Flight control system function logic model design method

Abstract

The invention relates to the technical field of flight control, in particular to a flight control system function logic model design method. The method comprises the following steps: acquiring multi-source data of an aircraft; performing data format unification on the aircraft multi-source data to generate an aircraft multi-source unified data set; performing flight virtual scene reconstruction on the multi-source unified data set of the aircraft to generate a three-dimensional flight virtual scene; carrying out aircraft flight condition analysis on the aircraft multi-source unified data set to obtain aircraft flight condition data; constructing a flight classifier according to the flight condition data of the aircraft to obtain an aircraft flight mode classifier; the aircraft flight mode classifier is used for carrying out aircraft flight mode recognition on the aircraft flight motion characteristic data, and aircraft flight mode data are generated. By unifying multi-source data, accurately analyzing the flight condition and optimizing the flight control strategy, the adaptability and optimization capacity of the flight control system function logic model design are improved.

Description

Technical Field

[0001] The present invention relates to the field of flight control technology, and in particular to a flight control system functional logic model design method. Background Art

[0002] The design of flight control systems mainly relies on traditional PID controllers, which achieve basic stability control of aircraft through simple proportional, integral and differential control. However, this approach has limited performance under complex environments and high performance requirements. With the development of computer technology, flight control systems based on microprocessors and digital signal processors (DSPs) have begun to appear. These systems are able to implement more complex control algorithms, such as model predictive control (MPC) and nonlinear control methods, improving the dynamic response and flight stability of aircraft. With the advancement of embedded systems and sensor technology, flight control systems have gradually integrated multiple sensors such as inertial measurement units (IMUs), global positioning systems (GPS) and visual sensors. These sensor data fusion technologies enable flight control systems to achieve precise navigation and autonomous flight functions, such as inertial navigation, automatic take-off and landing, and obstacle avoidance. At present, the design of flight control systems has covered multiple levels, including hardware design optimization, selection of real-time operating systems, and refinement of control algorithms. At the same time, the introduction of artificial intelligence and machine learning technologies, such as deep reinforcement learning and neural network control, is driving flight control systems to develop in a more intelligent, adaptive and efficient direction. However, current traditional methods often rely on simple rules or empirical judgments when analyzing and identifying aircraft flight modes and abnormal flight parameters, and lack high-precision analysis and detection capabilities. At the same time, flight control strategies are often based on simple control logic or fixed rules, lacking specificity and optimization, which leads to low adaptability and optimization capabilities in the design of functional logic models of flight control systems. Summary of the invention

[0003] Based on this, it is necessary to provide a flight control system functional logic model design method to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for designing a functional logic model of a flight control system is provided, the method comprising the following steps:

[0005] Step S1: Acquire multi-source data of the aircraft; unify the data format of the multi-source data of the aircraft to generate a multi-source unified data set of the aircraft; reconstruct a flight virtual scene for the multi-source unified data set of the aircraft to generate a three-dimensional flight virtual scene;

[0006] Step S2: analyzing the aircraft flight situation of the aircraft multi-source unified data set to obtain aircraft flight situation data; constructing a flight classifier based on the aircraft flight situation data to obtain an aircraft flight mode classifier; using the aircraft flight mode classifier to identify the aircraft flight mode of the aircraft flight motion feature data to generate aircraft flight mode data; extracting abnormal flight parameters from the aircraft flight mode data to generate abnormal aircraft flight parameters;

[0007] Step S3: Acquire the real-time flight position data of the aircraft; perform flight path tracking on the real-time flight position data of the aircraft according to the normal flight mode data of the aircraft to generate the real-time flight path of the aircraft; construct an initial control strategy for the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data;

[0008] Step S4: Based on the strategy stability analysis data, the initial flight control strategy is optimally solved to generate optimal strategy control data; according to the optimal strategy control data, the three-dimensional flight virtual scene is logically converted to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

[0009] The present invention collects aircraft data from various sensors and devices, including GPS position data, inertial measurement unit (IMU) data, camera images, laser radar data, etc. The data from different sources are converted and integrated to form a unified data set. A three-dimensional flight virtual scene is constructed using a unified data set, which can provide a comprehensive and multi-dimensional data perspective, help to better understand and analyze the behavior of the aircraft, and the generated three-dimensional virtual scene can be used to simulate and test various flight conditions of the aircraft, and improve the efficiency of aircraft design and testing. The unified data set is analyzed to extract the flight condition data of the aircraft. A classifier is constructed based on the flight condition data to identify different flight modes. The flight mode classifier is used to identify the flight mode in the flight motion feature data, generate flight mode data, and extract abnormal flight parameters from the flight mode data. Through flight mode recognition, different flight states of the aircraft can be automatically classified and identified, and the accuracy of aircraft monitoring and management can be improved. Extracting abnormal flight parameters helps to discover and deal with potential flight risks at an early stage and improve flight safety. The real-time position data of the aircraft during flight is collected, and the flight path of the real-time position data is tracked according to the normal flight mode data to generate a real-time flight path. Based on abnormal flight parameters, the initial control strategy is constructed for the real-time flight path, the stability analysis of the initial control strategy is performed, and the strategy stability analysis data is generated. Real-time flight path tracking can accurately monitor the current position and path of the aircraft, which is helpful for the navigation and positioning of the aircraft. The construction and stability analysis of the initial control strategy can help to adjust the control strategy of the aircraft in time to ensure the safety and stability of the flight process. Based on the strategy stability analysis data, the optimal control solution is performed on the initial flight control strategy to generate the optimal strategy control data. According to the optimal strategy control data, the logic control instruction conversion is performed on the three-dimensional flight virtual scene to generate the flight control logic control instruction. Through the optimal control solution, a more accurate and effective flight control strategy can be formulated to improve the performance and safety of the aircraft. The generated flight control logic control instruction can be directly applied to the flight control system to realize the design and optimization of the aircraft function logic model. Therefore, the present invention improves the adaptability and optimization ability of the flight control system function logic model design by unifying multi-source data, accurately analyzing the flight situation, and optimizing the flight control strategy.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: using a distributed sensor network to obtain multi-source data of the aircraft;

[0012] Step S12: performing data preprocessing on the aircraft multi-source data to generate standard aircraft multi-source data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0013] Step S13: unifying the data format of the standard aircraft multi-source data to generate an aircraft multi-source unified data set;

[0014] Step S14: Reconstruct the flight virtual scene of the aircraft multi-source unified data set through virtual reality enhancement technology to generate a three-dimensional flight virtual scene.

[0015] The present invention can cover a wider area, obtain data of more dimensions, and improve the comprehensiveness and accuracy of the data by using a distributed sensor network to obtain multi-source data of aircraft. Through preprocessing steps such as data cleaning, data denoising, and data missing value filling, the noise and outliers in the data can be effectively removed, the missing data can be filled, and the integrity and reliability of the data can be ensured. Data standardization enables data from different sources and formats to be processed and analyzed on the same platform, eliminating the processing complexity caused by data format differences and improving data processing efficiency. The data format of standard aircraft multi-source data is unified to generate a unified multi-source data set for aircraft, which further simplifies the data management and analysis process and improves the convenience and consistency of data utilization. The flight virtual scene reconstruction of the aircraft multi-source unified data set through virtual reality enhancement technology can provide a more intuitive and realistic three-dimensional flight virtual scene, which is conducive to better data analysis and result display, and improves the efficiency and effectiveness of decision support.

[0016] Preferably, step S14 comprises the following steps:

[0017] Step S141: extracting flight environment features from the aircraft multi-source unified data set to obtain aircraft environment feature data;

[0018] Step S142: reconstructing the aircraft environment feature data based on virtual reality enhancement technology to generate aircraft environment reconstruction data;

[0019] Step S143: dynamically simulating the aircraft using the aircraft environment reconstruction data to generate aircraft dynamic simulation data;

[0020] Step S144: Perform virtual sensor fusion based on the aircraft dynamic simulation data and the aircraft environment reconstruction data to generate a three-dimensional flight virtual scene.

