A method for predicting surface environmental parameters of aircraft

Abstract

This invention discloses a method for predicting environmental parameters on the surface of an aircraft, aiming to improve flight safety and efficiency by monitoring and predicting environmental parameters on the aircraft surface in real time. The method includes: using sensors to collect environmental parameter data near the aircraft surface in real time, such as temperature, humidity, air pressure, and wind speed; transmitting the collected data to a data processing module for preprocessing, including noise reduction and normalization, to improve data quality; constructing a prediction model based on a machine learning algorithm, training it using the preprocessed data, and generating an environmental parameter prediction model; inputting the real-time collected environmental parameters into the prediction model to calculate and predict future environmental parameters on the aircraft surface; and feeding the prediction results back to the flight control system to achieve real-time adjustment of flight strategies. This invention, by integrating multi-source data and advanced machine learning technology, accurately predicts multi-dimensional environmental parameters, providing more reliable decision support for aircraft flight control.

Description

Technical Field

[0001] This invention relates to the field of aircraft, and more specifically to a method for predicting surface environmental parameters of aircraft. Background Technology

[0002] In modern aviation, aircraft performance and flight safety are affected by a variety of environmental factors, including temperature, humidity, air pressure, and wind speed. Changes in these environmental parameters directly affect the aerodynamic characteristics, propulsion system, and navigation accuracy of aircraft, making real-time monitoring and prediction particularly important.

[0003] Currently, traditional methods for predicting environmental parameters largely rely on static meteorological models and historical meteorological data, lacking full utilization of real-time data. These methods often fail to accurately reflect the environmental changes encountered by aircraft during actual flight, leading to insufficient response time of flight control systems to sudden weather events, which may affect flight safety.

[0004] In recent years, with the rapid development of sensor technology and data processing capabilities, prediction methods combining real-time environmental data with machine learning algorithms have gradually gained attention. These methods can more accurately predict environmental parameters, optimize flight paths, and improve flight safety and efficiency. However, current related technologies still have the following shortcomings: Insufficient data fusion capability: Existing environmental parameter prediction systems typically lack effective multi-source data fusion mechanisms, making it difficult to fully integrate historical data, real-time sensor data, and meteorological model data. Insufficient model generalization capability: Most existing machine learning models have limited generalization capability under different environmental conditions, making it difficult to adapt to complex and ever-changing flight environments. Insufficient real-time performance: Although some methods can provide predictions of environmental parameters, their real-time performance still needs improvement and cannot meet the real-time requirements of flight control systems.

[0005] Therefore, there is an urgent need for a new method for predicting environmental parameters that can combine multi-source data to improve the model's prediction accuracy and generalization ability, thereby providing more reliable support for the safe and efficient operation of aircraft. Summary of the Invention

[0006] This invention provides a method for predicting surface environmental parameters of an aircraft, comprising:

[0007] The system uses sensors to collect real-time environmental parameter data near the surface of the aircraft, including temperature, humidity, air pressure, wind speed, solar radiation intensity, pollutant concentration, aerosol concentration, sound level, and other micro-meteorological parameters.

[0008] The environmental parameter data is transmitted to the data processing module for preprocessing, including noise reduction and normalization.

[0009] Construct a prediction model based on machine learning algorithms, train it using preprocessed data, and generate an environmental parameter prediction model;

[0010] The real-time collected environmental parameters are input into the prediction model to calculate and predict the future environmental parameters on the surface of the aircraft.

[0011] The prediction results are fed back to the flight control system for real-time adjustments to the flight strategy.

[0012] The method for predicting surface environmental parameters of an aircraft as described above includes sensors such as a temperature sensor, a humidity sensor, a barometric pressure sensor, a wind speed sensor, a solar radiation sensor, a pollutant sensor, an aerosol sensor, and a sound level sensor.

[0013] As described above, in the method for predicting aircraft surface environmental parameters, the denoising process in the preprocessing stage uses a noise suppression function. This function reduces the impact of noise on the data by adjusting the signal strength of the collected data, thereby improving the accuracy of the data.

