Wireless transmission and processing system for flight data of training plane

Abstract

The invention provides a training plane flight data wireless transmission and processing system, and belongs to the technical field of aviation wireless communication. The core of the system comprises a flight state vector analysis module which is used for processing sensor data and generating a real-time flight state vector; the data flow dynamic criticality evaluation module is used for calculating the dynamic criticality index of each data packet in combination with the flight state; the transmission strategy generation module is used for determining an optimal transmission mode according to the data criticality and the real-time channel quality; the wireless resource self-adaptive reconstruction module is used for performing real-time reconstruction on a physical layer and a media access control layer of the wireless transceiver according to the optimal mode; the system can analyze flight parameters in real time and dynamically evaluate the importance of data streams; when the aircraft enters critical states such as stall or large overload, the system can automatically improve the transmission priority of related data; the technical problem that in the prior art, a transmission strategy is rigid and cannot adapt to dynamic changes of flight situations is solved.

Description

Technical Field

[0001] This invention relates to the field of aviation wireless communication technology, specifically to a wireless transmission and processing system for flight data of a trainer aircraft. Background Technology

[0002] As the complexity of trainer aircraft training missions increases, the demand for data interaction between airborne systems and ground stations is growing. As a key component, the wireless data transmission system needs to process multiple types of data streams, including flight safety alarms, critical status parameters, and routine telemetry information. The reliability and real-time performance of its transmission directly affect flight safety and training effectiveness. Existing data transmission schemes typically employ static priorities or fixed transmission strategies. Under this mechanism, the importance of different data is pre-set and remains unchanged throughout the flight. However, both flight scenarios and wireless channel environments are constantly changing. When an aircraft enters a high-G maneuver or is near a stall, such rigid strategies cannot dynamically increase the transmission priority of relevant data according to the severity of the situation. At the same time, when the quality of the wireless channel deteriorates due to interference or obstruction, the system cannot adaptively adjust parameters such as modulation and coding or transmit power to ensure the stability of the communication link. This mechanism, lacking environmental awareness and adaptive adjustment capabilities, leads to suboptimal allocation of wireless resources, which may cause high latency or even loss of important data at critical moments, failing to maximize transmission performance with limited bandwidth resources. Therefore, how to construct a wireless transmission system that can sense flight status and channel changes in real time, and dynamically assess the importance of data and make intelligent decisions on the optimal transmission strategy to solve the problem of rigid strategies in existing technologies has become an urgent technical problem to be solved in this field. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a wireless transmission and processing system for trainer aircraft flight data. Specifically, the technical solution of this invention includes: The flight state vector parsing module is used to process sensor data acquired from the onboard avionics bus to generate real-time flight state vectors. The data stream dynamic criticality assessment module is used to calculate the dynamic criticality index for the data packet by combining the real-time flight state vector generated by the flight state vector parsing module, the preset basic criticality of the data packet, and the preset risk weight coefficient. The transmission strategy generation module is used to determine the optimal transmission mode for the data packet based on the dynamic criticality index calculated by the data stream dynamic criticality assessment module and real-time channel quality information. The wireless resource adaptive reconfiguration module is used to reconfigure the physical layer and media access control layer of the wireless transceiver in real time according to the optimal transmission mode determined by the transmission strategy generation module.

[0004] Preferably, the data stream dynamic criticality assessment module is specifically used for: Based on the flight state parameters in the real-time flight state vector, and through a preset scenario risk function, the scenario risk value is obtained; Calculate the risk adjustment term based on the scenario risk value and the preset risk weight coefficient; The dynamic criticality index is generated by combining the preset basic criticality of the data packet with the risk adjustment item.

[0005] Preferably, the transmission strategy generation module is specifically used for: For each transmission mode in the preset transmission mode set, calculate its transmission utility. The transmission mode with the highest calculated transmission utility value is determined as the optimal transmission mode.

