Flight equipment energy consumption management method and device and readable storage medium

Abstract

The invention provides a flight equipment energy consumption management method and apparatus, and a readable storage medium. The method comprises the steps of obtaining flight related data of flight equipment during execution of a flight task; based on the flight-related data, performing energy consumption prediction through a pre-trained power consumption prediction model to obtain an energy consumption prediction result; when the energy consumption prediction result has a risk, determining an emergency flight strategy; and sending the emergency flight strategy to a flight device to instruct the flight device to continue to execute a flight task according to the emergency flight strategy. According to the invention, through combination of the machine learning technology and the physical model, a more accurate, real-time and intelligent flight equipment energy consumption management scheme is realized, the power consumption can be predicted according to the real-time state and environmental conditions of the flight equipment, and optimization and adjustment are carried out through an emergency mechanism when the power is insufficient, so that smooth completion of a flight task is ensured.

Description

Technical Field

[0001] This application relates to the technical field of unmanned aerial vehicles, and particularly to a method, device and readable storage medium for energy consumption management of a flight device. Background Art

[0002] With the development of unmanned aerial vehicle technology, the application of unmanned aerial vehicles in fields such as cargo transportation, inspection, and monitoring has become increasingly widespread.

[0003] The autonomous flight tasks of unmanned aerial vehicles usually include transportation tasks from a starting point to a target point. One of the core challenges of the tasks is how to ensure that the unmanned aerial vehicle always maintains sufficient power throughout the flight process to avoid mission failure or flight interruption due to insufficient battery power. The power consumption of unmanned aerial vehicles is affected by various factors. In the current flight tasks, the prediction and monitoring of power mainly rely on simple battery power models, and these models cannot accurately reflect the complex impact of different flight states and environmental changes on power consumption.

[0004] Therefore, how to monitor the power change in real time during flight and make accurate power prediction and energy consumption management according to the state of the flight device and environmental conditions has become a major challenge in the autonomous flight of unmanned aerial vehicles. Summary of the Invention

[0005] The technical problem to be solved by this application is to provide a method, device and readable storage medium for energy consumption management of a flight device in view of the above deficiencies of the prior art, so as to solve the problems existing in the prior art.

[0006] In a first aspect, this application provides a method for energy consumption management of a flight device, the method

[0007] comprises:

[0008] S1. Obtain flight-related data of the flight device when performing a flight task;

[0009] S2. Based on the flight-related data, perform energy consumption prediction through a pre-trained power consumption prediction model to obtain an energy consumption prediction result;

[0010] S3. When there is a risk in the energy consumption prediction result, determine an emergency flight strategy;

[0011] S4. Send the emergency flight strategy to the flight device to instruct the flight device to continue to perform the flight task according to the emergency flight strategy.

[0012] In some embodiments, the flight-related data includes flight speed, flight altitude, wind speed, temperature, air density, load, remaining flight distance.

[0013] In some embodiments, S2 includes:

[0014] When the current remaining power of the flying device is lower than the first preset ratio of the maximum power of the device, based on the flight-related data, energy consumption prediction is performed through a pre-trained power consumption prediction model to obtain the predicted power consumption required for the flying device to complete the flight mission.

[0015] In some embodiments, in S3, when the difference between the current remaining power of the flying device and the predicted power consumption required for the flying device to complete the flight mission is lower than the second preset ratio of the current remaining power, it is determined that there is a risk in the energy consumption prediction result.

[0016] In some embodiments, in S3, determining an emergency flight strategy includes:

[0017] Determine the power consumption corresponding to each different flight speed according to the current remaining flight distance;

[0018] Determine the flight speed with power consumption lower than the target consumable power as the emergency flight speed, where the target consumable power is the third preset ratio of the current remaining power.

[0019] In some embodiments, according to the current remaining flight distance, the power consumption corresponding to each different flight speed is determined by the following formula:

[0020]

[0021] where E(v) is the power consumption, ρ is the air density, ν is the flight speed, C d is the drag coefficient of the flying device, A is the windward area of the flying device, α is the adjustment factor of the wind speed on the power consumption of the flying device, C m is the influence coefficient of the wind speed on the flying device, d is the remaining flight distance, η motor is the efficiency of the motor of the flying device.

