Airborne aero-engine digital device and aircraft
Through multi-physics field high-fidelity modeling and high-performance computing, the problems of insufficient system modeling accuracy and real-time performance of digital devices for aircraft engines have been solved, high-precision simulation and real-time fault diagnosis of aircraft engines have been achieved, and flight safety and R&D efficiency have been improved.
Patent Information
- Application Number
- CN202510759690.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-09
- Publication Date
- 2025-09-12
AI Technical Summary
Existing digital device systems for aircraft engines have deficiencies in system modeling accuracy, real-time performance, and implantability. They are unable to meet the requirements of real-world behavior simulation under high-dynamic, high-nonlinear, and multi-coupling conditions and integrated applications with flight control systems. They also have deficiencies in simulating complex operating conditions and integrating multi-source heterogeneous data.
Using multi-physics high-fidelity modeling technology, combined with high-performance computing capabilities and multi-level data fusion functions, we build aerodynamic, thermodynamic, and structural mechanics models to achieve seamless integration with the flight control system. We also use Kalman filtering and machine learning predictive correctors for real-time simulation and fault diagnosis, and utilize GPU parallel computing and lightweight design to integrate digital devices into the aircraft.
It achieves high-precision simulation and real-time performance simulation of aircraft engines in complex flight environments, supports online performance monitoring, fault warning and health management, and improves the efficiency of aircraft engine R&D and flight safety assurance capabilities.
Smart Images
Figure CN120633048A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of aviation engines, and in particular relates to an airborne aviation engine digital device and an aircraft. Background Art
[0002] With the rapid development of aviation technology, aircraft engines, as the core of aircraft propulsion systems, have a performance that directly determines the safety, economy, and reliability of aircraft. The R&D of modern aviation equipment places higher demands on the design, simulation, testing, and verification of aircraft engines. Traditional physical prototypes, due to their high cost, long cycle times, and complex debugging, cannot meet the demands for rapid iteration and high-precision verification. Therefore, digital device technology has gradually become a key tool in aircraft engine R&D.
[0003] Existing digital instrumentation systems for aircraft engines still face several key technical bottlenecks. For one thing, system modeling accuracy is limited, making it difficult to fully reflect the engine's true behavior under highly dynamic, highly nonlinear, and multi-coupled conditions. Furthermore, the digital instrumentation systems lack real-time performance and portability, making integration with actual flight control systems difficult. Furthermore, existing systems also lack the ability to simulate complex operating conditions, integrate multi-source heterogeneous data, and support in-service condition assessment, hindering their widespread application in airborne environments.
[0004] In view of this, the present invention is proposed. Summary of the Invention
[0005] To address the technical problems existing in the prior art, the present invention provides an airborne aero-engine digital device and aircraft. The digital device of the present invention possesses high-fidelity multi-physics modeling capabilities, high-performance computing capabilities, and multi-level data fusion capabilities. It can operate in real or semi-real flight environments and seamlessly integrate with flight control systems. The device also exhibits excellent system compatibility and portability, meeting the adaptation requirements of aero-engines of different models and architectures, thereby improving aero-engine R&D efficiency and flight safety assurance capabilities.
[0006] The present invention includes the following technical solutions: A first aspect of the present invention provides an airborne aircraft engine digital device, comprising: Modeling module: used to establish aerodynamic conservation model, thermodynamic model and structural mechanics model based on engine historical data; Data acquisition and analysis module: collects sensor data during engine operation in real time; and processes the sensor data to obtain processed sensor data; Real-time simulation module: used to obtain a diagnostic benchmark based on the sensor data processed by the engine, the aerodynamic conservation model, the thermodynamic model and the structural mechanics model; Airborne integration module: Determines whether the engine is faulty based on the processed sensor data and the obtained diagnostic benchmark.
[0007] Furthermore, the aerodynamic conservation model includes a mass conservation equation, a momentum conservation equation, and an energy conservation equation.
[0008] Furthermore, the thermodynamic model includes a heat conduction equation, a convection heat transfer model and a combustion chamber energy balance model.
[0009] Furthermore, the structural mechanics model includes a stress-strain relationship equation, a rotating blade centrifugal stress equation, and a thermal stress equation.
[0010] Furthermore, the real-time simulation module includes: Model correction unit: performs real-time correction on the aerodynamic conservation model, thermodynamic model and structural mechanics model according to the processed sensor data; Real-time simulation unit: obtains a nonlinear state space model based on the real-time corrected aerodynamic conservation model, thermodynamic model and structural mechanics model, and obtains a diagnostic benchmark based on the nonlinear state space model and the processed sensor data.
[0011] Furthermore, the sensor data includes temperature, pressure and vibration.