[0014] The above-described method for predicting surface environmental parameters of an aircraft includes a normalization process that transforms environmental parameter data into a unified dimension, enabling effective comparison and calculation of data with different characteristics.

[0015] The method for predicting surface environmental parameters of an aircraft as described above, wherein the constructed prediction model is a graph neural network-based model used to process the multidimensional relationships of environmental parameter data in order to improve the accuracy of prediction.

[0016] As described above, in a method for predicting surface environmental parameters of an aircraft, the preprocessed dataset is divided into a training set, a validation set, and a test set in a ratio of 70%:15%:15% to ensure that the model has good generalization ability on unseen data and to avoid overfitting.

[0017] The above-described method for predicting surface environmental parameters of an aircraft, wherein the output of the prediction model is the environmental parameter values ​​within a future time window, including temperature, humidity, air pressure, wind speed, etc., to facilitate decision-making by the flight control system.

[0018] In the aircraft surface environment parameter prediction method described above, the prediction results fed back to the flight control system can be dynamically adjusted according to real-time environmental changes to optimize the flight strategy.

[0019] The present invention also provides a computer storage medium, comprising: at least one memory and at least one processor;

[0020] Memory, used to store one or more program instructions;

[0021] A processor is used to run one or more program instructions to execute a method for predicting aircraft surface environmental parameters.

[0022] The beneficial effects achieved by this invention are as follows: By comprehensively utilizing data acquisition, processing, and prediction models, this invention can accurately and in real time predict environmental parameters on the surface of an aircraft, thereby providing a decision-making basis for the aircraft's control system and improving flight safety and performance reliability. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0024] Figure 1 This is a flowchart of a method for predicting surface environmental parameters of an aircraft, provided in Embodiment 1 of this application. Detailed Implementation

[0025] 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, not all, of the embodiments of the present invention. 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.

[0026] Example 1

[0027] like Figure 1 As shown, Embodiment 1 of this application provides a method for predicting surface environmental parameters of an aircraft, including the following steps:

[0028] Step S10: Use sensors to collect environmental parameter data near the surface of the aircraft in real time;

[0029] In this step, environmental parameters near the aircraft surface are monitored in real time using various sensors to ensure accurate and timely environmental data. These sensors include, but are not limited to, temperature sensors, humidity sensors, barometric pressure sensors, wind speed sensors, solar radiation sensors, pollutant concentration sensors, aerosol concentration sensors, and sound level sensors. The arrangement of each sensor should be optimized according to the aircraft's design and flight mode to minimize interference and errors.

[0030] Define the environmental parameter vector E to be collected, which contains the following elements:

[0031] E = [T,H,P,W,S,C] p C a [,L,M], where T represents temperature; H represents humidity; P represents air pressure; W represents wind speed; S represents solar radiation intensity; C p Indicates pollutant concentration; C a L represents aerosol concentration; M represents sound level; and M represents other micrometeorological parameters (such as precipitation, visibility, etc.).

[0032] Environmental parameter data is collected periodically (e.g., every second) using sensors. The data acquisition process includes: sensor initialization and calibration to ensure accuracy and sensitivity; real-time recording and storage of data, using high-frequency sampling to capture instantaneous changes.

[0033] After data acquisition, preliminary preprocessing is required to improve data quality. This includes noise reduction, which involves suppressing noise in the real-time acquired data and defining a noise suppression function. Where E represents the current environmental parameter value, such as temperature, humidity, and air pressure, and this value is the data input that needs to be noise-suppressed; σ represents the standard deviation, reflecting the volatility of historical data; m represents the number of historical data points, which is the number of samples collected within a certain time range; E mean The average value represents historical data and is obtained by statistically analyzing historically collected environmental parameters. This is the sum of squares of the deviations between current environmental parameters and the historical average. This calculation allows us to assess the relationship between current and historical data, helping to determine if the current data is affected by noise. To better understand the impact of environmental changes, a comprehensive parameter is defined. Used to assess the impact of various environmental parameters: In this formula, n is the number of environmental parameters; α i It is the weighting coefficient for each environmental parameter; E i It is the real-time value of the i-th environmental parameter; β i These are non-linear weights, representing the contribution of different parameters to the overall impact.

