An all-weather visual monitoring system for aircraft

Abstract

The application relates to the technical field of aircraft operation monitoring, and discloses an aircraft visual monitoring system under an all-state weather environment. The system comprises an aircraft state monitoring module, an all-state meteorological environment monitoring module, an airspace threat evaluation module and a visual decision center. The aircraft state monitoring module acquires and outputs flight state data in real time; the all-state meteorological environment monitoring module acquires and outputs meteorological environment data of a flight area in real time; the airspace threat evaluation module performs fusion calculation on the two types of data, and outputs an airspace threat evaluation result; and the visual decision center receives and graphically displays the evaluation result. The system realizes comprehensive perception and threat visualization of an aircraft operation environment under complex meteorological conditions, and assists in monitoring and decision making.

Description

Technical Field

[0001] This invention relates to the field of aircraft operation monitoring technology, specifically to an aircraft visualization monitoring system under all weather conditions. Background Technology

[0002] Currently, with the rapid development of air transport and drone applications, aircraft operational safety faces increasingly complex meteorological environments and airspace conditions. Traditional flight monitoring systems often rely on single data sources or limited meteorological information, making it difficult to comprehensively reflect the actual environmental conditions of the flight area. For example, common systems can only provide basic meteorological parameters such as wind speed, temperature, or precipitation, lacking the ability to monitor sudden meteorological phenomena such as lightning, hail, and low-altitude turbulence in real time. Furthermore, existing technologies typically process aircraft status data and meteorological data separately, failing to achieve deep fusion analysis of multi-source data, resulting in lag and inaccuracy in the identification of potential threats.

[0003] In airspace threat assessment, most systems employ rule-based or simple threshold-based methods, which are ill-suited to the dynamic changes in flight risks under varying weather conditions. For example, weather radar data is often analyzed independently of aircraft flight path information, making it difficult to accurately determine the real-time risk level along a specific flight path. Furthermore, existing visualization systems are mostly limited to two-dimensional displays or simple overlays, lacking an integrated presentation of multi-dimensional data (such as spatial hierarchy, time series, and threat levels). Operators must switch between different interfaces, reducing decision-making consistency and efficiency.

[0004] Monitoring all-weather meteorological environments requires the integration of multiple meteorological sensors and data sources, including satellite remote sensing, ground meteorological stations, upper-air sounding, and airborne meteorological radar. However, existing systems have shortcomings in data fusion processing. Significant differences in data formats, accuracy, and update frequencies from different sources lead to inconsistencies and redundancy in the fusion results. Furthermore, the lack of threat modeling methods tailored to aircraft characteristics and flight rules results in discrepancies between assessment results and actual flight requirements. Therefore, a monitoring system capable of integrating multi-source meteorological data and flight status data, achieving efficient fusion calculations, and providing intuitive visualization output is needed to address the complex requirements of aircraft monitoring in all-weather environments. Summary of the Invention

[0005] The purpose of this invention is to provide a visual monitoring system for aircraft in all weather conditions to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides a visual monitoring system for aircraft under all weather conditions, the system comprising:

[0007] The aircraft status monitoring module is used to acquire and output the aircraft's flight status data in real time.

[0008] The all-state meteorological environment monitoring module is used to acquire and output all-state meteorological environment data of the flight area in real time;

[0009] The airspace threat assessment module is connected to the aircraft status monitoring module and the all-state meteorological environment monitoring module. It is used to receive the flight status data and the all-state meteorological environment data, perform fusion calculations based on the received data, and output the airspace threat assessment result.

[0010] The visualization decision center is connected to the airspace threat assessment module and is used to receive and visualize the airspace threat assessment results.

[0011] Preferably, the airspace threat assessment module includes:

[0012] The data fusion unit is used to receive the flight status data and the overall meteorological environment data, and to perform spatiotemporal alignment and feature extraction on the flight status data and the overall meteorological environment data, and output fused feature data.

[0013] The threat calculation unit, connected to the data fusion unit, is used to receive the fused feature data and calculate the fused feature data based on preset threat assessment rules to generate the airspace threat assessment result.

[0014] Preferably, the system further includes:

[0015] A collaborative sensing and communication module, connecting the aircraft status monitoring module and the all-state meteorological environment monitoring module, is used to receive and relay the flight status data and the all-state meteorological environment data.

[0016] The airspace threat assessment module receives the flight status data and the overall meteorological environment data through the collaborative perception and communication module.

[0017] Preferably, the system further includes:

[0018] The flight trajectory prediction module connects the airspace threat assessment module and the visualization decision center. It is used to receive the airspace threat assessment results and the flight status data, predict the future flight trajectory of the aircraft based on the received data, and output the flight trajectory prediction data to the visualization decision center.

[0019] Preferably, the flight trajectory prediction module includes:

[0020] The dynamic model building unit is used to build a dynamic motion model of the aircraft based on the received flight status data and the airspace threat assessment results.

[0021] The trajectory extrapolation unit, connected to the dynamic model construction unit, is used to perform multi-step iterative calculations using the dynamic motion model to generate the flight trajectory prediction data.

[0022] Preferably, the system further includes:

[0023] An adaptive display control module, connected to the visualization decision center and the all-state meteorological environment monitoring module, is used to receive the all-state meteorological environment data and the display instructions issued by the visualization decision center, and adjust the display mode and rendering level of the visualization interface according to the received data.