[0022] In some embodiments, it further includes:

[0023] When the difference between the current remaining power of the flying device and the predicted power consumption required for the flying device to complete the flight mission is higher than or equal to the second preset ratio of the current remaining power, it is determined that there is no risk in the energy consumption prediction result;

[0024] After a preset duration after the previous energy consumption prediction is completed, re-obtain the flight-related data of the flying device, and re-perform energy consumption prediction through the pre-trained power consumption prediction model to obtain the energy consumption prediction result.

[0025] In a second aspect, the present application provides a flying device energy consumption management device, and the device includes:

[0026] A data acquisition module, which is configured to acquire flight-related data of a flight device during a flight mission;

[0027] An energy consumption prediction module, which is configured to perform energy consumption prediction based on the flight-related data through a pre-trained power consumption prediction model to obtain an energy consumption prediction result;

[0028] An emergency handling module, which is configured to determine an emergency flight strategy when the energy consumption prediction result is at risk;

[0029] A strategy sending module, which is configured to send the emergency flight strategy to the flight device to instruct the flight device to continue to perform the flight mission according to the emergency flight strategy.

[0030] In a third aspect, the present application provides a flight device energy consumption management device, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to implement the flight device energy consumption management method described in the first aspect above.

[0031] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the flight device energy consumption management method described in the first aspect above.

[0032] The flight device energy consumption management method, device and readable storage medium provided by the present application. The method includes: acquiring flight-related data of a flight device during a flight mission; performing energy consumption prediction based on the flight-related data through a pre-trained power consumption prediction model to obtain an energy consumption prediction result; determining an emergency flight strategy when the energy consumption prediction result is at risk; sending the emergency flight strategy to the flight device to instruct the flight device to continue to perform the flight mission according to the emergency flight strategy. Through the combination of machine learning technology and physical models, the present application realizes a more accurate, real-time and intelligent flight device energy consumption management solution, which can predict power consumption according to the real-time state and environmental conditions of the flight device, and optimize and adjust through an emergency mechanism when the power is insufficient to ensure the smooth completion of the flight mission. Compared with the prior art, the present application provides higher power prediction accuracy, stronger real-time performance and emergency handling ability, thus significantly improving the reliability and safety of the unmanned aerial vehicle in actual flight missions. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings here are incorporated into the description and constitute a part of this description, showing embodiments consistent with the present application and used together with the description to explain the principles of the present application.

[0034] Figure 1 It is a flowchart of a flight device energy consumption management method provided by an embodiment of the present application;

[0035] Figure 2 This is a schematic structural diagram of an energy consumption management device for a flight device provided by an embodiment of the present application;

[0036] Figure 3 This is a schematic structural diagram of another energy consumption management device for a flight device provided by an embodiment of the present application.

[0037] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and more detailed descriptions will be provided later. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed Embodiments

[0038] To enable those skilled in the art to better understand the technical solutions of the present application, the embodiments of the present application will be further described in detail below in conjunction with the drawings.

[0039] It can be understood that the specific embodiments and drawings described herein are only for explaining the present application, rather than limiting the present application.

[0040] It can be understood that, without conflict, the various embodiments and features in the embodiments of the present application can be combined with each other.

[0041] It can be understood that, for the sake of convenience of description, only the parts related to the present application are shown in the drawings of the present application, and the parts unrelated to the present application are not shown in the drawings.

[0042] It can be understood that each unit and module involved in the embodiments of the present application may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may also be integrated into one physical structure.

[0043] It can be understood that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, or to distinguish different processes for the same object, rather than to describe a specific order of the objects.

[0044] It can be understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present application may occur in an order different from that marked in the drawings.

