Aircraft electromechanical system joint simulation method

Abstract

The invention provides an aircraft electromechanical system joint simulation method. The aircraft electromechanical system joint simulation method comprises the following steps: a, acquiring basic parameter data of an aircraft electromechanical system, including working parameters of a power system, a control system, a transmission system, a sensor and an actuator, such as voltage, current, rotating speed and load, and performing real-time data transmission by adopting Internet of Things equipment to ensure the accuracy and timeliness of the data, the edge computing device is adopted to perform preliminary data processing, so that data delay is reduced, and data processing efficiency is improved. According to the aircraft electromechanical system joint simulation method, through accurate modeling of a nonlinear element and introduction of an environmental adaptability module, two main problems existing in an existing simulation technology are effectively solved: a nonlinear behavior is difficult to accurately reproduce and the environmental adaptability is relatively weak. A self-adaptive modeling method in which a high-order nonlinear equation is combined with a neural network is adopted, so that the precision of a simulation model can be dynamically optimized, and complex nonlinear behaviors can be accurately described.

Description

Technical Field

[0001] The present invention relates to the technical field of joint simulation of electromechanical systems, and specifically to a method for joint simulation of aircraft electromechanical systems. Background Art

[0002] "A method for joint simulation of aircraft electromechanical systems" mainly consists of two core parts: the modeling and simulation module of the aircraft electromechanical system, and the joint simulation and analysis module. First of all, the modeling part of the electromechanical system includes the modeling of various subsystems such as the power system, control system, and transmission system in the aircraft. Through detailed mathematical models, the interactions between subsystems are considered, and advanced power and electromechanical coupling models are used to describe the dynamic behavior of the system. Secondly, the joint simulation module integrates the models of all individual subsystems and realizes the prediction and analysis of the overall performance of the aircraft through multi-physics field simulation technology. This method can comprehensively evaluate the stability, response time, and reliability of the electromechanical system under different flight conditions, and conduct tests through a virtual environment, reducing the safety risks that may be brought during actual flight.

[0003] Although this joint simulation method has high application value, there are also some defects in actual applications. Since the electromechanical system of the aircraft contains a large number of nonlinear components, the accuracy of the simulation model is limited by the degree of simplification of the mathematical model, resulting in some complex nonlinear behaviors being difficult to accurately reproduce, which affects the accuracy of the simulation results. In addition, the adaptability of this method to environmental factors is weak, and the changing environments in real flights may not be fully considered, which also affects the reliability of the simulation system. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a method for joint simulation of aircraft electromechanical systems, which solves the problems that the accuracy of the simulation model is limited by the degree of simplification of the mathematical model for nonlinear components, resulting in some complex nonlinear behaviors being difficult to accurately reproduce and affecting the accuracy of the simulation results; and the weak adaptability to environmental factors, where the changing environments in real flights may not be fully considered, which also affects the reliability of the simulation system.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for joint simulation of aircraft electromechanical systems, including: a. Collecting the basic parameter data of the aircraft electromechanical system, including the working parameters of the power system, control system, transmission system, sensors, and actuators, such as voltage, current, rotational speed, and load; b. Accurately modeling the nonlinear components in the aircraft electromechanical system, using high-order nonlinear equations to describe the dynamic behavior of each component, avoiding the influence of simplifying assumptions on the simulation results. The specific modeling formula is: , where, Represents the system output, Represents the state variables, and are linear and non - linear matrices, is the damping matrix, is the non - linear characteristic function; c. Based on non - linear modeling, construct a co - simulation framework for the aircraft electromechanical system and determine the interaction relationships between subsystems; d. Introduce an environmental adaptability module, collect real - time external environmental data such as temperature, humidity, and air pressure during flight, and establish a coupling model between environmental factors and the electromechanical system. The coupling model is: , where is the system model under the reference state, is the correction term caused by environmental factors, temperature T, pressure P, and humidity H; e. Conduct a coupling simulation of environmental factors and the non - linear behavior inside the system, and use a real - time data feedback mechanism to dynamically update the simulation model to ensure that the simulation results reflect the changes in the real flight environment; f. Set multiple constraint conditions to ensure that when the non - linear components and environmental factors interact during the simulation process, the simulation system can operate stably and provide effective predictions; g. Provide a multi - level feedback mechanism, adjust the model parameters in real - time based on the results generated during the simulation process, optimize the simulation accuracy, and the feedback adjustment formula is: , where represents the feedback correction amount, is the actual observed value, is the simulation prediction value, is the feedback gain matrix; h. Conduct a sensitivity analysis of the simulation results to evaluate the impact of various factors on the performance of the aircraft electromechanical system to provide accurate predictions and performance evaluations. The sensitivity analysis formula is: , where is the sensitivity of the th variable, is the simulation output with respect to the input variable partial derivative; i. Combine big data analysis techniques to process and learn historical flight data, thereby optimizing the parameter settings of the simulation model and improving the accuracy of predictions; j. Adopt a distributed computing method to accelerate the simulation of the electromechanical system, reduce the amount of calculation and simulation time, and improve the real-time feedback ability; k. Verify the simulation system with the actual flight test system, conduct data comparison and analysis, and further improve the reliability and adaptability of the simulation model; I. Generate a complete performance report based on the simulation results, providing a comprehensive analysis of the state of the aircraft's electromechanical system, fault diagnosis, and optimization suggestions.

