Meteorological big data-based low-altitude route planning method and system

Abstract

The invention relates to the technical field of low-altitude aircrafts, and discloses a meteorological big data-based low-altitude route planning method and system, and the method comprises the following steps: collecting meteorological data through a meteorological monitoring device; monitoring flight parameters and environmental parameters of the aircraft; the meteorological data, the flight parameters and the environmental parameters are constructed into a graph, and a flight strategy is generated by using a graph neural network; by establishing a meteorological data real-time acquisition and transmission mechanism and combining with an aircraft parameter monitoring system, meteorological environment changes can be sensed in time, a flight strategy can be rapidly adjusted, and the method enables the aircraft to reduce the probability of occurrence of safety accidents in low-visibility, strong-wind and rainfall weather.

Description

Technical Field

[0001] The present invention relates to the technical field of low-altitude aircraft, and more specifically, to a low-altitude route planning method and system based on meteorological big data. Background Art

[0002] With the widespread use of low-altitude aircraft such as drones, the safety and reliability of low-altitude route planning are becoming increasingly important. At present, low-altitude aircraft face the following major challenges in complex meteorological environments: First, sudden changes in meteorological conditions (such as wind speed, visibility, precipitation, etc.) will significantly affect flight safety; second, traditional route planning methods mainly rely on pre-set fixed routes and lack the ability to dynamically respond to real-time meteorological changes; third, under severe weather conditions, the energy consumption of aircraft will increase significantly, and existing energy management systems are difficult to effectively cope with this situation.

[0003] In the existing technology, although there are some route planning methods based on meteorological data, there are still the following technical problems: when the meteorological conditions change drastically, the existing system cannot adjust the flight strategy in time and allocate energy reasonably. This is mainly because the existing technology lacks a deep integration mechanism of real-time meteorological data and aircraft performance parameters, and the energy management strategy is relatively fixed and difficult to adapt to the complex and changing meteorological environment; this technical problem seriously affects the safety and reliability of low-altitude aircraft in severe weather conditions. Summary of the invention

[0004] The purpose of the present invention is to provide a low-altitude route planning method and system based on meteorological big data in order to solve the above-mentioned problems.

[0005] The present invention provides a low-altitude route planning method based on meteorological big data, comprising:

[0006] Collect meteorological data through meteorological monitoring equipment;

[0007] Monitor the flight parameters and environmental parameters of the aircraft;

[0008] Meteorological data, flight parameters, and environmental parameters are constructed into a graph, and a graph neural network is used to generate flight strategies.

[0009] Furthermore, the flight strategy formulation based on graph neural network includes:

[0010] Encoding graphs using graph neural networks;

[0011] Input the graph encoding results into the decision network to generate the flight strategy;

[0012] Reinforcement learning algorithm is used to optimize the parameters of graph neural network and decision network.

[0013] Furthermore, it also includes:

[0014] Real-time monitoring of the communication link status through detection functions;

[0015] Automatically switch to an alternate communication link when a communication interruption is detected;

[0016] After communication is restored, data retransmission and synchronization are performed.

[0017] Furthermore, it also includes:

[0018] Conduct quality assessment of received meteorological data;

[0019] When the data quality is lower than the preset threshold, data fusion technology is used to fuse multi-source meteorological data;

[0020] Use fused weather data to re-plan flight strategies.

[0021] Furthermore, it also includes:

[0022] Real-time monitoring of the status of each component of the aircraft;

[0023] When performance degradation is detected, the flight strategy is re-established based on the new performance parameters.

[0024] Furthermore, it also includes:

[0025] Establish an energy demand forecasting model to predict total energy demand in future time periods , the formula is as follows:

[0026] ;

[0027] in, Indicates that in the future According to the energy consumption rate Over time Cumulative energy consumption of changes; Indicates that the navigation support related functions are in different operating states The minimum energy demand under

[0028] Evaluate the performance parameters of new energy storage technologies based on energy storage capacity , Charging efficiency , discharge efficiency , calculate the energy storage capacity of each new energy storage technology at a given time The effective energy supply that can be provided , the calculation formula is as follows:

[0029] ;

[0030] Design and deploy intelligent energy allocation algorithms to dynamically adjust energy allocation strategies.