[0024] Preferably, the adaptive display control module includes:

[0025] The rendering strategy generation unit is used to generate corresponding visualization rendering strategies based on the key meteorological elements in the full-state meteorological environment data.

[0026] The display driver unit is connected to the rendering strategy generation unit and is used to execute the visualization rendering strategy to drive the visualization interface to update.

[0027] Preferably, the system further includes:

[0028] The ground monitoring terminal connects to the visualization decision center and the adaptive display control module via a network. It is used to receive and display the adaptively adjusted visualization interface content, and at the same time send control commands to the visualization decision center.

[0029] Preferably, the system further includes:

[0030] An emergency response guidance module connects the airspace threat assessment module and the ground monitoring terminal. It is used to receive the airspace threat assessment results and generate an emergency guidance strategy and send it to the ground monitoring terminal when the assessment results exceed a preset threshold.

[0031] Preferably, the emergency response guidance module includes:

[0032] The strategy decision-making unit is used to analyze the airspace threat assessment results, determine the threat level, and select the corresponding emergency guidance strategy.

[0033] The instruction generation unit, connected to the strategy decision unit, is used to encode the selected emergency guidance strategy into executable control instructions.

[0034] Compared with the prior art, the beneficial effects of the present invention are:

[0035] This invention integrates aircraft status monitoring with comprehensive meteorological environment monitoring to achieve real-time acquisition and fusion of multi-source data. The airspace threat assessment module outputs a dynamic risk assessment based on the fusion results, enabling the system to comprehensively perceive changes in the flight environment. The visualization decision center presents the assessment results in a multi-dimensional format, helping operators intuitively understand airspace status and threat distribution, enhancing the intuitiveness and interactivity of overall monitoring.

[0036] The system can cover a variety of meteorological elements and flight parameters, including but not limited to temperature, humidity, wind speed, precipitation, lightning, heading, altitude, and speed. Through data fusion calculations, it improves the accuracy and timeliness of threat identification, reducing the possibility of misjudgments due to missing or delayed information. The output results take into account the actual flight characteristics of the aircraft and airspace constraints, making the assessment content closer to practical application needs.

[0037] The visual interface supports multi-level and multi-angle display of airspace threat information, including geographic information overlay, time-series animation, risk level coloring, and dynamic early warning prompts, improving human-computer interaction efficiency and reducing the cognitive load on operators. The system operates stably, adapts to long-term continuous monitoring tasks under complex weather conditions, and is highly scalable, compatible with various types of aircraft and meteorological data sources, meeting the functional requirements of different application scenarios. Overall, the system improves the reliability and response speed of flight safety monitoring, optimizes resource allocation and decision-making processes, and has broad applicability to flight safety assurance in civil aviation, military reconnaissance, and UAV management. Attached Figure Description

[0038] Figure 1 This is a timing diagram of the aircraft visualization monitoring system under all weather conditions described in this invention;

[0039] Figure 2 This is a flowchart of the airspace threat assessment module. Detailed Implementation

[0040] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] Please see Figure 1This invention provides a visual monitoring system for aircraft under all weather conditions. The system achieves real-time monitoring and decision support for aircraft under all weather conditions through multi-module collaboration. The aircraft status monitoring module collects real-time flight status data, including but not limited to position, altitude, speed, heading angle, and attitude angle data, using a multi-source sensor array mounted on the aircraft. This module employs a high-frequency sampling mechanism and outputs a structured data stream via a data bus at a fixed frame rate. The all-weather environment monitoring module is deployed in the ground stations and upper-air detection equipment network in the flight area, capable of acquiring multi-dimensional meteorological data such as atmospheric temperature, humidity, air pressure, wind speed, wind direction, turbulence intensity, and precipitation intensity in real time, and transmitting it to the central processing node via a wide-area communication link. The airspace threat assessment module, as the core processing unit, receives the above two types of data streams and performs fusion calculations. Internally, it uses a spatiotemporal registration algorithm to align heterogeneous data sources and utilizes a feature extraction engine to generate a fused feature vector. Finally, it outputs an airspace threat level with a probability distribution through a threat assessment model based on physical rules. The visualization decision center receives threat assessment results and transforms them into multi-layered graphical elements, dynamically rendering airspace situation maps, threat heat maps, and aircraft trajectory icons through a human-computer interaction interface.

[0042] Example 1: See Figure 2 The data fusion unit of the airspace threat assessment module continuously receives heterogeneous data streams from multiple sources through a high-speed data interface. Flight status data includes real-time three-dimensional position information, Euler angle attitude data, and multi-axis acceleration values ​​collected by the airborne sensor group. These data are marked with millisecond-level timestamps and transmitted via the aviation Ethernet protocol. The full-state meteorological environment data comes from a distributed meteorological monitoring network, which includes a gridded set of atmospheric parameters such as wind speed vector field, relative humidity gradient field, and radar reflectivity factor. These meteorological data are spatially registered through a geographic information system and accompanied by UTC timestamps. When the data fusion unit initiates the spatiotemporal alignment process, it uses a dynamic time warping algorithm to match data streams with different sampling rates. First, a three-dimensional spatiotemporal index grid centered on the aircraft's position is established. Meteorological grid data is mapped into this grid system using a trilinear interpolation algorithm, so that each flight status data point can be associated with the corresponding set of meteorological parameters. Then, the feature extraction engine extracts physically meaningful feature parameters from the aligned data cube. For example, it calculates the angle between the aircraft's heading and the wind direction to generate the relative drag coefficient, or it generates an energy consumption rate index by analyzing the coupling relationship between atmospheric density gradient and aircraft speed. The final output fused feature data is a multi-dimensional feature vector containing time series, where each dimension represents a dimensionally normalized physical feature.