[0034] Finally, wireless communication technology is used to transmit the preprocessed data and integrated parameters to the data processing module in real time for subsequent analysis and model training.

[0035] Step S20: Preprocess the environmental parameter data, including noise reduction and normalization.

[0036] In this step, the environmental parameter data transmitted to the data processing module needs to be preprocessed to ensure data quality and accuracy, laying the foundation for subsequent prediction model construction. Data preprocessing mainly includes denoising, normalization, and feature selection.

[0037] Denoising: To eliminate random noise in the sensor data, signal processing techniques are used to denoise the data. Filters are used to process the data. Assume the acquired raw data is D. raw =[d1,d2,…dn] ] Denoising data D clean It can be represented as: Among them, D clean (t) represents the data value after denoising at time t; k is the window size, i.e., the number of samples considered during denoising; d(tj) is the original data at time tj.

[0038] Normalization: To facilitate subsequent processing by machine learning models, parameters from different ranges need to be standardized to the same range (usually [0,1]). The formula for normalization is as follows: Where E represents the original data; E max and E min These are the maximum and minimum values ​​of the parameter, respectively. After normalization, all parameters will be on the same order of magnitude, which helps improve the efficiency and accuracy of model training.

[0039] Feature selection aims to identify the environmental parameters that have the greatest impact on model performance. Correlation analysis is used to calculate the correlation coefficient r between each environmental parameter and the target variable, as shown in the following formula: Where n represents the number of samples, the number of sample pairs involved in the calculation; and These are the means of feature E and the target variable T, respectively. Features with absolute correlation coefficients higher than a certain threshold are selected and retained for model training.

[0040] To train and validate the model, the preprocessed dataset needs to be split into training, validation, and test sets in a 70%:15%:15% ratio. This splitting process ensures the model has good generalization ability on unseen data, avoiding overfitting. After preprocessing, the cleaned, normalized, and feature-selected data is stored in a database or file system for subsequent model training and real-time prediction. The data storage structure should facilitate fast retrieval and loading, supporting efficient data access.

[0041] Step S30: Construct a prediction model based on machine learning algorithms, train it using preprocessed environmental parameter data, and generate an environmental parameter prediction model.

[0042] In this step, a machine learning prediction model is constructed using preprocessed environmental parameter data to accurately predict future environmental parameters on the aircraft surface. This step mainly includes model selection, model training, and model evaluation. Based on the characteristics of the environmental parameters and the prediction objective, an appropriate machine learning algorithm is selected. Considering the complexity of the environmental data and the interrelationships between parameters, a Graph Neural Network (GNN) is chosen, as GNNs can effectively capture the topological structure and dependencies between parameters.

[0043] The model's input is represented as X = [E, A], where E is the environment parameter matrix and A is the adjacency matrix, representing the interactions between parameters. After selecting the model, it is trained using a training set to optimize the model's parameters and minimize the loss function. To improve the model's prediction accuracy, an improved spatiotemporal loss function L is introduced. sp This function not only considers prediction error, but also integrates the correlation between parameters: Among them, y i The actual value; The model predicts the value; γ is a hyperparameter for adjusting the weights; corr(E) i E j ) represents environmental parameter E i and E j The correlation between them. This loss function not only effectively improves the model's prediction accuracy but also helps the model better understand the interaction of environmental parameters. Optimization techniques such as backpropagation and gradient descent are used to adjust the model parameters. The basic formula for updating model parameters is: Where θ represents the model parameters; τ is the learning rate; Let be the gradient of the loss function. By iterating this formula, the loss function is gradually reduced, thereby optimizing the model. A dynamic learning rate adjustment strategy is introduced to improve training performance and accelerate convergence, resulting in the adaptive learning rate formula: Here, τ0 is the initial learning rate; β is an adjustment parameter; and t is the current iteration number. This formula ensures that the learning rate is higher in the early stages of training to quickly find a better solution, and then gradually decreases in the later stages of training to refine the model's learning process, thereby preventing oscillations and overfitting.