[0006] Preferably, the calculation of the transmission utility includes: Based on the dynamic criticality index and the time cost of the transmission mode, the transmission revenue item is calculated; Based on the dynamic criticality index, the estimated packet error rate of the transmission mode, and the preset penalty factor, the transmission cost item is calculated. The transmission utility is obtained by subtracting the transmission cost from the transmission revenue item.

[0007] Preferably, the estimated packet error rate of the transmission mode is determined in the following way: Extract real-time channel quality metrics from the channel state information of the wireless transceiver; The real-time channel quality index is used as input and substituted into a pre-calibrated performance curve function or lookup table to obtain the estimated packet error rate corresponding to the transmission mode.

[0008] Preferably, the wireless resource adaptive reconfiguration module is specifically used for: Based on the optimal transmission mode, the modulation and coding scheme and the transmit power are determined; Configure the physical layer to set the modulation and coding scheme and the transmit power; Preemptive scheduling is performed at the media access control layer to prioritize the transmission of data packets with a high dynamic criticality index.

[0009] Preferably, the situational risk function is a piecewise function or a sigmoid function pre-defined based on the aircraft's aerodynamic model and flight manual.

[0010] Preferably, the initial value of the risk weight coefficient is determined through offline optimization using a flight simulator.

[0011] Preferably, the penalty factor is a system-level adjustable parameter preset based on the flight mission profile.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. By analyzing flight status parameters in real time, the system can dynamically assess the real-time criticality of data streams. When the aircraft enters special states such as near stall or high G-force, it can automatically increase the transmission priority of relevant data, solving the problem of rigid transmission strategies and inability to adapt to changes in flight scenarios in existing technologies. 2. The system comprehensively considers the dynamic criticality index of the data and the real-time channel quality, and intelligently decides the optimal transmission mode for each data packet by calculating the transmission utility, thereby achieving the optimal balance between transmission reliability and efficiency and avoiding the risk of delay or loss of critical data transmission due to channel degradation. 3. Based on the optimal transmission strategy, the system can adaptively reconstruct the physical layer and media access control layer of the wireless transceiver. By adjusting the modulation and coding scheme, transmission power and executing preemptive scheduling, it ensures that highly critical data, especially emergency alarm information related to security, can be sent with the lowest latency. 4. The system’s situational risk assessment is based on the aircraft’s aerodynamic model and flight manual. Key weight parameters are determined through offline optimization using a flight simulator, which provides a solid scientific basis for the decision-making model, improves the accuracy of risk perception and the overall reliability of the system, and avoids the uncertainty caused by relying on subjective experience to set parameters. Attached Figure Description

[0013] The present invention will be further explained below with reference to the accompanying drawings and embodiments: Figure 1 This is a structural diagram of the system of the present invention. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0015] Example 1: Please see Figure 1 A wireless transmission and processing system for flight data of a trainer aircraft, comprising: The flight state vector parsing module is used to process sensor data acquired from the onboard avionics bus to generate real-time flight state vectors. The data stream dynamic criticality assessment module is used to calculate the dynamic criticality index for the data packet by combining the real-time flight state vector generated by the flight state vector parsing module, the preset basic criticality of the data packet, and the preset risk weight coefficient. The transmission strategy generation module is used to determine the optimal transmission mode for the data packet based on the dynamic criticality index calculated by the data stream dynamic criticality assessment module and real-time channel quality information. The wireless resource adaptive reconfiguration module is used to reconfigure the physical layer and media access control layer of the wireless transceiver in real time according to the optimal transmission mode determined by the transmission strategy generation module.