[0012] Furthermore, processing the sensor data to obtain processed sensor data includes the following steps: Analyze sensor data and perform fault diagnosis through pure data-driven models; Identifying first sensor data with abnormal status and potential faults, and eliminating the first sensor data; Get the processed sensor data.
[0013] Furthermore, the model correction unit integrates a Kalman filter, an extended Kalman filter or a machine learning prediction corrector.
[0014] Furthermore, the real-time simulation module uses a graphics processing unit or a field programmable gate array to perform parallel computing.
[0015] A second aspect of the present invention provides an aircraft that integrates the aforementioned digital device. Using the aforementioned technical solution, the present invention has the following advantages: 1. The present invention builds a high-precision digital model of an aero-engine based on multi-physics field coupling technology (including aerodynamic, thermodynamic, and structural mechanics models), enabling accurate simulation of complex engine operating conditions.
[0016] 2. The present invention utilizes GPU parallel computing technology and dynamic simulation algorithms to achieve real-time performance simulation of aircraft engines in complex flight environments.
[0017] 3. The present invention generates a diagnostic benchmark that matches the actual operating status of the engine through a digital device, combines real-time sensor data to analyze engine operating anomalies, and provides fault identification and health assessment functions.
[0018] 4. The present invention integrates digital devices into aircraft through lightweight design and data bus architecture, supporting online performance monitoring, fault warning and health management suggestion output during flight.
[0019] 5. The modules of the present invention (modeling module and real-time simulation module) are connected through a unified communication interface and data bus to achieve efficient collaboration and fast data interaction.
[0020] 6. Based on the comparative analysis of digital device simulation results and real-time sensor data, the present invention provides early fault warning functions and proactive health management suggestions.
[0021] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0023] Figure 1 This is a schematic diagram of an airborne aircraft engine digital device according to an embodiment of the present invention; Figure 2 This is a flowchart of the installation of a digital device in an embodiment of the present invention. DETAILED DESCRIPTION
[0024] The following description provides many different embodiments or examples for implementing different features of the present invention. The components and arrangements described in the following specific examples are only used to simplify the present invention and are only used as examples, not to limit the present invention.
[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.
[0026] This embodiment provides an onboard aviation engine digital device, such as Figure 1 Shown, including: Modeling module: used to establish aerodynamic conservation model, thermodynamic model and structural mechanics model based on engine historical data; Data acquisition and analysis module: collects sensor data during engine operation in real time; and processes the sensor data to obtain processed sensor data; Real-time simulation module: used to obtain a diagnostic benchmark based on the sensor data processed by the engine, the aerodynamic conservation model, the thermodynamic model and the structural mechanics model; Airborne integration module: Determines whether the engine is faulty based on the processed sensor data and the obtained diagnostic benchmark.
[0027] In some embodiments, the aerodynamic conservation model includes a mass conservation equation, a momentum conservation equation, and an energy conservation equation.
[0028] The mass conservation equation is: ; The momentum conservation equation is: ; The energy conservation equation is: ; in, is the density, is the velocity vector, is pressure, μ is dynamic viscosity, T is temperature, e is specific internal energy, is the viscous dissipation term, is the local density change term in the mass conservation equation, is the local density change term in the mass conservation equation, ∇ is the gradient symbol, is the volume force term in the momentum equation, is the thermal conductivity, is the temperature gradient.
[0029] In some embodiments, the thermodynamic model includes a heat conduction equation, a convection heat transfer model, and a combustion chamber energy balance model.
[0030] The heat conduction equation is: ; The convective heat transfer model is: ; The combustion chamber energy balance model is: ; in, is the thermal diffusivity, is the thermal conductivity, is the specific heat capacity, is the heat exchange per unit time, is the convective heat transfer coefficient, is the heat exchange area, is the wall temperature, is the fluid temperature, For combustion efficiency, is the fuel-air ratio, Q is the fuel calorific value, is the specific heat capacity, Please add, Please add more.
[0031] In some embodiments, the structural mechanics model includes stress-strain relationship equations, rotating blade centrifugal stress equations, and thermal stress equations.
[0032] The stress-strain relationship equation is: ; The centrifugal stress equation of the rotating blade is: ; The thermal stress equation is: ; in, is the material density, is the angular velocity, is the blade length, is the coefficient of thermal expansion, is the temperature change value.
[0033] In some embodiments, the real-time simulation module includes: Model correction unit: performs real-time correction on the aerodynamic conservation model, thermodynamic model and structural mechanics model according to the processed sensor data; Real-time simulation unit: obtains a nonlinear state space model based on the real-time corrected aerodynamic conservation model, thermodynamic model and structural mechanics model, and obtains a diagnostic benchmark based on the nonlinear state space model and the processed sensor data.