[0021] The present invention can more accurately obtain the characteristic data of the environment in which the aircraft is located by extracting the flight environment characteristics from the aircraft multi-source unified data set. These data can include various factors such as terrain, weather, air flow, etc., to ensure that the aircraft can obtain more accurate environmental information support in actual flight. Using virtual reality augmented technology to reconstruct the environment can not only reproduce the actual flight environment of the aircraft more realistically, but also provide additional information and interactive functions through augmented reality technology, providing aircraft operators with a more intuitive and comprehensive understanding of the environment. Dynamic simulation can be performed through aircraft environment reconstruction data to generate detailed aircraft dynamic simulation data. These data can be used to predict the behavior and performance of the aircraft under different environmental conditions, thereby improving the safety and reliability of the aircraft. Virtual sensor fusion technology can organically combine aircraft dynamic simulation data and environmental reconstruction data to generate a three-dimensional flight virtual scene. This scene can not only be used for training and drills of aircraft operations, but also for planning and optimization of flight missions, providing all-round support for aircraft.

[0022] Preferably, step S2 comprises the following steps:

[0023] Step S21: analyzing the aircraft flight situation on the aircraft multi-source unified data set to obtain aircraft flight situation data;

[0024] Step S22: constructing a flight classifier according to the aircraft flight situation data to obtain an aircraft flight mode classifier;

[0025] Step S23: using an aircraft flight mode classifier to perform aircraft flight mode recognition on the aircraft flight motion feature data to generate aircraft flight mode data, wherein the aircraft flight mode data includes aircraft normal flight mode data and aircraft abnormal flight mode data;

[0026] Step S24: extracting abnormal flight parameters from the aircraft abnormal flight mode data to generate abnormal flight parameters of the aircraft.

[0027] The present invention can comprehensively and accurately obtain the flight data of the aircraft under different conditions by performing flight situation analysis on the multi-source unified data set of the aircraft. These data can include various flight parameters such as speed, direction, attitude, etc., providing a detailed information basis for subsequent analysis and classification. By constructing a flight classifier based on the flight situation data, a classification tool for different flight modes (such as normal flight and abnormal flight) can be created. This helps to identify and distinguish the flight modes of the aircraft in various states, and improve the accuracy and efficiency of classification. The flight mode classifier is used to perform flight mode recognition of flight motion feature data, and the flight mode of the aircraft can be automatically identified. This not only improves the speed and accuracy of flight mode recognition, but also can timely detect abnormal situations in flight and generate data including normal and abnormal flight modes. The abnormal flight parameter extraction process can deeply analyze the abnormal flight mode data and generate specific abnormal flight parameters. These parameters help to identify the faults or abnormal behaviors of the aircraft in flight, and provide important data support for fault diagnosis and prevention.

[0028] Preferably, step S22 includes the following steps:

[0029] Step S221: annotating the aircraft flight condition data to generate aircraft flight condition annotated data;

[0030] Step S222: extracting visual features and motion features from the aircraft flight situation annotation data to obtain aircraft visual feature data and aircraft motion feature data;

[0031] Step S223: merging the aircraft visual feature data and the aircraft motion feature data to obtain an aircraft flight feature data set; dividing the aircraft flight feature data set to generate a model training set and a model verification set;

[0032] Step S224: Perform model training on the model training set using a convolutional neural network algorithm to generate aircraft behavior pattern training data; perform model parameter tuning on the aircraft behavior pattern training data using a model verification set to generate an aircraft flight pattern classifier.

[0033] The present invention generates aircraft flight condition annotation data by annotating aircraft flight condition data. Accurate data annotation is the basis for subsequent feature extraction and model training, ensures the accuracy and consistency of data, and provides a reliable data source for the construction of a classifier. The visual features and motion features of the aircraft are extracted. The visual features may include the image data of the aircraft, and the motion features may include dynamic parameters such as speed and acceleration. By extracting these features, the flight state and behavior of the aircraft can be fully reflected, providing rich input data for the classifier. The visual feature data and the motion feature data are merged to generate a comprehensive flight feature data set, which is divided into a model training set and a model verification set. This step ensures the integrity and diversity of the data, so that the model training and verification have sufficient representativeness and extensiveness, thereby improving the generalization ability of the classifier. The model training set is trained using a convolutional neural network algorithm to generate aircraft behavior pattern training data. The convolutional neural network has a strong ability in processing image and time series data, and can effectively capture the complex behavior patterns of the aircraft. In addition, parameter tuning is performed through the model verification set to ensure that the classifier has high accuracy and robustness.

[0034] Preferably, step S24 includes the following steps:

[0035] Step S241: performing abnormal type identification on the aircraft abnormal flight mode data to generate aircraft abnormal flight type data, wherein the abnormal type identification includes aircraft external environment abnormality and aircraft internal environment abnormality;

[0036] Step S242: when it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as abnormal external environment of the aircraft, an environmental impact factor analysis is performed on the aircraft environment feature data to generate environmental impact factor data; external abnormal environment parameters are extracted from the abnormal flight mode data of the aircraft according to the environmental impact factor data to obtain abnormal external environment feature data of the aircraft;

[0037] Step S243: When it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as an abnormal internal environment of the aircraft, a flight structure analysis is performed on the aircraft to generate aircraft internal structure data; a fault detection is performed on the aircraft internal structure data to generate aircraft internal structure fault data;

[0038] Step S244: performing structural influence factor analysis based on the aircraft internal structural fault data to generate structural influence factor data; performing internal abnormal operation parameter extraction on the aircraft abnormal flight mode data based on the structural influence factor data to obtain aircraft internal operation abnormality feature data;

[0039] Step S245: Integrate the abnormal characteristic data of the external environment of the aircraft and the abnormal characteristic data of the internal operation of the aircraft to generate abnormal flight parameters of the aircraft.

[0040] The present invention classifies the abnormalities into external environment abnormalities and internal environment abnormalities by identifying the abnormality types of the abnormal flight mode data of the aircraft. This process can accurately distinguish the source of the abnormality and provide a basis for subsequent targeted analysis and processing. For the external environment abnormality, the environmental impact factor data is generated by analyzing the environmental feature data of the aircraft, and the external abnormal environment parameters are further extracted to obtain the abnormal characteristic data of the external environment of the aircraft. This step can deeply analyze the impact of the external environment on the flight of the aircraft and provide detailed data support for the external environment abnormality. For the internal environment abnormality, the internal structure data and internal structure fault data of the aircraft are generated through flight structure analysis and troubleshooting. This process can comprehensively check the internal structure of the aircraft, identify potential faults and problems, and provide detailed data support for the processing of internal abnormalities. By analyzing the structural impact factor of the internal structure fault data of the aircraft, the structural impact factor data is generated, and the internal abnormal operation parameters are further extracted to obtain the abnormal characteristic data of the internal operation of the aircraft. This step can deeply analyze the impact of the internal structure of the aircraft on the flight behavior and provide detailed data support for the internal environment abnormality. The abnormal characteristic data of the aircraft's external environment and the abnormal characteristic data of the aircraft's internal operation are integrated to generate the aircraft's abnormal flight parameters. This process can comprehensively analyze the combined impact of the external and internal environments on the aircraft's flight, provide comprehensive abnormal flight parameter data, and provide a reliable basis for the aircraft's fault diagnosis and maintenance.

[0041] Preferably, step S3 comprises the following steps:

[0042] Step S31: using GPS to obtain real-time flight position data of the aircraft;

[0043] Step S32: marking the real-time flight position data of the aircraft with spatial coordinate points according to the normal flight mode data of the aircraft to obtain the real-time flight spatial coordinate data of the aircraft; tracking the flight path of the aircraft through the real-time flight spatial coordinate data of the aircraft to generate the real-time flight path of the aircraft;

[0044] Step S33: Calculating the path deviation of the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain the abnormal flight deviation path of the aircraft;

[0045] Step S34: performing attitude control on the aircraft based on the abnormal flight deviation path of the aircraft to generate aircraft attitude control adjustment data; performing path trajectory planning adjustment on the abnormal flight deviation path of the aircraft based on the aircraft attitude control adjustment data to generate aircraft path trajectory planning adjustment data;

[0046] Step S35: construct an initial control strategy for the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data using the three-dimensional flight virtual scene to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data.