[0043] After receiving the fused feature data, the threat calculation unit activates a pre-built threat assessment rule base. This rule base adopts a hierarchical decision structure. The first layer of rules handles the independent threat determination of meteorological elements, such as calculating the wind shear threat index based on the modulus and rate of change of the wind speed vector. It obtains a standardized threat value by querying a mapping table between wind shear intensity and aircraft tolerance parameters. The second layer of rules performs multi-factor coupling analysis. For example, it inputs precipitation intensity and visibility data into a visual navigation degradation model and outputs a visibility threat level based on fuzzy logic. The third layer of rules performs dynamic weight adjustment, adaptively adjusting the contribution weight of different threat factors according to the aircraft's current altitude and speed status. The threat calculation unit adopts a parallel pipeline architecture. Each threat factor calculation thread runs independently and generates a comprehensive threat score through a weighted fusion algorithm. The final output airspace threat assessment result is encapsulated in JSON format, including threat type encoding, threat geographic range polygon vertex coordinates, threat level value, and threat effective time window.

[0044] The collaborative sensing and communication module, acting as a data relay hub, employs a multi-protocol adaptation architecture. It receives telemetry data packets from the aircraft status monitoring module via an aviation radio link. These packets are temporarily stored in a double-buffered memory after CRC verification and decryption. Simultaneously, it receives meteorological grid data streams pushed by the all-state meteorological and environmental monitoring module via a dedicated fiber optic line. This module has a built-in time synchronization unit, using GPS timing signals to assign a unified time stamp to all input data. Data transmission employs a priority scheduling mechanism, with aircraft status data given the highest priority to ensure real-time performance. Meteorological data utilizes data compression and differential transmission techniques to reduce bandwidth consumption. The airspace threat assessment module establishes a connection with the collaborative sensing and communication module via a gigabit Ethernet interface, employing a hybrid transmission mode combining request-response and push to obtain a synchronous data stream. The collaborative sensing and communication module also verifies the integrity of the relayed data, using a retransmission mechanism to replenish lost data packets to ensure the assessment module receives a continuous and complete data sequence.

[0045] The spatiotemporal alignment algorithm of the data fusion unit further employs predictive interpolation technology. When a slight delay in meteorological data transmission is detected, this unit constructs an ARIMA prediction model based on historical data sequences to generate predicted meteorological parameters for the next few seconds to temporarily fill data gaps. Correction and alignment are then performed once the actual data arrives. This mechanism significantly reduces evaluation errors caused by data transmission jitter. Sliding window variance analysis is also introduced during feature extraction. Variance indices within short time windows are calculated for aircraft attitude data to capture the impact of sudden turbulence. Simultaneously, principal component analysis is used to reduce the dimensionality of high-dimensional meteorological parameters, extracting the core feature subset that has the greatest impact on flight safety. These optimized feature parameters allow subsequent threat calculations to focus more on key influencing factors.

[0046] The threat calculation unit's rule base employs an online update mechanism, receiving remote rule update packets via a secure link. These packets contain new rules or parameter adjustment schemes generated based on historical incident data analysis. During evaluation, the calculation unit records all intermediate calculation results and input data snapshots; this log data is used for subsequent rule optimization and incident tracing analysis. The collaborative sensing communication module also features link redundancy switching. When a degradation in the quality of the primary communication link is detected, it automatically switches to a backup satellite link. The switching process uses data stream mirroring synchronization technology to ensure uninterrupted reception by the evaluation module. The module's network status monitoring unit continuously measures end-to-end transmission latency and packet loss rate, dynamically adjusting data transmission strategies based on the measurement results to maintain optimal transmission performance.

[0047] Example 2: The flight trajectory prediction module receives structured assessment results from the airspace threat assessment module and real-time data streams from the aircraft status monitoring module via a data bus. When initiating the initialization process, this module first verifies the validity of the input data, eliminating invalid data points with obvious outliers. Subsequently, the dynamic model building unit begins constructing a six-degree-of-freedom motion model of the aircraft. The model parameter library includes the aircraft's mass characteristic parameters, aerodynamic derivative matrix, and propulsion system thrust curves. These basic parameters are obtained by matching against the aircraft model database. The dynamic model building unit employs online parameter identification technology. By comparing the residuals between real-time sensor data and model prediction outputs, it uses an extended Kalman filter algorithm to dynamically adjust key parameters in the aerodynamic derivatives. For example, it corrects the pitch damping derivative based on the deviation between the actual pitch rate and the predicted value. This adaptive mechanism enables the model to accurately reflect the dynamic characteristics of the aircraft in real weather environments. During model construction, special attention is paid to integrating meteorological disturbance factors from the airspace threat assessment results. Wind field gradient data is converted into equivalent aerodynamic forces in the body coordinate system, and turbulence intensity data is modeled as random excitation signals injected into the motion equations, thereby forming a high-fidelity dynamic motion model capable of responding to weather changes.

