Low-altitude aircraft flight energy consumption optimization method based on meteorological conditions

Abstract

The invention discloses a low-altitude aircraft flight energy consumption optimization method based on meteorological conditions, and the method comprises the steps: obtaining multi-source meteorological data, and carrying out the fusion of the multi-source meteorological data, and obtaining meteorological data; fitting the energy consumption data of the aircraft according to the meteorological data to obtain an energy consumption change trend; obtaining performance parameters and task requirements of the aircraft, generating constraint conditions according to the performance parameters and the task requirements, and obtaining an initial flight strategy set by taking the minimum energy consumption as a target through a genetic algorithm according to an energy consumption change trend and the constraint conditions; and dynamically adjusting the initial flight strategy set to obtain a final flight strategy after flight energy consumption optimization.

Description

Technical Field

[0001] The present invention belongs to the technical field of flight planning, and particularly relates to a method for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions. Background Art

[0002] During the flight of a low-altitude aircraft, the influence of meteorological conditions on flight energy consumption is particularly significant. In order to optimize flight energy consumption, it is first necessary to obtain real-time meteorological data in the area where the aircraft is located. These data usually come from multiple data sources such as meteorological observation stations, radars, and satellites. However, there are differences in the data formats, accuracies, and update frequencies of different data sources, and the existing technologies cannot efficiently integrate these heterogeneous data to ensure the real-time and accuracy of the data. At the same time, the requirement analysis of flight missions is also crucial. The objectives, starting points, ending points, and time requirements of flight missions will all have a direct impact on flight energy consumption. For example, an emergency mission may require the aircraft to fly at maximum speed, but this will lead to a sharp increase in energy consumption. The existing technologies cannot optimize flight energy consumption while meeting the mission requirements, so there is a need for a flight optimization method for low-altitude aircraft that can consider mission requirements while reducing flight energy consumption on the basis of ensuring the effectiveness of meteorological data. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes a method for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions to solve the problems existing in the above-mentioned prior art.

[0004] To achieve the above object, the present invention provides a method for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions, including:

[0005] Obtain multi-source meteorological data, fuse the multi-source meteorological data to obtain meteorological data;

[0006] Fit the energy consumption data of the aircraft according to the meteorological data to obtain the energy consumption change trend;

[0007] Obtain the performance parameters and mission requirements of the aircraft, generate constraint conditions according to the performance parameters and mission requirements, and use the genetic algorithm with the minimum energy consumption as the goal to obtain an initial flight strategy set according to the energy consumption change trend and constraint conditions;

[0008] Dynamically adjust the initial flight strategy set to obtain the final flight strategy with optimized flight energy consumption.

[0009] Optionally, the process of fusing the multi-source meteorological data includes:

[0010] Standardize the format of the multi-source meteorological data; wherein the multi-source meteorological data includes wind speed, temperature, air pressure, and humidity obtained through meteorological observation stations, radars, and satellites.

[0011] Perform a weighted sum calculation on the data after format standardization to obtain meteorological data.

[0012] Optionally, before fusing the multi-source meteorological data, it further includes:

[0013] Preprocess the multi-source meteorological data, where the preprocessing process includes removing noise, filling missing data, and correcting outliers.

[0014] Optionally, the process of obtaining the energy consumption change trend includes:

[0015] Obtain the aircraft energy consumption data corresponding to the meteorological data, perform a linear correlation analysis on the meteorological data and the corresponding aircraft energy consumption data. When the result of the linear correlation analysis is greater than the threshold, then fit the meteorological data and the corresponding aircraft energy consumption data through a linear regression model to obtain the linear mapping relationship between the meteorological data and the aircraft energy consumption data, that is, the energy consumption change trend. Otherwise, fit the meteorological data and the corresponding aircraft energy consumption data through a machine learning model to obtain the non-linear mapping relationship between the meteorological data and the aircraft energy consumption data, that is, the energy consumption change trend.