[0047] The present invention obtains the real-time flight position data of the aircraft by utilizing GPS technology, ensures that the aircraft is always under monitoring during the flight process, and provides accurate position information for subsequent path tracking and attitude control. According to the normal flight mode data of the aircraft, the real-time flight position data is marked with spatial coordinate points to generate the real-time flight spatial coordinate data of the aircraft, and the flight path is tracked through these data to generate the real-time flight path. This step realizes the accurate monitoring of the flight path of the aircraft, ensuring that the aircraft flies according to the predetermined path. Based on the abnormal flight parameters of the aircraft, the path deviation of the real-time flight path is calculated to generate the abnormal deviation path of the aircraft flight. This process can timely discover the abnormal deviation in the flight path of the aircraft, and provide timely abnormal warning and processing basis. Based on the abnormal deviation path of the aircraft flight, attitude control is performed to generate the aircraft attitude control adjustment data, and the path trajectory planning adjustment of the abnormal deviation path is performed through these data to generate the aircraft path trajectory planning adjustment data. This process can timely adjust the flight attitude and path trajectory of the aircraft, ensure that the aircraft can return to the normal flight path, and avoid potential dangers. Using the three-dimensional flight virtual scene, the initial control strategy is constructed for the attitude control adjustment data and the path trajectory planning adjustment data, the initial flight control strategy is generated, and the stability analysis of the strategy is performed to generate the strategy stability analysis data. This step can ensure the reliability and stability of the initial flight control strategy and provide guarantee for the safe flight of the aircraft.

[0048] Preferably, step S35 includes the following steps:

[0049] Step S351: Parameter mapping is performed on the three-dimensional flight virtual scene according to the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to obtain a target attitude mapping sequence and a target flight path mapping data;

[0050] Step S352: constructing an initial control strategy based on the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to generate an initial flight control strategy; performing simulation control on the initial flight control strategy through a preset time step, and recording the control strategy performance data;

[0051] Step S353: Perform strategy stability analysis on the control strategy performance data to generate strategy stability analysis data.

[0052] The present invention generates a target attitude mapping sequence and a target flight path mapping data by performing parameter mapping on a three-dimensional flight virtual scene and using the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data. This step ensures that the attitude and path of the aircraft in the virtual scene are consistent with the actual flight conditions, and provides an accurate simulation environment for the subsequent control strategy construction. Based on the attitude control adjustment data and the path trajectory planning adjustment data, an initial flight control strategy is constructed. Then, simulation control is performed through a preset time step, and the obtained control strategy performance data is recorded. This process can verify the performance of the initial control strategy under different time steps and ensure the effectiveness of the strategy in practical applications. The control strategy performance data obtained by the simulation control is analyzed for strategy stability to generate strategy stability analysis data. This analysis process can evaluate the stability and robustness of the control strategy under different flight conditions and ensure the reliability of the strategy in actual flight. Through precise parameter mapping and simulation control, it can be ensured that the control strategy is highly consistent with the actual flight conditions, and the accuracy and reliability of the control strategy are improved. Through stability analysis, the unstable factors existing in the control strategy under different flight conditions can be identified and solved, and the stability and robustness of the strategy can be enhanced. The construction and verification process of the initial control strategy can continuously optimize the flight path and attitude control, ensuring that the aircraft can fly safely and smoothly in various environments.

[0053] Preferably, step S353 includes the following steps:

[0054] Step S3531: Perform basic performance index analysis on the control strategy performance data to obtain basic performance index data;

[0055] Step S3532: Evaluate the control effect of the initial flight control strategy through basic performance indicator data to generate strategy control effect evaluation data;

[0056] Step S3533: Calculate the control steady-state error of the strategy control effect evaluation data to obtain strategy stability index data;

[0057] Step S3534: Perform statistical analysis on the strategy stability index data to generate strategy control statistical analysis data; perform time series analysis on the control strategy performance data to generate strategy control time series stability data;

[0058] Step S3535: Integrate the basic performance indicator data, the policy stability indicator data, the policy control statistical analysis data and the policy control time series stability data to generate policy stability analysis data.

[0059] The present invention obtains basic performance index data by performing basic performance index analysis on control strategy performance data, such as control accuracy, response time, etc. This step can intuitively evaluate the basic performance of the control strategy and provide a basis for subsequent in-depth analysis. Based on the basic performance index data, the control effect of the initial flight control strategy is evaluated to generate strategy control effect evaluation data. This process can quantitatively evaluate the effect of the control strategy in practical applications and guide further optimization and adjustment of the strategy. The control steady-state error is calculated on the strategy control effect evaluation data to obtain strategy stability index data. This step can analyze the error of the control strategy in steady state and evaluate its stability and accuracy. The strategy stability index data is statistically analyzed to generate strategy control statistical analysis data; at the same time, the control strategy performance data is time-series analyzed to generate strategy control time-series stability data. These analyses can fully understand the performance of the control strategy under different conditions and reveal its potential advantages and room for improvement. The basic performance index data, strategy stability index data, strategy control statistical analysis data and strategy control time-series stability data are integrated to generate strategy stability analysis data. This step can comprehensively analyze the performance of the control strategy in multiple aspects and provide decision makers with comprehensive evaluation basis and optimization suggestions.

[0060] Preferably, step S4 comprises the following steps:

[0061] Step S41: performing optimal control solution on the initial flight control strategy based on the strategy stability analysis data to generate optimal strategy control data;

[0062] Step S42: performing Monte Carlo simulation on the three-dimensional flight virtual scene according to the optimal strategy control data to generate a control strategy simulation data set;

[0063] Step S43: Perform logic control instruction conversion based on the control strategy simulation data set to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

[0064] The present invention solves the optimal control of the initial flight control strategy based on the strategy stability analysis data and generates the optimal strategy control data. This step aims to find the best control strategy parameters through mathematical optimization methods to improve the control efficiency and stability of the aircraft. According to the optimal strategy control data, the three-dimensional flight virtual scene is simulated by Monte Carlo to generate a control strategy simulation data set. Monte Carlo simulation can simulate the influence of various random factors on the control strategy, evaluate its performance under various conditions, and improve the adaptability and robustness of the control strategy. Based on the control strategy simulation data set, the logic control instruction conversion is performed to generate the aircraft flight control logic control instructions. These instructions will be used to execute the functional logic model design of the flight control system to ensure that the aircraft can perform various flight tasks and operations as expected. Through the optimal control solution, the performance of the control strategy under various flight conditions can be improved, and the control accuracy and efficiency of the aircraft can be optimized. Monte Carlo simulation can comprehensively evaluate the stability and robustness of the control strategy under different random environments, and provide guarantee for actual flight to cope with complex situations. Through the logic control instruction conversion, it can ensure that the aircraft performs tasks according to the designed logic model, and improve the operational safety and reliability of the aircraft.

[0065] The beneficial effect of the present invention is that by unifying the format of multi-source data of aircraft and reconstructing the scene, a three-dimensional flight virtual scene can be obtained, which helps to simulate and analyze the operating environment of the aircraft more accurately. By analyzing the flight situation data of the aircraft, an aircraft flight mode classifier can be constructed to identify the flight mode of the aircraft. This helps to understand the behavior and performance of the aircraft and provides a basis for subsequent control strategies. By analyzing the flight mode data of the aircraft, abnormal flight parameters can be extracted, which can be used to detect and judge whether the aircraft has abnormal conditions, so as to take corresponding control measures to ensure the safe operation of the aircraft. According to the real-time flight position data and normal flight mode data of the aircraft, flight path tracking can be performed, and an initial flight control strategy can be constructed based on abnormal flight parameters. This helps the aircraft to remain stable and safe in real-time operation. Stability analysis is performed on the initial flight control strategy to ensure the effectiveness and safety of the control strategy. Then, by solving the optimal control, the optimal strategy control data is obtained, so as to achieve the best control performance of the aircraft. The optimal strategy control data is converted into aircraft flight control logic control instructions to perform the flight control system functional logic model design operation. This helps to achieve precise control and operation of the aircraft. Therefore, the present invention improves the adaptability and optimization capability of the design of the functional logic model of the flight control system by unifying multi-source data, accurately analyzing the flight situation, and optimizing the flight control strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A schematic diagram of the steps of a design method for a functional logic model of a flight control system;