[0045] It can be understood that in the flowcharts and block diagrams of the present application, the possible system architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present application are shown. Among them, each block in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart can be implemented by a hardware-based system for implementing the specified function, or by a combination of hardware and computer instructions.

[0046] It can be understood that the units and modules involved in the embodiments of the present application can be implemented in software or in hardware. For example, the units and modules can be located in the processor.

[0047] Currently, the existing technical solutions mainly include two types:

[0048] (1) Power prediction methods based on empirical formulas: These methods calculate power consumption based on parameters such as the speed, altitude, and load of the aircraft by setting fixed formulas or models. Such methods usually adopt simplified assumptions, such as a linear relationship between flight speed and power consumption, but they often ignore the influence of various environmental factors such as wind speed, temperature, and air density.

[0049] (2) Power prediction methods based on physical models: These methods predict power consumption by establishing a physical model of the aircraft and simulating factors such as air resistance and motor power during flight. These methods are theoretically more accurate, but due to the complex and variable flight conditions and environmental factors, a large amount of calculation and real-time adjustment are often required during actual application, resulting in poor real-time performance and inability to adapt to dynamically changing environmental conditions.

[0050] Although the existing technologies have been able to achieve power prediction to a certain extent, there are still the following main drawbacks:

[0051] Low prediction accuracy: Most of the existing power prediction methods ignore the dynamically changing environmental factors during flight, such as wind speed, temperature, and air density. The influence of these factors on power consumption is often simplified or ignored, resulting in a large error in the prediction results.

[0052] Poor real-time performance: Many existing methods cannot reflect the changes in flight status in real time, and in a rapidly changing flight environment, it may cause prediction delays and unable to make timely adjustments.

[0053] Unable to adapt to complex flight conditions: In a changing environment, the existing technologies are difficult to flexibly adjust the power prediction scheme according to the real-time status of the aircraft and environmental changes. For example, when a drone encounters strong headwinds or high-temperature weather, traditional models cannot be adjusted in time, which may lead to power shortage problems.

[0054] Lack of emergency mechanism: Existing solutions usually only provide simple warnings when predicting insufficient power, and there is no systematic emergency mechanism to handle the situation of insufficient power. This way of lacking an emergency plan may lead to mission failure or flight interruption in practical applications.

[0055] Aiming at the shortcomings in the prior art, the purpose of this application is to provide an integrated method for intelligent power prediction and emergency mechanism, which can accurately predict power consumption according to the current flight state and environmental conditions of the aircraft, so as to ensure that the UAV always has sufficient power during the flight mission.

[0056] Specifically, the purpose of this application is:

[0057] Improve the accuracy of power prediction: Combine multi-dimensional input data such as flight speed, flight altitude, wind speed, air temperature, air density, load, remaining battery capacity, etc., and use a machine learning model to accurately predict power consumption, thereby improving the prediction accuracy.

[0058] Enhance real-time performance: Use a prediction method that combines real-time data and historical flight data to ensure that power prediction can be dynamically adjusted during flight, and timely reflect environmental changes and flight states.

[0059] Implement a dynamic emergency mechanism: When the predicted remaining power is insufficient to complete the remaining mission, immediately activate a series of emergency measures, such as optimizing the flight path, adjusting the flight state, or charging midway, etc., to ensure the smooth completion of the flight mission.

[0060] Adapt to complex flight conditions: Through dynamic response to various environmental factors, timely adjust power prediction, so as to ensure that the aircraft can effectively manage battery power in complex flight environments (such as strong wind, high temperature, etc.) and avoid the risk of insufficient power.

[0061] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The following will describe the embodiments of this application in conjunction with the drawings.

[0062] This application provides a method for managing the energy consumption of a flight device. The working process of this method can be implemented by an electronic device, such as a computer, a handheld intelligent terminal, etc. For the convenience of explanation, in the embodiments of this application, the method execution subject is described as a computer.