[0031] Furthermore, complex environments may cause fluctuations in the performance of energy storage technologies, which in turn affect the reliability of energy distribution strategies, thus including:

[0032] Real-time monitoring of performance indicators of new energy storage technologies;

[0033] Dynamically update the performance of each new energy storage technology at a given time based on monitoring data The effective energy supply that can be provided , the calculation formula is updated to:

[0034] ;

[0035] in, is the real-time energy storage capacity, For real-time charging efficiency, is the real-time discharge efficiency;

[0036] Redo energy allocation decisions based on updated data.

[0037] Furthermore, the flight strategy adjustment also includes the following steps:

[0038] Real-time monitoring of the aircraft's attitude information during flight , acceleration information ;

[0039] Establish an energy consumption rate correction model. The energy consumption rate has a certain functional relationship with posture and acceleration. , establish the following formula:

[0040] ;

[0041] in is the uncorrected energy consumption rate, is the corrected energy consumption rate;

[0042] The corrected energy consumption rate Substitute into the energy demand forecast model and recalculate the total energy demand , the formula is:

[0043] .

[0044] Furthermore, the intelligent energy allocation algorithm adopts a distributed computing architecture:

[0045] Distribute computing tasks to multiple computing units for parallel processing;

[0046] Use simplified optimization algorithm model to reduce computational complexity;

[0047] The results of each calculation unit are summarized to obtain the final energy allocation strategy.

[0048] The present invention provides a low-altitude route planning system based on meteorological big data, which is used to store computer-readable instructions. When the computer-readable instructions are read, the aforementioned low-altitude route planning method based on meteorological big data can be executed.

[0049] The beneficial effects of the present invention are as follows: the present invention can timely perceive the changes in the meteorological environment and quickly adjust the flight strategy by establishing a real-time collection and transmission mechanism for meteorological data and combining it with an aircraft parameter monitoring system. This method reduces the probability of safety accidents in aircraft under low visibility, strong winds and precipitation weather.

[0050] Adopting intelligent energy allocation algorithm, dynamically adjusting energy use strategy according to real-time meteorological conditions, significantly improving energy utilization efficiency;

[0051] The accuracy and reliability of meteorological data are improved through multi-source data fusion technology and data quality assessment mechanism;

[0052] Designed a distributed computing architecture and simplified optimization model to reduce the system computing burden and shorten the response time of flight strategy adjustment;

[0053] A comprehensive communication guarantee mechanism has been established, which can quickly switch to alternative communication methods when the communication link is interrupted, ensuring reliable communication between the aircraft and the ground control center. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flow chart of a low-altitude route planning method based on meteorological big data of the present invention; DETAILED DESCRIPTION

[0055] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0056] At least one embodiment of the present invention discloses a low-altitude route planning method based on meteorological big data, such as Figure 1 As shown, the following steps are included:

[0057] Step 100: Meteorological data collection and transmission. Meteorological data, including wind speed, is collected in real time through various meteorological monitoring equipment. ,wind direction Temperature , air pressure ,visibility , precipitation intensity And transmit these data to the flight control system of the aircraft in real time through wireless communication technology.

[0058] In one embodiment of the present invention, the transfer function is ,in For the various meteorological data collected, the aircraft control system receives them through a specific interface and parses it into a meteorological data format that the system can recognize for subsequent flight strategy formulation.

[0059] Step 200: Aircraft parameter monitoring. The aircraft's own flight parameter monitoring system monitors the flight speed in real time. , Flight altitude , Flight direction The system can monitor the environmental parameters around the aircraft through air pressure sensors, temperature sensors, etc., and feed the monitored flight parameters and environmental parameters back to the flight control system in real time as input for formulating flight strategies.

[0060] Step 300: Flight strategy formulation based on graph neural network. Meteorological data, flight parameters and environmental parameters are constructed into a graph. , where the node , indicating various parameters (such as wind speed, wind direction, visibility, etc.), , indicating the relationship between parameters (such as the relationship between wind speed and wind direction). Each node With characteristic vector , represents the value of the parameter. Encode, learn the interaction patterns between nodes, and generate flight strategies. The specific steps are as follows:

[0061] Step 301: Use a graph neural network (such as graph convolutional network GCN, graph attention network GAT, etc.) to Encode. Indicates Layer graph neural network for nodes The feature code, initial value Each layer of the graph neural network can be expressed as:

[0062]

[0063] in Representation Node The set of neighbor nodes of Indicates Layer graph neural network for nodes The feature encoding of For Node and The attention weights of the interactions, For the The parameter matrix of the layer, is the activation function.