[0067] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0068] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0069] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0070] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0071] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0072] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0073] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0074] To achieve this, please refer to Figures 1 to 4 , a flight control system functional logic model design method, the method comprising the following steps:

[0075] Step S1: Acquire multi-source data of the aircraft; unify the data format of the multi-source data of the aircraft to generate a multi-source unified data set of the aircraft; reconstruct a flight virtual scene for the multi-source unified data set of the aircraft to generate a three-dimensional flight virtual scene;

[0076] Step S2: analyzing the aircraft flight situation of the aircraft multi-source unified data set to obtain aircraft flight situation data; constructing a flight classifier based on the aircraft flight situation data to obtain an aircraft flight mode classifier; using the aircraft flight mode classifier to identify the aircraft flight mode of the aircraft flight motion feature data to generate aircraft flight mode data; extracting abnormal flight parameters from the aircraft flight mode data to generate abnormal aircraft flight parameters;

[0077] Step S3: Acquire the real-time flight position data of the aircraft; perform flight path tracking on the real-time flight position data of the aircraft according to the normal flight mode data of the aircraft to generate the real-time flight path of the aircraft; construct an initial control strategy for the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data;

[0078] Step S4: Based on the strategy stability analysis data, the initial flight control strategy is optimally solved to generate optimal strategy control data; according to the optimal strategy control data, the three-dimensional flight virtual scene is logically converted to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

[0079] The present invention collects aircraft data from various sensors and devices, including GPS position data, inertial measurement unit (IMU) data, camera images, laser radar data, etc. The data from different sources are converted and integrated to form a unified data set. A three-dimensional flight virtual scene is constructed using a unified data set, which can provide a comprehensive and multi-dimensional data perspective, help to better understand and analyze the behavior of the aircraft, and the generated three-dimensional virtual scene can be used to simulate and test various flight conditions of the aircraft, and improve the efficiency of aircraft design and testing. The unified data set is analyzed to extract the flight condition data of the aircraft. A classifier is constructed based on the flight condition data to identify different flight modes. The flight mode classifier is used to identify the flight mode in the flight motion feature data, generate flight mode data, and extract abnormal flight parameters from the flight mode data. Through flight mode recognition, different flight states of the aircraft can be automatically classified and identified, and the accuracy of aircraft monitoring and management can be improved. Extracting abnormal flight parameters helps to discover and deal with potential flight risks at an early stage and improve flight safety. The real-time position data of the aircraft during flight is collected, and the flight path of the real-time position data is tracked according to the normal flight mode data to generate a real-time flight path. Based on abnormal flight parameters, the initial control strategy is constructed for the real-time flight path, the stability analysis of the initial control strategy is performed, and the strategy stability analysis data is generated. Real-time flight path tracking can accurately monitor the current position and path of the aircraft, which is helpful for the navigation and positioning of the aircraft. The construction and stability analysis of the initial control strategy can help to adjust the control strategy of the aircraft in time to ensure the safety and stability of the flight process. Based on the strategy stability analysis data, the optimal control solution is performed on the initial flight control strategy to generate the optimal strategy control data. According to the optimal strategy control data, the logic control instruction conversion is performed on the three-dimensional flight virtual scene to generate the flight control logic control instruction. Through the optimal control solution, a more accurate and effective flight control strategy can be formulated to improve the performance and safety of the aircraft. The generated flight control logic control instruction can be directly applied to the flight control system to realize the design and optimization of the aircraft function logic model. Therefore, the present invention improves the adaptability and optimization ability of the flight control system function logic model design by unifying multi-source data, accurately analyzing the flight situation, and optimizing the flight control strategy.

[0080] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for designing a functional logic model of a flight control system according to the present invention. In this example, the method for designing a functional logic model of a flight control system includes the following steps:

[0081] Step S1: Acquire multi-source data of the aircraft; unify the data format of the multi-source data of the aircraft to generate a multi-source unified data set of the aircraft; reconstruct a flight virtual scene for the multi-source unified data set of the aircraft to generate a three-dimensional flight virtual scene;

[0082] In an embodiment of the present invention, various sensor data on the aircraft are collected, including but not limited to GPS data, IMU data, camera image data, laser radar data, etc. Log data during the flight of the aircraft is obtained, including aircraft status, control instructions, flight events, etc. Environmental data of the aircraft flight area, such as weather conditions, topographic data, etc. are collected. External data related to the flight of the aircraft, such as airspace control information, other aircraft position data, etc. are obtained. Noise and outliers in the original data are cleaned to ensure the accuracy and consistency of the data. Data from different sources are aligned in time and space to ensure the consistency of each data source at the same time point and location. Data in different formats are converted into a unified format, for example, the data formats of different sensors are standardized into the same data structure. Different data sources are fused in time and space to generate a comprehensive multi-source data set. Data from different sensors are converted to a unified coordinate system, for example, GPS data, IMU data, etc. are converted to a geographic coordinate system or an aircraft body coordinate system. Point cloud data of the flight area is generated using laser radar data or visual SLAM (Simultaneous Localization and Mapping) technology. Use multi-view image data for image stitching and stereo reconstruction to generate a high-precision 3D model. Build a 3D model of the flight area, including terrain, buildings, vegetation, etc., based on environmental data and flight log data. Integrate the generated point cloud data and 3D model into the virtual scene to generate a complete 3D flight virtual scene. Texture map the 3D model to increase the realism and details of the scene. Optimize the virtual scene, including reducing the number of polygons and optimizing the texture size, to improve rendering efficiency and real-time performance. Evaluate the precision and accuracy of the virtual scene to ensure that the reconstructed 3D scene is consistent with the actual flight area. Test the rendering performance of the virtual scene on different platforms to ensure that it can run in real time in aircraft simulation training or control system testing.

[0083] Step S2: analyzing the aircraft flight situation of the aircraft multi-source unified data set to obtain aircraft flight situation data; constructing a flight classifier based on the aircraft flight situation data to obtain an aircraft flight mode classifier; using the aircraft flight mode classifier to identify the aircraft flight mode of the aircraft flight motion feature data to generate aircraft flight mode data; extracting abnormal flight parameters from the aircraft flight mode data to generate abnormal aircraft flight parameters;

[0084] In the embodiment of the present invention, the motion data of the aircraft, such as speed, acceleration, position, attitude, etc., are extracted from a multi-source unified data set. Data related to the environment during the flight, such as weather conditions, airspace information, etc., are extracted. The motion data of the aircraft are statistically analyzed to calculate the average speed, acceleration, attitude change, etc. of the aircraft in different flight stages. The typical motion patterns of the aircraft in different flight stages are identified by using data mining and machine learning technologies. Anomaly detection algorithms are used to identify abnormal conditions in flight data, such as sudden changes in speed, abnormal attitude changes, etc. The flight data are annotated to distinguish between normal flight modes and abnormal flight modes, and generate aircraft flight condition annotation data. Computer vision technology is used to extract visual features from image data, such as changes in the appearance of the aircraft, changes in the environment, etc. Motion features, such as speed, acceleration, attitude, etc., are extracted from motion data. Visual feature data and motion feature data are merged to generate a comprehensive aircraft flight feature data set. The flight feature data set is divided into a model training set and a model validation set to ensure that the training set and the validation set are balanced in terms of quantity and features. The model training set is trained using deep learning algorithms such as convolutional neural networks (CNN) to generate aircraft behavior pattern training data. The model parameters of the training data are tuned through the model verification set to optimize the model performance and generate an aircraft flight mode classifier. The trained flight mode classifier is used to perform pattern recognition on the real-time flight motion feature data of the aircraft, classify the current flight mode of the aircraft, generate aircraft flight mode data based on the recognition results, and distinguish between normal flight mode data and abnormal flight mode data. Identify flight anomalies caused by external environmental factors and generate aircraft external environment anomaly feature data. Identify flight anomalies caused by internal faults or abnormal operations of the aircraft and generate aircraft internal environment anomaly feature data. Analyze the external environment anomaly feature data to extract external anomaly parameters that affect the flight of the aircraft. Perform troubleshooting and structural analysis on the internal environment anomaly feature data to extract internal anomaly parameters that affect the flight of the aircraft. Integrate the external environment anomaly feature data and the internal environment anomaly feature data to generate aircraft abnormal flight parameters, which are provided to the flight control system for further processing and adjustment.