[0063] Figure 1 For the schematic diagram of the method for managing the energy consumption of the flight device provided by the embodiment of this application, as Figure 1As shown, the present application provides a method for managing the energy consumption of a flying device. The method includes S1 - S4, which are specifically as follows:

[0064] S1. Obtain the flight - related data of the flying device when performing a flight mission;

[0065] Among them, the flight - related data includes the flight data of the flying device and the environmental data.

[0066] In some embodiments, the flight - related data includes flight speed, flight altitude, wind speed, temperature, air density, load, and remaining flight distance. The definitions of each data are as follows:

[0067] Flight data

[0068] · Flight speed (v): The current flight speed (unit: m / s). The flight speed affects the air resistance and thus affects the power consumption.

[0069] · Flight altitude (h): The current flight altitude (unit: m). The flight altitude affects the air density and thus affects the power consumption.

[0070] · Load (m): The total load of the current flying device (unit: kg). Increasing the load will increase the power consumption of the flying device.

[0071] · Remaining flight distance (d): The remaining flight distance (unit: km) that the current flying device needs to complete when performing the mission.

[0072] Environmental data

[0073] · Wind speed (w): The current wind speed (unit: m / s). The wind speed affects the air resistance of the flying device. Headwind will cause an increase in power consumption, while tailwind may reduce the power consumption.

[0074] · Temperature (T): The ambient temperature (unit: °C). The temperature affects the air density and the internal resistance of the battery, and thus affects the power consumption. A lower temperature may cause a decrease in battery efficiency and an increase in power consumption.

[0075] · Air density (ρ): The density of air (unit: kg / m 3 )), which is related to factors such as temperature, humidity, and air pressure. When the air density is large, the resistance of the flying device is large and the power consumption is also higher.

[0076] Specifically, the flying device executes a mission from point A to point B. During the flight, it is necessary to regularly predict whether the remaining power is sufficient to complete the remaining flight mission. Specifically, it is necessary to predict the power required for the remaining distance based on the current flight state (such as flight speed, wind speed, air density, temperature, etc.) in order to determine whether it is necessary to activate the emergency mechanism. Traditional power consumption models usually only consider the influence of air resistance. In fact, power consumption is also affected by multiple factors, including flight speed, air density, temperature, flight altitude, the load of the flying device, etc. Therefore, it is necessary to introduce more physical factors to improve the prediction accuracy of power consumption. In this application, considering multiple factors, according to the flight speed, flight altitude, wind speed, temperature, air density, load data, and the remaining flight distance, the power consumption of the flying device to complete a certain flight distance under the current load and environment is predicted.

[0077] S2. Based on the flight-related data, perform energy consumption prediction through a pre-trained power consumption prediction model to obtain an energy consumption prediction result;

[0078] Among them, the pre-trained power consumption prediction model can use a random forest regression model. This model is based on an ensemble method of decision trees, can handle multiple variables, and is very effective for non-linear relationships. Its advantage is that it can automatically capture the complex laws during the flight by training historical data without completely relying on a priori physical models.

[0079] After the flying device takes off, it is necessary to predict the power consumption required for the flying device to complete the remaining flight distance according to the current flight data and environment. This requires combining a large amount of historical flight data and considering multiple factors such as the load of the flying device, meteorological conditions, and flight speed. In order to make an accurate power consumption prediction based on the current flight data and historical flight data, a random forest regression model is selected. This model is particularly suitable for handling complex non-linear relationships and can effectively learn the laws of the flying device's power consumption from historical data.

[0080] In order to perform energy consumption prediction, model training must be carried out first. The data used is the power consumption data of historical flight missions (each record includes the above parameters (flight speed, flight altitude, wind speed, temperature, air density, load, and the corresponding power consumption)). Since this data records the power consumption of the flying device when completing tasks under different environmental conditions, these historical data will be used to train a machine learning model to capture the complex relationship between power consumption and different factors.

[0081] In this application, the specific steps for model training are as follows:

[0082] 1.1 Data preparation and preprocessing

[0083] In the data processing stage, it is first necessary to clean, normalize, and perform feature engineering on the input data to ensure that the data can be effectively input into the machine learning model.