[0016] Optionally, the constraint conditions include performance parameter constraints and mission constraints. Among them, the performance parameter constraints include the maximum flight speed, minimum flight speed, maximum climb rate, and maximum descent rate, and the mission constraints include the starting point, ending point, and time requirements.

[0017] Optionally, the process of obtaining the initial flight strategy set includes:

[0018] Construct initial variables according to the flight strategy, where the flight strategy includes the flight path and flight speed of the aircraft, obtain real-time meteorological data, iteratively adjust the initial variables under the constraints of the constraint conditions through a genetic algorithm, and calculate the energy consumption data corresponding to the initial variables according to the energy consumption change during the adjustment process. With the goal of minimizing the energy consumption data, obtain the initial flight strategy set;

[0019] Where the energy consumption data is the product result of the sum of the initial energy consumption of the UAV, the energy consumption change value, and 1.

[0020] Optionally, the process of dynamically adjusting the initial flight strategy includes:

[0021] Obtain the energy consumption value of the initial flight strategy set, and the energy consumption value is calculated according to the mapping relationship between the real-time meteorological data, the aircraft data, and the energy consumption value. The aircraft data includes the aircraft and the load weight;

[0022] Segment the altitude of the flight strategies in the initial flight strategy set, calculate the adjusted energy consumption value, and judge the adjusted flight strategies according to the constraints. Based on the calculated energy consumption value and the judgment result, obtain the final flight strategy with optimized flight energy consumption.

[0023] Optionally, predict future meteorological data based on real-time meteorological data, and replace the real-time meteorological data with the future meteorological data to calculate the energy consumption change value and the energy consumption value.

[0024] Compared with the prior art, the present invention has the following advantages and technical effects:

[0025] The present invention discloses a method for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions. The method first obtains meteorological data from multiple sources, and through data cleaning and fusion processing, forms a comprehensive meteorological data set. Combining the performance parameters of the aircraft, the present invention calculates the energy consumption change trend under different meteorological conditions. At the same time, task constraint conditions are generated according to the requirements of the task management system. The core of the present invention is to use a genetic algorithm to generate an initial flight strategy set, and optimize it through a dynamic programming algorithm, and finally screen out the flight strategy that meets the task requirements and has the lowest energy consumption. This method can effectively balance the flight task requirements and energy consumption, improve the operation efficiency of the aircraft and the quality of task completion, and is of great significance for improving the operation ability of the aircraft in complex meteorological environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings:

[0027] Figure 1 is a flowchart of the method for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions according to an embodiment of the present invention;

[0028] Figure 2 is a structural diagram of the system for optimizing the flight energy consumption of a low-altitude aircraft based on meteorological conditions according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other. The following will refer to the drawings and combine the embodiments to detail this application.

[0030] It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0031] As Figure 1 shown, a flight energy consumption optimization method and system for low-altitude aircraft based on meteorological conditions in this embodiment may specifically include:

[0032] S101. Obtain multi-source meteorological data from meteorological observation stations, radars, and satellites, including data such as wind speed, temperature, air pressure, and humidity information.

[0033] Obtain wind speed values, temperature values, air pressure values, and humidity values according to observation stations, radar stations, and satellite points.

[0034] Specifically, meteorological monitoring stations, combined with weather radar and satellite data, constitute the basic network for meteorological monitoring. Observation stations measure basic data such as wind speed, temperature, air pressure, and humidity through standardized meteorological instruments. Weather radar obtains atmospheric motion information by measuring reflectivity and Doppler velocity. Meteorological satellites provide data on large-scale cloud system development and water vapor distribution, etc. The corresponding wind speed, temperature, air pressure, and humidity are calculated and identified based on weather radar and meteorological satellites.

[0035] S102. Use data cleaning technology to preprocess the multi-source meteorological data, remove noise and outliers, and unify the data format and accuracy.

[0036] Perform denoising and outlier correction on the wind speed values, temperature values, air pressure values, and humidity values in the data source. If the wind speed value exceeds the preset threshold, it is judged as abnormal data and corrected.