[0085] Step S3: Acquire the real-time flight position data of the aircraft; perform flight path tracking on the real-time flight position data of the aircraft according to the normal flight mode data of the aircraft to generate the real-time flight path of the aircraft; construct an initial control strategy for the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data;

[0086] In the embodiment of the present invention, the acquisition of high-precision position data is ensured by configuring and calibrating the GPS receiver on the aircraft. Real-time GPS data of the aircraft, including longitude, latitude, altitude, etc., is continuously collected. Noise and outliers in the GPS data are cleaned to ensure the accuracy of the data. Time synchronization of GPS data and other sensor data is ensured to ensure data consistency. The real-time position data of the aircraft is filtered and smoothed using the Kalman filter algorithm to improve the accuracy of path tracking. Short-term trajectory prediction is performed based on the real-time position and speed data of the aircraft to enhance the stability of path tracking. The real-time flight path of the aircraft is calculated based on the GPS position data and the normal flight mode data of the aircraft. The real-time flight path data is visualized for easy monitoring and analysis. Based on the abnormal flight parameters of the aircraft, the deviation of the real-time flight path of the aircraft is calculated, including position deviation and attitude deviation. Abnormal features in the flight path are extracted, such as sudden altitude changes, sharp turns, etc. According to the abnormal flight parameters of the aircraft, the initial flight control strategy is designed, including attitude control, speed control, and direction control, etc. The initial parameters of the control strategy, such as control gain, response time, etc., are set to ensure that the initial strategy can effectively deal with abnormal conditions of the flight path. Conduct simulation tests on the initial flight control strategy in a simulation environment to evaluate its performance under different flight conditions. Evaluate the control effect of the initial control strategy, including path tracking accuracy, attitude stability, response speed, etc. Perform basic performance index analysis on the control strategy performance data to obtain basic performance index data. Evaluate the control effect of the initial flight control strategy through the basic performance index data to generate strategy control effect evaluation data. Calculate the control steady-state error on the strategy control effect evaluation data to obtain strategy stability index data. Perform statistical analysis on the strategy stability index data to generate strategy control statistical analysis data. Perform time series analysis on the control strategy performance data to generate strategy control time series stability data. Integrate the basic performance index data, strategy stability index data, strategy control statistical analysis data, and strategy control time series stability data to generate strategy stability analysis data.

[0087] Step S4: Based on the strategy stability analysis data, the initial flight control strategy is optimally solved to generate optimal strategy control data; according to the optimal strategy control data, the three-dimensional flight virtual scene is logically converted to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

[0088] In the embodiment of the present invention, the objective function of the optimal control problem is set according to the strategy stability analysis data, which generally includes minimizing the path deviation, minimizing the fuel consumption, maximizing the stability, etc. The physical constraints and operational constraints of the aircraft are set, such as the maximum acceleration, the maximum speed, the attitude change range, etc. The genetic algorithm is used for global optimization, which is applicable to nonlinear and multi-peak optimization problems. The particle swarm optimization algorithm is used for rapid convergence, which is applicable to optimization problems in high-dimensional space. For problems with time-series decision characteristics, the dynamic programming method can be used to solve the optimal control strategy. The parameters of the optimization algorithm are initialized according to the initial flight control strategy and the strategy stability analysis data. The optimization algorithm is run to iteratively solve the optimal control strategy, and the control parameters are continuously updated until convergence to the optimal solution. The validity and reliability of the optimal strategy control data are verified to ensure that it can be effectively executed in practical applications. The optimal strategy control data is mapped to the control parameters of the three-dimensional flight virtual scene, such as position, speed, attitude, etc. According to the mapping results, the optimal control strategy is converted into specific flight control logic control instructions, including heading instructions, speed instructions, attitude adjustment instructions, etc. According to the functional logic model of the flight control system, the generation rules and execution flow of the logic control instructions are designed. Verify the correctness and feasibility of the logic control instructions through simulation and testing to ensure that they can be effectively executed in the three-dimensional flight virtual scene. Set up a variety of flight scenarios and environmental conditions, perform Monte Carlo simulation on the optimal control strategy, and generate a control strategy simulation data set. Analyze the simulation results, evaluate the performance of the optimal control strategy in different scenarios, and verify its robustness and adaptability. Based on the simulation data set, formulate the rules for generating logic control instructions to ensure the accuracy and timeliness of the instructions. Generate real-time flight control logic control instructions based on real-time flight data and the optimal control strategy to ensure the safety and stability of the aircraft. According to the flight control requirements of the aircraft, build a functional logic model of the flight control system, including modules such as instruction reception, instruction parsing, and instruction execution. Verify the correctness and reliability of the functional logic model through simulation and testing to ensure that it can effectively execute flight control logic control instructions.

[0089] Preferably, step S1 comprises the following steps:

[0090] Step S11: using a distributed sensor network to obtain multi-source data of the aircraft;

[0091] Step S12: performing data preprocessing on the aircraft multi-source data to generate standard aircraft multi-source data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization;

[0092] Step S13: unifying the data format of the standard aircraft multi-source data to generate an aircraft multi-source unified data set;

[0093] Step S14: Reconstruct the flight virtual scene of the aircraft multi-source unified data set through virtual reality enhancement technology to generate a three-dimensional flight virtual scene.

[0094] In an embodiment of the present invention, multi-source data of an aircraft is collected by using a distributed sensor network (including GPS, inertial measurement unit (IMU), remote sensing sensor, etc.). These data sources can be obtained from various components and environments of the aircraft to obtain comprehensive flight status and environmental information. Data preprocessing includes the following steps: Data cleaning: removing outliers, erroneous data or incomplete data in the data. Data denoising: eliminating noise in the data to ensure data quality. Data missing value filling: filling in missing data points to make the data set complete. Data standardization: converting data into a unified standard format or unit for subsequent processing and analysis. Unifying the preprocessed data to ensure the consistency and comparability of the data set involves unifying the data collected by different sensors into the same data structure and data type. Virtual reality enhancement technology, such as computer graphics and three-dimensional modeling technology, is used to reconstruct the flight virtual scene of the multi-source unified data set of the aircraft. This includes: Scene modeling: creating a virtual environment around the aircraft based on information such as position, motion, and environmental parameters in the data set. Visual enhancement: enhancing the visual effect of the virtual scene so that it reflects the actual flight environment as realistically as possible. Interactive design: Ensure that users can interact and observe in the virtual scene to simulate the actual situation under different flight conditions.

[0095] Preferably, step S14 comprises the following steps:

[0096] Step S141: extracting flight environment features from the aircraft multi-source unified data set to obtain aircraft environment feature data;

[0097] Step S142: reconstructing the aircraft environment feature data based on virtual reality enhancement technology to generate aircraft environment reconstruction data;

[0098] Step S143: dynamically simulating the aircraft using the aircraft environment reconstruction data to generate aircraft dynamic simulation data;

[0099] Step S144: Perform virtual sensor fusion based on the aircraft dynamic simulation data and the aircraft environment reconstruction data to generate a three-dimensional flight virtual scene.

[0100] In the embodiment of the present invention, by using data processing and analysis technology, feature data of the environment in which the aircraft is located is extracted from the aircraft multi-source unified data set. These feature data include environmental parameters such as aircraft position, attitude, speed, surrounding terrain and weather. Virtual reality enhancement technology, such as computer graphics and three-dimensional modeling technology, is used to reconstruct the environment feature data of the aircraft extracted from step S141. This process includes: creating a virtual environment around the aircraft according to the environmental feature data, including terrain, buildings, vegetation, etc., and enhancing the visual effect of the virtual scene to make it reflect the appearance and atmosphere of the actual flight environment as realistically as possible. The aircraft is dynamically simulated using the environmental reconstruction data to simulate the movement and behavior of the aircraft in the actual environment. According to the motion characteristics and environmental conditions of the aircraft, the flight path, attitude changes, etc. of the aircraft are simulated. According to the motion characteristics and environmental conditions of the aircraft, the flight path, attitude changes, etc. of the aircraft are simulated. The aircraft dynamic simulation data generated in step S143 and the aircraft environment reconstruction data generated in step S142 are virtual sensor fused. This includes: integrating data from different sensors (such as visual sensors, radars, GPS, etc.) into a unified virtual sensor data set. The information provided by different sensors is integrated using data fusion algorithms to obtain more comprehensive and accurate aircraft status and environmental information.