[0084] Data cleaning: Delete missing values or outliers. For example, if the temperature, wind speed, or air density values in some records are abnormal, it may be necessary to delete or fill in these missing data.

[0085] Feature normalization / standardization: Normalize or standardize numerical features (such as flight speed, load, etc.). A common method is to perform Z-score standardization on each feature (subtract the mean and then divide by the standard deviation), which can avoid the dimensional difference between different features.

[0086] 1.2 Training the model

[0087] Dataset division: Divide the historical flight data into a training set and a test set. Usually, 80% of the data is used as the training set, and the remaining 20% is used as the test set.

[0088] Model training: Use the training set to train the random forest regression model. A power consumption prediction model will be trained based on input features such as the flight speed, flight altitude, wind speed, temperature, air density, load, etc. of the flight equipment.

[0089] Model hyperparameter tuning: Adjust the hyperparameters of the random forest model, such as the number of trees (n_estimators), the maximum depth of the tree (max_depth), the maximum number of features (max_features), etc., through cross-validation to improve the prediction accuracy.

[0090] 1.3 Prediction

[0091] Once the model training is completed, the model can be used to predict the power consumption of new flight data. The specific steps are as follows:

[0092] Input data: Use the current flight speed v, flight altitude h, wind speed w, temperature t, air density ρ, load m, and remaining flight distance d as input data.

[0093] Model prediction: The model predicts the power consumption required to complete the specified flight distance under the current flight conditions based on the rules learned during the training process.

[0094] Epred = RandomForestRegressor(v, h, w, T, ρ, m, d)

[0095] Among them, Epred (Epredictconsume) is the predicted power consumption (unit: Wh).

[0096] 1.4 Model Evaluation and Optimization

[0097] Model Evaluation

[0098] Mean Squared Error (MSE): The accuracy of the model is evaluated by calculating the prediction error of the model. The smaller the MSE value, the better the prediction effect of the model.

[0099]

[0100] Among them, Etrue is the actual power consumption, Epred is the power consumption predicted by the model, and N is the size of the data set.

[0101] Model Optimization

[0102] Feature Selection: According to the model evaluation results, the feature selection can be further optimized. The complexity of the model is reduced by removing features with weak correlations (for example, some environmental factors have little impact on power consumption).

[0103] Hyperparameter Tuning: The hyperparameters of the random forest regression model are further adjusted by using Grid Search or Random Search to improve the prediction accuracy.

[0104] This method has a high prediction accuracy and can provide a scientific prediction of power consumption for flight missions, helping flight equipment adjust flight strategies.

[0105] In some embodiments, S2 includes:

[0106] When the current remaining power of the flight equipment is lower than the first preset ratio of the maximum power of the equipment, based on the flight-related data, the power consumption prediction model is used to perform energy consumption prediction to obtain the predicted power consumption required for the flight equipment to complete the flight mission.

[0107] When the flight equipment has taken off for a certain period of time and the current remaining power is at the first preset ratio of the maximum power of the equipment (for example, 70%, the first preset ratio cannot be set too low, because it may be too late to predict whether the mission can be completed when the power is too low), start to perform energy consumption prediction through the power consumption prediction model to obtain the predicted power consumption required to complete the remaining flight mission.

[0108] Specifically, the flight-related data is input into the power consumption prediction model, and the model will output a predicted power consumption Epredictconsume, which represents the power consumption when the flight equipment completes the remaining flight mission. The unit is Wh, indicating the consumed electrical energy. S3. When there is a risk in the energy consumption prediction result, determine the emergency flight strategy;

[0109] In some embodiments, when the difference between the current remaining power Eremaining of the flying device and the predicted power consumption Epredictconsume required for the flying device to complete the flying mission is higher than or equal to a second preset ratio (such as 20% etc.) of the current remaining power Eremaining, it is determined that there is no risk in the energy consumption prediction result;

[0110] After a preset duration after the previous energy consumption prediction is completed, the flight-related data of the flying device is retrieved again, and the energy consumption is predicted again through the pre-trained power consumption prediction model to obtain the energy consumption prediction result.