[0016] This embodiment provides a wireless transmission and processing system for flight data of a trainer aircraft. The system aims to solve the technical problem that the data transmission strategy in the prior art is rigid and cannot adapt to the dynamic changes in flight situation and channel conditions. Its core idea is to build a closed-loop control system from real-time perception of flight situation, dynamic evaluation of data criticality, intelligent decision-making of transmission strategy to adaptive execution of wireless resources, so as to achieve a dynamic balance between high reliability and low latency transmission of critical data and maximum throughput of conventional data under limited airborne and wireless resources. In this embodiment, the system, as a complete and self-consistent technical closed loop, includes the following four core modules, which work closely together in logical order: The flight state vector analysis module aims to provide a unified, real-time, and standardized context-aware input for the entire system's decision-making. As the system's context input unit, this module is responsible for real-time collection and processing of multi-source heterogeneous sensor data acquired from the onboard avionics bus. In this embodiment, it generates a standardized real-time flight state vector by collecting, analyzing, and normalizing raw sensor data, including angle of attack, normal overload, roll rate, engine speed, and altitude. The vector is immediately output to the data stream dynamic criticality assessment module, serving as the sole data basis for its contextual analysis, ensuring the real-time nature and accuracy of subsequent decisions. The data stream dynamic criticality assessment module aims to assign a dynamically changing priority to each data packet to be transmitted based on the real-time flight context. As the core decision-making module of the system, it receives the real-time flight state vector generated by the flight state vector resolution module. In addition, a quantified dynamic criticality index is calculated for each data packet to be sent, based on the packet's own preset basic criticality and preset risk weight coefficient. This index abandons the rigid mechanism of traditional static prioritization, enabling the importance of data to be precisely matched with the actual urgency of the flight mission. The transmission strategy generation module aims to select the optimal transmission resource allocation scheme based on the dynamic criticality of data packets and real-time channel quality. As the system's transmission planning unit, this module receives the dynamic criticality index calculated by the data stream dynamic criticality evaluation module. In conjunction with real-time channel quality information obtained from the wireless transceiver, an optimization decision model is used to determine the optimal transmission mode for the data packet that maximizes transmission efficiency. ; The wireless resource adaptive reconfiguration module aims to transform the abstract policy instructions generated by the upper-layer module into specific configuration and scheduling actions for the wireless communication hardware. As the system's physical execution unit, this module receives the optimal transmission mode determined by the transmission policy generation module. Based on this, the physical layer (PHY) and media access control layer (MAC) of the wireless transceiver are reconstructed in real time; this includes, but is not limited to, adjusting the modulation and coding scheme, transmit power, and performing preemptive channel access scheduling. Through the sequential execution and close collaboration of the above four modules, this embodiment constructs a complete closed-loop adaptive control link from perception, decision-making, planning to execution. It can perceive the ever-changing flight situation and electromagnetic environment in real time, dynamically and accurately assess the real-time importance of each data packet, and intelligently and adaptively schedule and reconstruct limited wireless resources accordingly. While ensuring deterministic low-latency transmission of key flight event data such as stall alarms, it maximizes the transmission bandwidth of conventional telemetry data and the overall transmission efficiency of the system, significantly improving the data interaction capability and flight safety level of the trainer aircraft in complex training scenarios.

[0017] Example 2: The data flow dynamic criticality assessment module is specifically used for: Based on the flight state parameters in the real-time flight state vector, and through a preset scenario risk function, the scenario risk value is obtained; Calculate the risk adjustment term based on the scenario risk value and the preset risk weight coefficient; The dynamic criticality index is generated by combining the preset basic criticality of the data packet with the risk adjustment item.