[0048] The trajectory extrapolation unit performs multi-step look-ahead calculations based on the constructed dynamic motion model. It employs a fourth-order Runge-Kutta numerical integration method to advance the system state with millisecond-level time steps. Each iteration includes a complete solution process for the force and moment balance equations. Real-time updated flight state data is continuously incorporated during the extrapolation process as initial condition corrections. The extrapolation algorithm uses a multi-hypothesis prediction architecture to generate multiple possible trajectory branches starting from the current state. Each branch corresponds to different meteorological scenario assumptions and control strategy selections. These branch trajectories are probability-weighted using Monte Carlo simulation methods, ultimately forming a trajectory prediction envelope with confidence intervals. The trajectory extrapolation unit also integrates obstacle avoidance logic. When the predicted trajectory intersects with a high-risk area in the airspace threat assessment results, a trajectory replanning algorithm is automatically triggered to generate avoidance paths. These avoidance strategies are calculated based on the flight performance envelope, ensuring that the recommended avoidance actions are physically feasible.

[0049] The flight trajectory prediction module outputs structured prediction data to the visualization decision center. The data format uses a time-series-based set of three-dimensional coordinates, with each coordinate point accompanied by a probability weight and an uncertainty radius. The visualization decision center converts this data into dynamic predicted trajectory lines overlaid on the airspace situation map. The predicted trajectory lines use gradient color coding to represent the direction of time evolution, while a semi-transparent color band represents the probability distribution range of the trajectory. The prediction data update mechanism uses differential transmission, sending only the change in prediction results relative to the previous period. This design significantly reduces data transmission bandwidth requirements and improves rendering efficiency. The visualization decision center also provides a reliability indicator for the predicted trajectory, visually displaying the prediction reliability at different time periods through changes in color intensity.

[0050] The dynamic model building unit initiates an enhanced modeling program when dealing with special weather conditions. When severe turbulence or wind shear threats are detected, it automatically switches to a high-order nonlinear dynamic model. This model includes empirical relationships between aerodynamic parameters and flow separation, enabling more accurate prediction of the aircraft's handling characteristics under extreme weather conditions. During model building, it also interacts with the flight control system database to obtain current control surface deflection and throttle position information. These control inputs are incorporated as feedforward signals into the dynamic equations, allowing the model to reflect trajectory changes caused by the aircraft's active control. This design ensures that trajectory prediction not only includes the influence of environmental factors but also fully considers the aircraft's intelligent response behavior.

[0051] The trajectory extrapolation unit employs a multi-rate calculation strategy. For near-term trajectories (1-3 minutes ahead), it uses a high-precision integration step size and a detailed meteorological disturbance model; for long-term trajectories (3-30 minutes ahead), it uses a simplified dynamic model and statistical meteorological forecast data. This hierarchical calculation method effectively controls computational load while ensuring the accuracy of near-term predictions. During the extrapolation process, the deviation between the predicted trajectory and the real-time trajectory is continuously monitored. When the deviation exceeds a set threshold, a model recalibration process is automatically triggered. By adjusting model parameters or resetting initial conditions, the prediction converges back to the actual flight path. This closed-loop correction mechanism ensures that the reliability of long-term predictions remains at a reasonable level. The extrapolation results also include energy management prediction information, calculating the trends of potential and kinetic energy changes based on the trajectory profile, providing a quantitative basis for evaluating the performance margin of the aircraft under complex weather conditions.

[0052] For example, a Boeing 737 passenger aircraft suddenly entered a developing cumulonimbus cloud system during the cruise phase. The aircraft status monitoring module immediately detected abnormal data fluctuations: the airspeed indicator showed a rate of change of ±15 knots per second, the vertical acceleration sensor recorded fluctuations of ±0.3g, and the attitude reference system showed pitch angles oscillating within a range of 2 degrees. The all-state meteorological environment monitoring module detected a strong echo center in the area via weather radar, with a radar reflectivity factor reaching 45 dBZ. The wind profiler radar showed significant wind shear at the flight altitude, with wind speeds varying vertically by 25 knots per 100 meters. The microwave radiometer measured a sharp increase in liquid water content within the cloud to 3.5 g / m³. This real-time data was transmitted to the flight trajectory prediction module via the collaborative sensing and communication module, triggering a high-priority processing flow.

[0053] Upon receiving the data stream, the dynamic model building unit of the flight trajectory prediction module immediately initiates an emergency modeling process. It extracts the aerodynamic parameter envelope of the aircraft model from the aircraft performance database, including the lift coefficient versus angle of attack curve, drag polar plot, and engine thrust attenuation model. During modeling, special attention is paid to the integration of meteorological disturbance factors. Measured wind shear data is converted into a three-dimensional disturbance force vector in the airframe coordinate system. A random disturbance sequence is generated based on the turbulence spectrum model, and the engine power attenuation coefficient is calculated by combining cloud liquid water content data. The dynamic model building unit employs a parameter identification algorithm. By comparing the differences between actual flight data and model output, it corrects the damping and cross-coupling terms in the aerodynamic derivatives in real time, ensuring that the model accurately reflects the dynamic characteristics of the aircraft under strong disturbances.