[0006] Preferably, the modeling of the non-linear element adopts an adaptive modeling method based on neural network. The neural network dynamically optimizes the modeling accuracy by learning the non-linear relationships in historical data. The environmental adaptability module is connected to the meteorological data interface to obtain real-time environmental data during flight and adjusts the correction terms of the simulation model according to different flight stages.

[0007] Preferably, the multi-level feedback mechanism includes an adaptive adjustment module based on error correction, which uses a Kalman filter to dynamically correct the feedback data and optimize the model parameters. The sensitivity analysis adopts the Monte Carlo simulation method to evaluate the influence degree of key uncertain factors on the results through multiple simulation calculations.

[0008] Preferably, the big data analysis technology adopts the support vector machine algorithm to extract key feature variables from flight data to optimize the simulation model. The distributed computing method adopts the parallel computing technology based on GPU to shorten the simulation time through task decomposition and multi-core processing.

[0009] Preferably, the simulation framework uses multi-physics field simulation technology to consider the interaction between electricity, mechanics, and thermotics to improve the simulation accuracy. The performance report includes system fault prediction, performance evaluation, optimization suggestions, and analysis of adaptability to environmental changes.

[0010] Preferably, the coupled simulation process adopts a solution algorithm based on time-step adaption to dynamically adjust the calculation accuracy to balance the speed and accuracy requirements. The acquisition module of the environmental data adopts a distributed sensing network system to monitor the external environmental changes of the aircraft in real time.

[0011] Preferably, the real-time data feedback mechanism is linked with the control system, and can quickly correct the influence of environmental changes on the system performance through edge computing. The dynamic modeling process of the non-linear behavior combines the finite element analysis method to enhance the structure behavior prediction ability.

[0012] Preferably, the verification stage of the simulation system includes multiple flight condition simulations to ensure a wide range of applicability of the model. The optimization suggestion part provides improvement strategies for energy-saving performance and service life.

[0013] The present invention provides a joint simulation method for aircraft electromechanical systems, which has the following beneficial effects: By accurately modeling non-linear components and introducing an environmental adaptability module, two main problems existing in the existing simulation technologies are effectively solved: the non-linear behavior is difficult to accurately reproduce and the environmental adaptability is weak. An adaptive modeling method combining high-order non-linear equations and neural networks enables the simulation model to dynamically optimize the accuracy and accurately describe complex non-linear behaviors. In addition, by real-time collecting external environmental data such as temperature, humidity, and air pressure during flight and establishing a coupling model between the environment and the electromechanical system, the adaptability of the simulation system to the real flight environment is significantly improved. A multi-level feedback mechanism combining a Kalman filter and an error correction module ensures the dynamic adjustment ability of the simulation results and effectively improves the stability and prediction accuracy of the system.

[0014] This method shows significant advantages in model optimization and calculation efficiency by combining big data analysis and distributed computing technologies. The support vector machine algorithm extracts key feature variables, which helps to optimize the model parameters, while the parallel computing technology based on GPU shortens the simulation time and enhances the real-time feedback ability of the system. The multi-physics field simulation technology further improves the simulation accuracy of the interactions in multiple fields such as electricity, mechanics, and thermotics, greatly enhancing the prediction ability of the system under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] As Figure 1 shown, the embodiment of the present invention provides a joint simulation method for aircraft electromechanical systems, including: a. Collecting the basic parameter data of the aircraft electromechanical system, including the working parameters of the power system, control system, transmission system, sensors, and actuators, such as voltage, current, rotational speed, and load, using Internet of Things devices for real-time data transmission to ensure the accuracy and timeliness of the data, and using edge computing devices for preliminary data processing to reduce data latency and improve data processing efficiency.