[0018] Based on the system described in Example 1, this example further specifies the implementation method of the data flow dynamic criticality assessment module; in order to transform the abstract flight scenario into a precise, quantifiable dynamic criticality index, this module is implemented according to the following logical steps: Based on the flight state parameters in the real-time flight state vector, and through a preset scenario risk function, the scenario risk value is obtained; Real-time flight state vector This refers to the flight state vector analysis module that generates multiple normalized flight parameters. Vectors such as angle of attack and normal overload; situational risk function. This refers to one or more pre-defined nonlinear mapping functions, whose function is to map individual flight state parameter values. This is mapped to a dimensionless risk value that quantifies the severity of the parameter. This risk value is derived from pre-defined parameters based on the aircraft's aerodynamic model and flight manual, and stored in the onboard configuration; for example, when the real-time flight state vector... When the angle-of-attack parameter value is close to the stall boundary, the corresponding situational risk function It will output a situational risk value that increases rapidly and non-linearly; Calculate the risk adjustment term based on the scenario risk value and the preset risk weight coefficient; Risk weighting coefficient This refers to a coefficient associated with a specific data packet type, used to adjust the degree of influence of different flight parameter risks on the final criticality of that data packet. Its function is to reflect the difference in importance of different flight parameters for different types of data, and its source is preset values ​​stored in the onboard database. For example, for an engine temperature data packet, the risk weight coefficients of its associated engine speed and temperature parameters would be set higher. The risk adjustment term is obtained by adjusting the situational risk values ​​corresponding to each flight parameter. Its corresponding risk weight coefficient The summation of the multiplication results in a comprehensive analysis of the risk contributions of all current flight parameters. The dynamic criticality index is generated by combining the preset basic criticality of the data packet with the risk adjustment item; Preset basic key This refers to an initial criticality level statically assigned based on data type. Its function is to provide a fundamental measure of importance for data packets, independent of real-time context. This level is derived from static values ​​determined a priori by flight experts based on data properties and stored in an onboard database. For example, this applies to stall warnings. Far exceeding conventional GPS positioning information; ultimately, the dynamic criticality index The fundamental criticality of the data packet The risk adjustment term is calculated using a specific mathematical model, for example, by multiplying the basic criticality by a gain factor consisting of the risk adjustment term; It establishes a clear and interpretable computational path from multidimensional flight parameters to single quantified risk, and finally to dynamic criticality; this design ensures that the assessment of data criticality considers not only the inherent importance of the data packet. It innovatively incorporates a real-time, multi-dimensional quantitative assessment of the risk level of the current flight situation, thereby greatly enhancing the system's situational adaptability and enabling the allocation decisions of transmission resources to more accurately match the actual urgency of the flight mission.

[0019] Example 3: The transmission strategy generation module is specifically used for: For each transmission mode in the preset transmission mode set, calculate its transmission utility. The transmission mode with the highest calculated transmission utility value is determined as the optimal transmission mode.

[0020] Based on the system described in Example 1, this example optimizes the specific method for the transmission strategy generation module to determine the optimal transmission mode; to avoid using a simple hard handover mechanism based on threshold judgment, this example introduces an optimization decision model based on utility theory to seek the global optimal solution; The system has a pre-defined set that includes multiple transmission modes. Transmission mode It refers to a specific combination of physical layer and media access control layer parameters. For example, different modulation and coding schemes (MCS), transmit power levels, etc. together constitute a transmission mode. Each mode corresponds to different transmission rates, reliability and time overhead. For each transmission mode in the preset transmission mode set, calculate its transmission utility. Transmission efficiency This refers to a quantitative indicator used to evaluate the use of a specific transmission mode. To send current dynamic key indexes The net benefit that can be obtained from the data packet; this calculation takes into account the value of the data packet, the timeliness of transmission, and the potential cost of packet loss; The transmission mode with the highest calculated transmission utility value is determined as the optimal transmission mode. ; This step involves iterating through all candidate transport modes. And compare their transmission utility values The optimal transmission mode is selected based on the mode that maximizes the output value of the utility function. It is then passed to the wireless resource adaptive reconfiguration module for execution; This embodiment transforms the transmission mode selection problem from an empirical rule-based judgment into a quantifiable optimization problem. By calculating a specific transmission utility score for each possible transmission mode, the system can make a mathematically optimal trade-off between various options such as fast but unstable and slow but reliable, thereby ensuring that every decision is made to maximize overall benefits. This avoids the suboptimal selection problem of traditional strategies and significantly improves the utilization efficiency of wireless resources and the overall system performance.