[0034] The nonlinear state space model can be: ； in: : Engine internal state (such as compressor speed, temperature, pressure, combustion efficiency, etc.), : Control input (such as injection amount, guide angle, etc.), : Output (thrust, SFC, vibration, etc.), process noise, measurement noise, 、 Both represent nonlinear functions.
[0035] In some embodiments, the sensor data includes temperature and vibration. The temperature and pressure in the sensor data serve as inputs to a nonlinear state-space model, which outputs a vibration diagnostic baseline. This diagnostic baseline is then compared with the vibration in the sensor data. If the vibration in the sensor data is no longer within the diagnostic baseline, it indicates an engine fault.
[0036] In some embodiments, processing the sensor data to obtain processed sensor data includes the following steps: Analyze sensor data and perform fault diagnosis through pure data-driven models; Identifying first sensor data with abnormal status and potential faults, and eliminating the first sensor data; Get the processed sensor data.
[0037] In some embodiments, the model correction unit integrates a Kalman filter, an extended Kalman filter, or a machine learning prediction corrector.
[0038] In some embodiments, the real-time simulation module uses a graphics processing unit (GPU) or a field-programmable gate array (FPGA) to perform parallel computing.
[0039] Use GPU parallel computing architecture (such as CUDA / OpenCL) or FPGA custom logic acceleration to implement parallel computing of nonlinear state-space models: For example, to solve a system of state differential equations using the parallelized Euler / Runge-Kutta method:
[0040] in, is the state variable (such as speed, temperature), For control input (such as fuel flow), is the system parameter, and is the derivative symbol.
[0041] This embodiment also provides an aircraft that integrates the above-mentioned digital device. The modules and units in the digital device are connected through a unified communication interface and data bus to achieve efficient collaboration and fast data exchange.
[0042] like Figure 2 As shown, the digital device integration installation process is as follows: Step 1: Obtain the hardware computing constraints of the onboard equipment First, we collected and analyzed hardware resource information for the aircraft's onboard computing platform, including but not limited to processor power, memory capacity, storage space, power supply capabilities, and real-time requirements. Through quantitative analysis, we determined the upper limit of the platform's tolerable computing load and data transmission rate, which served as fundamental constraints for subsequent digital device design and optimization.
[0043] Step 2: Set the design goals and interface specifications for the digital device Based on hardware constraints, clarify the functional objectives of onboard digital devices, including performance prediction, fault diagnosis, and health management. Simultaneously define the input and output interfaces of digital devices, covering sensor data acquisition interfaces, command input interfaces, status output interfaces, and data interaction specifications with other onboard systems (such as flight control systems and health management systems) to ensure compatibility and scalability for subsequent integration.
[0044] Step 3: Start digital installation construction In view of the complex physical processes of aircraft engines, multi-physics field coupling modeling technology is used to establish three core digital models of aerodynamics, thermodynamics, and structural mechanics: Aerodynamic model: Based on the fusion of CFD (computational fluid dynamics) simulation and test data, a high-fidelity aerodynamic performance map covering different engine operating conditions (takeoff, cruise, acceleration, etc.) is established.
[0045] Thermodynamic model: Through the principles of energy conservation, heat transfer and engine thermal management system parameters, a thermodynamic subsystem with strong dynamic response capabilities and real-time calculation is constructed.
[0046] Structural mechanics model: Combining finite element analysis (FEA) with fatigue life prediction methods, a structural mechanics model is established to estimate the real-time stress-strain state of rotating components (such as fans, compressors, and turbines).
[0047] Each sub-model is modularly packaged through a unified data interface standard (such as the FMI / FMU standard), and multi-domain calibration technology is used to perform joint calibration based on test data and historical flight data to ensure consistency between models and overall accuracy meets engineering application requirements.
[0048] Technical features: For the first time, high-precision multi-physics field real-time collaborative modeling is achieved in an airborne environment, breaking through the limitations of traditional ground digital devices.
[0049] Step 4: Lightweight processing and model compression On the premise of ensuring that the model accuracy meets the application requirements, the following methods are used for lightweight processing to significantly reduce the onboard computing load: Model Order Reduction (MOR): Extracts the main dynamic characteristics and compresses the state space dimension through mathematical methods such as principal component analysis (PCA) and singular value decomposition (SVD).
[0050] Surrogate Modeling: Introducing surrogate models such as neural networks and response surface methods (RSM) for complex submodules to approximate high-overhead computational processes.
[0051] Sparsification and quantization technology: Perform weight sparsification and low-bit quantization on neural network models to accelerate inference speed.