[0044] After training, the model's performance is evaluated using stability feedback assessment. Prediction results are collected over multiple time periods, and the consistency of the feedback is calculated. The stability function S is defined as follows: in, It is the predicted value at the current moment; y i-1This represents the true value at the previous moment; N is the number of observation periods. This formula measures the relative change between adjacent predictions, reflecting the stability of the model. After model training is complete, the trained model is saved to a database or file system to ensure its reusability and version traceability.

[0045] Step S40: Input the real-time collected environmental parameters into the environmental parameter prediction model to calculate and predict the future environmental parameters on the surface of the aircraft.

[0046] In this step, the environmental parameters collected in real time are used as input data and passed to the previously built prediction model to calculate and predict the future environmental parameters of the aircraft surface.

[0047] The environmental parameters collected by real-time sensors are integrated into an input vector X. input To adapt to the input requirements of the model;

[0048] X input =[T current H current ,P current W current ,S current C current A current ,L current M current ]

[0049] Among them, T current Indicates temperature; H current Indicates humidity; P current Indicates air pressure; W current Indicates wind speed; S current Indicates solar radiation intensity; C current Indicates pollutant concentration; A current Indicates aerosol concentration; L current Indicates sound level; M current Represent other micrometeorological parameters. The formatted environmental parameter vector X... input The pre-trained prediction model is input, which learns from historical data and can capture the complex relationships between environmental parameters. Machine learning algorithms process the input data to generate predictions of future environmental states. The model will produce predicted values ​​for future environmental parameters.

[0050]

[0051] The model's output (predicted future environmental parameters) is integrated into a data package for subsequent processing. The prediction results are fed back to the flight control system in real time via a data channel, supporting dynamic adjustments to flight strategies. The system monitors the differences between actual and predicted environmental parameters, using this information to continuously optimize the model and improve the accuracy of future predictions.

[0052] Step S50: Feed the prediction results back to the flight control system for real-time adjustment of the flight strategy.

[0053] During this phase, the generated predictions of future environmental parameters will be transmitted to the flight control system to support real-time decision-making and flight strategy adjustments.

[0054] The predicted environmental parameters are integrated into a structured data packet for processing by the flight control system. The formatted prediction results are sent to the flight control system in real time using reliable communication protocols (such as TCP / IP and UDP). Timeliness and integrity of data transmission are ensured so that the flight control system can respond quickly. During transmission, the flight control system should perform data verification to ensure that the received prediction results are valid and complete. After receiving the prediction results, the flight control system analyzes and processes them, and comprehensively evaluates the predicted environmental parameters using the following formula. Compared with actual environmental parameters E actual The relationship between them: Where ΔE is the overall error assessment of environmental parameters; n is the number of predicted parameters (such as temperature, humidity, etc.); It is the i-th predicted future environmental parameter; Here, ΔE is the i-th actual environmental parameter; α is a constant controlling the decay rate, used to emphasize the importance of larger errors. An acceptable error threshold is set. If ΔE exceeds this threshold, it indicates that the prediction may not be accurate enough, and strategy adjustments are needed. For example, if the predicted wind speed and direction differ significantly from the actual data, the heading may need to be adjusted. Using the current wind speed and heading information, the optimal heading can be recalculated to reduce wind resistance and improve flight efficiency. If the actual air pressure and temperature data differ significantly from the predicted values, it may affect flight performance and safety. Based on the actual meteorological conditions and aircraft performance characteristics, the flight altitude should be adjusted to find a more suitable aerodynamic environment and improve flight stability.

[0055] Continuously monitor actual environmental parameters and compare them with predicted values ​​to ensure timely detection of new changes. Feed the effects of adjusted strategies back to the model for optimization in future predictions, thereby improving the model's accuracy and adaptability.

[0056] Corresponding to the above embodiments, the present invention provides a computer storage medium, including: at least one memory and at least one processor;

[0057] The memory is used to store one or more program instructions;

[0058] A processor is used to run one or more program instructions to execute a method for predicting aircraft surface environmental parameters.