[0054] The trajectory extrapolation unit performs multi-step prediction calculations based on the constructed dynamic motion model, employing a variable-step numerical integration method to advance the system state. Initial conditions are set to the aircraft's current true position, velocity, and attitude data. The extrapolation process considers various control strategy assumptions, including maintaining the current autopilot mode, crew intervention, and activation of automatic emergency procedures, generating corresponding trajectory branch sets. The extrapolation algorithm pays particular attention to the temporal evolution trend of the wind shear field, predicting the wind field change pattern within the next two minutes using linear extrapolation. This predicted wind field data is then used as external input to solve the dynamic equations. Each iteration includes a complete solution to the six-degree-of-freedom motion equations. The calculation step size is dynamically adjusted according to the intensity of motion, automatically shortening to improve calculation accuracy during periods of rapid state change.

[0055] The trajectory prediction unit outputs a structured prediction data packet containing one state point prediction per second for the next ten minutes. Each state point includes three-dimensional position coordinates, velocity vector, and attitude angle data, along with a probability confidence index. This data is transmitted via a data bus to the visualization decision center, where it is converted into a graphical predicted trajectory line and displayed as an orange semi-transparent strip on the main flight display. The strip width represents the range of uncertainty in the trajectory prediction, and the color intensity reflects the chronological order. The visualization system simultaneously displays the most probable trajectory line and the boundary line of extreme situations, providing the flight crew with intuitive situational awareness support. Throughout the prediction process, the flight trajectory prediction module maintains close interaction with the airspace threat assessment module. When the predicted trajectory indicates that the aircraft will enter a region of stronger turbulence within the next three minutes, a warning signal is immediately triggered and sent to the emergency response system. Based on the prediction results, the system generates suggested evasive maneuvers, including a recommended descent of 500 meters and a 30-degree right turn to escape the danger zone. These suggestions are transmitted via data link to the flight management system and simultaneously displayed on the cockpit navigation display. Based on this prediction information, the flight crew took timely evasive action and successfully escaped the area of ​​strong turbulence. Subsequent flight data confirmed that the deviation between the predicted trajectory and the actual trajectory was within the allowable range, verifying the effectiveness of the prediction system.

[0056] The flight trajectory prediction module continuously updates its predictions throughout the entire event, receiving new measured data every second and rerunning the inference algorithm to ensure that the predicted trajectory always reflects the latest flight status and environmental conditions. The module records complete prediction process data, including input parameters, model intermediate states, and output results. This data is subsequently used for system performance evaluation and algorithm optimization. Through this practical application, the system demonstrated its ability to provide accurate trajectory predictions under complex weather conditions, providing crucial technical support for flight safety decision-making.

[0057] Example 3: The adaptive display control module receives real-time meteorological data streams from the full-state meteorological environment monitoring module and display control commands issued by the visualization decision center via a high-speed data interface. Upon startup, this module first parses and classifies the input data. The meteorological data includes multi-dimensional environmental parameters such as cloud optical thickness, precipitation particle concentration, atmospheric transmittance distribution, and wind speed vector field. The display commands include view zoom level, focus target identifier, and visualization theme preference settings. The rendering strategy generation unit extracts key influencing factors based on the parsed meteorological data and uses a factor weight allocation algorithm to determine the dominant meteorological factors. For example, under severe convective weather conditions, turbulence intensity and wind shear gradient are used as the primary visualization factors; in low-visibility scenarios, fog concentration and precipitation intensity are used as core rendering indicators. These factors are normalized and then input into the strategy selector, which matches the most suitable visualization rendering strategy from a pre-set strategy library.

[0058] The strategy library employs a multi-dimensional classification storage structure, indexed according to meteorological condition type, flight stage, and display device characteristics. Each strategy entry contains a complete set of rendering parameters, including color mapping scheme, dynamic effect parameters, layer transparency configuration, and refresh rate settings. The strategy selection process uses a fuzzy matching algorithm, selecting the best matching scheme based on the similarity score between real-time meteorological elements and strategy feature vectors. The rendering strategy generation unit also has strategy fusion capabilities. When multiple meteorological elements simultaneously reach significant levels, a weighted mixing algorithm is used to generate composite rendering strategies. For example, when simultaneously handling heavy precipitation and turbulence conditions, a special rendering mode combining a high-contrast color scheme with a high-frequency dithering effect is created.

[0059] After receiving the generated visualization rendering strategy, the display driver unit converts it into a sequence of drawing commands executable by the underlying graphics library. This unit maintains a multi-level rendering pipeline, with each layer corresponding to different types of visualization elements, such as the base map layer, real-time weather layer, flight trajectory layer, and threat indication layer. The driver unit dynamically adjusts the rendering priority and blending mode of each layer according to the strategy requirements. During execution, a progressive update mechanism is used. Differential rendering technology is employed for frequently changing weather element layers, redrawing only the changed areas to reduce computational load. For static element layers, a caching and reuse strategy is used to improve rendering efficiency. All drawing operations are implemented through a hardware-accelerated graphics interface to ensure a smooth frame rate on high-resolution display devices.