[0101] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0102] Step S21: analyzing the aircraft flight situation on the aircraft multi-source unified data set to obtain aircraft flight situation data;

[0103] Step S22: constructing a flight classifier according to the aircraft flight situation data to obtain an aircraft flight mode classifier;

[0104] Step S23: using an aircraft flight mode classifier to perform aircraft flight mode recognition on the aircraft flight motion feature data to generate aircraft flight mode data, wherein the aircraft flight mode data includes aircraft normal flight mode data and aircraft abnormal flight mode data;

[0105] Step S24: extracting abnormal flight parameters from the aircraft abnormal flight mode data to generate abnormal flight parameters of the aircraft.

[0106] In an embodiment of the present invention, aircraft data including position, speed, acceleration, attitude, battery status, etc. are collected from different sensors and data sources. Data is cleaned, missing values ​​and outliers are processed, and data quality is ensured. Useful features are extracted from the original data, such as the motion trajectory, attitude change, flight speed change, etc. of the aircraft. The extracted feature data is statistically analyzed, time series analyzed, or spatially analyzed to reveal the flight conditions and behavior patterns of the aircraft. According to the flight condition data, normal flight and abnormal flight data are marked. Appropriate features are selected and machine learning or deep learning models, such as support vector machines, decision trees, neural networks, etc., are trained to construct an aircraft flight mode classifier. The performance of the model is evaluated using methods such as cross-validation, and the model is tuned to improve classification accuracy and generalization ability. The flight feature data of the aircraft is input into the flight mode classifier for preprocessing to ensure the consistency of data format and features. The trained classifier is used to classify the data and identify different flight modes of the aircraft, including normal flight mode and abnormal flight mode. The identified flight mode data is stored or output for subsequent anomaly detection and analysis. The abnormal flight mode data is analyzed to identify abnormal events or behaviors. Extract key parameters or features from abnormal flight data, such as abnormal attitude, speed change, energy consumption, etc. Analyze abnormal parameters and generate abnormal flight reports or alerts to support aircraft operation management and maintenance decisions.

[0107] Preferably, step S22 includes the following steps:

[0108] Step S221: annotating the aircraft flight condition data to generate aircraft flight condition annotated data;

[0109] Step S222: extracting visual features and motion features from the aircraft flight situation annotation data to obtain aircraft visual feature data and aircraft motion feature data;

[0110] Step S223: merging the aircraft visual feature data and the aircraft motion feature data to obtain an aircraft flight feature data set; dividing the aircraft flight feature data set to generate a model training set and a model verification set;

[0111] Step S224: Perform model training on the model training set using a convolutional neural network algorithm to generate aircraft behavior pattern training data; perform model parameter tuning on the aircraft behavior pattern training data using a model verification set to generate an aircraft flight pattern classifier.

[0112] In an embodiment of the present invention, the collected aircraft data, including various sensor data such as position, speed, and attitude, are prepared. The data is manually or automatically annotated to mark the time periods or events of normal flight and abnormal flight. The accuracy and consistency of the annotated data are ensured, and the existing inconsistencies or ambiguities are handled. Computer vision technology and motion analysis methods are used to extract visual features such as image or video content, and motion features such as speed, acceleration, etc. from the annotated data. The extracted feature data is converted into a format that can be processed by the model, such as a vector or matrix form. The visual feature data and the motion feature data are merged according to time or event association to form a complete flight feature data set. The merged data set is divided into a model training set and a model validation set, which are usually divided by cross-validation or retention set methods to ensure the independence and effectiveness of model training and evaluation. The training set is trained using a deep learning model such as a convolutional neural network (CNN) to learn the behavior pattern of the aircraft. The model is evaluated and parameterized using the validation set to optimize the performance and generalization ability of the model. Finally, an aircraft flight mode classifier is generated, which can accurately classify the normal and abnormal flight modes of the aircraft, providing support for subsequent flight behavior analysis and anomaly detection.

[0113] Preferably, step S24 includes the following steps:

[0114] Step S241: performing abnormal type identification on the aircraft abnormal flight mode data to generate aircraft abnormal flight type data, wherein the abnormal type identification includes aircraft external environment abnormality and aircraft internal environment abnormality;

[0115] Step S242: when it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as abnormal external environment of the aircraft, an environmental impact factor analysis is performed on the aircraft environment feature data to generate environmental impact factor data; external abnormal environment parameters are extracted from the abnormal flight mode data of the aircraft according to the environmental impact factor data to obtain abnormal external environment feature data of the aircraft;

[0116] Step S243: When it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as an abnormal internal environment of the aircraft, a flight structure analysis is performed on the aircraft to generate aircraft internal structure data; a fault detection is performed on the aircraft internal structure data to generate aircraft internal structure fault data;

[0117] Step S244: performing structural influence factor analysis based on the aircraft internal structural fault data to generate structural influence factor data; performing internal abnormal operation parameter extraction on the aircraft abnormal flight mode data based on the structural influence factor data to obtain aircraft internal operation abnormality feature data;

[0118] Step S245: Integrate the abnormal characteristic data of the external environment of the aircraft and the abnormal characteristic data of the internal operation of the aircraft to generate abnormal flight parameters of the aircraft.

[0119] In an embodiment of the present invention, the abnormal flight mode data is analyzed and classified by using a classification algorithm or a rule engine to identify the type of abnormality, such as external environmental abnormality or internal structural abnormality. The external environmental conditions of the aircraft are analyzed, including factors such as weather, air quality, and electromagnetic interference. Based on the environmental influencing factor data, the external environmental parameters that affect the normal operation of the aircraft, such as wind speed, humidity, and temperature, are extracted. The internal structure of the aircraft is analyzed, including components such as circuit boards, sensors, and motors. Based on the internal structure data of the aircraft, internal faults that cause abnormal flight, such as sensor failures and circuit short circuits, are checked. The degree of influence of internal faults on the flight behavior of the aircraft is analyzed, and the influence factors of different faults on the aircraft are evaluated. The external environmental abnormality feature data and the internal operation abnormality feature data are merged to form complete abnormal flight parameters of the aircraft.

[0120] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0121] Step S31: using GPS to obtain real-time flight position data of the aircraft;

[0122] Step S32: marking the real-time flight position data of the aircraft with spatial coordinate points according to the normal flight mode data of the aircraft to obtain the real-time flight spatial coordinate data of the aircraft; tracking the flight path of the aircraft through the real-time flight spatial coordinate data of the aircraft to generate the real-time flight path of the aircraft;

[0123] Step S33: Calculating the path deviation of the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain the abnormal flight deviation path of the aircraft;

[0124] Step S34: performing attitude control on the aircraft based on the abnormal flight deviation path of the aircraft to generate aircraft attitude control adjustment data; performing path trajectory planning adjustment on the abnormal flight deviation path of the aircraft based on the aircraft attitude control adjustment data to generate aircraft path trajectory planning adjustment data;

[0125] Step S35: construct an initial control strategy for the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data using the three-dimensional flight virtual scene to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data.

[0126] In an embodiment of the present invention, the current longitude, latitude, altitude and other position information of the aircraft are obtained through a GPS module or system. Ensure that the aircraft position data can be updated in real time to reflect the current position state of the aircraft. The real-time acquired GPS data is marked and processed according to the spatial coordinate system to obtain the coordinate data of the aircraft in three-dimensional space. The real-time position data of the aircraft is processed and predicted using a tracking algorithm (such as a Kalman filter or a path planning algorithm) to generate the current real-time flight path of the aircraft. The normal flight path is compared and analyzed using abnormal flight parameter data to calculate the deviation of the aircraft from the expected path. According to the abnormal deviation path data, the attitude control parameters of the aircraft are adjusted so that the path deviation can be corrected more effectively. Based on the adjusted attitude control data, the path trajectory of the aircraft is replanned to ensure that the aircraft can fly safely along the corrected path. The attitude control and path planning adjustment process of the aircraft is simulated in a three-dimensional flight virtual scene to generate an initial flight control strategy. The initial control strategy is analyzed for stability using an engineering method or a mathematical model to evaluate its stability and reliability under various flight conditions.