[0059] Corresponding to the above embodiments, this embodiment of the invention provides a computer-readable storage medium containing one or more program instructions, which are executed by a processor to provide a method for predicting aircraft surface environmental parameters.

[0060] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions that, when executed on a computer, cause the computer to perform the aforementioned method for predicting aircraft surface environmental parameters.

[0061] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0062] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0063] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0064] Among them, non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory.

[0065] Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0066] The storage media described in the embodiments of the present invention are intended to include, but are not limited to, these and any other suitable types of memory.

[0067] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this invention can be implemented using a combination of hardware and software. When applied as software, the corresponding functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. Storage media can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0068] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting surface environmental parameters of an aircraft, characterized in that, The method comprises: Collecting environmental parameter data near the surface of the aircraft in real time using sensors; Preprocessing the environmental parameter data, including denoising and normalization processing; Building a prediction model based on machine learning algorithms, training the preprocessed environmental parameter data to generate an environmental parameter prediction model; Inputting the real-time collected environmental parameters into the prediction model, calculating and predicting the future environmental parameters of the aircraft surface; Feedback the prediction results to the flight control system for real-time adjustment of flight strategy; Wherein the input of the model is represented as: X=[E,A], where E is the environmental parameter matrix; A is the adjacency matrix, representing the mutual influence between parameters; After model selection, the model is trained using the training set, introducing a modified spatio-temporal loss function that not only considers the prediction error but also integrates the correlation between parameters: where is the true value; is the model prediction value; is a hyperparameter that adjusts the weight; represents the correlation between environmental parameters and . The back propagation algorithm and gradient descent method are used to optimize the model parameters, and the basic formula for updating the model parameters is: wherein, represents the parameters of the model; is the learning rate; is the gradient of the loss function, and by continuously iterating this formula, the loss function is gradually reduced, thereby optimizing the model; a dynamic learning rate adjustment strategy is introduced to improve the training effect and accelerate the convergence, and an adaptive learning rate formula is introduced: , is the initial learning rate; is an adjustment parameter, and t is the current iteration number; After the training is completed, the performance of the model is evaluated using stability feedback evaluation; the prediction results of multiple time periods are collected, the consistency of the feedback is calculated, and a stability function is defined wherein, is the predicted value at the current time; is the true value at the previous time; N is the number of observation time periods, and the formula measures the relative change between adjacent predictions, reflecting the stability of the model; The flight control system receives the prediction results, analyzes and processes them, and evaluates the predicted environmental parameters synthetically through the following formula fucture The relationship between the actual environmental parameters E actual wherein, is the overall error evaluation of the environmental parameters; n is the number of predicted parameters; is the i-th predicted future environmental parameter; is the i-th actual environmental parameter; is a constant that controls the rate of decay, used to emphasize the importance of larger errors; an acceptable error threshold is set.​ 2. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 1, wherein, The sensors include temperature sensors, humidity sensors, air pressure sensors, wind speed sensors, solar radiation sensors, pollutant sensors, aerosol sensors and sound level sensors.

3. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 2, wherein, The denoising process in the preprocessing process uses a noise suppression function, which reduces the influence of noise on data by adjusting the signal strength of the collected data, and improves the accuracy of the data.

4. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 3, wherein, The normalization process converts the environmental parameter data into a unified dimension, so that data of different characteristics can be effectively compared and calculated.

5. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 4, wherein, The constructed prediction model is a graph neural network-based model, which is used to process the multi-dimensional relationship of environmental parameter data to improve the accuracy of prediction.

6. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 5, wherein, The output of the prediction model is the environmental parameter value in the future time window, including temperature, humidity, air pressure and wind speed, which is convenient for the flight control system to make decisions.

7. A method of predicting an environmental parameter on a surface of an aircraft as recited in claim 6, wherein, The prediction results fed back to the flight control system can be dynamically adjusted according to the real-time environmental changes to optimize the flight strategy.

8. A computer storage medium, comprising, The method comprises: At least one memory and at least one processor; Memory for storing one or more program instructions; Processor for running one or more program instructions to execute a method for predicting environmental parameters on the surface of an aircraft according to any one of claims 1-7.

Images