[0018] b. Accurately modeling the non-linear components in the aircraft electromechanical system, using high-order non-linear equations to describe the dynamic behaviors of each component, avoiding the influence of simplified assumptions on the simulation results. The specific modeling formula is: , Among them, represents the system output, represents the state variable, and are linear and non - linear matrices, is the damping matrix, is the non - linear characteristic function. The modeling of non - linear components adopts an adaptive modeling method based on neural networks. The neural network dynamically optimizes the modeling accuracy by learning the non - linear relationships in historical data. The environmental adaptability module is connected through the meteorological data interface to obtain real - time environmental data during flight and adjusts the correction terms of the simulation model according to different flight phases. For the modeling of high - order non - linear components, combined with deep - learning algorithms for dynamic behavior prediction, the modeling accuracy is optimized by continuously learning the non - linear relationships, further overcoming the influence of environmental changes on the modeling of non - linear components. The neural network utilizes the non - linear relationships in historical flight data to optimize the model accuracy through training; Adjust the learning process of the neural network through real - time feedback of environmental data to make it adapt to environmental changes.

[0019] c. Based on non - linear modeling, construct a co - simulation framework for the aircraft's electromechanical system and determine the interaction relationships between subsystems.

[0020] d. Introduce an environmental adaptability module to collect real - time external environmental data such as temperature, humidity, and air pressure during flight and establish a coupling model between environmental factors and the electromechanical system. The coupling model is: , Among them, is the system model under the reference state, is the correction term caused by environmental factors, temperature T, pressure P, and humidity H. In the environmental adaptability module, in addition to factors such as temperature, humidity, and air pressure, real - time acquisition and modeling of dynamic factors such as aircraft flight speed, aircraft attitude, and air flow are added to further enhance the environmental adaptability of the simulation system. The change of each environmental factor dynamically adjusts the correction term through an adaptive control algorithm, improving the real - time performance and accuracy of the simulation model.

[0021] e. Conduct a coupling simulation of environmental factors and the non - linear behavior inside the system, and adopt a real - time data feedback mechanism to dynamically update the simulation model to ensure that the simulation results reflect the changes in the real flight environment.

[0022] f. Set multiple constraint conditions to ensure that when the nonlinear components interact with the changes in environmental factors during the simulation process, the simulation system can operate stably and provide effective predictions. To ensure the stability and reliability of the system in a complex environment, the present invention introduces a control strategy based on robust control theory to ensure that the system can maintain stable operation when the environmental fluctuations are large and has strong anti-interference ability. Robust control optimizes the control parameters to ensure the stability of the simulation system under various non-ideal operating conditions.

[0023] g. Provide a multi-level feedback mechanism to adjust the model parameters in real time based on the results generated during the simulation process and optimize the simulation accuracy. The feedback adjustment formula is: , where, represents the feedback correction amount, is the actual observed value, is the simulation prediction value, is the feedback gain matrix. The multi-level feedback mechanism includes an adaptive adjustment module based on error correction, which uses a Kalman filter to dynamically correct the feedback data and optimize the model parameters. The sensitivity analysis uses the Monte Carlo simulation method to evaluate the influence degree of key uncertain factors on the results through multiple simulation calculations. In the multi-level feedback mechanism, an adaptive adjustment method based on particle swarm optimization is added to iteratively optimize the model parameters through the particle swarm algorithm to adapt to the changing flight environment and nonlinear behavior. This method can effectively improve the stability of the system during long-term simulation.

[0024] h. Conduct sensitivity analysis on the simulation results to evaluate the influence of each factor on the performance of the aircraft's electromechanical system to provide accurate predictions and performance evaluations. The sensitivity analysis formula is: , where, is the sensitivity of the th variable, is the simulation output with respect to the partial derivative of the input variable .

[0025] i. Combine big data analysis technology to process and learn historical flight data, thereby optimizing the parameter setting of the simulation model and improving the accuracy of predictions. The big data analysis technology uses the support vector machine algorithm to extract key feature variables from flight data to optimize the simulation model. The distributed computing method uses GPU-based parallel computing technology to shorten the simulation time through task decomposition and multi-core processing. In big data analysis, combine deep reinforcement learning technology. Through the comparison training of simulation and actual flight data, let the system gradually learn how to dynamically adjust the simulation strategy according to different environments and states to improve the simulation accuracy and reliability.

[0026] j. Adopt a distributed computing method to accelerate the simulation of the electromechanical system, reduce the computational amount and simulation time, and improve the real-time feedback ability.

[0027] k. Verify the simulation system with the actual flight test system, conduct data comparison and analysis, further improve the reliability and adaptability of the simulation model. The simulation framework uses multi-physics field simulation technology, considering the interaction between electricity, mechanics, and thermotics to improve simulation accuracy. The performance report includes system fault prediction, performance evaluation, optimization suggestions, and analysis of adaptability to environmental changes.

[0028] I. Generate a complete performance report based on the simulation results, providing a comprehensive analysis of the state, fault diagnosis, and optimization suggestions of the aircraft electromechanical system. The coupled simulation process uses a time-step adaptive solution algorithm to dynamically adjust the calculation accuracy to balance the requirements of speed and accuracy. The environmental data acquisition module adopts a distributed sensing network system to monitor the changes in the external environment of the aircraft in real time. The real-time data feedback mechanism is linked with the control system, and the influence of environmental changes on the system performance can be quickly corrected through edge computing. The dynamic modeling process of non-linear behavior combines the finite element analysis method to enhance the ability to predict structural behavior. The verification stage of the simulation system includes multiple flight condition simulations to ensure a wide range of applicability of the model. The optimization suggestion part provides improvement strategies for energy-saving performance and service life.