[0037] Specifically, correlation filtering denoising method is used for denoising, and forward filling method is used to fill in the missing values. In data anomaly detection, taking wind speed as an example, when the observed value is greater than forty meters per second, it may be due to equipment failure or extreme weather, and it is necessary to combine surrounding observations and historical data for correction. The same threshold detection is used to judge outliers for other data types.

[0038] S103. Based on the preset fusion rules, integrate the cleaned multi-source meteorological data into a comprehensive meteorological data set with a single spatio-temporal dimension.

[0039] Obtain multi-source meteorological data according to meteorological stations, radar maps, and satellite maps, and use the preset fusion rules to integrate the multi-source data in spatio-temporal dimensions to obtain a comprehensive meteorological data set.

[0040] Perform normalization processing on the wind speed values, temperature values, air pressure values, and humidity values in the comprehensive meteorological data set. If the wind speed value exceeds the preset threshold, it is judged as abnormal data and corrected. Calculate the dew point temperature according to the temperature value and humidity value, calculate the atmospheric density through the air pressure value and temperature value, and obtain meteorological characteristic parameters.

[0041] Use the random forest algorithm to perform meteorological prediction on the comprehensive meteorological dataset and meteorological characteristic parameters to obtain the meteorological prediction results. Use the support vector machine algorithm to classify the meteorological prediction results, and determine the meteorological type according to the classification results. Use the neural network algorithm to identify the meteorological type to obtain the final meteorological prediction result. Generate a meteorological forecast report based on the final meteorological prediction result to complete the meteorological prediction task.

[0042] Specifically, the data fusion of meteorological stations, radar maps, and satellite images first needs to solve the problem of data standardization. For example, among multiple meteorological stations in the Beijing area, the wind speed recording unit of the Chaoyang District Meteorological Station is meters per second, while the Haidian District Meteorological Station uses kilometers per hour, which needs to be uniformly converted to meters per second. The radar map data contains reflectivity values and needs to be converted into actual precipitation through the precipitation conversion formula. The satellite cloud image needs to convert the infrared brightness temperature value into the actual temperature value.

[0043] During the data fusion process, the data of each monitoring source needs to be cross-checked and supplemented. For example, during a certain period, the measured wind speed in a certain area is eight meters per second, while the radar-inverted wind speed is ten meters per second, and the satellite-inverted wind speed is nine meters per second. A more reliable wind speed estimate value can be obtained through weighted averaging. Similarly, temperature, pressure, and humidity values are also fused using a similar method.

[0044] Data normalization can unify data with different dimensions to the same scale. For example, the temperature range is between minus ten degrees and forty degrees, while the relative humidity is between zero percent and one hundred percent. Through normalization, it can be evenly distributed between zero and one, which is convenient for subsequent analysis. The temperature value is normalized using the maximum-minimum method, and the Celsius temperature value is compressed to the range of zero to one. The pressure value is normalized based on the standard atmospheric pressure of 1013 hPa. The humidity value is already in the percentage range and does not require additional normalization.

[0045] The calculation of the dew point temperature requires air temperature and relative humidity values. For example, when the air temperature is 20 degrees and the relative humidity is 80%, the dew point temperature is approximately 16 degrees. The calculation of atmospheric density requires pressure and temperature values. Taking the standard atmospheric pressure of 1013 hPa and a temperature of 20 degrees as an example, the atmospheric density is approximately 1.2 kg / m³. For every 100 hPa increase in pressure or every 10-degree decrease in temperature, the atmospheric density will change accordingly. The calculation of the dew point temperature involves the relationship between temperature and humidity. For example, when the air temperature is 25 degrees Celsius and the relative humidity is 80%, the dew point temperature is approximately 21 degrees Celsius through the Magnus formula. The atmospheric density is positively correlated with temperature and pressure. Under standard atmospheric pressure, for every 1-degree increase in temperature, the atmospheric density decreases by approximately 0.3%. The subsequent prediction can be carried out by combining the above dew point temperature and atmospheric density.