[0064] Step 302: Output the last layer of the graph encoding Input into the decision network (such as multi-layer perceptron MLP) to generate a flight strategy. Let the decision network be the function , then the flight strategy is:

[0065]

[0066] in A vector containing the adjustment values ​​of flight parameters such as flight speed, direction, and altitude.

[0067] Step 303: generate the flight strategy The data is input into the environmental model (such as the meteorological model), its safety and efficiency are evaluated, and the optimization goal (such as minimizing energy consumption) is calculated. Then, the parameters of the graph neural network and decision network are optimized using reinforcement learning algorithms (such as REINFORCE, PPO, etc.), so that the flight strategy can minimize energy consumption while ensuring flight safety.

[0068] Step 400: Implement the guarantee mechanism. Establish a real-time communication link between the aircraft and the ground control center. The aircraft transmits the monitored real-time flight status data through the communication function. Sent to the ground control center, where The ground control center receives real-time flight status information from the aircraft. Information will be provided, and further flight guidance or emergency measures will be given when necessary, while surrounding airspace resources will be coordinated to ensure smooth low-altitude navigation.

[0069] In one embodiment of the present invention, since the flight strategy adjustment may cause additional energy consumption, it is necessary to establish a complete energy management mechanism, which also includes the following steps:

[0070] Step 501: Establish an energy demand prediction model. Energy consumption rate data of low-altitude aircraft in different complex environments The flight test can be carried out in a variety of typical complex environments (such as different weather conditions, different flight attitudes, etc.) to record the aircraft's performance in different time periods. The energy consumption of the system is analyzed and processed by data analysis. The minimum energy demand of the navigation support related functions under different operating conditions It can be determined based on the design specifications of each function, historical operation data, and industry standards. Based on the data obtained, an energy demand forecasting model is established to predict the energy demand in the future. The total energy demand of the internal aircraft is as follows:

[0071]

[0072] in, Indicates that in the future According to the energy consumption rate Over time Cumulative energy consumption of changes; Indicates that the navigation support related functions are in different operating states The minimum energy requirement under

[0073] Step 502: Evaluate new energy storage technologies. To evaluate new energy storage technologies, one can consult relevant technical information and research reports to obtain theoretical performance parameters of various new energy storage technologies, and then evaluate their energy storage capacity in combination with actual test data. , Charging efficiency , discharge efficiency Analyze and compare key parameters such as energy storage capacity. , Charging efficiency , discharge efficiency Parameters such as The effective energy supply that can be provided , the calculation formula is as follows:

[0074]

[0075] Step 503: Design an intelligent energy allocation algorithm. The goal is to maximize the energy demand of navigation support related functions. and the effective energy supply of different new energy storage technologies , through the optimization algorithm to allocate the charging and discharging strategies of different energy storage technologies at different times , the optimization model is established as follows:

[0076]

[0077] in, The maximum charge and discharge power of the aircraft energy system, which limits the upper limit of the charge and discharge power of the entire energy system at any time; and Respectively The minimum and maximum charging and discharging powers of various energy storage technologies constrain the power range of each energy storage technology during the charging and discharging process.

[0078] Common optimization algorithms can be used to solve the optimization model, such as linear programming algorithms (such as simplex method), nonlinear programming algorithms (such as interior point method) or heuristic algorithms (such as genetic algorithm, particle swarm algorithm, etc.). According to actual needs and computing resources, the appropriate algorithm is selected to obtain the optimal charging and discharging strategy. .

[0079] Step 504: deploy the intelligent energy allocation algorithm. The designed intelligent energy allocation algorithm is deployed to the energy management system of the low-altitude aircraft to monitor the energy consumption of the aircraft, the status of the energy storage technology and other information in real time, and dynamically adjust the energy allocation strategy according to the actual situation to ensure the normal operation of related functions of air traffic control in complex environments.

[0080] In one embodiment of the present invention, since the communication link is easily disturbed or interrupted in a complex meteorological environment, which will directly affect the guidance and monitoring of the aircraft by the ground control center, it is necessary to establish a reliable communication guarantee mechanism.

[0081] Step 601, fault detection and location. The communication equipment on the aircraft side and the ground control center side has an automatic detection function. Suppose the detection function is ,in Indicates the relevant parameters of the communication equipment. Indicates that a communication link interruption fault is detected. Indicates that no fault is detected. When a fault is detected, an attempt is made to locate the approximate area where the fault occurs.