[0111] For example, if Eremaining - Epredictconsume ≥ Eremaining * 20%, no processing is required. After waiting for a fixed time (which can be a bit longer, such as 5 minutes), a second prediction is made, and so on.

[0112] In some embodiments, in S3, when the difference between the current remaining power of the flying device and the predicted power consumption required for the flying device to complete the flying mission is lower than the second preset ratio of the current remaining power, it is determined that there is a risk in the energy consumption prediction result.

[0113] For example, if Eremaining - Epredictconsume < Eremaining * 20%, it means that there is a certain risk in whether the current remaining flying distance can be completed. Here, Eremaining is the current remaining power of the flying device, and 20% is set to leave some leeway. After all, during the entire flight process of the flying device, there are also some power consumptions for navigation, communication, etc.

[0114] Optionally, since the external environment is constantly changing, for example, the air density and wind speed when the flying device flies to another place may be different, which may cause the prediction data to change. To improve the prediction accuracy, if risks are predicted twice in a row, it is determined that there is a risk in the energy consumption prediction result, and then an emergency flight strategy is determined.

[0115] Specifically, after it is predicted that there is a risk, the flight speed is selected to be adjusted. Because the flight speed affects the power consumption. For example, when flying from low speed to high speed, the increase in air resistance is not linear but increases sharply, which results in more power consumption during high-speed flight. In addition, at low speed, the thrust is small and the battery consumption is low; but as the speed increases, the thrust demand increases, especially at higher speeds, the thrust demand may increase significantly, resulting in greater power consumption.

[0116] Although low-speed flight reduces air resistance, the flight time increases. During low-speed flight, the motor may be in a more efficient operating range, resulting in less power consumption per unit time. However, due to the longer flight time, the overall power consumption may increase (if the flight distance is long). During high-speed flight, the air resistance increases significantly, and the power consumption accelerates. However, the flight time is shorter, so the total power consumption may be lower. Therefore, adjusting the speed may not necessarily mean reducing the speed; it may also mean increasing the speed. So, an optimal economic flight speed needs to be selected at which the consumption balance of air resistance and thrust is achieved and the battery consumption is the lowest.

[0117] In some embodiments, in S3, determining an emergency flight strategy includes:

[0118] According to the current remaining flight distance, determining the power consumption corresponding to each different flight speed;

[0119] Determining the flight speed with power consumption lower than the target consumable power as the emergency flight speed, where the target consumable power is the third preset ratio of the current remaining power.

[0120] Specifically, assuming the remaining flight distance is Dremaining, the remaining flight time tremaining of the flying device can be calculated by the following formula:

[0121]

[0122] To ensure that the flying device can complete the task, the remaining power needs to support the power consumption for the flight time tremaining.

[0123] At the existing speed, traverse different speeds v and calculate the corresponding flight time tremaining = Dremaining / v.

[0124] Calculate the power consumption E(v) at each speed until a suitable emergency flight speed vtarget is found that satisfies:

[0125] E(v target )≤E target

[0126] Then this speed can be selected.

[0127] Where Etarget is the target consumable power. Here, a target consumption power is set so that the flying device can complete the task within Etarget. For safety reasons, the target consumable power is set as the third preset ratio (e.g., 80%) of the current remaining power, that is:

[0128] E target =0.8·E remaining

[0129] In some embodiments, according to the current remaining flight distance, the power consumption corresponding to each flight speed is determined by the following formula:

[0130]

[0131] where E(v) is the power consumption, ρ is the air density, v is the flight speed, C d is the drag coefficient of the flying device, A is the frontal area of the flying device, α is the adjustment factor of the wind speed on the power consumption of the flying device, C m is the influence coefficient of the wind speed on the flying device, d is the remaining flight distance, η motor is the efficiency of the motor of the flying device.

[0132] In the above formula, the definitions of the parameters are as follows:

[0133] ρ: air density (varying with altitude and temperature, unit: kg / m 3 ).

