire real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. The simulation module 200, based on a preset hot and cold wall heat flow calculation method, determines the heat flow control parameters of the target aircraft according to the design operating condition data and offline simulation data, and determines the initial force and thermal environment simulation results based on the heat flow control parameters, the pre-constructed xenon lamp array, and the preset power component device. The optimization module 300 is used to calculate the aerodynamic thermal environment of the target aircraft based on a pre-established machine learning proxy model, the initial force and thermal environment simulation results, and real-time operating condition data to obtain the optimized parameters of the target aircraft, so as to conduct wind tunnel experiments based on the optimized parameters of the target aircraft.

[0052] Furthermore, in some embodiments, the design condition data includes thermal environment parameters of the target aircraft at multiple locations corresponding to various spatiotemporal states.

[0053] Furthermore, in some embodiments, the acquisition module 100 is specifically used to: acquire real flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meet a preset accuracy of the target aircraft; and obtain offline simulation data of the target aircraft based on the real flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meet a preset accuracy of the target aircraft.

[0054] Furthermore, in some embodiments, the simulation module 200 is specifically used for: calculating hot wall heat flow data and heat flow control parameters based on pre-built xenon lamp array and real-time operating data of the target aircraft, according to a preset cold and hot wall heat flow calculation formula; determining the heat flow control parameters of the target aircraft based on the hot wall heat flow data and heat flow control parameters; decoupling and controlling the pre-built xenon lamp array and the preset power component device based on the heat flow control parameters of the target aircraft; and obtaining the initial force and heat environment simulation results based on the decoupling and control results using a preset force and heat coupling method.

[0055] Furthermore, in some embodiments, each xenon lamp in the xenon lamp array is independently controlled, wherein each xenon lamp concentrates energy onto a preset heating part of the target aircraft test piece through a condenser lens.

[0056] It should be noted that the foregoing explanation of the embodiment of the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control also applies to the digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control in this embodiment, and will not be repeated here.

[0057] The digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control provided in this embodiment of the invention acquires real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. First, it determines the heat flow control parameters based on a preset hot and cold wall heat flow calculation method, combined with the design operating condition data and offline simulation data. Then, it obtains the initial force and thermal environment simulation results based on the xenon lamp array and power component device. Finally, it calculates the aerodynamic thermal environment based on a machine learning proxy model, combined with the initial simulation results and real-time operating condition data, to obtain optimized parameters for wind tunnel experiments. This solves the problems of low experimental efficiency, high R&D cycle, and high cost in related technologies, improves wind tunnel experimental efficiency, and reduces R&D cycle and cost.

[0058] Figure 6 This is a schematic diagram of an electronic device provided according to an embodiment of the present invention. The electronic device may include: The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0059] When the processor 602 executes the program, it implements the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control provided in the above embodiments.

[0060] Furthermore, electronic devices also include: Communication interface 603 is used for communication between memory 601 and processor 602.

[0061] The memory 601 is used to store computer programs that can run on the processor 602.

[0062] The memory 601 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0063] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0064] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0065] Processor 602 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention.

[0066] In addition, embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control.

[0067] In addition, embodiments of the present invention also provide a computer program product, including a computer program, which is executed to implement the above-mentioned digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control.

[0068] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0069] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0070] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control, characterized in that, Includes the following steps: Acquire real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft; Based on the preset hot and cold wall heat flow calculation method, the heat flow control parameters of the target aircraft are determined according to the design working condition data and the offline simulation data. Based on the heat flow control parameters, the initial force and heat environment simulation results are determined according to the pre-constructed xenon lamp array and the preset power component device. Based on a pre-established machine learning agent model, the aerodynamic and thermal environment of the target aircraft is calculated according to the initial force and thermal environment simulation results and the real-time operating condition data to obtain the optimized parameters of the target aircraft, so as to conduct wind tunnel experiments based on the optimized parameters of the target aircraft.

2. The method according to claim 1, characterized in that, The design operating condition data includes thermal environment parameters of the target aircraft at multiple locations under various spatiotemporal conditions.

3. The method according to claim 1, characterized in that, The acquisition of offline simulation data of the target aircraft includes: Acquire real flight test data, ground wind tunnel test data, and aerodynamic thermal simulation data that meet preset accuracy for the target aircraft; The offline simulation data of the target aircraft is obtained based on the real flight test data of the target aircraft, the ground wind tunnel test data, and the aerodynamic thermal simulation data that meets the preset accuracy.

4. The method according to claim 1, characterized in that, The method for calculating heat flux based on preset hot and cold walls determines the heat flux control parameters of the target aircraft according to the design operating condition data and the offline simulation data, and determines the initial force and thermal environment simulation results based on the heat flux control parameters, according to the pre-constructed xenon lamp array and the preset power component device, including: Based on the pre-constructed xenon lamp array and the real-time operating data of the target aircraft, the hot wall heat flow data and heat flow control parameters are calculated according to the preset cold and hot wall heat flow calculation formula, and the heat flow control parameters of the target aircraft are determined based on the hot wall heat flow data and the heat flow control parameters. Based on the thermal flow control parameters of the target aircraft, the pre-constructed xenon lamp array and the preset power component device are decoupled and controlled respectively. Based on the preset force-thermal coupling method, the initial force-thermal environment simulation results are obtained according to the decoupling control results.

5. The method according to claim 1, characterized in that, Each xenon lamp in the xenon lamp array is independently controlled, and each xenon lamp concentrates energy onto a preset heating part of the target aircraft test piece through a condenser lens.

6. A digital wind tunnel experimental device based on artificial intelligence-assisted dynamic control, characterized in that, include: The acquisition module is used to acquire real-time operating condition data, design operating condition data, and offline simulation data of the target aircraft. The simulation module, based on a preset hot and cold wall heat flow calculation method, determines the heat flow control parameters of the target aircraft according to the design working condition data and the offline simulation data, and determines the initial force and heat environment simulation results based on the heat flow control parameters, according to the pre-constructed xenon lamp array and the preset power component device. The optimization module is used to calculate the aerodynamic and thermal environment of the target aircraft based on the initial force and heat environment simulation results and the real-time operating condition data, according to a pre-established machine learning agent model, to obtain the optimized parameters of the target aircraft, and to conduct wind tunnel experiments based on the optimized parameters of the target aircraft.

7. The apparatus according to claim 6, characterized in that, The design operating condition data includes thermal environment parameters of the target aircraft at multiple locations under various spatiotemporal conditions.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the digital wind tunnel experimental method based on artificial intelligence-assisted dynamic control as described in any one of claims 1-5.

Images