Artificial intelligence-based charging parameter optimization method and system

Abstract

The application discloses an artificial intelligence-based charging parameter optimization method and system, and relates to the field of unmanned aerial vehicle charging. The method comprises the following steps: acquiring the battery type, current power and remaining flight task of an unmanned aerial vehicle; determining the charging mode and initial charging parameters of the unmanned aerial vehicle based on the battery type, current power and remaining flight task; in response to a charging signal of the unmanned aerial vehicle, monitoring the battery charging curve of the unmanned aerial vehicle in real time; based on the battery charging curve of the current time period, adopting an artificial intelligence model to dynamically adjust the charging parameters of the unmanned aerial vehicle battery in the next preset time period at the end moment of the current time period, wherein the charging parameters comprise a charging current and a charging voltage; and charging the unmanned aerial vehicle battery according to the charging parameters at the start moment of the next preset time period. The application can maximize the shortening of the charging time while ensuring the safety and service life of the unmanned aerial vehicle battery.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of unmanned aerial vehicle (UAV) charging, and in particular to a charging parameter optimization method and system based on artificial intelligence. BACKGROUND

[0002] With the rapid development of UAV technology, UAVs have been widely used in surveying and mapping, agriculture, logistics, emergency rescue and many other fields. However, the battery endurance has always been a key bottleneck restricting the long-time operation of UAVs. At present, the flight time of most commercial UAVs is only 20-30 minutes, while the charging time often takes 1-2 hours. This contradiction between "short flight and long charging" seriously affects the working efficiency and task continuity of UAVs. Especially in high-time-efficiency scenarios such as emergency rescue and large-scale surveying and mapping, the long charging time can lead to task interruption and missed critical opportunities. Therefore, how to shorten the charging time of UAVs while ensuring the safety and life of the battery and improve the working efficiency of UAVs has become a problem to be solved in the industry.

[0003] Traditional UAV charging methods mainly include constant current charging, constant voltage charging and constant current and constant voltage charging.

[0004] Constant current charging refers to a charging method that maintains a constant charging current during the charging process. This method has a fast charging speed, but it can easily cause the battery to overheat and overcharge, affecting the battery life. Constant voltage charging maintains a constant charging voltage during the charging process. The initial charging current is large, and as the battery capacity increases, the charging current gradually decreases. This method is relatively safe, but the charging speed is slow, especially in the later charging stage.

[0005] At present, most UAVs use constant current and constant voltage charging, that is, first charging with a constant current, and then switching to constant voltage charging when the battery voltage reaches a certain value. This method is a combination of the first two methods, balancing the charging speed and safety to some extent. However, different types and different aging degrees of batteries have different charging characteristics. The traditional charging method uses the above fixed charging strategy to ensure safety, but at the expense of charging speed to some extent, resulting in low charging efficiency or unnecessary damage to battery life.

[0006] Therefore, there is an urgent need for a method that can intelligently adjust the charging strategy according to the real-time state of the battery, maximize the charging time, and improve the working efficiency and task continuity of the UAV while ensuring the safety and life of the battery. SUMMARY

[0007] Embodiments of the present application provide a charging parameter optimization method and system based on artificial intelligence, which is used to maximize the charging time while ensuring the safety and life of the UAV battery.

[0008] To achieve the above object, the embodiments of the present application adopt the following technical solutions:

[0009] In a first aspect, a method for optimizing charging parameters based on artificial intelligence is provided, the method comprising:

[0010] obtaining a battery type, a current power and a remaining flight task of a UAV;

[0011] determining a charging mode and initial charging parameters of the UAV based on the battery type, the current power and the remaining flight task;

[0012] in response to a charging signal of the UAV, monitoring a battery charging curve of the UAV in real time, wherein the battery charging curve is constructed based on real-time charging voltage, real-time charging current and real-time battery temperature;

[0013] based on the battery charging curve of a current time period, using an artificial intelligence model to dynamically adjust charging parameters of the battery of the UAV in a next preset time period at an ending moment of the current time period, the charging parameters including charging current and charging voltage;

[0014] charging the battery of the UAV according to the charging parameters at a starting moment of the next preset time period.

[0015] In a possible implementation manner of the first aspect, the determining of the charging mode and the initial charging parameters of the UAV based on the battery type, the current power and the remaining flight task comprises:

[0016] according to the battery type of the UAV, obtaining corresponding battery safety parameter thresholds from a preset battery parameter database;

[0017] judging a charging phase in which the battery is located according to the current power;

[0018] determining a flight emergency degree according to the remaining flight task, wherein the flight emergency degree includes high, medium and low;

[0019] based on the battery safety parameter thresholds, the charging phase and the flight emergency degree, determining the charging mode as any one of a constant current charging mode, a constant voltage charging mode or a constant current and constant voltage combined charging mode, and determining an initial charging current value or a charging voltage value according to the charging mode.

[0020] In another possible implementation manner of the first aspect, the remaining flight task includes a task type and a predicted flight time, and the determining of the flight emergency degree according to the remaining flight task comprises:

[0021] in a case where the task type is a preset first task type, determining the flight emergency degree as high;

[0022] In a case where the task type is not the first task type, determining that the flight emergency level is medium or low based on the predicted flight time;

[0023] In a case where the predicted flight time is less than the preset time threshold, determining that the flight emergency level is medium, and in a case where the predicted flight time is not less than the preset time threshold, determining that the flight emergency level is low.

[0024] In a case where the task type is not the first task type, determining that the flight emergency level is medium or low based on the predicted flight time;

[0025] In a case where the charging phase is the first charging phase and the flight emergency level is high, determining that the charging mode is the constant-current constant-voltage combined charging mode, and setting the initial charging current value to be a first preset percentage of the safety current threshold;

[0026] In a case where the charging phase is the first charging phase and the flight emergency level is medium or low, determining that the charging mode is the constant-current charging mode, and setting the initial charging current value to be a second preset percentage of the safety current threshold, wherein the second preset percentage is less than the first preset percentage;

[0027] In a case where the charging phase is the second charging phase, determining that the charging mode is the constant-voltage charging mode, and setting the initial charging voltage value to be a third preset percentage of the safety voltage threshold.

[0028] In a case where the task type is not the first task type, determining that the flight emergency level is medium or low based on the predicted flight time;

[0029] Analyzing the change trend of the battery charging curve by the artificial intelligence model to obtain an analysis result, the analysis result including a battery health degree and optimal charging parameters;

[0030] Based on the battery health degree and the optimal charging parameters, dynamically adjusting the charging parameters of the unmanned aerial vehicle battery in the next preset time period at the end of the current time period.

[0031] In a case where the task type is not the first task type, determining that the flight emergency level is medium or low based on the predicted flight time;

[0032] In a possible implementation manner of the first aspect, the trend of the battery charging curve is analyzed by the artificial intelligence model, and analysis results are obtained, the analysis results including a battery health degree and optimal charging parameters, including:

[0033] The battery charging curve data in the current time period is collected, the battery charging curve data being time series data including a charging voltage, a charging current and a battery temperature;

[0034] The time series data is preprocessed;

[0035] The preprocessed time series data is input into a convolutional neural network layer to extract local features of the battery charging curve;

[0036] The local features are input into a long short-term memory network layer to learn a time series change rule of a battery charging state;

[0037] Based on a deviation of the battery charging curve from a standard charging curve, a battery internal resistance change rate, a capacity attenuation rate and a temperature sensitivity index are calculated;

[0038] According to the internal resistance change rate, the capacity attenuation rate and the temperature sensitivity index, a battery health degree is calculated by using a preset battery health degree function;

[0039] The local features and the time series change rule are input into a policy network and a value network, and charging efficiency and battery life under different charging parameters are predicted to obtain optimal charging parameters.

[0040] In a possible implementation manner of the first aspect, based on the battery health degree and the optimal charging parameters, charging parameters of a drone battery in a next preset time period are dynamically adjusted at an ending moment of the current time period, including:

[0041] In a case where the battery health degree is lower than a first preset threshold, the charging current in the next preset time period is reduced to a first preset proportion of the optimal charging parameters, and the charging voltage is reduced to a second preset proportion of the optimal charging parameters at the ending moment of the current time period;

[0042] In a case where the battery health degree score is not lower than the first preset threshold and not higher than a second preset threshold, the charging parameters in the next preset time period are set as the optimal charging parameters at the ending moment of the current time period;

[0043] In a case where the battery health degree score is higher than the second preset threshold and a flight emergency degree is high, the charging current in the next preset time period is increased to a third preset proportion of the optimal charging parameters and does not exceed a battery safety parameter threshold at the ending moment of the current time period.

[0044] In a possible implementation manner of the first aspect, the trend of the battery charging curve is analyzed by the artificial intelligence model, and analysis results are obtained, the analysis results including a battery health degree and optimal charging parameters, including:

[0045] a memory configured to store instructions; and

[0046] a processor configured to invoke the instructions from the memory and implement the above-mentioned artificial intelligence-based charging parameter optimization method when the instructions are executed.

[0047] In a third aspect, the present application provides an artificial intelligence-based charging parameter optimization system, comprising:

[0048] an electronic device;

[0049] a UAV connected to the electronic device.

[0050] Through the above technical solution, the battery type, current power and remaining flight task of the UAV are obtained, and the appropriate charging mode and initial parameters are determined; by real-time monitoring of the battery charging curve and using a deep reinforcement learning model to dynamically adjust the charging parameters, intelligent management of the UAV battery charging process is achieved. According to the real-time state, health degree and task urgency of the battery, the charging strategy can be adaptively adjusted, the charging efficiency is maximized under the premise of ensuring the safety and life of the battery. Compared with the traditional fixed charging strategy, this method can effectively shorten the charging time and prolong the battery life, significantly improve the working efficiency and task continuity of the UAV, and is particularly suitable for high-time-efficiency scenes such as emergency rescue and large-scale surveying and mapping. In addition, this method also has good adaptability and scalability, and can adapt to different types and different aging degrees of batteries.

[0051] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF DRAWINGS

[0052] Figure 1 a flowchart of an artificial intelligence-based charging parameter optimization method provided by the embodiments of the present application;

[0053] Figure 2 a structural diagram of an artificial intelligence model provided by the embodiments of the present application;

[0054] Figure 3 a structural diagram of an artificial intelligence-based charging parameter optimization system provided by the embodiments of the present application. DETAILED DESCRIPTION

[0055] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the specific implementation described herein is only used to explain and illustrate the embodiments of the present application, and is not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0056] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative positional relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the directional indications also change accordingly.

[0057] In addition, if the embodiments of the present application involve descriptions such as "first", "second", etc., the descriptions of "first", "second", etc. are only for description purposes, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the fact that a person of ordinary skill in the art can realize it, and when the combination of technical solutions contradicts each other or cannot be realized, it should be considered that the combination of technical solutions does not exist, and is also not within the scope of protection claimed by the present application.