[0046] In random forest prediction, 500 decision trees can be set, and each tree uses a different combination of features. For example, the first tree uses temperature and humidity to predict the precipitation probability, and the second tree uses air pressure and wind speed for prediction. Finally, the weather trend is determined through voting. Support vector machines can classify the meteorological prediction results into types such as sunny, cloudy, and rainy, and set a Gaussian kernel function for non-linear classification. Neural network recognition adopts a three-layer structure. The input layer receives meteorological features, the hidden layer extracts features, and the output layer gives the specific weather type. For example, the input layer contains eight nodes such as temperature, humidity, and air pressure, the hidden layer has 16 nodes, and the output layer corresponds to six weather types. The final prediction result is determined through a probability threshold. If the probability of sunny exceeds 70%, the forecast result is set as sunny. When generating a meteorological forecast report, the numerical results need to be converted into text descriptions. For example, if the system predicts that the maximum temperature tomorrow is 28 degrees Celsius, the minimum temperature is 18 degrees Celsius, the southeast wind is level 3, and the precipitation probability is 60%, the forecast text can be generated: Tomorrow will be cloudy turning to overcast, with temperatures ranging from 18 to 28 degrees Celsius, a southeast wind of level 3, and there will be showers.

[0047] S104. Extract performance parameters from the aircraft database, including the maximum flight speed, minimum flight speed, maximum climb rate, and maximum descent rate.

[0048] Extract the values of the maximum flight speed, minimum flight speed, maximum climb rate, and maximum descent rate from the aircraft database.

[0049] Perform normalization processing on the extracted values. If the values exceed the preset threshold range, they are judged as outliers and corrected. Calculate the flight speed range based on the normalized maximum flight speed and minimum flight speed. Calculate the vertical movement ability of the aircraft through the maximum climb rate and maximum descent rate. Use the random forest algorithm to predict the flight performance based on the flight speed range and vertical movement ability. Use the support vector machine algorithm to classify the flight performance prediction results and determine the performance level of the aircraft. Generate an aircraft performance analysis report based on the performance level to complete the aircraft performance evaluation task.

[0050] Specifically, the key performance indicators included in the aircraft database usually involve two categories: speed and lifting ability. The maximum flight speed reflects the fastest speed that the aircraft can reach under specific altitude and meteorological conditions. For example, the maximum flight speed of a certain type of civil airliner at cruising altitude is 900 kilometers per hour. The minimum flight speed reflects the lowest speed required for the aircraft to maintain stable flight. For example, the minimum flight speed of a certain light sport aircraft is 120 kilometers per hour.

[0051] Normalizing these values can unify indicators with different dimensions into the range of zero to one. For example, the maximum climb rate of a certain type of helicopter is 800 meters per minute, and the maximum descent rate is 600 meters per minute. Through normalization, the relative values 0.8 and 0.6 can be obtained. When it is found that the maximum flight speed of a certain type of aircraft far exceeds that of similar models, it is necessary to combine parameters such as engine thrust and aerodynamic layout to determine whether it is an outlier. The calculation of the flight speed range is of great significance for evaluating the practicality of the aircraft. Taking a certain type of fighter as an example, its maximum flight speed is 2400 kilometers per hour, and the minimum flight speed is 200 kilometers per hour, indicating that it has a relatively wide speed range, which is conducive to performing different types of tasks. The vertical movement ability reflects the maneuverability of the aircraft. The maximum climb rate of a certain type of transport aircraft is 600 meters per minute, and the maximum descent rate is 400 meters per minute, indicating that it has good altitude adjustment ability. The random forest algorithm can comprehensively consider multiple performance indicators to predict the overall performance of the aircraft. By establishing a decision tree ensemble model, indicators such as the speed range and vertical movement ability are used as input features to predict the flight performance. The support vector machine algorithm can classify the aircraft into different performance levels according to the prediction results. For example, a certain type of UAV is classified as a high-performance level according to its speed range and lifting ability. The performance analysis report comprehensively evaluates the aircraft performance through quantitative analysis of various indicators. The report content includes speed performance analysis, lift performance analysis, and comprehensive performance evaluation. The determination of the performance level helps in the classification management and task assignment of the aircraft, providing a basis for the user unit to select the appropriate aircraft. The performance analysis report can also provide a more abundant reference for the further selection of the aircraft.