[0134] v: speed of the flying device (unit: m / s).

[0135] Cd: drag coefficient, depending on the shape and surface roughness of the flying device.

[0136] A: frontal area of the flying device (unit: m 2 ).

[0137] d: remaining flight distance (unit: m).

[0138] Cm: influence coefficient of the wind speed on the flying device.

[0139] α: adjustment factor of the wind speed on the power consumption of the flying device.

[0140] ηmotor: efficiency of the motor of the flying device.

[0141] Among them, ηmotor refers to the power consumption of the propulsion system of the flying device, which is a function of the speed v and can be modeled by the relationship between the thrust of the flying device and the flight speed. Assuming that the relationship between the thrust of the flying device and the speed is non-linear (because the efficiency of the flying device usually varies at different speeds), it can be represented by a polynomial model:

[0142] η motor (v) = jv 3 + kv 2

[0143] Among them, j and k are constants related to the type of flying device and the propulsion system, and these constants can be estimated through experiments or the technical parameters of the flying device. That is to say, the power consumption here is based on the following factors:

[0144] · Air resistance: It varies with the flight speed, air density, the windward area of the flying device, etc.

[0145] · Motor efficiency: The efficiency of the motor (usually varying non-linearly) will affect the power consumption.

[0146] · External environment: Such as wind speed, temperature, etc., which will all affect the flight resistance and flight efficiency.

[0147] Considering that the flight altitude of the aircraft changes and the calculation is rather troublesome, for the sake of simplicity, this application only considers the case of the flying device flying horizontally. That is, it refers to flying at a certain altitude, such as horizontal steady straight flight, horizontal straight acceleration and deceleration flight, maneuvering flight in the horizontal plane, etc.

[0148] The above method can ensure that the flying device will not consume too much power due to too high a speed, nor will it increase the flight time and cause more power consumption due to too low a speed.

[0149] S4. Send the emergency flight strategy to the flying device to instruct the flying device to continue to execute the flight task according to the emergency flight strategy.

[0150] Considering that prediction and calculation require a large amount of power consumption, in this application, it can be assumed that there is a server on the ground. The flying device only sends the flight and environmental data to the server, and the prediction and decision-making are both calculated by the ground server and then the results are sent to the flying device. The flying device is responsible for execution. The communication between the two can be implemented based on the 5G network or other communication methods, and this application does not make any limitations in this regard.

[0151] Through the combination of machine learning technology and physical models, this application has realized a more accurate, real-time and intelligent energy consumption management solution for flying devices, which can predict the power consumption according to the real-time state of the flying device and environmental conditions, and optimize and adjust through an emergency mechanism when the power is insufficient to ensure the smooth completion of the flight task. Compared with the prior art, this application provides higher power prediction accuracy, stronger real-time performance and emergency handling capabilities, thus significantly improving the reliability and safety of drones in actual flight tasks.

[0152] It should be understood that although the steps in the flowcharts in the above embodiments are sequentially shown according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and they can be executed in other orders. Moreover, at least a part of the steps in the figure may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0153] Figure 2 The following is a schematic diagram of the flight device energy consumption management device provided by the embodiments of the present application. As Figure 2 shown, the present application provides a flight device energy consumption management device, and the device includes:

[0154] A data acquisition module 11, which is configured to acquire flight-related data of the flight device when performing a flight mission;

[0155] An energy consumption prediction module 12, which is configured to perform energy consumption prediction based on the flight-related data through a pre-trained power consumption prediction model to obtain an energy consumption prediction result;

[0156] An emergency processing module 13, which is configured to determine an emergency flight strategy when there is a risk in the energy consumption prediction result;

[0157] A strategy sending module 14, which is configured to send the emergency flight strategy to the flight device to instruct the flight device to continue to perform the flight mission according to the emergency flight strategy.

[0158] Regarding the definition of the flight device energy consumption management device, reference can be made to the definition of the flight device energy consumption management method in the above embodiments of the present application, and this embodiment will not be elaborated here.