[0058] Figure 1 A flowchart of a method for optimizing charging parameters based on artificial intelligence according to an embodiment of the present application is schematically shown. As shown in Figure 1 The method for optimizing charging parameters based on artificial intelligence provided by the embodiments of the present application can include the following steps.

[0059] S110, obtaining the battery type, current power and remaining flight task of the unmanned aerial vehicle;

[0060] S120, determining the charging mode and initial charging parameters of the unmanned aerial vehicle based on the battery type, current power and remaining flight task;

[0061] S130, in response to the charging signal of the unmanned aerial vehicle, monitoring the battery charging curve of the unmanned aerial vehicle in real time, wherein the battery charging curve is constructed based on real-time charging voltage, real-time charging current and real-time battery temperature;

[0062] S140, based on the battery charging curve of the current time period, adopting an artificial intelligence model to dynamically adjust the charging parameters of the unmanned aerial vehicle battery in the next preset time period at the end moment of the current time period, the charging parameters including charging current and charging voltage;

[0063] S150, charging the unmanned aerial vehicle battery according to the charging parameters at the beginning moment of the next preset time period.

[0064] The battery type, current capacity and remaining flight task of the unmanned aerial vehicle are obtained. Specifically, the battery type information can be obtained through the battery management system (BMS) on the unmanned aerial vehicle, including but not limited to lithium polymer battery (LiPo), lithium ion battery (Li-ion), lithium iron battery (LiFePO4) and the like. The battery type information usually contains the chemical composition, nominal voltage, capacity, maximum discharge rate and other parameters of the battery.

[0065] The current capacity can be obtained through the capacity calculation module in the BMS, which calculates the actual remaining capacity percentage of the battery by measuring the battery terminal voltage, internal resistance and temperature parameters, combined with the discharge characteristic curve of the battery.

[0066] The remaining flight task information can be obtained from the task planning system of the unmanned aerial vehicle, including task type (such as emergency rescue, regular mapping, agricultural spraying, etc.), estimated flight time, flight path complexity, etc. In actual application, these information can be transmitted through the wireless communication interface between the unmanned aerial vehicle and the charging station, such as Wi-Fi, Bluetooth, ZigBee or special wireless communication protocol.

[0067] Based on the battery type, current capacity and remaining flight task, the charging mode and initial charging parameters of the unmanned aerial vehicle are determined. Specifically, first, according to the battery type of the unmanned aerial vehicle, the corresponding battery safety parameter threshold is obtained from the preset battery parameter database, including maximum charging current, maximum charging voltage, highest safety temperature, etc. Then, according to the current capacity, the charging stage of the battery is judged. For example, when the battery capacity is less than 30%, it can be determined as the first charging stage (deep discharge state); when the battery capacity is between 30% and 80%, it can be determined as the second charging stage (normal charging state); when the battery capacity is higher than 80%, it can be determined as the third charging stage (close to saturation state).

[0068] The flight emergency level is determined according to a remaining flight task. In a case where the task type is a preset first task type (such as emergency rescue), the flight emergency level is determined to be high; in a case where the task type is not the first task type, the flight emergency level is determined to be medium or low based on a predicted flight time. In a case where the predicted flight time is less than a preset time threshold, the flight emergency level is determined to be medium, and in a case where the predicted flight time is not less than the preset time threshold, the flight emergency level is determined to be low. According to the charging stage of the battery and the flight emergency level, a charging mode and initial charging parameters are determined. For example, in a case where the charging stage is a first charging stage and the flight emergency level is high, the charging mode is determined to be a constant-current and constant-voltage combined charging mode, and the initial charging current value is set to a first preset percentage (such as 90%) of a safety current threshold; in a case where the charging stage is the first charging stage and the flight emergency level is medium or low, the charging mode is determined to be a constant-current charging mode, and the initial charging current value is set to a second preset percentage (such as 70%) of the safety current threshold, wherein the second preset percentage is less than the first preset percentage; in a case where the charging stage is a second charging stage, the charging mode is determined to be a constant-voltage charging mode, and the initial charging voltage value is set to a third preset percentage (such as 95%) of a safety voltage threshold. In this way, the most suitable charging mode and initial parameters can be selected according to the actual state of the battery and the task demand, ensuring charging efficiency while taking into account battery safety and service life.

[0069] In response to the charging signal of the unmanned aerial vehicle, a battery charging curve of the unmanned aerial vehicle is monitored in real time, wherein the battery charging curve is constructed based on real-time charging voltage, real-time charging current and real-time battery temperature. Specifically, when the unmanned aerial vehicle establishes physical connection with the charging station and sends a charging request signal, the charging control system of the unmanned aerial vehicle starts charging the battery, and simultaneously starts a real-time monitoring module. The module collects real-time charging voltage, real-time charging current and real-time battery temperature data of the battery at a preset sampling frequency (such as 10 times per second) through high-precision voltage sensors, current sensors and temperature sensors.

[0070] The battery charging curve is a multi-dimensional time series data set, including voltage-time curve, current-time curve and temperature-time curve. These curves can comprehensively reflect the state change and response characteristics of the battery during the charging process. For example, the voltage-time curve can reflect the charging acceptance ability and internal resistance change of the battery; the current-time curve can reflect the charging control strategy and charging efficiency of the battery; and the temperature-time curve can reflect the thermal characteristics and safety state of the battery.

[0071] Based on the battery charging curve of the current time period, an artificial intelligence model is adopted to dynamically adjust the charging parameters of the drone battery in the next preset time period at the end of the current time period, including the charging current and the charging voltage. Specifically, first, the battery charging curve data in the current time period is collected, which is time series data including charging voltage, charging current and battery temperature. Then, the time series data is preprocessed, including data standardization, outlier detection and processing, missing value filling, etc., to improve data quality.

[0072] The preprocessed time series data is input into an artificial intelligence model for analysis and prediction. The artificial intelligence model is a deep reinforcement learning model, including a convolutional neural network layer for extracting battery charging curve features, a long short-term memory network layer for learning the time series variation law of the battery charging state, a policy network and a value network for predicting the optimal charging parameters. Specifically, the preprocessed time series data is input into the convolutional neural network layer to extract the local features of the battery charging curve; the local features are input into the long short-term memory network layer to learn the time series variation law of the battery charging state; based on the deviation of the battery charging curve from the standard charging curve, the battery internal resistance change rate, the capacity attenuation rate and the temperature sensitivity index are calculated; according to the internal resistance change rate, the capacity attenuation rate and the temperature sensitivity index, a preset battery health function is used to calculate the battery health; the local features and the time series variation law are input into the policy network and the value network to predict the charging efficiency and the battery life under different charging parameters, and the best charging parameters are obtained.

[0073] According to the battery health and the flight emergency level, the charging parameters of the next preset time period are dynamically adjusted. In the case where the battery health is lower than a first preset threshold (such as 60%), the charging current of the next preset time period is reduced to a first preset proportion (such as 80%) of the best charging parameter at the end of the current time period, and the charging voltage is reduced to a second preset proportion (such as 90%) of the best charging parameter, in order to protect the battery; in the case where the battery health score is not lower than the first preset threshold and not higher than a second preset threshold (such as 80%), the charging parameters of the next preset time period are set to the best charging parameters at the end of the current time period; in the case where the battery health score is higher than the second preset threshold and the flight emergency level is high, the charging current of the next preset time period is increased to a third preset proportion (such as 110%) of the best charging parameter at the end of the current time period, and does not exceed the battery safety parameter threshold, in order to speed up the charging speed. In this way, the charging parameters can be dynamically adjusted according to the real-time state and health of the battery, which can ensure the charging efficiency, and also take into account the battery safety and life.

[0074] At the starting moment of the next preset time period, the drone battery is charged according to the charging parameters. Specifically, after the current time period ends, the charging control system will immediately adjust the output current and voltage of the charging circuit according to the charging parameters determined in the previous step, and charge the drone battery.

[0075] To ensure smooth transition of charging parameters and avoid sudden impact on the battery, a gradual adjustment strategy can be used, that is, the charging parameters are gradually adjusted from the current value to the target value within a short time (such as 100 milliseconds). During the charging process, the real-time state of the battery is continuously monitored, including voltage, current, temperature and other parameters. If abnormal conditions occur (such as excessive temperature, abnormal voltage fluctuation, etc.), a safety protection mechanism will be triggered immediately, such as reducing the charging power, suspending the charging or issuing an alarm. At the same time, the charging data of each time period is recorded, including charging parameters, battery response, charging efficiency, etc., which is used for real-time monitoring and adjustment on the one hand, and stored for subsequent data analysis and model optimization on the other hand. In addition, the expected charging completion time, current charging speed, and the amount of charged electricity can also be calculated and displayed, which helps users understand the charging progress and plan subsequent tasks. In this way, safe and efficient charging of the drone battery can be achieved, which can meet the rapid charging needs of emergency tasks and protect the battery life in normal situations, improving the overall efficiency and economy of the drone.

[0076] The embodiment determines the appropriate charging mode and initial parameters by obtaining the battery type, current capacity and remaining flight tasks of the drone; by real-time monitoring of the battery charging curve, a deep reinforcement learning model is used to dynamically adjust the charging parameters, achieving intelligent management of the drone battery charging process. It can adaptively adjust the charging strategy according to the real-time state, health and task urgency of the battery, maximize the charging efficiency while ensuring the safety and life of the battery. Compared with the traditional fixed charging strategy, this method can effectively shorten the charging time and prolong the battery life, significantly improving the working efficiency and task continuity of the drone, especially suitable for high time efficiency scenarios such as emergency rescue and large-scale surveying and mapping. In addition, this method also has good adaptability and scalability, which can adapt to different types and different aging degrees of batteries.

[0077] In one embodiment of the embodiment, the charging mode and initial charging parameters of the drone are determined based on the battery type, current capacity and remaining flight tasks, including the following steps:

[0078] S210, according to the battery type of the drone, obtaining the corresponding battery safety parameter threshold from the preset battery parameter database;

[0079] S220, according to the current capacity, judging the charging stage of the battery;

[0080] S230, determining a flight emergency level according to the remaining flight task, wherein the flight emergency level comprises high, medium and low;

[0081] S240, determining the charging mode to be any one of constant current charging mode, constant voltage charging mode or constant current and constant voltage combined charging mode based on the battery safety parameter threshold, the charging stage and the flight emergency level, and determining the initial charging current value or the charging voltage value according to the charging mode.