[0052] S105. Calculate the energy consumption change trend of the aircraft under different meteorological conditions according to the comprehensive meteorological dataset and the aircraft performance parameters.

[0053] Extract temperature, wind speed, air pressure, and humidity from the comprehensive meteorological dataset as key meteorological factors, and obtain the aircraft performance parameters including the maximum flight speed and the maximum climb rate. Perform standardization processing on the meteorological factors and performance parameters. If the data exceeds the preset range, correct it to the boundary value. According to the standardized meteorological factors and performance parameters, establish a relationship matrix between the meteorological factors and the energy consumption change. Use the linear regression algorithm to analyze the influence coefficient of the meteorological factors on the energy consumption, and calculate the slope of the energy consumption change trend. If the correlation coefficient between the meteorological factors and the energy consumption change is lower than the preset threshold, use the random forest algorithm to refit the relationship model. Predict the energy consumption change under different meteorological conditions through the relationship model, and generate an energy consumption change trend chart. According to the energy consumption change trend chart, determine the peak and valley values of the energy consumption change of the aircraft under extreme meteorological conditions.

[0054] Specifically, the research on the impact of meteorological factors on the energy consumption of aircraft first requires obtaining comprehensive meteorological data. Taking a comprehensive meteorological station as an example, it can provide key parameters such as sea-level pressure, ground air temperature, relative humidity, and ten-minute average wind speed. For example, in the data recorded by an upper-air meteorological station, the temperature range is usually between minus fifty degrees and forty degrees, the wind speed ranges from calm to sixty meters per second, the air pressure ranges from eight hundred to one thousand one hundred hectopascals, and the relative humidity ranges from ten percent to ninety-five percent. Based on the performance parameters of the aircraft, the maximum flight speed and the maximum climb rate need to be concerned. Usually, the maximum flight speed of a medium-sized fixed-wing UAV is about one hundred and twenty kilometers per hour, and the maximum climb rate is three hundred meters per minute. These parameters need to be standardized so that data with different dimensions can be comparable. For example, the temperature data is normalized to the range of zero to one through the maximum and minimum values, and the out-of-range outliers are corrected to the boundary values. During the establishment of the relationship matrix between meteorological factors and energy consumption, the combined effects of multiple meteorological factors need to be considered. For example, in a low-temperature and high-humidity environment, the energy consumption of the engine will increase significantly, which may lead to a fifteen to twenty percent increase in energy consumption per hour. Through linear regression analysis, the influence weights of different meteorological factors on energy consumption can be obtained. For example, for every ten-degree decrease in temperature, the energy consumption increases by eight percent; for every five-meter-per-second increase in the headwind speed, the energy consumption increases by twelve percent. When the relationship between meteorological factors and energy consumption shows non-linear characteristics, the correlation coefficient of linear regression may be lower than the preset threshold of 0.7. At this time, the random forest algorithm can better fit the complex non-linear relationship. Through the prediction of the random forest model, it is found that under extreme conditions of minus twenty degrees Celsius and a wind speed of twenty meters per second, the energy consumption may reach 1.8 times the normal value. The energy consumption change trend chart can visually display the impact of meteorological conditions on the energy consumption of the aircraft. At noon in summer, under the conditions of a temperature of thirty-five degrees Celsius and a relative humidity of eighty percent, the energy consumption reaches the peak, which is forty percent higher than that under standard atmospheric conditions. While under mild meteorological conditions, such as a temperature of twenty degrees Celsius and a relative humidity of fifty percent, the energy consumption is at the lowest level, only sixty percent of that at the peak. These data have important reference value for formulating flight plans and optimizing flight routes, and can help the aircraft achieve optimal energy consumption control under different meteorological conditions.

[0055] S106. Obtain the target, starting point, ending point, and time requirements of the flight mission from the mission management system, and generate mission constraint conditions.