[0082] Step 602: Activate the backup communication link. The aircraft and the ground control center are pre-equipped with a backup communication link (such as a satellite communication link) as a backup for the wireless communication link. ), immediately switch to the backup communication link.

[0083] Let the switching function be ,in Indicates the current communication status. Indicates the use of the primary communication link, Indicates the use of a backup communication link. The switching process is:

[0084]

[0085] Step 603, data retransmission and synchronization. After switching to the backup communication link, the aircraft retransmits the flight status data that was not successfully transmitted during the interruption to the ground control center. Suppose the retransmission function is ,in Indicates a data set that was not successfully transmitted. The retransmission process is ,in It is the communication function between the aircraft and the ground control center to ensure that the ground control center can obtain complete aircraft flight status information and restore the normal operation of the guarantee mechanism.

[0086] In one embodiment of the present invention, since the accuracy of meteorological data directly affects the formulation of flight strategies and further affects energy efficiency, a data quality assurance mechanism needs to be established. Specifically, the following steps are included:

[0087] Step 701, data quality assessment. The flight control system of the aircraft performs quality assessment on the received meteorological data. The assessment function is ,in Represents the set of received meteorological data. By comparing meteorological data from different sources (such as meteorological satellites, meteorological monitoring stations, airborne meteorological radars, etc.) and combining the rules of historical meteorological data, the currently received meteorological data is evaluated. (The threshold can be set according to actual conditions), indicating that the data quality is poor and needs further processing.

[0088] Step 702: Data fusion and correction. When , data fusion technology is used to fuse meteorological data from different sources to improve the accuracy of the data. Suppose the fusion function is ,in Represents a collection of meteorological data from different sources. For example, for wind speed data , if the wind speed data obtained from the meteorological satellite is , the wind speed data obtained from the meteorological monitoring station is , the wind speed data obtained from the airborne weather radar is , then the fused wind speed data is:

[0089]

[0090] in , , is a weighting factor set according to the reliability of each data source, and Other meteorological data (such as wind direction, visibility, etc.) are also processed accordingly through data fusion to correct inaccurate meteorological data.

[0091] Step 703: Use the corrected weather data to formulate a flight strategy. The flight control system uses the corrected weather data to re-formulate a flight strategy to ensure that the flight strategy can adapt to the actual weather conditions and ensure flight safety.

[0092] In one embodiment of the present invention, when the performance of the aircraft degrades, it will not only affect the execution of the flight strategy, but also affect the energy consumption prediction, so it is necessary to establish a performance evaluation and adjustment mechanism. Specifically, the following steps are included:

[0093] Step 801, fault monitoring and performance evaluation. The aircraft itself has a real-time monitoring system. Suppose the monitoring function is ,in Indicates the relevant parameters of each component of the aircraft. Indicates that a component failure has been detected. Indicates that no fault is detected. At the same time, let the performance evaluation function be ,in Represents the current performance parameter set of the aircraft. By comparing the current performance parameters with the normal performance parameters, the degree of aircraft performance degradation is evaluated.

[0094] Step 802: Re-formulate the flight strategy. Once the aircraft performance is detected to be degraded ( ), the flight control system uses the performance evaluation function according to the evaluated performance degradation The new aircraft performance parameters are used to re-formulate the flight strategy. For example, if the wind speed exceeds the maximum safe wind speed that the current aircraft can withstand, When , the formula for re-adjusting the flight direction is:

[0095]

[0096] in is the adjustment factor determined based on the new aircraft performance parameters, For wind direction With flight direction Angle Similarly, the flight strategy adjustment formula for other meteorological conditions is also modified according to the new performance parameters to ensure that the flight strategy can adapt to the sudden decline in aircraft performance and ensure flight safety.

[0097] In one embodiment of the present invention, since complex environments may cause fluctuations in the performance of energy storage technology, thereby affecting the reliability of energy allocation strategies, it is necessary to establish a real-time monitoring and dynamic adjustment mechanism. Specifically, the following steps are included:

[0098] Step 901, establish a real-time monitoring system. Perform real-time monitoring of various performance indicators (such as energy storage capacity, charging and discharging efficiency, etc.) of the new energy storage technology in a complex environment. Install corresponding sensors on the aircraft to monitor various performance indicators of the new energy storage technology. Suppose the monitored real-time energy storage capacity is , the real-time charging efficiency is , the real-time discharge efficiency is .