[0082] According to the type of the battery of the unmanned aerial vehicle, the corresponding battery safety parameter threshold is obtained from a preset battery parameter database. Specifically, the battery parameter database contains the type of the battery of the unmanned aerial vehicle and the corresponding safety parameter threshold. The battery types mainly include lithium polymer battery (LiPo), lithium ion battery (Li-ion), lithium iron battery (LiFePO4), nickel-hydrogen battery (NiMH) and the like. For each type of battery, the database stores safety parameter thresholds such as nominal voltage, maximum charging current rate (C rate), maximum charging voltage, maximum safe temperature, minimum safe temperature, maximum discharge rate and the like. For example, for a typical 3S lithium polymer battery, the maximum charging current rate is usually 1C-2C, the maximum charging voltage is 12.6V (4.2V per section), the maximum safe temperature is 45℃, and the minimum safe temperature is 0℃. After the unmanned aerial vehicle establishes a connection with the charging station, the model identifier of the battery or the type information of the battery is obtained through the communication interface of the battery management system. For example, a certain unmanned aerial vehicle uses a 4S lithium polymer battery with a capacity of 5000mAh, and the model is "LP4S5000". After receiving this information, the charging system looks up the corresponding record in the battery parameter database to obtain the safety parameter thresholds of the battery of this model: the maximum charging current is 5A (1C), the maximum charging voltage is 16.8V (4.2V per section), the maximum safe temperature is 45℃, and the minimum safe temperature is 5℃. The database can also dynamically adjust the safety parameter thresholds according to the production date and the number of uses of the battery. For example, for a lithium polymer battery that has been used more than 300 times, the maximum charging current rate can be reduced by 20% to prolong the service life of the battery.

[0083] According to the current power, it is judged that the battery is in a charging stage. Specifically, the current power percentage of the battery is first obtained through the battery management system. The current power of the battery is usually measured by coulomb counting method or open circuit voltage method. The coulomb counting method is to calculate the power change by integrating the charging and discharging current of the battery, and the open circuit voltage method is to estimate the power by measuring the open circuit voltage of the battery combined with the voltage-capacity curve of the battery. In practical applications, the two methods are often combined and fused through Kalman filtering algorithm and the like to improve the accuracy of power estimation.

[0084] After obtaining the current power, the charging process is divided into different stages according to the preset power threshold. Generally, the charging process of a lithium battery can be divided into three main stages: pre-charging stage, constant current charging stage and constant voltage charging stage. In this embodiment, according to the current power percentage of the battery, the charging process is divided into the following three stages: first charging stage (deep discharge state): when the battery power is less than 30%, the battery is in a deep discharge state, at this time the active material inside the battery is in a highly unstable state, and a gentler charging strategy is needed to avoid damage to the battery caused by a large current impact. Second charging stage (normal charging state): when the battery power is between 30% and 80%, the battery is in a normal charging state, at this time the battery has good charging acceptance ability, and a larger charging current can be used to improve charging efficiency. Third charging stage (near saturation state): when the battery power is higher than 80%, the battery is close to saturation state, at this time the charging acceptance ability of the battery begins to decline, and continuing to use a large current to charge may cause the battery to overheat and shorten its life, so the charging current needs to be gradually reduced. For example, if the current power of a certain drone battery is 25%, according to the above division standard, it is determined that the battery is in the first charging stage (deep discharge state). In different charging stages, the internal resistance, temperature sensitivity and charging efficiency of the battery are different, so different charging strategies need to be adopted. By accurately determining the charging stage of the battery, important basis can be provided for subsequent charging mode selection and parameter optimization, which can not only ensure charging safety, but also maximize charging efficiency and prolong battery life.

[0085] According to the remaining flight task, the flight emergency degree is determined, wherein the flight emergency degree includes high, medium and low. Specifically, first, the detailed information of the remaining flight task is obtained from the task planning system of the unmanned aerial vehicle, including task type, estimated flight time, flight path complexity, task priority, etc. The task type refers to the specific nature of the task performed by the unmanned aerial vehicle, such as emergency rescue, disaster monitoring, routine mapping, agricultural spraying, entertainment aerial photography, etc.

[0086] The estimated flight time refers to the estimated time required to complete the remaining task, which is usually calculated by the task planning system according to factors such as flight path length, flight speed and hovering time. The flight path complexity refers to the complexity of the flight path, including factors such as the number of turns, the frequency of height changes, and the density of obstacles. The task priority refers to the importance and urgency of the task, which is usually specified by the user when planning the task. According to the obtained task information, a preset rule or machine learning model is used to determine the flight emergency degree.

[0087] In the embodiment, the step of determining the flight emergency level is as follows: first, determine the basic emergency level according to the task type. The task type is divided into three categories: the first category includes high emergency tasks such as emergency rescue and disaster monitoring, and the basic emergency level is high; the second category includes medium emergency tasks such as routine mapping and inspection, and the basic emergency level is medium; the third category includes low emergency tasks such as agricultural spraying and recreational aerial photography, and the basic emergency level is low. Then, adjust the emergency level according to the estimated flight time. If the estimated flight time is less than a preset time threshold T1 (such as 30 minutes), the emergency level is increased by one level (if it is already high, it remains unchanged); if the estimated flight time is greater than a preset time threshold T2 (such as 2 hours), the emergency level is decreased by one level (if it is already low, it remains unchanged).

[0088] Further adjust the emergency level according to the task priority. If the task priority is the highest, the emergency level is set to high; if the task priority is the lowest, the emergency level is set to low. For example, the remaining flight task of a certain unmanned aerial vehicle is search and rescue in an earthquake disaster area, the task type is emergency rescue (first category), the estimated flight time is 45 minutes, and the task priority is the highest. According to the above rules, the basic emergency level is high, the estimated flight time is between 30 minutes and 2 hours, the emergency level is not adjusted, the task priority is the highest, and the emergency level is set to high. Therefore, the final flight emergency level of the unmanned aerial vehicle is high.

[0089] Based on the battery safety parameter threshold, the charging stage and the flight emergency level, the charging mode is determined to be any one of the constant current charging mode, the constant voltage charging mode or the constant current and constant voltage combined charging mode, and the initial charging current value or the charging voltage value is determined according to the charging mode. Specifically, first, determine the safe upper limit of the charging current and the charging voltage according to the battery safety parameter threshold. For example, for a 4S lithium polymer battery with a capacity of 5000mAh, the maximum safe charging current is 5A (1C) and the maximum safe charging voltage is 16.8V. Then, according to the charging stage and the flight emergency level of the battery, a preset decision matrix is used to determine the charging mode and the initial charging parameters.

[0090] The decision matrix is as follows: for the first charging stage (deep discharge state, power < 30%): if the flight emergency level is high, select the constant current and constant voltage combined charging mode, set the initial charging current to 90% of the maximum safe charging current (i.e. 4.5A), and set the initial charging voltage to 95% of the maximum safe charging voltage (i.e. 16.0V); if the flight emergency level is medium, select the constant current charging mode, set the initial charging current to 70% of the maximum safe charging current (i.e. 3.5A); if the flight emergency level is low, select the constant current charging mode, set the initial charging current to 50% of the maximum safe charging current (i.e. 2.5A). For the second charging stage (regular charging state, 30% ≤ power ≤ 80%): if the flight emergency level is high, select the constant current charging mode, set the initial charging current to 100% of the maximum safe charging current (i.e. 5A); if the flight emergency level is medium, select the constant current charging mode, set the initial charging current to 80% of the maximum safe charging current (i.e. 4A); if the flight emergency level is low, select the constant current charging mode, set the initial charging current to 60% of the maximum safe charging current (i.e. 3A). For the third charging stage (near saturation state, power > 80%): if the flight emergency level is high, select the constant voltage charging mode, set the initial charging voltage to 100% of the maximum safe charging voltage (i.e. 16.8V); if the flight emergency level is medium or low, select the constant voltage charging mode, set the initial charging voltage to 98% of the maximum safe charging voltage (i.e. 16.5V).

[0091] For example, a certain UAV uses a 4S lithium polymer battery with a capacity of 5000mAh, and the current power is 25% (first charging stage), and the flight emergency level is high. According to the above decision matrix, the constant current and constant voltage combined charging mode is selected, the initial charging current is set to 4.5A (90% of the maximum safe charging current 5A), and the initial charging voltage is set to 16.0V (95% of the maximum safe charging voltage 16.8V). In practical application, the temperature factor of the battery also needs to be considered. If the battery temperature is close to the highest safe temperature (such as 40℃), the charging current should be appropriately reduced to prevent the battery from overheating; if the battery temperature is close to the lowest safe temperature (such as 5℃), the charging current should also be reduced because the charging acceptance ability of the battery decreases at low temperature. In this way, the most suitable charging mode and initial parameters can be selected according to the actual state of the battery and the task requirements, which can ensure charging efficiency, and also consider battery safety and life.

[0092] The AI-based charging parameter optimization method provided in this embodiment obtains battery safety parameter thresholds from a preset battery parameter database, determines the battery's charging stage based on the current battery level, assesses the urgency of the flight based on the remaining flight mission, and determines the charging mode and initial charging parameters based on this information, thus achieving intelligent management of the UAV battery charging process. This method can adaptively select the most suitable charging strategy based on the actual battery state and mission requirements, maximizing charging efficiency while ensuring battery safety and lifespan. Compared to traditional fixed charging strategies, this method better balances the relationship between charging speed, battery safety, and battery lifespan, making it particularly suitable for time-sensitive scenarios such as emergency rescue and large-scale mapping.

[0093] In one embodiment of this invention, the remaining flight missions include mission type and estimated flight time. Determining the flight urgency level based on the remaining flight missions includes the following steps:

[0094] S310. If the mission type is the preset first mission type, determine the flight urgency level as high;

[0095] S320. If the mission type is not the primary mission type, determine the flight urgency level as medium or low based on the estimated flight time.

[0096] Specifically, if the estimated flight time is less than a preset time threshold, the flight urgency level is determined to be medium; if the estimated flight time is not less than the preset time threshold, the flight urgency level is determined to be low.

[0097] When the mission type is the preset first mission type, the flight urgency level is determined to be high. Specifically, the preset first mission type refers to missions with high timeliness and high importance. These missions are often related to personal safety or major property safety and require the drone to complete them in the shortest possible time. Typical first mission types include: emergency rescue missions, such as search and rescue operations after natural disasters such as earthquakes, floods, and fires, which are directly related to the safety of people in disaster areas; security monitoring missions, such as forest fire monitoring, border patrols, and security monitoring of important facilities; medical assistance missions, such as the delivery of emergency medicines, blood, and medical equipment, which usually have strict time window requirements; and emergency response missions, such as traffic accident scene investigation and hazardous chemical leak monitoring, which require rapid response to prevent the situation from escalating.

[0098] When the task management system of the UAV receives a task instruction, it will first analyze the task type identifier. Once it is confirmed that the current task belongs to the preset first task type, the flight emergency level is set to high. Setting the flight emergency level to high means that in the subsequent charging strategy formulation, priority will be given to charging speed to ensure that the UAV can complete charging and perform tasks in the shortest time. This mechanism ensures that in the face of emergencies, the UAV can respond quickly and maximize its role in emergency scenarios.

[0099] In the case where the task type is not the first task type, the flight emergency level is determined to be medium or low based on the estimated flight time. Specifically, when the task of the UAV does not belong to the preset first task type, further analysis of other characteristics of the task can be performed to determine the flight emergency level based on the estimated flight time. The estimated flight time refers to the estimated time required to complete the remaining tasks, which is usually calculated based on factors such as flight path length, flight speed, hovering time, task operation time, etc.