[0021] Example 4: The calculation of transmission utility includes: Based on the dynamic criticality index and the time cost of the transmission mode, the transmission revenue item is calculated; Based on the dynamic criticality index, the estimated packet error rate of the transmission mode, the preset penalty factor, and the time cost of the transmission mode, the transmission cost item is calculated. The transmission utility is obtained by subtracting the transmission cost from the transmission revenue item.

[0022] Based on the system described in Example 3, this example further clarifies the method for calculating transmission utility, which is implemented through a mathematical model that integrates benefits and costs; Transmission efficiency The calculation specifically includes the following steps: Based on the dynamic criticality index and the time cost of the transmission mode, the transmission revenue item is calculated; Dynamic Keyness Index This refers to the numerical value output by the data stream dynamic criticality assessment module, which quantifies the current importance of data packets; time overhead. This refers to selecting a specific transmission mode. The time required to send a standard data packet is derived from a predetermined value obtained by consulting the onboard hardware parameter library based on the data rate and standard packet length of this mode; the transmission benefit term is designed as a dynamic criticality index. Functions such as logarithmic functions To reflect diminishing marginal utility and to correlate with time expenditure Inversely proportional; its physical meaning is that the higher the value of the information, the faster it is successfully delivered, and the greater the resulting benefit; specifically, the benefit of transmission... The calculation formula can be expressed as: ; in, The preset dimensionless profit coefficient is used; this formula uses This format ensures that when key indicators... When the value is 0, the benefit term is 0, which avoids the singularity problem in mathematical calculation and enhances the robustness of the model; Based on the dynamic criticality index, the estimated packet error rate of the transmission mode, the preset penalty factor, and the time cost of the transmission mode, the transmission cost item is calculated. Estimated packet error rate This refers to using a specific transmission mode under the current channel conditions. The estimated probability of packet loss when sending data packets; penalty factor. This refers to a system-level adjustable parameter that quantifies the severity of critical losses caused by packet loss. To ensure dimensional consistency, the transmission cost term is designed as a time-dependent expected loss rate. Its physical meaning is that the higher the value of the information, the greater the cost per unit time if it is lost due to unreliable transmission methods. Specifically, the transmission cost term... The calculation formula can be expressed as: ; The transmission utility is obtained by subtracting the transmission cost from the transmission revenue item. This subtraction operation intuitively embodies the concept of net benefit, which is to use the potential benefit per unit of time to offset the risk cost per unit of time, ultimately obtaining the transmission utility value. It is a decision-making criterion that integrates speed, reliability, and data value.

[0023] This embodiment provides a transmission utility calculation model with a clear structure and explicit physical meaning. It concretizes the abstract concept of transmission quality into the unity of opposites between benefits and costs, making the decision-making process more scientific and transparent. Through this model, the system can accurately quantify and avoid the high costs of packet loss while pursuing high-speed transmission and high benefits. In this way, it can intelligently find the best balance point for different key data in highly dynamic and error-prone wireless channels, achieving dual optimization of transmission efficiency and reliability.

[0024] Example 5: The estimated packet error rate of the transmission mode is determined in the following way: Extract real-time channel quality metrics from the channel state information of the wireless transceiver; The real-time channel quality index is used as input and substituted into a pre-calibrated performance curve function or lookup table to obtain the estimated packet error rate corresponding to the transmission mode.