[0060] The process of generating the visualization rendering strategy includes a meteorological optical effect evaluation model, which calculates the visual perception quality index under current meteorological conditions:

[0061] ;

[0062] in: This represents the visual perception quality index. Representing the Weighting coefficients of meteorological elements This indicates the current measurement value of the element. This represents the basic threshold for this element. It is a positive integer representing the total number of meteorological elements included in the visual perception quality assessment. The model output value is used to determine the overall rendering intensity level; a higher index indicates a stronger visual enhancement effect is required.

[0063] The display driver unit implements intelligent resource management, continuously monitoring system rendering load and display device performance indicators. When a drop in rendering frame rate is detected, it automatically initiates a detail level adjustment mechanism to dynamically simplify the geometric complexity of scene elements far from the viewpoint. Simultaneously, it optimizes rendering efficiency for non-critical visualization elements using instantiation rendering technology. The driver unit also supports multi-view synchronous rendering, maintaining consistency in visualization style across views in split-screen display mode. It ensures coordinated visual expression across different display terminals by sharing rendering strategy descriptors. The rendering strategy generation unit incorporates a feedback learning mechanism, recording operator adjustments to visualization effects. By analyzing this adjustment data, it optimizes the weight allocation parameters in the strategy matching algorithm, enabling the system to adapt to different users' visual preferences and decision-making habits. The strategy library supports online updates, receiving new rendering strategy templates or modifying existing strategy parameters over the network. This dynamic update capability allows the system to adapt to new weather phenomena or special task requirements. The display driver unit achieves cross-platform compatibility; its abstraction layer architecture supports multiple graphics application programming interfaces, including OpenGL, Vulkan, and DirectX, and can automatically select the optimal rendering backend based on the operating environment. The driving unit also includes a color management subsystem, which performs color space conversion for the color gamut characteristics of different display devices to ensure that weather warning color codes present consistent visual meanings on different displays. At the same time, it provides special color mapping schemes for users with color vision deficiencies to ensure unimpeded perception of key information.

[0064] Example 4: The ground monitoring terminal, serving as the system's human-machine interface hub, is deployed in a distributed architecture. Its main display array consists of a seamless splicing wall composed of multiple 4K resolution displays. Each display is connected to the graphics rendering server via a dedicated video link. The terminal's built-in multi-input / output interface supports simultaneous reception of situational data streams from the visualization decision-making center and rendering commands from the adaptive display control module. In a typical operational scenario, when severe convective weather occurs in the monitored area, the terminal first receives encrypted data packets from the visualization decision-making center, containing the position vectors of all aircraft in the current airspace, threat assessment matrices, and predicted trajectory data packets. These data are decrypted and verified before being sent to the graphics processing pipeline. The terminal display subsystem adopts a layered rendering architecture. The bottom layer displays the electronic aeronautical chart background layer, the middle layer overlays a color cloud image formed by real-time meteorological radar data, and the top layer renders aircraft icons and threat warning symbols. All layers are visually fused using alpha blending technology.

[0065] Operators interact with the system via a console interface. The touchscreen control interface supports gesture controls, allowing adjustment of the display area through pinch gestures and switching of the display view through swipe gestures. The physical control panel is equipped with a multi-function knob and button array for precise adjustment of threat display thresholds and filtering of specific types of aircraft. When focusing on an aircraft encountering severe weather, the operator triggers a selection command by clicking the target icon on the touchscreen. The terminal immediately sends a data request command to the visualization decision center, requesting detailed status parameters and historical trajectory records of the aircraft. These commands are encapsulated in JSON format and transmitted via gigabit Ethernet.

[0066] The emergency response guidance module continuously monitors the structured data stream output by the airspace threat assessment module. Internally, it features multi-level threshold detectors, each corresponding to different categories of meteorological threat indicators. When any indicator exceeds a preset threshold, the strategy generation process is immediately initiated. For example, when the wind shear index exceeds 0.3 and the aircraft altitude is below 3000 meters, the module automatically classifies it as a high-risk state. The strategy engine retrieves matching response strategies from the contingency plan library, generating a complete plan including avoidance path planning, communication protocol switching, and backup airport recommendations. These strategy plans are encoded into standard instruction sequences, which are sent to the instruction execution queue of the ground monitoring terminal via a digital communication link. Simultaneously, a red warning window pops up on the console interface to prompt operator review. The ground monitoring terminal's network communication module employs a dual-redundancy design. The primary link uses a fiber optic Ethernet connection, while the backup link maintains a hot backup state via a microwave communication system. The communication protocol stack supports both TCP / IP and UDP dual-mode transmission, automatically selecting the optimal transmission method based on data priority. The terminal has an internal data caching mechanism that intelligently buffers the received visual data stream, maintaining display continuity even during brief network interruptions. It also records performance indicators such as data packet loss rate for communication quality assessment. The strategy generation process for the emergency response guidance module should refer to the following communication parameter configuration.