[0100] The calculation formula of the estimated flight time can be expressed as: estimated flight time = path flight time + hovering operation time + task execution time + safety margin time. Among them, the path flight time refers to the time required for the UAV to fly along the planned path, and the calculation method is path length divided by average flight speed; the hovering operation time refers to the time required for the UAV to hover at a specific location to perform operations; the task execution time refers to the time required to complete a specific task operation (such as taking pictures, measuring, dropping items, etc.); the safety margin time is the time reserved to cope with possible wind speed changes, path adjustments, and other uncertain factors. For example, a UAV needs to perform a farmland surveying and mapping task, the planned path length is 5 kilometers, the average flight speed is 10 meters / second, it needs to hover and take pictures at 10 location points, each hovering time is 30 seconds, and the photographing operation time is 5 seconds, and the safety margin time is set to 10% of the total time. Then the estimated flight time is calculated as follows: path flight time = 5000 meters ÷ 10 meters / second = 500 seconds; hovering operation time = 10 times × 30 seconds / time = 300 seconds; task execution time = 10 times × 5 seconds / time = 50 seconds; subtotal time = 500 seconds + 300 seconds + 50 seconds = 850 seconds; safety margin time = 850 seconds × 10% = 85 seconds; estimated flight time = 850 seconds + 85 seconds = 935 seconds ≈ 15.6 minutes.

[0101] Non-first task types usually include routine mapping, agricultural monitoring, environmental monitoring, recreational aerial photography, etc. These tasks usually do not have extremely high timeliness requirements.

[0102] In the case where the predicted flight time is less than the preset time threshold, the flight emergency degree is determined to be medium, and in the case where the predicted flight time is not less than the preset time threshold, the flight emergency degree is determined to be low. Generally, the preset time threshold can be set to 30%-50% of the average endurance time of the unmanned aerial vehicle in a full power state. For example, if the average endurance time of a certain model of unmanned aerial vehicle is 60 minutes, the preset time threshold can be set to 20-30 minutes. When the predicted flight time is less than this threshold, it means that the task is relatively short and can be completed in a short time, but still needs to be guaranteed for a certain time, so the flight emergency degree is set to medium. For example, a certain unmanned aerial vehicle needs to perform a city building inspection task, and the calculated predicted flight time is 15 minutes, while the preset time threshold is 20 minutes. Since 15 minutes is less than 20 minutes, the flight emergency degree is set to medium. The flight emergency degree of medium means that in the charging strategy, both the charging speed and the battery life protection are considered, and a medium charging current is usually used to balance between the charging speed and the battery protection.

[0103] When the predicted flight time is not less than the preset time threshold, it means that the task is relatively long and has sufficient time to prepare, and does not need particularly urgent charging. For example, a certain unmanned aerial vehicle needs to perform a large-area farmland monitoring task, and the calculated predicted flight time is 35 minutes, while the preset time threshold is 20 minutes. Since 35 minutes is greater than 20 minutes, the flight emergency degree is set to low. The flight emergency degree of low means that in the charging strategy, the battery life protection will be given priority, and a lower charging current will be usually used to prolong the charging time, so as to maximize the protection of the battery and prolong its service life.

[0104] In addition, the preset time threshold is not a fixed parameter and can be dynamically adjusted according to actual application scenarios, seasonal changes, battery aging degree and other factors. For example, in cold weather, the preset time threshold can be appropriately reduced due to the influence of low temperature on battery performance; for a battery that has been used for a long time, the preset time threshold can also be adjusted accordingly due to capacity attenuation. Through this dynamic adjustment mechanism, various complex environments and task requirements can be better adapted to.

[0105] The task feature-based flight emergency degree determination method provided by the embodiment realizes intelligent judgment of the flight emergency degree by analyzing the task type and the predicted flight time of the unmanned aerial vehicle. The method first identifies whether the task belongs to a preset first task type with high emergency; for non-first task types, the emergency degree is further determined to be medium or low based on the comparison between the predicted flight time and the preset threshold. Compared with the traditional fixed charging strategy, the present method can adaptively adjust the charging parameters according to the actual requirements of the task, maximize the timeliness requirements of task execution under the premise of ensuring the safety and life of the battery. It is particularly suitable for multi-task and multi-scene unmanned aerial vehicle application environments.

[0106] In one of the embodiments of the present embodiment, the battery safety parameter threshold value includes a safety current threshold value and a safety voltage threshold value, and based on the battery safety parameter threshold value, the charging stage and the flight emergency level, any one of the constant current charging mode, the constant voltage charging mode or the constant current and constant voltage combined charging mode is determined as the charging mode, and according to the charging mode, the initial charging current value or the charging voltage value is determined, including the following steps:

[0107] S410, in the case that the charging stage is the first charging stage and the flight emergency level is high, the charging mode is determined as the constant current and constant voltage combined charging mode, and the initial charging current value is set as a first preset percentage of the safety current threshold value;

[0108] S420, in the case that the charging stage is the first charging stage and the flight emergency level is medium or low, the charging mode is determined as the constant current charging mode, and the initial charging current value is set as a second preset percentage of the safety current threshold value, wherein the second preset percentage is less than the first preset percentage;

[0109] S430, in the case that the charging stage is the second charging stage, the charging mode is determined as the constant voltage charging mode, and the initial charging voltage value is set as a third preset percentage of the safety voltage threshold value.

[0110] In the case that the charging stage is the first charging stage and the flight emergency level is high, the charging mode is determined as the constant current and constant voltage combined charging mode, and the initial charging current value is set as a first preset percentage of the safety current threshold value. Specifically, the first charging stage generally refers to the initial stage of battery charging, at which time the state of charge (SOC) of the battery is relatively low, and the internal electrochemical reaction of the battery is active, which can accept a larger charging current. In the charging process of a lithium ion battery, the first charging stage generally corresponds to the stage in which the SOC of the battery is from 0% to about 70% to 80%. If the current is in the first charging stage and the flight emergency level is high, it means that the battery needs to obtain sufficient power in a short time to perform an emergency task. In this case, the constant current and constant voltage combined charging mode is adopted.

[0111] The constant current and constant voltage combined charging mode is a charging mode that first charges at a constant current and then charges at a constant voltage. In the initial charging stage, a constant larger current is maintained, and when the battery voltage reaches a certain value, the charging mode is switched to constant voltage charging, and the current gradually decreases. This charging mode can achieve faster charging speed while ensuring the safety of the battery. The safety current threshold value refers to the maximum charging current that the battery can safely accept. Exceeding this threshold value may cause safety problems such as battery overheating, increased internal impedance, and electrolyte decomposition. The safety current threshold value is usually provided by the battery manufacturer and is related to factors such as the chemical composition, structural design and capacity of the battery.

[0112] The first preset percentage refers to the proportion of the initial charging current value to the safety current threshold in an emergency. Considering the timeliness requirement of emergency tasks, the first preset percentage is usually set at a high level, for example, 80% to 95%. Both the fast charging speed and the safety margin for the battery are ensured. Taking the above 5000 mAh battery as an example, if the safety current threshold is 10000 mA and the first preset percentage is set to 90%, the initial charging current value is 10000 mA x 90% = 9000 mA. In actual application, the setting of the initial charging current value also needs to consider the influence of the environmental temperature. For example, in a low-temperature environment (such as below 0°C), the charging acceptance ability of the lithium ion battery will be significantly reduced, and at this time, even if the emergency level is high, the first preset percentage also needs to be appropriately reduced to prevent safety problems such as lithium metal precipitation. Similarly, in a high-temperature environment (such as above 40°C), the charging current also needs to be reduced to prevent the battery from overheating. Therefore, the embodiment also introduces a temperature compensation mechanism to dynamically adjust the first preset percentage according to the environmental temperature. For example, in a 25°C environment, the first preset percentage is 90%; in a 0°C environment, it is reduced to 70%; and in a 40°C environment, it is reduced to 80%. In this way, the safe charging of the battery can be ensured under different environmental conditions, while the timeliness requirement of emergency tasks is maximized.

[0113] In the case that the charging phase is the first charging phase and the flight emergency level is medium or low, the charging mode is determined to be the constant current charging mode, and the initial charging current value is set to a second preset percentage of the safety current threshold, wherein the second preset percentage is less than the first preset percentage. Specifically, if the current is in the first charging phase and the flight emergency level is medium or low, it means that the battery charging does not need to be particularly fast, and a more moderate charging strategy can be adopted to prolong the battery life. In this case, the constant current charging mode is adopted. The constant current charging mode refers to charging the battery with a constant current during the charging process until the battery voltage reaches a certain value. Compared with the constant current and constant voltage combined charging mode, the pure constant current charging mode pays more attention to battery life protection in the first charging phase, and the charging speed is relatively slow. The second preset percentage refers to the proportion of the initial charging current value to the safety current threshold in a non-emergency situation. Considering the demand for battery life protection, the second preset percentage is usually set at a low level, for example, 50% to 70%, to significantly reduce the heat generation in the charging process and reduce the internal stress of the battery, thereby prolonging the cycle life of the battery.

[0114] In practical applications, the specific value of the second preset percentage can also be subdivided according to the different degrees of flight emergency. For example, when the degree of flight emergency is medium, the second preset percentage can be set to 65% to 70%; when the degree of flight emergency is low, the second preset percentage can be set to 50% to 60%, so as to more finely balance the relationship between charging speed and battery life. In addition, the setting of the second preset percentage also needs to consider the state of health (SOH) of the battery. As the number of uses of the battery increases, its internal impedance will gradually increase, and its charging acceptance ability will gradually decrease. Therefore, the present embodiment also introduces a battery health state evaluation mechanism to dynamically adjust the second preset percentage according to the actual health state of the battery. For example, for a new battery (SOH>90%), a standard second preset percentage can be used; for an aged battery (SOH<70%), the second preset percentage can be reduced by 10% to 20% to reduce the charging pressure on the battery. In this way, the charging strategy can be adaptively adjusted according to the actual condition of the battery and the task demand, and the battery life is maximized under the premise of ensuring the safety of the battery. At the same time, since a lower charging current is used, the heat generated during the charging process will also be reduced, which is particularly important for charging systems such as unmanned aerial vehicles that have high requirements for thermal management.

[0115] In the case of the charging phase being a second charging phase, the charging mode is determined to be a constant voltage charging mode, and the initial charging voltage value is set to a third preset percentage of a safety voltage threshold. Specifically, the second charging phase generally refers to the later stage of battery charging, at which time the state of charge (SOC) of the battery is already relatively high, generally above 70% to 80%. During the charging process of a lithium ion battery, if a constant current is continued to be used when the battery voltage reaches a certain value, it may cause the battery to overcharge, increasing the safety risk. Therefore, using a constant voltage charging mode in the second charging phase is a necessary measure to protect the battery. The constant voltage charging mode refers to charging the battery at a constant voltage during the charging process. As the battery charge increases, the charging current will gradually decrease until it reaches a preset cutoff current value. The safety voltage threshold refers to the maximum charging voltage that the battery can safely withstand. Exceeding this threshold may cause safety problems such as overcharging of the battery, decomposition of the electrolyte, and gas generation. The safety voltage threshold is usually provided by the battery manufacturer and is closely related to the chemical composition of the battery. For example, for a standard lithium ion battery (graphite negative electrode, lithium cobaltate positive electrode), the safety voltage threshold of a single battery is usually 4.2V; for a lithium iron phosphate battery, the safety voltage threshold is usually 3.65V.