[0127] Preferably, step S35 includes the following steps:

[0128] Step S351: Parameter mapping is performed on the three-dimensional flight virtual scene according to the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to obtain a target attitude mapping sequence and a target flight path mapping data;

[0129] Step S352: constructing an initial control strategy based on the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to generate an initial flight control strategy; performing simulation control on the initial flight control strategy through a preset time step, and recording the control strategy performance data;

[0130] Step S353: Perform strategy stability analysis on the control strategy performance data to generate strategy stability analysis data.

[0131] In an embodiment of the present invention, the attitude control adjustment data and path planning adjustment data of the aircraft are mapped to model parameters in a three-dimensional flight virtual scene, including the target attitude sequence and target flight path data of the aircraft. The flight process of the aircraft is simulated in a virtual environment to ensure the accuracy and real-time performance of attitude and path adjustment. An initial flight control strategy is constructed based on the mapped target attitude and path data. The flight control strategy is simulated and controlled according to a preset time step in the virtual scene to simulate the attitude adjustment and path planning process of the aircraft. Performance data during the control process is recorded, including parameters such as attitude stability and path tracking accuracy. The recorded performance data is analyzed and evaluated using engineering methods or mathematical models to evaluate the stability and reliability of the control strategy under different conditions. The initial control strategy is optimized based on the stability analysis results to ensure that the aircraft can maintain stable attitude and path control under various flight conditions. More specifically, computer graphics and virtual reality technology are used to map the attitude control adjustment data (such as Euler angles or quaternions) and path planning adjustment data of the aircraft to the aircraft model in the three-dimensional scene. In the virtual environment, the attitude and position of the aircraft model are dynamically adjusted based on the mapped target attitude sequence and flight path data to simulate the actual flight process. Design initial control algorithms and strategies, such as PID controllers or model predictive control (MPC), based on the attitude and path adjustment requirements of the aircraft in the virtual scene. Implement the initial control strategy in the virtual environment, simulate the movement of the aircraft through simulation software or real-time rendering engine, and record the actual attitude and path adjustment of the aircraft. Record key performance data during the control process in real time, such as attitude stability, path deviation, response time, etc., for subsequent analysis and evaluation. Use system analysis tools or mathematical modeling techniques to quantitatively analyze the recorded performance data and evaluate the stability and robustness of the control strategy under different conditions. Adjust and optimize the initial control strategy based on the results of the stability analysis, improve the control algorithm parameters or enhance the adaptability of the control strategy to improve the control accuracy and safety of the aircraft.

[0132] Preferably, step S353 includes the following steps:

[0133] Step S3531: Perform basic performance index analysis on the control strategy performance data to obtain basic performance index data;

[0134] Step S3532: Evaluate the control effect of the initial flight control strategy through basic performance indicator data to generate strategy control effect evaluation data;

[0135] Step S3533: Calculate the control steady-state error of the strategy control effect evaluation data to obtain strategy stability index data;

[0136] Step S3534: Perform statistical analysis on the strategy stability index data to generate strategy control statistical analysis data; perform time series analysis on the control strategy performance data to generate strategy control time series stability data;

[0137] Step S3535: Integrate the basic performance indicator data, the policy stability indicator data, the policy control statistical analysis data and the policy control time series stability data to generate policy stability analysis data.

[0138] In an embodiment of the present invention, the recorded control strategy performance data includes basic performance indicators such as posture stability, path deviation, and response time. Extract key performance indicator data, such as maximum posture deviation, mean and variance of path tracking error, etc. Evaluate the effect of the control strategy based on the extracted performance indicator data, and analyze the response speed, accuracy and stability of the controller. Record various effect data obtained during the evaluation process, such as the response curve of the controller, posture stability score, etc. Calculate the error of the controller in a stable state, and evaluate the control strategy's ability to continuously control the target posture and path. Extract statistical data of steady-state errors, such as average steady-state error, error variance, etc. Use statistical methods to analyze stability indicator data and evaluate the stability and consistency of the control strategy under different conditions. Analyze the stability changes of the control strategy in time series and explore the evolution trend of the control effect over time. Integrate the data obtained from the above analyses into a complete strategy stability analysis report or data set. Generate a comprehensive stability analysis report including basic performance indicators, stability indicators, statistical analysis and timing analysis to provide a basis and reference for control strategy optimization and improvement.

[0139] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0140] Step S41: performing optimal control solution on the initial flight control strategy based on the strategy stability analysis data to generate optimal strategy control data;

[0141] Step S42: performing Monte Carlo simulation on the three-dimensional flight virtual scene according to the optimal strategy control data to generate a control strategy simulation data set;

[0142] Step S43: Perform logic control instruction conversion based on the control strategy simulation data set to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

[0143] In the embodiment of the present invention, the initial flight control strategy is optimized and solved based on the strategy stability analysis data by using an optimization algorithm (such as a genetic algorithm, a particle swarm optimization or a simulated annealing algorithm) to improve the efficiency and performance of the control strategy. According to the optimal control parameters and strategy adjustment data obtained by solving, an optimized optimal flight control strategy is generated. The stability and reliability of the optimal control strategy under various flight conditions are verified and evaluated by random sampling and multiple simulations in a three-dimensional flight virtual scene. The stability and reliability of the optimal control strategy under various flight conditions are verified and evaluated by random sampling and multiple simulations in a three-dimensional flight virtual scene. According to the analysis and evaluation of the simulation data set, the logical control instructions of the aircraft flight control system are designed, including functions such as attitude adjustment, flight path planning and emergency response. The designed logical control instructions are converted into an instruction format that the flight control system can understand and execute, so as to realize various control tasks and operations of the aircraft in actual flight, and the optimization algorithm suitable for the characteristics of the problem is specifically selected, such as a genetic algorithm, a particle swarm optimization, a simulated annealing, etc. Considering the real-time and complexity of flight control, a hybrid algorithm or an adaptive algorithm is used to improve the convergence speed and the quality of the solution. Optimize key parameters of the control strategy, such as control gain, path planning parameters or attitude adjustment strategy, to maximize the performance and stability of the control system. Convert the optimal control parameters and strategy adjustment data obtained from the optimization into a data format that can be actually executed by the aircraft control system. Cover various flight conditions and environmental changes through random sampling and a large number of repeated simulations in the simulation environment. Record the control effect data during the simulation process, including indicators in multiple aspects such as attitude stability, path tracking accuracy, and response speed. Integrate and process simulation data to form a simulation data set containing a large number of control strategy effect evaluations for subsequent evaluation and verification. According to the analysis results and requirements of the simulation data set, design specific flight control logic control instructions, including takeoff, landing, heading control, altitude control and other flight tasks. Convert the designed logic control instructions into an instruction format that can be understood and executed by a specific flight control system to ensure compatibility with the hardware platform and software algorithm. Load the generated flight control logic control instructions into the flight control system of the aircraft, perform actual functional logic model design operations, and verify and optimize the actual effect and performance of the control strategy.

[0144] The beneficial effect of the present invention is that by unifying the format of multi-source data of aircraft and reconstructing the scene, a three-dimensional flight virtual scene can be obtained, which helps to simulate and analyze the operating environment of the aircraft more accurately. By analyzing the flight situation data of the aircraft, an aircraft flight mode classifier can be constructed to identify the flight mode of the aircraft. This helps to understand the behavior and performance of the aircraft and provides a basis for subsequent control strategies. By analyzing the flight mode data of the aircraft, abnormal flight parameters can be extracted, which can be used to detect and judge whether the aircraft has abnormal conditions, so as to take corresponding control measures to ensure the safe operation of the aircraft. According to the real-time flight position data and normal flight mode data of the aircraft, flight path tracking can be performed, and an initial flight control strategy can be constructed based on abnormal flight parameters. This helps the aircraft to remain stable and safe in real-time operation. Stability analysis is performed on the initial flight control strategy to ensure the effectiveness and safety of the control strategy. Then, by solving the optimal control, the optimal strategy control data is obtained, so as to achieve the best control performance of the aircraft. The optimal strategy control data is converted into aircraft flight control logic control instructions to perform the flight control system functional logic model design operation. This helps to achieve precise control and operation of the aircraft. Therefore, the present invention improves the adaptability and optimization capability of the design of the functional logic model of the flight control system by unifying multi-source data, accurately analyzing the flight situation, and optimizing the flight control strategy.