[0056] Obtain the target, starting point, ending point, and time value of the flight mission from the mission management system, and generate constraint values. According to the constraint values and the aircraft performance values, obtain the performance parameters of the aircraft, including the maximum flight speed and the maximum climb rate.

[0057] Specifically, the constraint values in the mission management system directly affect the overall structure of flight planning. For example, if an aircraft needs to fly from Guangzhou Baiyun Airport to Shenzhen Bao'an Airport within a specified time, the system will generate corresponding constraint values based on this basic information. Combining these constraint values with the aircraft performance values can determine the range of actually available flight parameters. For example, when the maximum flight speed of the aircraft is 150 kilometers per hour and the maximum climb rate is 10 meters per minute, the parameters are optimized in combination with the mission constraints.

[0058] S107. Generate an initial set of flight strategies using a genetic algorithm according to the energy consumption change trend and mission constraint conditions.

[0059] Extract the peak value and valley value from the energy consumption change trend graph, generate constraint values in combination with the mission constraint conditions, match the constraint values with the aircraft performance parameters to obtain the maximum flight speed and maximum climb rate of the aircraft. Use a genetic algorithm according to the above mission constraint conditions and calculate the corresponding objective function based on the energy consumption change trend, where the objective value in the objective function is to minimize the energy consumption.

[0060] Specifically, the energy consumption change trend graph shows the energy consumption changes under different meteorological conditions through continuous sampling points, where the peak and valley values reflect the extreme states of energy consumption. Taking a certain UAV performing a transportation mission in August as an example, when the temperature reaches 38 degrees Celsius and the relative humidity is 85%, the energy consumption reaches 1.6 times that under standard working conditions, forming a peak. And in the early morning when the temperature is 20 degrees Celsius and the humidity is 50%, the energy consumption drops to 0.75 times that of the standard working condition, constituting a valley value. The matching process between the mission constraint conditions and the aircraft performance parameters needs to consider multiple factors. For example, the mission requires transporting goods from Guangzhou to Shenzhen within one hour, and the flight distance is 120 kilometers. The maximum flight speed of the aircraft is 180 kilometers per hour, and the maximum climb rate is 15 meters per minute. After considering the safety margin, the actual available speed range is 80 to 150 kilometers per hour, and the climb rate is controlled between 5 and 10 meters per minute.

[0061] Taking the combination of flight strategies as variables, where the flight strategies include flight speed and flight path, and the flight path contains several stop positions. Use a genetic algorithm to optimize the above variables and calculate the possible energy consumption during flight in real time based on the above variables. The above real-time measured meteorological data or the predicted meteorological data can be used as the possible real-time meteorological data during flight and added to the calculation of energy consumption. After the calculation is completed, select several flight strategies with the lowest energy consumption as the initial set of flight strategies and provide them to the subsequent dynamic programming to further improve and adapt to the corresponding mission.

[0062] S108. Optimize the initial set of flight strategies based on the dynamic programming algorithm to screen out the flight strategy that meets the mission requirements and has the lowest energy consumption.

[0063] For the initial set of flight strategies, obtain the constraint conditions of the mission requirements. Combining with the performance parameters of the aircraft, for a single aircraft, use the linear regression algorithm to analyze the influence coefficient of meteorological values on the energy consumption value, or use the non - linear mapping model to determine the mapping relationship between meteorological values and energy consumption values. According to the mapping relationship between meteorological values, aircraft data and energy consumption values, calculate the energy consumption value of each strategy in the initial set of flight strategies to generate an energy consumption value set.

[0064] Use the dynamic programming algorithm to optimize the energy consumption value set and screen out the flight strategy with the lowest energy consumption. If the screened - out flight strategy meets the constraint conditions of the mission requirements, then determine this strategy as the final flight strategy. If the screened - out flight strategy does not meet the constraint conditions of the mission requirements, then adjust the performance parameters of the aircraft and recalculate the energy consumption values of the initial set of flight strategies. According to the adjusted performance parameters of the aircraft, use the dynamic programming algorithm again to optimize the energy consumption value set and screen out the flight strategy that meets the mission requirements and has the lowest energy consumption. After determining the final flight strategy, generate the flight path and flight parameters to complete the flight strategy optimization process.