[0052] By combining the above multiple strategies, the efficient operation of airborne digital devices on resource-constrained platforms can be achieved.
[0053] Innovations include: proposing a lightweight solution combining "model reduction + proxy modeling + sparse quantization" to achieve both real-time and high fidelity.
[0054] Step 5: Expand fault diagnosis and health management capabilities Based on the digital device, the following extended functions are further developed: Fault simulation module: Injects typical fault characteristics (such as blade damage, incomplete combustion, and bearing wear) into each physical domain model to form a fault mode library.
[0055] Health indicator prediction: Based on the operating status of digital devices, key health indicators (such as pressure ratio drop, thermal efficiency reduction, and mechanical wear rate) are estimated in real time.
[0056] Anomaly detection and predictive maintenance: Combine machine learning methods to develop anomaly detection algorithms to achieve early detection of potential failures and prediction of remaining life.
[0057] Technical features: The digital device is not only used for performance simulation, but also serves as a health management engine, opening up a closed loop of condition monitoring and predictive maintenance.
[0058] Step 6: Onboard integration and optimized deployment Finally, the constructed digital device is integrated on the aircraft platform and deployed and optimized based on actual flight test data: Optimize data flow and computing process to reduce system latency; Dynamic resource scheduling, adjusting model accuracy and operation frequency according to the flight phase; Ensure system security and stability, and meet aviation software safety certification standards such as DO-178C.
[0059] Through continuous iteration and optimization, we ensure that airborne digital devices can operate stably and efficiently under various extreme working conditions, providing reliable support for the intelligent operation and maintenance of aircraft engines.
[0060] This embodiment also provides an aircraft that integrates the above-mentioned digital device.
[0061] In the description of the present invention, 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 the technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.
[0062] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they may refer to fixed, detachable, or integral connections; mechanical, electrical, or intercommunication connections; direct or indirect connections through an intermediary; and may encompass internal connectivity between multiple components or interactions between multiple components. Those skilled in the art will understand the specific meanings of these terms in the present invention based on specific circumstances.
[0063] In the description of the present invention, it should be understood that all terms used to indicate orientation or positional relationships are based on the orientation or positional relationships shown in the accompanying drawings. 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 operate in a specific orientation, and cannot be understood as a limitation on the present invention.
[0064] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions carried by the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. An airborne aviation engine digital device, characterized in that: include: Modeling module: used to establish aerodynamic conservation model, thermodynamic model and structural mechanics model based on engine historical data; Data acquisition and analysis module: collects sensor data during engine operation in real time; and processes the sensor data to obtain processed sensor data; Real-time simulation module: used to obtain a diagnostic benchmark based on the sensor data processed by the engine, the aerodynamic conservation model, the thermodynamic model and the structural mechanics model; Airborne integration module: Determines whether the engine is faulty based on the processed sensor data and the obtained diagnostic benchmark.
2. The airborne aircraft engine digital device according to claim 1, characterized in that: The aerodynamic conservation model includes a mass conservation equation, a momentum conservation equation, and an energy conservation equation.
3. The airborne aircraft engine digital device according to claim 1, characterized in that: The thermodynamic model includes a heat conduction equation, a convection heat transfer model and a combustion chamber energy balance model.
4. The airborne aircraft engine digital device according to claim 1, characterized in that: The structural mechanics model includes a stress-strain relationship equation, a rotating blade centrifugal stress equation, and a thermal stress equation.
5. The onboard aircraft engine digital device according to claim 1, characterized in that: The real-time simulation module includes: Model correction unit: performs real-time correction on the aerodynamic conservation model, thermodynamic model and structural mechanics model according to the processed sensor data; Real-time simulation unit: obtains a nonlinear state space model based on the real-time corrected aerodynamic conservation model, thermodynamic model and structural mechanics model, and obtains a diagnostic benchmark based on the nonlinear state space model and the processed sensor data.
6. The onboard aircraft engine digital device according to claim 5, characterized in that: The sensor data includes temperature, pressure and vibration.
7. The onboard aircraft engine digital device according to claim 6, characterized in that: Processing the sensor data to obtain processed sensor data includes the following steps: Analyze sensor data and perform fault diagnosis through pure data-driven models; Identifying first sensor data with abnormal status and potential faults, and eliminating the first sensor data; Get the processed sensor data.
8. The onboard aircraft engine digital device according to claim 5, characterized in that: The model correction unit integrates a Kalman filter, an extended Kalman filter or a machine learning prediction corrector.
9. The onboard aircraft engine digital device according to claim 5, characterized in that: The real-time simulation module uses a graphics processing unit or a field programmable gate array for parallel computing.
10. An aircraft, characterized in that: The digital device according to any one of claims 1 to 9 is integrated.