[0116] The third preset percentage refers to the proportion of the initial charging voltage value to the safety voltage threshold. Considering the balance between battery safety and life, the third preset percentage is usually set to between 95% and 100%.

[0117] In practical applications, the setting of the third preset percentage needs to consider various factors. First of all, the battery life factor. Reducing the charging cutoff voltage can significantly extend the cycle life of lithium-ion batteries. For example, reducing the charging cutoff voltage from 4.2V to 4.1V can increase the cycle life of the battery by 30%-50%, but at the same time, about 10% of the capacity will be lost. Therefore, in non-emergency situations, the third preset percentage can be reduced to extend the battery life. Secondly, the temperature factor. In high-temperature environments, lithium-ion batteries are more prone to side reactions, and the safety risk increases. Therefore, in high-temperature environments (such as above 35°C in summer), the third preset percentage should be reduced, for example, from 98% to 95%. In addition, the aging degree of the battery also needs to be considered. As the battery is used, its internal structure will gradually change, and its sensitivity to high voltage will increase. Therefore, for batteries that have been used for a long time, the third preset percentage should also be appropriately reduced. By precisely controlling the voltage value of the constant-voltage charging stage, the charging speed and battery life can be balanced according to actual needs while ensuring the safety of the battery.

[0118] In another embodiment, the charging current value is reduced to a safe level when the real-time battery temperature exceeds the preset temperature threshold. The safe level of the current value is determined based on the current state of the battery. Specifically, when the real-time battery temperature exceeds the preset temperature threshold, the safety protection mechanism is triggered immediately, and the charging current value is reduced to a safe level to prevent safety hazards and performance damage caused by battery overheating.

[0119] In specific implementation, the battery temperature monitoring system uses high-precision thermistors or thermocouple sensors arranged at multiple key positions of the battery pack, such as near the positive and negative terminal posts, the center area of the battery cell, and the hot spot area. The temperature measurement accuracy of these sensors can reach ±0.5°C, and the sampling frequency is set to 1-2 times per second to ensure that small changes in temperature can be captured in a timely manner. After filtering the collected temperature data, it is compared with the preset temperature threshold.

[0120] For lithium polymer batteries, three temperature thresholds can be set: a first warning threshold of 40°C, a second warning threshold of 43°C, and a third warning threshold of 45°C. When the battery temperature exceeds the first warning threshold but is below the second warning threshold, a warning is issued but the charging current does not need to be immediately reduced; when the temperature exceeds the second warning threshold but is below the third warning threshold, the charging current is reduced moderately; and when the temperature exceeds the third warning threshold, the charging current is significantly reduced or the charging is suspended.

[0121] In practical applications, the temperature threshold can be dynamically adjusted according to the ambient temperature. For example, in high-temperature environments (such as summer above 35°C), the temperature thresholds of each level can be appropriately reduced by 2-3°C; in low-temperature environments (such as winter below 0°C), the temperature thresholds of each level can be appropriately increased by 1-2°C.

[0122] When the real-time battery temperature exceeds the preset temperature threshold, the system needs to reduce the charging current to a safe level. The safe level is not fixed, but dynamically determined based on the current state of the battery, to achieve the best balance between safety and efficiency. The current state of the battery includes but is not limited to temperature, state of charge (SOC), state of health (SOH), internal resistance, voltage and other key parameters.

[0123] The determination of the safe charging current adopts a multi-parameter comprehensive evaluation model, which considers factors such as the thermal characteristics, electrochemical characteristics and safety boundaries of the battery.

[0124] After determining the safe charging current, the charger output is adjusted in real time, and the battery response is continuously monitored through a closed-loop feedback control mechanism to ensure the safety and stability of the charging process.

[0125] During the adjustment process, the key parameters of the battery, especially the temperature change trend, are continuously monitored. If the temperature continues to rise or the rising rate does not slow down, the charging current is further reduced; if the temperature starts to drop or remains stable, the current current value is maintained. This fine-tuning mechanism based on real-time feedback can keep the charging current at the best balance point between safety and efficiency. In actual implementation, it can adapt to different models, different aging degrees of batteries, and different environmental conditions and use scenarios. It can continuously learn and optimize the charging strategy to make the charging process more and more in line with the actual needs of the specific battery.

[0126] This embodiment adopts different charging strategies for different charging stages and task urgency: in the first charging stage and high urgency, the constant current and constant voltage combined charging mode is adopted and a higher charging current is used to quickly increase the battery power; in the first charging stage and medium or low urgency, the constant current charging mode is adopted and a lower charging current is used to balance the charging speed and battery life; in the second charging stage, regardless of the urgency, the constant voltage charging mode is adopted and the charging voltage is set to the third preset percentage of the safe voltage threshold to ensure the safety of the battery. Thus, the charging parameters can be dynamically adjusted according to the actual situation, meeting the timeliness requirements of emergency tasks and maximizing the protection of battery safety and prolonging the battery life. Compared with the traditional fixed charging strategy, it can effectively shorten the charging time in emergency situations, while effectively prolonging the battery cycle life in non-emergency situations, significantly improving the overall performance and reliability of the unmanned aerial vehicle system.

[0127] In one embodiment of the present embodiment, based on the battery charging curve of the current time period, an artificial intelligence model is used to dynamically adjust the charging parameters of the unmanned aerial vehicle battery in the next preset time period at the end of the current time period, including the following steps:

[0128] S510, analyze the change trend of the battery charging curve through an artificial intelligence model to obtain an analysis result, the analysis result including a battery health degree and optimal charging parameters;

[0129] S520, based on the battery health degree and the optimal charging parameters, dynamically adjust the charging parameters of the unmanned aerial vehicle battery in the next preset time period at the end moment of the current time period.

[0130] The change trend of the battery charging curve is analyzed through an artificial intelligence model to obtain an analysis result, the analysis result including a battery health degree and optimal charging parameters. Specifically, the battery charging curve refers to a curve graph of parameters such as battery voltage, current, temperature, etc. changing with time during the charging process. Through analysis of the curve, the health condition of the battery and the most suitable charging strategy can be understood in depth.

[0131] In practical application, first, real-time data of the battery during charging needs to be collected, including but not limited to battery voltage, charging current, battery surface temperature, ambient temperature, charging duration, etc. After the data collection is completed, these time series data are input into a pre-trained artificial intelligence model for analysis. The artificial intelligence model can be implemented by using various algorithms, such as long short-term memory network (LSTM), which is suitable for processing time series data and capturing long-term dependencies therein.

[0132] Taking the LSTM model as an example, the network structure thereof includes an input layer, multiple LSTM layers, and an output layer. The input layer receives standardized battery parameter time series data; the LSTM layer is responsible for extracting time series features and learning the internal law of battery parameter changes; and the output layer generates battery health degree evaluation and optimal charging parameter suggestions. The training process of the model needs a large amount of historical charging data and corresponding battery health state labels, and the model parameters are optimized through supervised learning. For example, for a 5000 mAh lithium polymer battery, its charging and discharging data from a new battery to an aging process can be collected, and the actual capacity thereof is measured through experiments as a health degree label.

[0133] After the model is trained, in actual application, when the battery is charging, the model will analyze the charging curve data in the current time period (such as 15 minutes or 30 minutes) in real time. By analyzing the voltage rise rate, current drop curve, temperature change trend and other characteristics, the model can evaluate the current health status of the battery. For example, a healthy new battery has a relatively flat and stable voltage rise rate during the constant current charging phase; while an aging battery has a faster and unstable voltage rise rate. At the same time, the model also analyzes the internal resistance change trend of the battery, and the internal resistance of a healthy battery is low and stable, while the internal resistance of an aging battery is high and may fluctuate greatly during charging. Based on these analyses, the model outputs the battery health degree evaluation results, usually in percentage form, such as 90% indicating that the battery is in good condition, and 60% indicating that the battery has obviously aged. In addition to the battery health degree, the model will also predict the optimal charging parameters based on the current charging curve characteristics, including the charging current, charging voltage upper limit, and charging cutoff conditions for the next time period.

[0134] Based on the battery health degree and the optimal charging parameters, the charging parameters of the drone battery in the next preset time period are dynamically adjusted at the end of the current time period. Specifically, after obtaining the battery health degree and the optimal charging parameters analyzed by the artificial intelligence model, the charging strategy for the next preset time period can be dynamically adjusted according to the analysis results at the end of the current time period. This dynamic adjustment mechanism can make the charging process more adaptive to the real-time state changes of the battery.

[0135] According to the battery health degree evaluation results, the overall conservative degree of the charging strategy is adjusted. For batteries with a health degree of 90% or above, a relatively aggressive charging strategy can be used to improve charging efficiency; while for aging batteries with a health degree below 70%, a more conservative charging strategy needs to be used to prolong the remaining service life. The specific adjustment methods include: when the battery health degree is in the range of 90% to 100%, the charging current can be maintained at a high level, such as 0.8C-1.0C (C is the multiple of the rated capacity of the battery, for example, for a 5000mAh battery, 1C charging current is 5000mA); when the battery health degree is in the range of 70% to 90%, the charging current is appropriately reduced to 0.5C-0.8C; when the battery health degree is below 70%, the charging current is further reduced to 0.3C-0.5C, and the charging cutoff voltage may be reduced, such as from 4.2V to 4.1V or 4.0V.

[0136] Based on the best charging parameter suggestions given by the artificial intelligence model, the specific charging parameters for the next preset time period are fine-tuned. These parameters include but are not limited to: charging current size, charging voltage upper limit, charging cutoff condition (such as cutoff current), charging mode (constant current, constant voltage, or constant current constant voltage combination), etc. For example, if the analysis finds that the current battery temperature rising rate is too fast, it is recommended to reduce the charging current in the next time period to prevent the battery from overheating; if the battery internal resistance abnormally increases, the constant current charging phase is ended in advance and the constant voltage charging phase is entered.

[0137] In practical applications, this dynamic adjustment is usually carried out in preset time periods, and the length of the time period can be flexibly set according to the application scenario and computing resources. Common settings are 5 minutes, 15 minutes, or 30 minutes. Taking 15 minutes as an example, at the end of each 15-minute time period, based on the charging data collected in that time period, the battery health and the best charging parameters are analyzed by the artificial intelligence model, and then the charging strategy for the next 15-minute time period is adjusted accordingly. This segmented dynamic adjustment strategy can respond to changes in battery status in a timely manner, while avoiding system instability caused by too frequent parameter adjustments. Through the dynamic adjustment mechanism based on artificial intelligence analysis, personalized charging strategies can be provided according to the real-time state and characteristics of the battery, ensuring charging efficiency while maximizing battery protection and extending battery life.