[0099] Step 902: Dynamically adjust the energy allocation strategy. Recalculate the energy allocation strategy of each new energy storage technology at a given time based on real-time monitoring data. The effective energy supply that can be provided For rechargeable energy storage technology, the calculation formula is updated to:

[0100]

[0101] The updated Substitute it into the intelligent energy allocation algorithm and make new energy allocation decisions to ensure the rationality of energy allocation and meet the actual energy needs of navigation support related functions.

[0102] In one embodiment of the present invention, since the flight strategy adjustment may cause frequent changes in flight attitude, thereby affecting the accuracy of energy consumption prediction, it is necessary to establish an energy consumption correction mechanism. Specifically, the following steps are included:

[0103] Step 1001: Use multi-sensor fusion technology to install various sensors such as attitude sensors and acceleration sensors on the aircraft to obtain the attitude information of the aircraft during flight. , acceleration information wait.

[0104] Step 1002: Establish an energy consumption rate correction model. Establish an energy consumption rate correction model based on the acquired sensor data. The energy consumption rate has a certain functional relationship with the posture and acceleration. , assuming the corrected energy consumption rate is , then establish the following formula:

[0105]

[0106] in is the uncorrected energy consumption rate. Here the function Based on a large amount of flight test data, it is determined through data analysis and modeling methods, such as regression analysis, machine learning algorithms (such as neural networks), etc., to find the quantitative relationship between attitude, acceleration and energy consumption rate.

[0107] Step 1003: Correct the energy demand prediction model. Substitute into the energy demand forecast model and recalculate the total energy demand , the formula is:

[0108]

[0109] in To ensure the relevant functions of the navigation in different operating states Based on the updated total energy demand , re-carry out subsequent energy distribution and other related operations to ensure the normal operation of navigation support related functions.

[0110] In one embodiment of the present invention, since various types of data and computing tasks need to be processed simultaneously, which may lead to excessive computing burden, it is necessary to establish an efficient computing architecture. Specifically, the following steps are included:

[0111] Step 1101, using a distributed computing architecture. Multiple computing units, such as processor cores, are set up on the aircraft to allocate decision variables of the intelligent energy allocation algorithm. , energy demand forecasting model and the effective energy supply of different new energy storage technologies The relevant data is distributed to each computing unit. Each computing unit performs calculations in parallel based on the data allocated to it and obtains its own calculation results. The calculation results of each computing unit are summarized and integrated to obtain the final energy allocation strategy. Distributed computing architecture is a computing mode that decomposes computing tasks into multiple subtasks and processes them in parallel by multiple computing nodes. It can make full use of the processing power of multiple computing units, improve computing efficiency, and reduce computing time.

[0112] Step 1102, using a simplified optimization algorithm model. Simplify the optimization model in the intelligent energy allocation algorithm to reduce the computational complexity. For example, a nonlinear optimization problem can be simplified to a linear optimization problem, or a heuristic algorithm can be used instead of an exact solution algorithm. Suppose the objective function of the simplified optimization algorithm model is:

[0113]

[0114] in To simplify the decision variables in the algorithm, their values ​​can be taken from the original decision variables A finite number of discrete values ​​are selected from the range of values ​​to reduce the scale and amount of calculation of the optimization problem. By adopting a simplified optimization algorithm model, the computational complexity of the algorithm can be significantly reduced while ensuring a certain energy allocation effect, and the real-time performance of the algorithm can be improved. The linear optimization problem is to find the maximum or minimum value of a linear objective function under a set of linear constraints. Compared with the nonlinear optimization problem, its computational complexity is lower; the heuristic algorithm is an algorithm based on experience or intuition. It reduces the amount of calculation by finding an approximate optimal solution. Although it may not necessarily obtain the global optimal solution, it can often obtain better results within an acceptable time in practical applications.

[0115] The following takes a low-altitude flight scene of a drone in a provincial capital city in central China as an example to illustrate the specific application effect of this embodiment:

[0116] Table 1, examples of real-time meteorological data collected by the meteorological monitoring device of the present invention;

[0117]

[0118] Table 2, examples of flight parameters monitored in real time by the aircraft of the present invention;

[0119]

[0120] Table 3, examples of flight strategy adjustment effects of the present invention;

[0121]

[0122] It can be seen from Table 1, Table 2, and Table 3 that when the weather conditions change, the present embodiment can adjust the flight strategy in time:

[0123] 1. At 14:10, due to reduced visibility, the system automatically reduced the flight speed;

[0124] 2. At 14:15, due to the increase in wind speed, the system adjusted the flight direction according to the wind direction;

[0125] 3. At 14:20, due to the increase in precipitation intensity, the system increased the flight altitude.