[0025] Based on the system described in Example 4, this example estimates the packet error rate of the key parameter transmission mode. The determination method was explained in detail, ensuring the accuracy and real-time performance of the transmission cost calculation. Estimated packet error rate It is determined in real time through a two-step process: Extract real-time channel quality metrics from the channel state information of the wireless transceiver; Channel State Information (CSI) refers to the raw data set from which the physical layer of a wireless transceiver perceives the current channel characteristics in real time. In this embodiment, one or more key Channel Quality Indicators (CQIs), such as Signal-to-Noise Ratio (SNR), are extracted from it. This step ensures that the packet error rate estimate is based on the most realistic current channel physical conditions. The real-time channel quality index is used as input and substituted into a pre-calibrated performance curve function or lookup table to obtain the estimated packet error rate corresponding to the transmission mode. Performance curve functions or lookup tables refer to a pre-established mathematical relationship model. Its function is to describe a specific transmission mode adopted under a specific channel quality index. For example, the packet error rate at a specific MCS (Multi-Channel System) is generated through offline calibration or link-level simulation of the wireless transceiver under different channel conditions and stored in onboard memory; this is achieved by measuring channel quality indicators in real time, such as... By inputting values ​​into this model, you can query or calculate the estimated packet error rate for each alternative transmission mode under the current conditions. ; This implementation provides crucial, real-time, and accurate input for the transmission utility model; it transforms packet error rate prediction from blind guessing to scientific inference based on real-time physical channel measurements, greatly improving the accuracy of transmission strategy decisions; since the estimated packet error rate can reflect instantaneous changes in the channel in real time, the system thus has the ability to quickly respond to channel degradation, such as when the signal-to-noise ratio suddenly drops, it can quickly switch critical data to a more robust transmission mode, thereby effectively ensuring communication reliability in scenarios with drastic channel changes, such as high-maneuverability flight.

[0026] Example 6: The wireless resource adaptive reconfiguration module is specifically used for: Based on the optimal transmission mode, the modulation and coding scheme and the transmit power are determined; Configure the physical layer to set the modulation and coding scheme and the transmit power; Preemptive scheduling is performed at the media access control layer to prioritize the transmission of data packets with a high dynamic criticality index.

[0027] Based on the system described in Example 1, this example refines the specific execution functions of the wireless resource adaptive reconfiguration module to ensure that upper-layer decisions can be accurately translated into actual actions of the underlying hardware. The specific implementation of this module includes the following three levels of operations: Based on the optimal transmission mode, the modulation and coding scheme and the transmit power are determined; Optimal transmission mode The decision result is output by the transmission strategy generation module; the wireless resource adaptive reconfiguration module will parse the mode and map it to a set of specific physical layer parameters; the modulation and coding scheme (MCS) and transmit power are the two most critical parameters, which directly determine the data transmission rate and anti-interference capability. Configure the physical layer to set the modulation and coding scheme and the transmit power; This step involves specific hardware configuration actions; the module adjusts its operating parameters dynamically and in real time by sending instructions to the physical layer controller of the wireless transceiver to keep them consistent with the determined MCS and transmit power. Preemptive scheduling is performed at the media access control layer to prioritize the transmission of data packets with a high dynamic criticality index; In addition to reconstructing physical layer parameters, this module also implements an advanced scheduling strategy at the MAC layer; preemptive scheduling refers to a scheduling mechanism that allows high-priority tasks to interrupt low-priority tasks; in this embodiment, when a task with a high dynamic criticality index... When a data packet is generated, the MAC layer scheduler will immediately allocate channel resources to it, and may even interrupt the currently transmitting lower-critical data packets to ensure that the most urgent data is processed and sent with the highest priority. By configuring physical layer parameters in real time and preemptive scheduling of the media access control layer, this embodiment completely transforms the intent of the transmission strategy into hardware actions. This hardware-software collaborative reconfiguration mechanism enables dynamic and refined management of wireless resources at the microsecond level. More importantly, the introduction of preemptive scheduling provides the highest priority transmission rights for highly critical data, ensuring its low-latency transmission characteristics, which is crucial for handling sudden emergency alarm information that concerns flight safety.

[0028] Example 7: The situational risk function is a piecewise function or sigmoid function pre-defined based on the aircraft's aerodynamic model and flight manual.