[0065] Specifically, the initial set of flight strategies generated by the genetic algorithm needs to be optimized and screened according to the actual mission requirements. Taking a cargo drone performing an inter - city transportation mission as an example, the mission requirement constraints include transportation timeliness and route safety. When the transportation timeliness requires completing the cargo delivery between Guangzhou and Shenzhen within one hour, the flight strategy must ensure that the average speed is not less than 120 kilometers per hour. Route safety requires that the flight altitude is between 200 and 500 meters and avoid flying over important facilities. The performance parameters of the aircraft have an important impact on strategy optimization. A certain model of electric multi - rotor drone has performance indicators such as a maximum take - off weight of 10 kilograms, a flight endurance of 90 minutes, and a maximum climb rate of 15 meters per minute. After considering the safety margin, the actual available performance is about 80% of the maximum value, and these parameters constitute the basic constraints of the flight strategy.

[0066] The mapping relationship between meteorological values, aircraft data, and energy consumption is established through the above linear regression algorithm or non-linear mapping model. Aircraft data includes data such as the aircraft and payload weight. Data analysis shows that for every one-degree Celsius increase in temperature, for every 1 kg increase in aircraft payload, the energy consumption increases by 0.6%. For every one-meter per second increase in wind speed, for every 1 kg increase in aircraft payload, the energy consumption increases by 1.5% against the wind and decreases by 0.8% with the wind. When performing tasks in summer, the increase in temperature leads to a decrease in battery efficiency and a significant increase in energy consumption. When the temperature reaches 35 degrees Celsius, the energy consumption increases by 21% compared to the standard operating conditions. When the dynamic programming algorithm optimizes the set of energy consumption values, the flight route is divided into multiple segments. The energy consumption value of each segment is related to parameters such as flight altitude and speed. In a certain mission, the initial route plan was a straight flight at a constant altitude, and the predicted energy consumption value was 150 watt-hours per kilometer. After optimization by dynamic programming, a strategy of adjusting the altitude in segments was adopted, and the energy consumption was reduced to 120 watt-hours per kilometer by utilizing the tailwind layer to save energy. When the optimized flight strategy does not meet the constraint conditions, it is necessary to adjust the performance parameters and re-optimize. For example, in the case of strong headwinds, if the maximum speed of 150 kilometers per hour still cannot meet the timeliness requirements, it is necessary to reduce the payload to improve the maneuverability. In a certain mission, by adjusting the payload from 8 kg to 6 kg and increasing the maximum speed to 180 kilometers per hour, the timeliness requirements were successfully met. The finally determined flight strategy needs to generate detailed flight paths and parameters, including waypoint coordinates, flight altitude, speed, and other information. When executing the flight route from Guangzhou to Shenzhen, twenty key waypoints were set, three alternate landing points were planned, and specific speed values were set for different altitude layers to ensure that the flight strategy can safely and efficiently execute the transportation task.

[0067] As Figure 2 shown, the present invention provides a low-altitude aircraft flight energy consumption optimization system based on meteorological conditions, mainly including:

[0068] A data acquisition module, used to obtain multi-source meteorological data from meteorological observation stations, radars, and satellites, including wind speed, temperature, pressure, and humidity information;

[0069] A data cleaning module, used to preprocess the multi-source meteorological data using data cleaning techniques, remove noise and outliers, and unify the data format and accuracy;

[0070] A data fusion module, used to integrate the cleaned multi-source meteorological data into a comprehensive meteorological data set with a single spatio-temporal dimension based on preset fusion rules;

[0071] A performance parameter extraction module, used to extract performance parameters from the aircraft database, including the maximum flight speed, minimum flight speed, maximum climb rate, and maximum descent rate;

[0072] An energy consumption calculation module, configured to calculate the energy consumption change trend of the aircraft under different meteorological conditions according to the comprehensive meteorological data set and the aircraft performance parameters;

[0073] A mission constraint generation module, configured to obtain the target, starting point, ending point and time requirements of the flight mission from the mission management system, and generate mission constraint conditions;

[0074] An initial strategy generation module, configured to generate an initial flight strategy set by using a genetic algorithm for the energy consumption change trend and the mission constraint conditions;

[0075] A strategy optimization module, configured to optimize the initial flight strategy set based on a dynamic programming algorithm, and screen out the flight strategy that meets the mission requirements and has the lowest energy consumption.