[0067] Table 1: Emergency Communication Channel Parameter Configuration Table

[0068]

[0069] These parameters are embedded in the communication commands of the emergency guidance strategy, automatically switching to the corresponding communication channel when the system triggers an emergency response. Upon receiving an emergency command, the ground monitoring terminal first prompts the operator for confirmation with a flashing icon on the display interface. Simultaneously, it activates the voice synthesis system to read aloud the key points of the emergency plan. The operator can choose to execute immediately or modify the command before execution via physical buttons or touch gestures. All command execution processes are recorded in the operation log, including the command content, execution timestamp, and operator identifier. This log data is used for subsequent event review and system optimization.

[0070] For example, when a civilian drone encounters sudden low cloud cover in a mountainous area, the airspace threat assessment module detects a sharp drop in visibility and abnormal fluctuations in the aircraft's attitude. The emergency response guidance module immediately generates a level-three emergency strategy. The strategy includes instructions such as immediately descending to a safe altitude, activating the obstacle avoidance radar at full power, and switching to a high-reliability communication channel. These instructions are encapsulated into binary data packets and sent to the ground monitoring terminal. After observing the warning, the terminal operator retrieves the drone's detailed status page via a touchscreen. Confirming that the automatically generated emergency plan matches the situation, the operator clicks the execute button. The instructions are then transmitted via data link to the drone's flight control system, guiding the aircraft safely away from the hazardous weather area. The entire decision-making and execution process is completed within seconds, demonstrating the system's rapid response capability under complex weather conditions.

[0071] The ground monitoring terminal also features multi-workstation collaboration capabilities, supporting simultaneous access to system resources from multiple consoles. It manages data access conflicts through a distributed locking mechanism, and each operator's control commands are accompanied by authentication information to ensure operational security. The terminal display system supports multiple layout templates and can automatically adjust the arrangement of information panels according to the current monitoring task type. During weather warnings, it automatically switches to an emergency layout mode, highlighting aircraft and weather radar data in the affected area. The terminal periodically generates system operation status reports, including communication quality statistics, command response latency data, and user operation frequency analysis. These reports provide data support for system maintenance and upgrades.

[0072] Example 5: The strategy decision-making unit of the emergency response guidance module continuously receives structured data streams output by the airspace threat assessment module through a high-speed data interface. This data stream includes multi-dimensional threat indicators such as wind shear intensity gradient, turbulent energy density, visibility attenuation rate, and precipitation intensity change rate. Upon startup, the strategy decision-making unit first normalizes the input data, converting threat indicators of different dimensions into a unified threat index. The strategy decision-making unit adopts a hierarchical analysis architecture. The first layer processes the rapid assessment of single threat indicators, converting each indicator into a standardized value within the range of 0-1 by querying a pre-set threat level mapping table. The second layer performs multi-indicator coupling analysis, using a weighted aggregation algorithm to calculate a comprehensive threat score. The weighting coefficients are dynamically adjusted based on the aircraft type characteristics and the current flight phase. The third layer performs decision logic judgment, selecting the appropriate level of emergency guidance strategy from the strategy library based on the comprehensive score result.

[0073] The strategy library employs a tree-structured index, organized by threat type, severity, and response priority. It contains hundreds of validated emergency strategy templates, each detailing the operational sequence and parameter settings for specific threat scenarios. When a commercial flight encounters moderate turbulence during cruise and its overall threat score reaches 0.7, the strategy decision unit automatically triggers a retrieval process, matching the "cruise altitude turbulence response strategy" from the library. This strategy includes altitude adjustment suggestions, speed control schemes, and communication protocol switching instructions. The strategy selection process uses a fuzzy matching algorithm to calculate the matching score between real-time threat characteristics and strategy templates. The template with the highest score is selected as the base solution, and then adaptive adjustments are made based on the specific aircraft performance parameters.

[0074] The instruction generation unit receives the text-based emergency guidance strategy output by the strategy decision unit, initiates the instruction encoding program to convert it into a machine-executable sequence of control instructions, and follows the aviation communication protocol standard, using the ASN.1 encoding rule to structurally encapsulate each instruction element. The control instructions contain multiple logical fields: the instruction header field indicates the instruction type and priority identifier; the coordinate field specifies the suggested waypoint latitude and longitude coordinates; the action code field defines the specific operation type, such as altitude change or heading adjustment; and the parameter field contains detailed operation values ​​and execution time windows. After encoding, the instruction generation unit performs redundancy check calculations on the instruction sequence, adds a CRC checksum to ensure transmission integrity, and finally sends the instruction stream to the ground monitoring terminal and related aircraft flight control systems via a digital communication link.

[0075] Taking the sudden appearance of a severe convective weather system in a certain area as an example, the airspace threat assessment module detected a sharp increase in the wind shear index in the airspace where multiple aircraft were located. The strategy decision unit immediately initiated batch processing mode. The system identified three civil aviation passenger aircraft in the high-risk area, with comprehensive threat scores of 0.82, 0.79, and 0.85, respectively. The strategy decision unit processed these three cases in parallel, retrieved "strong wind shear avoidance strategies" from the strategy library, and generated differentiated solutions based on the specific location and performance characteristics of each aircraft. For the flight with the highest score, an emergency plan was generated to immediately descend and change course. For the flight with a slightly lower score, a conservative plan was generated to maintain the current altitude but adjust the speed. All plans were verified by a conflict detection algorithm to ensure a safe separation between aircraft in the airspace.