[0029] Based on the system described in Example 2, this example improves the situational risk function. The mathematical form and origin of the mathematical form are explained in detail; Contextual risk function It is a piecewise function or Sigmoid function pre-defined according to the aerodynamic model and flight manual of the aircraft; Aerodynamic models and flight manuals provide objective, physical, and engineering-practice-based criteria for setting the function; for example, flight manuals clearly define the safety envelope and stall boundaries under different flight conditions, and these key thresholds provide a basis for setting the scenario risk function. It provides a direct reference; Piecewise functions or sigmoid functions are two commonly used forms of nonlinear functions. The reason for choosing these functions is that flight risks usually do not change linearly. For example, when the angle of attack changes slightly within the normal range, the risk increases slowly; but when it approaches the stall angle of attack, the risk increases sharply and nonlinearly. The sigmoid function can well simulate this rapid transition from a safe to a dangerous state. These functions are pre-calibrated and stored in the airborne database for the data stream dynamic criticality assessment module to call at runtime. This implementation method ensures that the quantification of situational risks is not arbitrary, but based on solid aerodynamic theory and engineering practice, thus guaranteeing the scientific nature and accuracy of risk assessment. By using piecewise or nonlinear functions such as the sigmoid function, the characteristics of risk mutations in the physical world of flight can be more realistically reflected, making the system more sensitive to dangerous flight conditions such as near stall or overload. This allows for earlier and more accurate elevation of the criticality level of relevant data, gaining valuable time for subsequent priority transmission.

[0030] Example 8: The initial value of the risk weight coefficient was determined through offline optimization using a flight simulator.

[0031] Based on the system described in Example 2, this example adjusts the risk weighting coefficient. The method for determining the initial value is explained in detail; The initial values ​​of the risk weighting coefficients were determined through offline optimization using a flight simulator; Flight simulators provide a high-fidelity, repeatable, and risk-free virtual flight environment; offline optimization refers to finding an optimal set of parameter configurations through a large number of simulation experiments before system deployment. The specific implementation process is as follows: Simulation tasks covering various typical flight profiles, such as conventional cruise, high-G maneuvers, takeoff and landing, are run in a flight simulator; with the optimization objective of minimizing the end-to-end transmission delay of critical events, such as simulated stall alarms, machine learning algorithms, such as genetic algorithms and reinforcement learning, are used to iteratively adjust the combination of risk weight coefficients bound to each data packet type. This process continues until a set of weight coefficient values ​​that best performs under the objective is found; this set of optimal values ​​is then fixed into the airborne database as the initial configuration. This implementation transforms the setting of risk weight coefficients from subjective experience-based assignment to an objective and scientific determination process based on large-scale simulation data and optimization objectives. By conducting thorough offline optimization in the flight simulator, it can be ensured that this set of weight coefficients has good adaptability to various typical flight scenarios before the system is put into actual use. This allows the data-critical evaluation model to be in a near-optimal working state from the beginning, greatly improving the initial performance and reliability of the system.

[0032] Example 9: The penalty factor is a system-level adjustable parameter preset based on the flight mission profile.

[0033] Based on the system described in Example 4, this example adjusts the penalty factor. The basis for its setting has been explained in detail; Punishment factor These are system-level adjustable parameters preset based on the flight mission profile; Flight mission profile refers to the type of mission planned before flight, such as routine ferry cruise, basic pilot training, or high-risk tactical combat training; different mission profiles have different tolerances for data loss. System-level adjustable parameters imply a penalty factor The value of the penalty factor is not static but can be adjusted according to the nature of the task; for example, in high-risk tactical combat training missions, the loss of any critical data can lead to serious consequences, therefore the penalty factor should be adjusted accordingly. Setting it to a high value will make the transmission utility function more sensitive to the estimated packet error rate. In other words, when the risk is more sensitive, a higher reliability transmission mode will be preferred when making decisions; conversely, in routine cruise missions, the penalty factor can be appropriately reduced. The value is set to prioritize transmission efficiency while ensuring basic reliability; this parameter can be set by the ground station or pilot through the mission planning system before the mission begins. This implementation gives the system task-level adaptability; by using a penalty factor By associating the transmission strategy with the flight mission profile, the risk preference of the transmission strategy can be matched with the overall risk level of the mission. This is a higher level of adaptability, which allows the system to adapt not only to micro-level, instantaneous changes in flight status, but also to macro-level, continuous changes in mission context. This makes the allocation strategy of radio resources more reasonable globally, meeting the reliability requirements of the most demanding missions while avoiding unnecessary performance redundancy in routine missions, thus achieving efficient use of resources.