[0076] The above is only a preferred specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for optimizing the flight energy consumption of low-altitude aircraft based on meteorological conditions, characterized in that, Including: Obtain multi-source meteorological data, fuse the multi-source meteorological data to obtain meteorological data; Fit the energy consumption data of the aircraft according to the meteorological data to obtain the energy consumption change trend; Obtain the performance parameters and mission requirements of the aircraft, generate constraint conditions according to the performance parameters and mission requirements, and use the genetic algorithm with the minimum energy consumption as the goal. According to the energy consumption change trend and constraint conditions, obtain the initial flight strategy set; Dynamically adjust the initial flight strategy set to obtain the final flight strategy with optimized flight energy consumption.

2. The method according to claim 1, wherein The process of fusing the multi-source meteorological data includes: Standardize the format of the multi-source meteorological data; wherein the multi-source meteorological data includes wind speed, temperature, air pressure, and humidity obtained through meteorological observation stations, radars, and satellites. Perform weighted sum calculation on the data after format standardization to obtain meteorological data.

3. The method according to claim 1, wherein Before fusing the multi-source meteorological data, it further includes: Preprocess the multi-source meteorological data, and the preprocessing process includes removing noise, filling missing data, and correcting outliers.

4. The method according to claim 1, wherein The process of obtaining the energy consumption change trend includes: Obtain the aircraft energy consumption data corresponding to the meteorological data, perform linear correlation analysis on the meteorological data and the corresponding aircraft energy consumption data. When the result of the linear correlation analysis is greater than the threshold, then fit the meteorological data and the corresponding aircraft energy consumption data through a linear regression model to obtain the linear mapping relationship between the meteorological data and the aircraft energy consumption data, that is, the energy consumption change trend. Otherwise, fit the meteorological data and the corresponding aircraft energy consumption data through a machine learning model to obtain the non-linear mapping relationship between the meteorological data and the aircraft energy consumption data, that is, the energy consumption change trend.

5. The method according to claim 1, wherein The constraint conditions include performance parameter constraints and mission constraints. Among them, the performance parameter constraints include maximum flight speed, minimum flight speed, maximum climb rate, and maximum descent rate, and the mission constraints include starting point, ending point, and time requirements.

6. The method according to claim 1, wherein The process of obtaining the initial flight strategy set includes: Construct initial variables according to the flight strategy, where the flight strategy includes the flight path and flight speed of the aircraft, obtain real-time meteorological data, and use the genetic algorithm to iteratively adjust the initial variables under the constraints of the constraint conditions. During the adjustment process, calculate the energy consumption data corresponding to the initial variables according to the energy consumption change, and take the minimum energy consumption data as the goal to obtain the initial flight strategy set; Wherein the energy consumption data is the product result of the sum of the initial energy consumption of the UAV, the energy consumption change value, and 1.

7. The method according to claim 6, wherein The process of dynamically adjusting the initial flight strategy includes: Obtain the energy consumption value of the initial flight strategy set, and the energy consumption value is calculated according to the real-time meteorological data in combination with the mapping relationship between the aircraft data and the energy consumption value. The aircraft data includes the aircraft and the load weight; Segment the altitude of the flight strategies in the set of initial flight strategies, calculate the adjusted energy consumption value, and judge the adjusted flight strategies according to the constraint conditions. Based on the calculated energy consumption value and the judgment result, obtain the final flight strategy with optimized flight energy consumption.

8. The method according to claim 6, wherein Predict future meteorological data based on real-time meteorological data, and replace the real-time meteorological data with the future meteorological data to calculate the energy consumption change value and the energy consumption value.

Images