[0138] The present embodiment uses an artificial intelligence model to deeply analyze the battery charging curve, extracting battery health information and best charging parameter suggestions; then based on the analysis results, the charging strategy for the next time period is dynamically adjusted at the end of each preset time period, realizing real-time optimization of the charging process. This data-driven adaptive charging method has significant advantages over traditional fixed charging strategies: it can provide personalized charging solutions according to the actual state of the battery, ensuring charging efficiency while maximizing battery protection; it can detect abnormal battery states in a timely manner and make corresponding adjustments, improving charging safety; by optimizing charging parameters, the service life of the battery is effectively extended, reducing the maintenance cost of the unmanned aerial vehicle. By using this method, the cycle life of the battery is effectively improved, the charging efficiency is improved, and the risk of battery overheating and overcharging is significantly reduced, providing a strong guarantee for long-term and high-reliability operation of the unmanned aerial vehicle system.

[0139] In one embodiment of the present embodiment, the artificial intelligence model is a deep reinforcement learning model, including a convolutional neural network layer for extracting features of the battery charging curve, a long short-term memory network layer for learning the time series variation law of the battery charging state, a policy network and a value network for predicting the optimal charging parameters.

[0140] Reference Figure 2, the artificial intelligence model is a deep reinforcement learning model, wherein a convolutional neural network layer is first adopted to extract battery charging curve features. Specifically, a convolutional neural network (CNN) layer is used as a front-end processing unit of the deep reinforcement learning model to extract valuable feature information from the original battery charging curve data. The battery charging curve usually contains multi-dimensional time series data such as voltage, current, and temperature, which are recorded in a high-frequency sampling manner to form a large number of data points. Directly inputting these raw data into the neural network will cause high computational complexity and easily introduce noise interference, so feature extraction and dimension reduction processing are needed through the CNN layer. In actual implementation, the input of the CNN layer is multi-channel time series data within a fixed time window, for example, voltage, current, and temperature data sampled at 1-second intervals within a 10-minute window, forming a two-dimensional data matrix with a shape of [600, 3]. The CNN layer is usually composed of multiple convolution blocks, each of which contains convolution operation, batch normalization, and activation function. Taking a typical CNN structure as an example, the first layer of convolution uses 32 convolution kernels with a size of 5x1 and a step of 1 to perform convolution operation on the input data to capture the parameter change features in the local time period; then a ReLU activation function is introduced for nonlinear transformation; then a max-pooling layer (pooling window size of 2x1, step of 2) is used for downsampling to reduce the data dimension and retain significant features. The second layer of convolution uses 64 convolution kernels with a size of 3x1 to further extract higher-level features; similarly, ReLU activation and max-pooling operations are performed. Finally, the third layer of convolution uses 128 convolution kernels with a size of 3x1 to extract the highest level of abstract features. This multi-layer convolution structure can effectively capture different scale features in the battery charging curve, such as short-term fluctuations, medium-term trends, and long-term change patterns. For example, for the constant current charging phase in the lithium battery charging process, the CNN can identify the slope change feature of the voltage rising curve; for the constant voltage charging phase, the CNN can capture the exponential decay feature of the current falling curve. In addition, the CNN can also extract key features such as temperature rise rate and temperature fluctuation from the temperature curve to evaluate the battery health status and safety. In this way, the CNN layer converts the original high-dimensional time series data into a low-dimensional but information-rich feature vector, providing a more refined and effective input for the subsequent long short-term memory network layer, greatly improving the learning efficiency and prediction accuracy of the model.

[0141] The long short-term memory network layer is used to learn the time series variation law of the battery charging state. Specifically, the long short-term memory network (LSTM) layer receives the feature vector sequence from the convolutional neural network layer to process the time series dependence in the battery charging process.

[0142] Battery charging is a typical time-series process, and the current battery state is not only related to the current charging parameters but also closely related to the historical charging process. LSTM network can effectively learn long-term dependencies and capture the inherent law of battery state evolution over time due to its special gating mechanism (including input gate, forget gate, and output gate). In practical implementation, the LSTM layer is usually composed of multiple layers of bidirectional LSTM units to enhance the ability to capture time-series information. Taking a two-layer bidirectional LSTM structure as an example, the first layer LSTM contains 128 hidden units and receives the feature sequence output by the CNN layer. Each LSTM unit contains three gating units: the input gate determines how much new information is stored in the cell state at the current time; the forget gate determines how much cell state at the previous time is retained; and the output gate controls how much current cell state is output. This gating mechanism enables LSTM to selectively remember or forget information, making it particularly suitable for processing long time-series data such as battery charging. The design of bidirectional LSTM enables the network to consider both past and future information, further improving the ability to understand time-series patterns. The second layer LSTM contains 64 hidden units to further extract higher-level time-series features. The stacking of two-layer LSTM enables the network to learn more complex time-series patterns, such as the state transition law of the battery in different charging stages (pre-charging, constant current charging, and constant voltage charging). During the battery charging process, the LSTM layer can learn a variety of important time-series rules. For example, for a healthy new battery, the voltage rise rate usually remains relatively stable during the constant current charging stage; while for an aging battery, the voltage rise rate may gradually accelerate with charging time. LSTM can capture this time-varying trend and use it as an important basis for evaluating the battery health state. Similarly, LSTM can also learn the relationship between temperature change and charging state, such as the correlation between temperature rise rate and battery internal resistance during high-current charging. By learning these time-series change rules, the LSTM layer can accurately evaluate the current state of the battery and provide rich state representation for the subsequent policy network and value network, thereby supporting more accurate charging parameter prediction.

[0143] The policy network is used to predict the optimal charging parameters. Specifically, the policy network receives the state representation from the LSTM layer and outputs the optimal charging parameter distribution for the current battery state. In the reinforcement learning framework, the policy network is responsible for making charging decisions based on the observed battery state. The policy network adopts a probabilistic policy, i.e., outputs a probability distribution for each possible charging parameter combination, rather than directly outputting deterministic parameter values. In actual implementation, the policy network is usually composed of multiple fully connected neural network layers. Taking a typical policy network structure as an example, the first fully connected layer contains 256 neurons, which receives the state representation output by the LSTM layer and introduces non-linear transformation through the ReLU activation function; the second fully connected layer contains 128 neurons, also using the ReLU activation function; the number of neurons in the last fully connected layer depends on the dimension of the action space, for example, if both charging current and charging voltage upper limit need to be controlled, and each parameter is discretized into 10 possible values, then the output layer contains 20 neurons (10+10). The output layer uses the Softmax activation function to convert the original output of the neural network into a probability distribution. During training, the policy network continuously optimizes its parameters through the policy gradient algorithm to maximize the expected cumulative reward. The reward function design is the core of reinforcement learning, and for the battery charging task, the reward function usually considers multiple goals: charging speed (the shorter the charging time, the higher the reward), charging efficiency (the higher the energy conversion efficiency, the higher the reward), and battery health protection (temperature control within a safe range, avoiding overcharging and overdischarging, etc.).

[0144] In practical applications, the policy network can dynamically adjust the charging parameters according to the real-time state of the battery. For example, for a 5000mAh lithium polymer battery, when it is detected that the battery temperature rises too fast, the policy network outputs the decision to reduce the charging current, such as from 1.0C (5000mA) to 0.5C (2500mA); when it is detected that the battery enters the constant voltage charging phase, the policy network gradually reduces the charging current and accurately controls the cutoff current to achieve the best charging effect. In this way, the policy network can achieve intelligent control of the charging process and find the best balance point between charging speed, efficiency, and battery protection.

[0145] The value network is used to evaluate the long-term value of the current battery state and charging strategy. Specifically, the value network receives the same state representation as the policy network and outputs an estimate of the value of the current state, i.e., the expected cumulative reward that can be obtained by following the current policy from the current state. The value network provides more accurate gradient estimates for the policy network, reduces the variance of policy updates, and improves learning efficiency and stability.

[0146] In practical implementation, the value network usually shares the first few layers of network structure with the policy network to improve computational efficiency. The independent part of the value network is also composed of multiple fully connected neural network layers. Taking a typical value network structure as an example, the first fully connected layer contains 128 neurons, receives the output of the shared layer, and passes through the ReLU activation function; the second fully connected layer contains 64 neurons, also uses the ReLU activation function; and the last fully connected layer has only one neuron, directly outputs the state value estimate, and does not use the activation function. During the training process, the value network continuously optimizes its parameters through the time-difference (TD) learning method, so that the predicted state value approximates the true expected return.

[0147] Specifically, the loss function of the value network is usually defined as the mean square error between the predicted value and the target value. The introduction of the value network enables the deep reinforcement learning model to be applicable to solving complex control problems with continuous states and continuous actions, such as battery charging. In practical applications, the value network can evaluate the long-term effects of different charging strategies, helping the policy network make more intelligent decisions. For example, for two possible charging strategies: strategy A uses a higher charging current (1.0C) for fast charging, and strategy B uses a lower charging current (0.5C) for slow charging. On the surface, strategy A can increase the battery power faster and obtain a higher immediate reward; but the value network, by evaluating the long-term cumulative reward, may find that strategy B, although slower in charging, can better protect the battery health and reduce capacity decay, resulting in a higher overall return in the long run. In this way, the value network provides the policy network with a more comprehensive and long-term decision basis, allowing the charging control strategy to consider both short-term benefits and long-term value.

[0148] This embodiment realizes intelligent control of the battery charging process of the unmanned aerial vehicle through the organic combination of the convolutional neural network layer, the long short-term memory network layer, the policy network and the value network. The model first extracts key features from multi-dimensional charging curve data using the convolutional neural network layer, then learns the time series variation law of the battery state through the long short-term memory network layer, and finally realizes dynamic optimization decision of the charging parameters based on the policy network and the value network. This deep reinforcement learning model can automatically learn complex battery charging patterns without the need for manual design of control rules, can provide personalized charging strategies according to individual differences and aging levels of the battery, can find the best balance point between charging speed, efficiency and battery life, effectively improving the cycle life of the battery, shortening the charging time, and at the same time maintaining a relatively low temperature rise and capacity decay rate, providing a solid guarantee for the long-time and high-reliability operation of the unmanned aerial vehicle in various complex environments.

[0149] In one of the implementations of the embodiment, the trend of the battery charging curve is analyzed by an artificial intelligence model to obtain an analysis result, the analysis result including a battery health degree and optimal charging parameters, including the following steps:

[0150] S710, collecting battery charging curve data in a current time period, the battery charging curve data being time series data including charging voltage, charging current and battery temperature;

[0151] S720, preprocessing the time series data;

[0152] S730, inputting the preprocessed time series data into a convolutional neural network layer to extract local features of the battery charging curve;

[0153] S740, inputting the local features into a long short-term memory network layer to learn the time series variation law of the battery charging state;

[0154] S750, calculating the battery internal resistance change rate, capacity attenuation rate and temperature sensitivity index based on the deviation of the battery charging curve from the standard charging curve;

[0155] S760, calculating the battery health degree according to the internal resistance change rate, capacity attenuation rate and temperature sensitivity index by using a preset battery health degree function;

[0156] S770, inputting the local features and the time series variation law into a policy network and a value network to predict the charging efficiency and battery life under different charging parameters to obtain the optimal charging parameters.