[0034] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A system for wireless transmission and processing of flight data from a trainer aircraft, comprising: a flight data acquisition system; a wireless transmitter; a wireless receiver; a wireless network; and a computer system. The application relates to a flight data dynamic criticality evaluation system, comprising: a flight state vector analysis module for processing sensor data acquired from an airborne avionics bus to generate a real-time flight state vector; a data flow dynamic criticality evaluation module for calculating a dynamic criticality index for a data packet in combination with the real-time flight state vector generated by the flight state vector analysis module, preset basic criticality of the data packet and a preset risk weight coefficient; a transmission strategy generation module for determining an optimal transmission mode for the data packet according to the dynamic criticality index calculated by the data flow dynamic criticality evaluation module and real-time channel quality information; a wireless resource adaptive reconstruction module for real-time reconstruction of a physical layer and a medium access control layer of a wireless transceiver according to the optimal transmission mode determined by the transmission strategy generation module.

2. The flight data wireless transmission and processing system of a trainer aircraft according to claim 1, characterized in that, The data flow dynamic criticality evaluation module is specifically configured to: obtain a situational risk value based on a flight state parameter in the real-time flight state vector and through a preset situational risk function; calculate a risk adjustment term according to the situational risk value and the preset risk weight coefficient; and generate the dynamic criticality index in combination with the preset basic criticality of the data packet and the risk adjustment term.

3. The flight data wireless transmission and processing system of a trainer aircraft according to claim 1, characterized in that, The transmission strategy generation module is specifically configured to: calculate a transmission utility of each transmission mode in a preset transmission mode set respectively; and determine the transmission mode with the highest transmission utility value as the optimal transmission mode.

4. The flight data wireless transmission and processing system of a trainer aircraft according to claim 3, characterized in that, The transmission utility calculation comprises: calculating a transmission benefit term based on the dynamic criticality index and time overhead of the transmission mode; calculating a transmission cost term based on the dynamic criticality index, an estimated packet error rate of the transmission mode and a preset penalty factor; and obtaining the transmission utility by subtracting the transmission cost term from the transmission benefit term.

5. The flight data wireless transmission and processing system of a trainer aircraft according to claim 4, characterized in that, The estimated packet error rate of the transmission mode is determined by: extracting a real-time channel quality indicator from channel state information of a wireless transceiver; inputting the real-time channel quality indicator into a pre-calibrated performance curve function or lookup table to obtain the estimated packet error rate corresponding to the transmission mode.

6. The flight data wireless transmission and processing system of a trainer aircraft according to claim 1, characterized in that, The wireless resource adaptive reconstruction module is specifically configured to: determine a modulation and coding scheme and a transmission power according to the optimal transmission mode; configure the physical layer to set the modulation and coding scheme and the transmission power; and perform preemptive scheduling at the medium access control layer to preferentially transmit data packets with higher dynamic criticality indexes.

7. The flight data wireless transmission and processing system of a trainer aircraft according to claim 2, characterized in that, The situational risk function is a segmented function or a Sigmoid function preset according to an aerodynamics model of an aircraft and a flight manual.

8. The flight data wireless transmission and processing system of a trainer aircraft according to claim 2, characterized in that, The initial value of the risk weight coefficient is determined through offline optimization of a flight simulator.

9. The flight data wireless transmission and processing system of a trainer aircraft according to claim 4, characterized in that, The penalty factor is a system-level adjustable parameter preset according to a flight mission profile.

Images