[0126] These automatic adjustments ensure the safe operation of the aircraft in adverse weather conditions. Actual operation data show that after adopting the method of this embodiment, the safety accident rate of the aircraft in low visibility, strong wind and precipitation weather is reduced by 85%, and the flight mission completion rate is increased by 60%.

[0127] In at least one embodiment of the present invention, a low-altitude route planning system based on meteorological big data is provided, which is used to store computer-readable instructions, and when the computer-readable instructions are read, the aforementioned low-altitude route planning method based on meteorological big data can be executed.

[0128] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are protected by this embodiment.

Claims

1. A low-altitude route planning method based on meteorological big data, characterized in that: The following steps are involved: Collect meteorological data through meteorological monitoring equipment; Monitor the flight parameters and environmental parameters of the aircraft; Meteorological data, flight parameters, and environmental parameters are constructed into a graph, and a graph neural network is used to generate flight strategies.

2. A low-altitude route planning method based on meteorological big data according to claim 1, characterized in that: The flight strategy formulation based on graph neural network includes the following steps: Encoding graphs using graph neural networks; Input the graph encoding results into the decision network to generate the flight strategy; Reinforcement learning algorithm is used to optimize the parameters of graph neural network and decision network.

3. The low-altitude route planning method based on meteorological big data according to claim 1 is characterized in that: The following steps are also included: Real-time monitoring of the communication link status through detection functions; Automatically switch to an alternate communication link when a communication interruption is detected; After communication is restored, data retransmission and synchronization are performed.

4. The low-altitude route planning method based on meteorological big data according to claim 1 is characterized in that: The following steps are also included: Conduct quality assessment of received meteorological data; When the data quality is lower than the preset threshold, data fusion technology is used to fuse multi-source meteorological data; Use fused weather data to re-plan flight strategies.

5. The low-altitude route planning method based on meteorological big data according to claim 1 is characterized in that: The following steps are also included: Real-time monitoring of the status of each component of the aircraft; When performance degradation is detected, the flight strategy is re-established based on the new performance parameters.

6. The low-altitude route planning method based on meteorological big data according to claim 1 is characterized in that: Also includes: Establish an energy demand forecasting model to predict total energy demand in future time periods , the formula is as follows: ； in, Indicates that in the future According to the energy consumption rate Over time Cumulative energy consumption of changes; Indicates that the navigation support related functions are in different operating states The minimum energy demand under Evaluate the performance parameters of new energy storage technologies based on energy storage capacity , Charging efficiency , discharge efficiency , calculate the energy storage capacity of each new energy storage technology at a given time The effective energy supply that can be provided , the calculation formula is as follows: ； Design and deploy intelligent energy allocation algorithms to dynamically adjust energy allocation strategies.

7. A low-altitude route planning method based on meteorological big data according to claim 6, characterized in that: Complex environments may cause fluctuations in the performance of energy storage technologies, which in turn affect the reliability of energy distribution strategies, including: Real-time monitoring of performance indicators of new energy storage technologies; Dynamically update the performance of each new energy storage technology at a given time based on monitoring data The effective energy supply that can be provided , the calculation formula is updated to: ； in, is the real-time energy storage capacity, For real-time charging efficiency, is the real-time discharge efficiency; Redo energy allocation decisions based on updated data.

8. The low-altitude route planning method based on meteorological big data according to claim 7 is characterized in that: The flight strategy adjustment also includes the following steps: Real-time monitoring of the aircraft's attitude information during flight , acceleration information ; Establish an energy consumption rate correction model. The energy consumption rate has a certain functional relationship with posture and acceleration. , establish the following formula: ； in is the uncorrected energy consumption rate, is the corrected energy consumption rate; The corrected energy consumption rate Substitute into the energy demand forecast model and recalculate the total energy demand , the formula is: 。 9. The low-altitude route planning method based on meteorological big data according to claim 8 is characterized in that: The smart energy allocation algorithm adopts a distributed computing architecture: Distribute computing tasks to multiple computing units for parallel processing; Use simplified optimization algorithm model to reduce computational complexity; The results of each calculation unit are summarized to obtain the final energy allocation strategy.

10. A low-altitude route planning system based on meteorological big data, characterized in that: It is used to store computer-readable instructions, which, when read, can execute a low-altitude route planning method based on meteorological big data as described in any one of claims 1-9.

Images