[0029] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A joint simulation method for an aircraft electromechanical system, characterized in that: The following steps are involved: a. Collect basic parameter data of aircraft electromechanical systems, including operating parameters of power systems, control systems, transmission systems, sensors and actuators, such as voltage, current, speed and load; b. Accurately model the nonlinear components in the aircraft electromechanical system, use high-order nonlinear equations to describe the dynamic behavior of each component, and avoid the impact of simplified assumptions on the simulation results. The specific modeling formula is: ， in, Represents the system output, represents the state variable, and are linear and nonlinear matrices, is the damping matrix, is a nonlinear characteristic function; Based on nonlinear modeling, a joint simulation framework for aircraft electromechanical systems is constructed, and the interaction relationship between each subsystem is determined; d. Introduce the environmental adaptability module to collect real-time external environmental data such as temperature, humidity, and air pressure during flight, and establish a coupling model between environmental factors and electromechanical systems. The coupling model is: ， in, is the system model under the baseline state, It is the correction term caused by environmental factors, temperature T, pressure P and humidity H; e. Carry out coupled simulation of environmental factors and nonlinear behaviors within the system, and dynamically update the simulation model using real-time data feedback mechanism to ensure that the simulation results reflect changes in the real flight environment; f. Set multiple constraints to ensure that the simulation system can operate stably and provide effective predictions when nonlinear elements interact with changes in environmental factors during the simulation process; g. Provide a multi-level feedback mechanism to adjust model parameters in real time based on the results generated during the simulation process to optimize simulation accuracy. The feedback adjustment formula is: ， in, is the feedback correction amount, is the actual observed value, is the simulation prediction value, is the feedback gain matrix; h. Perform sensitivity analysis on the simulation results to evaluate the impact of various factors on the performance of the aircraft electromechanical system to provide accurate prediction and performance evaluation. The sensitivity analysis formula is: ， in, For the The sensitivity of the variables, Output for simulation For input variables The partial derivative of i. Combine big data analysis technology to process and learn historical flight data, thereby optimizing the parameter settings of the simulation model and improving the accuracy of prediction; j. Use distributed computing methods to accelerate the simulation of electromechanical systems, reduce the amount of calculation and simulation time, and improve real-time feedback capabilities; k. Verify the simulation system with the actual flight test system, conduct data comparison and analysis, and further improve the reliability and adaptability of the simulation model; I. Generate a complete performance report based on the simulation results, providing a comprehensive analysis of the aircraft electromechanical system status, fault diagnosis and optimization suggestions.

2. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The modeling of the nonlinear element adopts an adaptive modeling method based on a neural network. The neural network dynamically optimizes the modeling accuracy by learning the nonlinear relationship in the historical data. The environmental adaptability module obtains the environmental data during the flight in real time by connecting with the meteorological data interface, and adjusts the correction items of the simulation model according to different flight stages.

3. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The multi-level feedback mechanism includes an adaptive adjustment module based on error correction, which uses a Kalman filter to dynamically correct feedback data and optimize model parameters. The sensitivity analysis uses a Monte Carlo simulation method to evaluate the impact of key uncertain factors on the results through multiple simulation calculations.

4. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The big data analysis technology uses a support vector machine algorithm to extract key feature variables from flight data to optimize the simulation model. The distributed computing method uses a GPU-based parallel computing technology to shorten the simulation time through task decomposition and multi-core processing.

5. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The simulation framework utilizes multi-physics field simulation technology and considers the interaction between electricity, mechanics, and heat to improve simulation accuracy. The performance report includes system fault prediction, performance evaluation, optimization suggestions, and analysis of adaptability to environmental changes.

6. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The coupled simulation process adopts a solution algorithm based on time step adaptation to dynamically adjust the calculation accuracy to balance the speed and accuracy requirements. The environmental data acquisition module adopts a distributed sensor network system to monitor the changes in the external environment of the aircraft in real time.

7. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The real-time data feedback mechanism is linked with the control system, and the impact of environmental changes on system performance can be quickly corrected through edge computing. The dynamic modeling process of nonlinear behavior is combined with the finite element analysis method to enhance the structural behavior prediction capability.

8. The aircraft electromechanical system joint simulation method according to claim 1, characterized in that: The verification phase of the simulation system includes multiple flight condition simulations to ensure the model has a wide range of applicability, and the optimization suggestion part provides improvement strategies for energy-saving performance and service life.

Images