[0145] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0146] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A flight control system functional logic model design method, characterized in that: The following steps are involved: Step S1: Acquire multi-source data of aircraft; Unify the data format of multi-source data of aircraft to generate a unified multi-source data set of aircraft; reconstruct the flight virtual scene of the multi-source unified data set of aircraft to generate a three-dimensional flight virtual scene; Step S2: analyzing the aircraft flight situation of the aircraft multi-source unified data set to obtain aircraft flight situation data; constructing a flight classifier based on the aircraft flight situation data to obtain an aircraft flight mode classifier; using the aircraft flight mode classifier to identify the aircraft flight mode of the aircraft flight motion feature data to generate aircraft flight mode data; extracting abnormal flight parameters from the aircraft flight mode data to generate abnormal aircraft flight parameters; Step S3: Acquire the real-time flight position data of the aircraft; perform flight path tracking on the real-time flight position data of the aircraft according to the normal flight mode data of the aircraft to generate the real-time flight path of the aircraft; construct an initial control strategy for the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data; Step S4: Based on the strategy stability analysis data, the initial flight control strategy is optimally solved to generate optimal strategy control data; according to the optimal strategy control data, the three-dimensional flight virtual scene is logically converted to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

2. The flight control system functional logic model design method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using a distributed sensor network to obtain multi-source data of the aircraft; Step S12: performing data preprocessing on the aircraft multi-source data to generate standard aircraft multi-source data, wherein the data preprocessing includes data cleaning, data denoising, data missing value filling and data standardization; Step S13: unifying the data format of the standard aircraft multi-source data to generate an aircraft multi-source unified data set; Step S14: Reconstruct the flight virtual scene of the aircraft multi-source unified data set through virtual reality enhancement technology to generate a three-dimensional flight virtual scene.

3. The flight control system functional logic model design method according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: extracting flight environment features from the aircraft multi-source unified data set to obtain aircraft environment feature data; Step S142: reconstructing the aircraft environment feature data based on virtual reality enhancement technology to generate aircraft environment reconstruction data; Step S143: dynamically simulating the aircraft using the aircraft environment reconstruction data to generate aircraft dynamic simulation data; Step S144: Perform virtual sensor fusion based on the aircraft dynamic simulation data and the aircraft environment reconstruction data to generate a three-dimensional flight virtual scene.

4. The flight control system functional logic model design method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: analyzing the aircraft flight situation on the aircraft multi-source unified data set to obtain aircraft flight situation data; Step S22: constructing a flight classifier according to the aircraft flight situation data to obtain an aircraft flight mode classifier; Step S23: using an aircraft flight mode classifier to perform aircraft flight mode recognition on the aircraft flight motion feature data to generate aircraft flight mode data, wherein the aircraft flight mode data includes aircraft normal flight mode data and aircraft abnormal flight mode data; Step S24: extracting abnormal flight parameters from the aircraft abnormal flight mode data to generate abnormal flight parameters of the aircraft.

5. The flight control system functional logic model design method according to claim 4, characterized in that: Step S22 includes the following steps: Step S221: annotating the aircraft flight condition data to generate aircraft flight condition annotated data; Step S222: extracting visual features and motion features from the aircraft flight situation annotation data to obtain aircraft visual feature data and aircraft motion feature data; Step S223: merging the aircraft visual feature data and the aircraft motion feature data to obtain an aircraft flight feature data set; dividing the aircraft flight feature data set to generate a model training set and a model verification set; Step S224: Perform model training on the model training set using a convolutional neural network algorithm to generate aircraft behavior pattern training data; perform model parameter tuning on the aircraft behavior pattern training data using a model verification set to generate an aircraft flight pattern classifier.

6. The flight control system functional logic model design method according to claim 5, characterized in that: Step S24 includes the following steps: Step S241: performing abnormal type identification on the aircraft abnormal flight mode data to generate aircraft abnormal flight type data, wherein the abnormal type identification includes aircraft external environment abnormality and aircraft internal environment abnormality; Step S242: when it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as abnormal external environment of the aircraft, an environmental impact factor analysis is performed on the aircraft environment feature data to generate environmental impact factor data; external abnormal environment parameters are extracted from the abnormal flight mode data of the aircraft according to the environmental impact factor data to obtain abnormal external environment feature data of the aircraft; Step S243: When it is confirmed that the abnormal type of the abnormal flight mode data of the aircraft is identified as an abnormal internal environment of the aircraft, a flight structure analysis is performed on the aircraft to generate aircraft internal structure data; a fault detection is performed on the aircraft internal structure data to generate aircraft internal structure fault data; Step S244: performing structural influence factor analysis based on the aircraft internal structural fault data to generate structural influence factor data; performing internal abnormal operation parameter extraction on the aircraft abnormal flight mode data based on the structural influence factor data to obtain aircraft internal operation abnormality feature data; Step S245: Integrate the abnormal characteristic data of the external environment of the aircraft and the abnormal characteristic data of the internal operation of the aircraft to generate abnormal flight parameters of the aircraft.

7. The flight control system functional logic model design method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: using GPS to obtain real-time flight position data of the aircraft; Step S32: marking the real-time flight position data of the aircraft with spatial coordinate points according to the normal flight mode data of the aircraft to obtain the real-time flight spatial coordinate data of the aircraft; tracking the flight path of the aircraft through the real-time flight spatial coordinate data of the aircraft to generate the real-time flight path of the aircraft; Step S33: Calculating the path deviation of the real-time flight path of the aircraft based on the abnormal flight parameters of the aircraft to obtain the abnormal flight deviation path of the aircraft; Step S34: performing attitude control on the aircraft based on the abnormal flight deviation path of the aircraft to generate aircraft attitude control adjustment data; performing path trajectory planning adjustment on the abnormal flight deviation path of the aircraft based on the aircraft attitude control adjustment data to generate aircraft path trajectory planning adjustment data; Step S35: construct an initial control strategy for the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data using the three-dimensional flight virtual scene to obtain an initial flight control strategy; perform stability analysis on the initial flight control strategy to generate strategy stability analysis data.

8. The flight control system functional logic model design method according to claim 7, characterized in that: Step S35 includes the following steps: Step S351: Parameter mapping is performed on the three-dimensional flight virtual scene according to the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to obtain a target attitude mapping sequence and a target flight path mapping data; Step S352: constructing an initial control strategy based on the aircraft attitude control adjustment data and the aircraft path trajectory planning adjustment data to generate an initial flight control strategy; performing simulation control on the initial flight control strategy through a preset time step, and recording the control strategy performance data; Step S353: Perform strategy stability analysis on the control strategy performance data to generate strategy stability analysis data.

9. The flight control system functional logic model design method according to claim 8, characterized in that: Step S353 includes the following steps: Step S3531: Perform basic performance index analysis on the control strategy performance data to obtain basic performance index data; Step S3532: Evaluate the control effect of the initial flight control strategy through basic performance indicator data to generate strategy control effect evaluation data; Step S3533: Calculate the control steady-state error of the strategy control effect evaluation data to obtain strategy stability index data; Step S3534: Perform statistical analysis on the strategy stability index data to generate strategy control statistical analysis data; perform time series analysis on the control strategy performance data to generate strategy control time series stability data; Step S3535: Integrate the basic performance indicator data, the policy stability indicator data, the policy control statistical analysis data and the policy control time series stability data to generate policy stability analysis data.

10. The flight control system functional logic model design method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing optimal control solution on the initial flight control strategy based on the strategy stability analysis data to generate optimal strategy control data; Step S42: performing Monte Carlo simulation on the three-dimensional flight virtual scene according to the optimal strategy control data to generate a control strategy simulation data set; Step S43: Perform logic control instruction conversion based on the control strategy simulation data set to generate aircraft flight control logic control instructions to execute the flight control system functional logic model design task.

Images