[0157] In the embodiment, in order to ensure the integrity and continuity of the data, a sliding window mechanism is used to collect the battery charging curve data in the current time period, the battery charging curve data being time series data including charging voltage, charging current and battery temperature, the window size being usually set to 10 minutes and the step being 1 minute, i.e. the data window is updated once every minute, and the time series data of the last 10 minutes is retained for subsequent analysis.

[0158] The time series data preprocessing includes four main links: data cleaning, data standardization, data enhancement and time alignment. Data cleaning is used to process the outliers and noise in the original data. The sliding window median filtering method is used to remove short-term noise; the data standardization link is used to convert different dimensional data to the same scale, so that the neural network can learn more effectively. For voltage, current and temperature, three different physical quantities, Z-score standardization method is used respectively. For example, for voltage data, assuming the mean is 3.7V and the standard deviation is 0.3V, the original voltage value 4.0V becomes 1.0 after standardization. This standardization makes the data of different physical quantities concentrated on the distribution with mean 0 and standard deviation 1, which is conducive to the training convergence of neural network.

[0159] Data enhancement is used to expand the training samples by artificially synthesizing data to improve the generalization ability of the model. Gaussian noise can be added to achieve this, that is, random noise with mean 0 and standard deviation 10% of the original data standard deviation is superimposed on the original data; time alignment is used to solve the problem of inconsistent sampling frequency of different sensors. Since the sampling frequency of voltage and current is 10Hz, and the sampling frequency of temperature is 1Hz, it is necessary to align these data to the unified time axis. Linear interpolation method is used to interpolate temperature data from 1Hz to 10Hz, so that the three kinds of data are completely aligned in time dimension. After the above four links of preprocessing, the original irregular and high noise time series data is transformed into standardized, aligned and low noise data set, providing high quality input for subsequent feature extraction and model training.

[0160] The pre-processed time series data is input into a convolutional neural network layer to extract local features of the battery charging curve. Specifically, a convolutional neural network (CNN) layer is used to extract local feature patterns such as voltage rise rate, current drop characteristics, temperature fluctuations, etc. from the normalized battery charging curve. CNN can effectively capture local patterns in time series data without being affected by location. In actual implementation, the input of the CNN layer is a two-dimensional tensor with shape [T, 3], where T is the time step (usually 6000, corresponding to the number of data points sampled at 10Hz within a 10-minute window), and 3 represents the three channels of voltage, current and temperature. The CNN layer consists of three consecutive convolutional blocks, each containing a convolutional layer, a batch normalization layer, an activation function layer and a pooling layer. The first convolutional block uses 32 convolutional kernels with a size of 15x1 and a step size of 1 to perform convolution operations on the input data. The convolution kernel size of 15 means that a data window of 1.5 seconds (15 / 10Hz) is considered each time, which can capture the parameter change characteristics in a short time. After the convolution operation, a batch normalization layer is used to stabilize the training process, followed by a ReLU activation function to introduce non-linear transformation, and finally a max pooling layer with a pooling window size of 2 and a step size of 2 to reduce the data dimension by half while retaining significant features. The second convolutional block uses 64 convolutional kernels with a size of 10x1, with similar settings as the first convolutional block, but the pooling window size is increased to 3 to further reduce the data dimension. The third convolutional block uses 128 convolutional kernels with a size of 5x1 and a pooling window size of 4. Through these three consecutive convolutional blocks, the original [6000, 3] input data is converted into a feature map with a shape of approximately [125, 128], greatly reducing the data dimension while retaining key information. In battery charging curve analysis, the CNN layer can extract a variety of valuable local features. In this way, the CNN layer converts the original high-dimensional time series data into a feature representation containing rich semantic information, providing high-quality input for the subsequent long short-term memory network layer and greatly improving the model's understanding of the battery charging state.

[0161] The local features are input into a long short-term memory network layer to learn the time series variation rules of the battery charging state. Specifically, the long short-term memory network (LSTM) layer receives the local feature representation from the CNN layer, and its main task is to capture the long-term dependence and variation rules of the battery charging state over time.

[0162] In practical implementation, the input of the LSTM layer is the feature sequence output by the CNN layer, with a shape of about [125, 128], representing 125 time steps and 128-dimensional features at each step. The LSTM layer adopts a bidirectional structure, containing two LSTM subnetworks in the forward and backward directions, which can consider both past and future context information to improve the understanding of time series patterns. The LSTM layer is composed of two layers of stacked bidirectional LSTM units, with 64 hidden units in the first layer (32 in each direction) and 32 hidden units in the second layer (16 in each direction). Each LSTM unit contains three gating units and a memory unit. Taking one unit of the first layer LSTM as an example, the input gate is controlled by a sigmoid function, which determines how much information in the current input is stored in the memory unit; the forget gate is also controlled by a sigmoid function, which determines how much of the memory unit state at the last time step is retained; the output gate controls how much of the current memory unit state is output as the hidden state. This fine gating mechanism enables LSTM to selectively remember or forget information, making it particularly suitable for capturing long-term trends in the battery charging process. In battery charging analysis, the LSTM layer can learn various important time series variation patterns. For example, for a healthy new battery, the voltage rise curve usually exhibits a specific nonlinear pattern during constant current charging, and LSTM can learn this pattern and identify abnormal situations that deviate from the normal pattern; for an aging battery, LSTM can capture the change in the relationship between temperature rise rate and charging time during charging, which usually reflects the increase in internal impedance of the battery. In addition, LSTM can also learn the transition features between different charging stages, such as the transition point features from pre-charging to constant current charging and from constant current charging to constant voltage charging, which are crucial for evaluating the battery health state. Through the two-layer stacked bidirectional LSTM structure, the model can extract high-level time series patterns from local features to form a comprehensive understanding of the battery charging state. The output of the LSTM layer is a feature sequence with a shape of [125, 32], which contains the time series variation patterns of the battery charging state, providing a solid foundation for subsequent battery health evaluation and charging parameter optimization.

[0163] Based on the deviation of the battery charging curve from the standard charging curve, the battery internal resistance change rate, capacity decay rate, and temperature sensitivity index are calculated. Specifically, by comparing the deviation between the actual battery charging curve and the standard charging curve (i.e., the charging curve of a new battery under ideal conditions), key indicators reflecting the battery health state can be extracted. Taking a 5000mAh lithium polymer battery as an example, its standard charging curve library contains standard voltage, current, and temperature curves at 0.2C, 0.5C, and 1.0C charging rates.

[0164] When the actual battery's charging curve is obtained, the matched standard curve is automatically selected for comparison according to the charging conditions. The calculation of the battery internal resistance change rate is based on Ohm's law and the battery equivalent circuit model. The specific calculation method is: in the constant current charging stage, multiple time points (usually 10 evenly distributed points) are selected, and the instantaneous internal resistance R = ΔV / I is calculated at each point, where ΔV is the voltage increment relative to the open circuit voltage, and I is the charging current; then the average internal resistance of these points is calculated, compared with the standard internal resistance, and the internal resistance change rate ΔR% = (Ractual - Rstandard) / Rstandard x 100% is obtained. For example, if the standard internal resistance is 20 mΩ, and the actual measured average internal resistance is 24 mΩ, then the internal resistance change rate is (24-20) / 20x100%=20%, indicating that the battery internal resistance has increased by 20%.

[0165] The capacity attenuation rate is the second key indicator, reflecting the degree of decline in the battery's energy storage capability. Its calculation is based on the integral area comparison of the charging curve. The specific method is: the current-time integral in the constant current charging stage is calculated to obtain the actual charging capacity Qactual; this capacity is compared with the standard charging curve under the same conditions to obtain the capacity attenuation rate ΔQ% = (Qstandard - Qactual) / Qstandard x 100%. For example, if the standard capacity is 4800 mAh, and the actual measured capacity is 4320 mAh, then the capacity attenuation rate is (4800-4320) / 4800x100%=10%, indicating that the battery capacity has decreased by 10%.

[0166] The temperature sensitivity index is the third key indicator, reflecting the change in the battery's heating characteristics during charging. Its calculation is based on the slope comparison of the temperature rise curve. The specific method is: the average slope k_actual of the temperature rise curve during charging is calculated k_actual = ΔT / Δt; this slope is compared with the standard temperature rise slope k_standard to obtain the temperature sensitivity index ΔT% = (k_actual - k_standard) / k_standard x 100%. For example, if the standard temperature rise slope is 0.05°C / min, and the actual measured slope is 0.08°C / min, then the temperature sensitivity index is (0.08-0.05) / 0.05x100%=60%, indicating that the battery's temperature sensitivity has increased by 60%, i.e. it is more likely to heat up under the same charging conditions. By calculating these three key indicators, the system can comprehensively evaluate the battery's health status and provide quantitative basis for subsequent battery health degree calculation.

[0167] According to the internal resistance change rate, capacity attenuation rate and temperature sensitivity index, the battery health degree is calculated by using a preset battery health degree function. Specifically, the battery health degree is a percentage index that comprehensively reflects the overall health status of the battery, and is usually taken as the state of a brand-new battery (100%) as the benchmark, and gradually decreases as the battery ages. The calculation of the battery health degree adopts a weighted comprehensive scoring function, and the three key indexes (internal resistance change rate, capacity attenuation rate and temperature sensitivity index) calculated in the previous step are converted into health degree scores through nonlinear mapping. The preset battery health degree function adopts the following form:

[0168] SOH = 100% - [w1xf1(AR%) + w2xf2(AQ%) + w3xf3(AT%)], wherein w1, w2 and w3 are weight coefficients, respectively representing the influence degree of the three indexes on the battery health degree; f1, f2 and f3 are nonlinear mapping functions for converting the indexes into health degree loss. Usually, w1 (internal resistance weight) is 0.3, w2 (capacity weight) is 0.5, and w3 (temperature weight) is 0.2, reflecting that the capacity attenuation has the greatest influence on the battery health degree, followed by the internal resistance change, and finally the temperature sensitivity. The nonlinear mapping function adopts a sigmoid type function, which can handle the saturation effect of the index value, i.e., when the index exceeds a certain threshold, the influence on the health degree tends to be stable.

[0169] Taking the mapping function of the internal resistance change rate as an example: f1(AR%) = 100% x [1-exp(-AR% / a1)] / [1+exp(-AR% / a1)], wherein a1 is an adjustment parameter, usually taking a value of 30%, indicating that when the internal resistance change rate reaches 30%, the influence on the health degree reaches a medium degree. The mapping functions of the capacity attenuation rate and the temperature sensitivity index are similar, but the adjustment parameters are different, being a2 = 20% and a3 = 50%, respectively.