[0159] Figure 3 The following is another schematic diagram of the flight device energy consumption management device provided by the embodiments of the present application. As Figure 3 shown, the device includes a memory 22 and a processor 21. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the methods in the above embodiments of the present application.

[0160] Among them, the memory is connected to the processor. The memory can adopt flash memory or read-only memory or other memories, and the processor can adopt a central processing unit or a single-chip microcomputer.

[0161] In some embodiments, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the methods in the above various embodiments of the present application are implemented.

[0162] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, computer program modules, or other data. The computer-readable storage medium includes, but is not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), digital versatile disc (DVD) or other optical disc storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0163] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principles of the present application, and the present application is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present application, and these modifications and improvements are also regarded as the protection scope of the present application.

Claims

1. A method for managing the energy consumption of a flying device, characterized in that, The method includes: S1. Obtain flight-related data of the flight device when performing a flight mission; S2. Based on the flight-related data, perform energy consumption prediction through a pre-trained power consumption prediction model to obtain an energy consumption prediction result; S3. When there is a risk in the energy consumption prediction result, determine an emergency flight strategy; S4. Send the emergency flight strategy to the flight device to instruct the flight device to continue performing the flight mission according to the emergency flight strategy.

2. The flight equipment energy consumption management method according to claim 1, wherein The flight-related data includes flight speed, flight altitude, wind speed, temperature, air density, load, and remaining flight distance.

3. The flight equipment energy consumption management method according to claim 1, characterized in that, S2 includes: When the current remaining power of the flight device is lower than the first preset ratio of the maximum power of the device, based on the flight-related data, perform energy consumption prediction through a pre-trained power consumption prediction model to obtain the predicted power consumption required for the flight device to complete the flight mission.

4. The flight device energy consumption management method according to claim 1, wherein In S3, when the difference between the current remaining power of the flight device and the predicted power consumption required for the flight device to complete the flight mission is lower than the second preset ratio of the current remaining power, it is determined that there is a risk in the energy consumption prediction result.

5. The method for managing the energy consumption of a flight device according to claim 1, wherein, In S3, determining the emergency flight strategy includes: According to the current remaining flight distance, determine the power consumption corresponding to each different flight speed; Determine the flight speed with power consumption lower than the target consumable power as the emergency flight speed, where the target consumable power is the third preset ratio of the current remaining power.

6. The flight device energy consumption management method according to claim 5, characterized in that According to the current remaining flight distance, determine the power consumption corresponding to each different flight speed through the following formula: Among them, E(v) is the power consumption, ρ is the air density, ν is the flight speed, C d is the drag coefficient of the flying device, A is the windward area of the flying device, α is the adjustment factor of the wind speed on the power consumption of the flying device, C m is the influence coefficient of the wind speed on the flying device, d is the remaining flight distance, η motor is the efficiency of the motor of the flying device.

7. The flight device energy consumption management method according to any one of claims 1-6, characterized in that It also includes: When the difference between the current remaining power of the flight device and the predicted power consumption required for the flight device to complete the flight mission is higher than or equal to the second preset ratio of the current remaining power, it is determined that there is no risk in the energy consumption prediction result; After a preset duration after the previous energy consumption prediction is completed, re-obtain the flight-related data of the flight device and re-perform energy consumption prediction through a pre-trained power consumption prediction model to obtain an energy consumption prediction result.

8. An energy consumption management device for a flying device, characterized in that, The device includes: A data acquisition module configured to obtain flight-related data of the flight device when performing a flight mission; An energy consumption prediction module configured to perform energy consumption prediction through a pre-trained power consumption prediction model based on the flight-related data to obtain an energy consumption prediction result; An emergency processing module configured to determine an emergency flight strategy when there is a risk in the energy consumption prediction result; A strategy sending module configured to send the emergency flight strategy to the flight device to instruct the flight device to continue performing the flight mission according to the emergency flight strategy.

9. An energy consumption management device for a flying device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to implement the flight device energy consumption management method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the flight device energy consumption management method according to any one of claims 1-7.

Images