[0076] After receiving the three text strategies, the instruction generation unit uses a pipelined parallel encoding method. Each strategy is decomposed into multiple atomic instruction elements. For example, the altitude control instruction includes the target altitude value, descent rate limit, and transition waypoint setting; the heading adjustment instruction includes the new heading angle, turning radius constraint, and recovery point coordinates. During the encoding process, aviation communication standard documents are referenced to ensure that the format and semantics of each instruction field conform to industry specifications. The generated binary instruction packets are sent simultaneously through different communication channels: high-risk instructions are transmitted with the highest priority using the emergency communication link, while medium-risk instructions are sent through the regular control channel. Upon receiving these instructions, the ground monitoring terminal displays the emergency plans for each aircraft on the flight monitoring interface using different color codes. Operators can view the instruction details and choose to execute immediately or make manual adjustments.

[0077] The emergency response guidance module also features command execution status monitoring. It receives confirmation of the aircraft's response to commands via a data link and automatically initiates a retransmission mechanism or generates an alternative when a command is not executed in a timely manner. All command generation and execution processes are meticulously recorded in the audit log, including raw threat data, strategy decision logic, generated command content, and execution results. This log data is used for subsequent system optimization and event analysis. The module periodically evaluates the effectiveness of the strategy library, iteratively optimizing the parameter settings and applicability conditions of strategy templates by analyzing the success rate data of historical response cases, continuously improving the accuracy and reliability of emergency response.

[0078] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A visual monitoring system for aircraft under all weather conditions, characterized in that, The system includes: The aircraft status monitoring module is used to acquire and output the aircraft's flight status data in real time. The all-state meteorological environment monitoring module is used to acquire and output all-state meteorological environment data of the flight area in real time; The airspace threat assessment module is connected to the aircraft status monitoring module and the all-state meteorological environment monitoring module. It is used to receive the flight status data and the all-state meteorological environment data, perform fusion calculations based on the received data, and output the airspace threat assessment result. The visualization decision center is connected to the airspace threat assessment module and is used to receive and visualize the airspace threat assessment results. The system also includes: The flight trajectory prediction module connects the airspace threat assessment module and the visualization decision center. It is used to receive the airspace threat assessment results and the flight status data, predict the future flight trajectory of the aircraft based on the received data, and output the flight trajectory prediction data to the visualization decision center. The flight trajectory prediction module includes: The dynamic model building unit is used to build a dynamic motion model of the aircraft based on the received flight status data and the airspace threat assessment results. The trajectory extrapolation unit, connected to the dynamic model construction unit, is used to perform multi-step iterative calculations using the dynamic motion model to generate the flight trajectory prediction data.

2. The aircraft visualization monitoring system under all weather conditions according to claim 1, characterized in that, The airspace threat assessment module includes: The data fusion unit is used to receive the flight status data and the overall meteorological environment data, and to perform spatiotemporal alignment and feature extraction on the flight status data and the overall meteorological environment data, and output fused feature data. The threat calculation unit, connected to the data fusion unit, is used to receive the fused feature data and calculate the fused feature data based on preset threat assessment rules to generate the airspace threat assessment result.

3. The aircraft visualization monitoring system under all weather conditions according to claim 2, characterized in that, The system also includes: A collaborative sensing and communication module, connecting the aircraft status monitoring module and the all-state meteorological environment monitoring module, is used to receive and relay the flight status data and the all-state meteorological environment data. The airspace threat assessment module receives the flight status data and the overall meteorological environment data through the collaborative perception and communication module.

4. The aircraft visualization monitoring system under all weather conditions according to claim 1, characterized in that, The system also includes: An adaptive display control module, connected to the visualization decision center and the all-state meteorological environment monitoring module, is used to receive the all-state meteorological environment data and the display instructions issued by the visualization decision center, and adjust the display mode and rendering level of the visualization interface according to the received data.

5. The aircraft visualization monitoring system under all weather conditions according to claim 4, characterized in that, The adaptive display control module includes: The rendering strategy generation unit is used to generate corresponding visualization rendering strategies based on the key meteorological elements in the full-state meteorological environment data. The display driver unit is connected to the rendering strategy generation unit and is used to execute the visualization rendering strategy to drive the visualization interface to update.

6. The aircraft visualization monitoring system under all weather conditions according to claim 5, characterized in that, The system also includes: The ground monitoring terminal connects to the visualization decision center and the adaptive display control module via a network. It is used to receive and display the adaptively adjusted visualization interface content, and at the same time send control commands to the visualization decision center.

7. The aircraft visualization monitoring system under all weather conditions according to claim 6, characterized in that, The system also includes: An emergency response guidance module connects the airspace threat assessment module and the ground monitoring terminal. It is used to receive the airspace threat assessment results and generate an emergency guidance strategy and send it to the ground monitoring terminal when the assessment results exceed a preset threshold.

8. The aircraft visualization monitoring system under all weather conditions according to claim 7, characterized in that, The emergency response guidance module includes: The strategy decision-making unit is used to analyze the airspace threat assessment results, determine the threat level, and select the corresponding emergency guidance strategy. The instruction generation unit, connected to the strategy decision unit, is used to encode the selected emergency guidance strategy into executable control instructions.

Images