[0170] The calculation result of the battery health degree not only directly reflects the overall health status of the battery, but also can be used to predict the remaining service life of the battery. Generally, it is considered that when the battery health degree decreases to below 80%, the battery enters an accelerated aging stage; and when it decreases to below 60%, the battery is recommended to be replaced. In addition, the battery health degree is also an important basis for formulating a charging strategy, and a battery with a lower health degree usually needs to adopt more conservative charging parameters to delay the aging speed.

[0171] The local features and the time sequence change rules are input into the policy network and the value network, and the charging efficiency and the battery life under different charging parameters are predicted to obtain the optimal charging parameters. Specifically, the policy network and the value network are used to predict the optimal charging parameters according to the current state of the battery. The two networks receive the local features from the CNN layer and the time sequence change rules from the LSTM layer, and output the optimal charging strategy for the current battery state. The policy network is responsible for generating actions (charging parameters); and the value network is responsible for evaluating the value of the actions. Since the policy network and the value network have been specifically described above, the present application will not be repeated here.

[0172] The present embodiment collects voltage, current and temperature time sequence data in the battery charging process through a high-precision sensor network, and then performs data preprocessing, including data cleaning, standardization, enhancement and time alignment. The preprocessed data is input into a convolutional neural network layer to extract local features, and then a long short-term memory network layer is used to learn the time sequence change rules. Based on the extracted features, the system calculates the battery internal resistance change rate, capacity attenuation rate and temperature sensitivity index, and comprehensively evaluates the battery health state through a pre-set health degree function. Finally, the policy network and the value network predict and output the optimal charging parameters based on the current state and the health degree of the battery, so as to monitor the battery health state in real time, warn potential risks in advance, provide personalized charging strategies according to the individual differences and aging degree of the battery, and find the best balance point between charging speed, efficiency and battery life.

[0173] In one of the embodiments of the present embodiment, based on the battery health degree and the optimal charging parameters, the charging parameters of the unmanned aerial vehicle battery in the next preset time period are dynamically adjusted at the end time of the current time period, including the following steps:

[0174] S810, in the case where the battery health degree is lower than the first preset threshold, the charging current in the next preset time period is reduced to the first preset proportion of the optimal charging parameter, and the charging voltage is reduced to the second preset proportion of the optimal charging parameter at the end time of the current time period;

[0175] S820, in the case where the battery health degree score is not lower than the first preset threshold and not higher than the second preset threshold, the charging parameters in the next preset time period are set to the optimal charging parameters at the end time of the current time period;

[0176] S830, in the case where the battery health degree score is higher than the second preset threshold and the flight emergency degree is high, the charging current in the next preset time period is increased to the third preset proportion of the optimal charging parameter, and does not exceed the battery safety parameter threshold at the end time of the current time period.

[0177] At the end of the current time period, the battery charging parameters of the next preset time period are dynamically adjusted according to the battery health and the optimal charging parameters. This method balances the relationship between battery life protection and charging efficiency by monitoring the battery health in real time and adopting corresponding charging strategies in combination with the urgency of the flight task.

[0178] When the battery health score is lower than the first preset threshold, it indicates that the battery is in a poor health state, and a protective charging strategy needs to be adopted. At the end of the current time period, the charging current of the next preset time period is automatically reduced to a first preset proportion of the optimal charging parameter, and the charging voltage is reduced to a second preset proportion of the optimal charging parameter. This way of reducing charging parameters can effectively reduce the pressure on the battery and slow down the battery performance degradation rate.

[0179] In specific implementation, the first preset threshold can be set to 80, which can be adjusted appropriately according to the type of the unmanned aerial vehicle battery and the use environment. The first preset proportion can be set to 0.7, i.e., the charging current is reduced to 70% of the optimal charging current; the second preset proportion can be set to 0.9, i.e., the charging voltage is reduced to 90% of the optimal charging voltage. For example, if the optimal charging current of a certain type of lithium battery is 2A and the optimal charging voltage is 4.2V, when its health score is 75, the system will automatically adjust the charging current to 1.4A (2A x 0.7) and the charging voltage to 3.78V (4.2V x 0.9) in the next time period after the current charging time period ends.

[0180] This way of reducing charging parameters can significantly reduce the accumulation of heat and electrochemical stress inside the battery, and reduce the risk of electrolyte decomposition and electrode material structure damage. In practical application, using this charging strategy for a battery in poor health can avoid further damage to the battery caused by fast charging and provide a buffer period for the battery to recover.

[0181] When the battery health score is not lower than the first preset threshold and not higher than the second preset threshold, it indicates that the battery is in a normal health state, and a standard charging strategy can be adopted. At the end of the current time period, the charging system will set the charging parameters of the next preset time period to the optimal charging parameters, which can ensure charging efficiency and will not cause excessive damage to the battery.

[0182] In practical application, the second preset threshold can be set to 90. When the battery health score is between 80 and 90, the optimal charging parameters are used for charging. The optimal charging parameters refer to the parameter combination that can achieve high charging efficiency under the premise of ensuring the safety and life of the battery.

[0183] With the optimal charging parameters, the charging speed can be relatively ideal while ensuring the safety of the battery. Under this charging strategy, the battery can usually complete 80% of the capacity charging within 1-1.5 hours, meeting the needs of most conventional use scenarios. At the same time, since the parameters are set within the safe range, there will be no obvious additional damage to the battery, and the battery can maintain normal cycle life. This balanced charging strategy is suitable for daily use scenarios and can balance charging efficiency and battery life protection.

[0184] When the battery health score is higher than the second preset threshold and the flight task urgency is high, it indicates that the battery is in good condition and there is a need for fast charging. At the end of the current time period, the charging current of the next preset time period is increased to a third preset proportion of the optimal charging parameter to speed up the charging speed, but at the same time ensure that it does not exceed the battery safety parameter threshold to prevent overcharging and cause safety hazards.

[0185] In the specific implementation process, the third preset proportion can be set to 1.3, i.e., the charging current is increased to 130% of the optimal charging current. The battery safety parameter threshold includes the maximum allowed charging current, the highest charging temperature, and other key indicators. For example, if the optimal charging current of a certain type of battery is 3A, the maximum allowed charging current is 4.5A, and when its health score is 95 points and the flight task urgency is high, the charging current of the next time period will be adjusted to 3.9A (3A x 1.3) after the current charging time period ends. Since this value does not exceed the maximum allowed charging current of 4.5A, it can be safely implemented.

[0186] It should be noted that although increasing the charging current can speed up the charging speed, it will also increase the amount of heat generated by the battery. Therefore, in the implementation process, the charging system will continuously monitor the battery temperature, and once it approaches the safety threshold (usually 45°C), the charging current will be automatically reduced to ensure the safety of the battery. Since this strategy is only applicable to batteries in good health and is limited by safety parameter thresholds, the impact on battery life is relatively controllable.

[0187] In another embodiment, according to the battery temperature variation trend, the battery temperature of the next preset time period is predicted, and the charging current is reduced in advance to prevent the battery from overheating when the predicted temperature approaches the safety threshold; through an adaptive control algorithm, the charging parameters are adjusted in real time to make the actual charging curve gradually approach the theoretical optimal charging curve.

[0188] Specifically, according to the battery temperature variation trend, the battery temperature of the next preset time period can be predicted, and the charging current can be reduced in advance to prevent the battery from overheating when the predicted temperature approaches the safety threshold. Compared with the traditional passive response temperature control, the battery safety can be more effectively protected and the battery life can be extended.

[0189] In implementation, the temperature change data in the last 30 minutes is recorded, and the temperature change rate and trend are analyzed by mathematical models such as linear regression or exponential smoothing. For example, if the current battery temperature is 38℃, and the temperature has risen at an average rate of 0.2℃ per minute in the last 15 minutes, it can be predicted that if the current charging current is maintained, the battery temperature will reach 44℃ at the end of the next 30-minute preset period. If the battery safety temperature threshold is set to 45℃, the predicted temperature is close to the safety threshold, and the preventive current reduction measure will be triggered.

[0190] The magnitude of the preventive current reduction can be dynamically determined according to the closeness of the predicted temperature to the safety threshold. For example, a three-level current reduction strategy can be set: when the predicted temperature reaches 85% of the safety threshold, the charging current is reduced to 80% of the current value; when the predicted temperature reaches 90% of the safety threshold, the charging current is reduced to 60% of the current value; when the predicted temperature reaches 95% of the safety threshold, the charging current is reduced to 40% of the current value.

[0191] This preventive current reduction strategy based on temperature prediction can effectively avoid the risk of battery temperature exceeding the safety threshold and reduce temperature fluctuations during charging. Although it may slightly prolong the charging time in some cases (usually by 10%-15%), it significantly improves charging safety and reduces damage to battery materials at high temperatures, which can extend the actual service life of the battery in the long run. In addition, a more stable temperature curve also helps to improve battery charging efficiency and consistency of charging depth, thereby improving the endurance and reliability of the UAV.

[0192] Through the adaptive control algorithm, the charging parameters can be adjusted in real time, so that the actual charging curve gradually approaches the theoretical optimal charging curve, thereby maximizing charging efficiency and battery life while ensuring battery safety.

[0193] The adaptive control algorithm is based on a closed-loop feedback mechanism and mainly includes three core links: state observation, deviation calculation, and parameter adjustment. First, the key state parameters of the battery are monitored in real time, including terminal voltage, charging current, temperature, internal resistance estimate, etc. Second, these actual parameters are compared with the pre-established theoretical optimal charging model to calculate the deviation value. Finally, according to the deviation value and its trend, the charging parameter increment to be adjusted is calculated through algorithms such as PID (Proportional-Integral-Derivative) controller or fuzzy logic controller, and applied to the next control cycle.

[0194] The theoretical optimal charging curve is usually determined based on the chemical properties of the battery and the use scenario.

[0195] In practical applications, the adjustment period of the adaptive control algorithm can be set to once every 30 seconds, and the adjustment amplitude of each adjustment does not exceed 5% of the current parameter to ensure system stability. For example, if the current charging current is 2A and the actual charging curve is lower than the theoretical curve, the current is adjusted to 2.1A; if the battery temperature rise rate exceeds the expectation, the current is reduced to 1.9A. This fine-tuning process will continue until the deviation between the actual charging curve and the theoretical curve is controlled within an acceptable range (such as ±3%).

[0196] Based on the battery temperature change trend prediction and the adaptive control algorithm for adjusting the charging parameters, the intelligent and fine management of the unmanned aerial vehicle battery charging process is realized. This method effectively avoids the risk of battery overheating; at the same time, with the help of the adaptive control algorithm, the charging parameters are adjusted in real time, so that the actual charging process gradually approaches the theoretical optimal state. The combination of the two technologies forms a closed-loop optimized charging management system, which can not only ensure the safety of the battery, but also maximize the charging efficiency and battery life.

[0197] For unmanned aerial vehicle operation, this means shorter ground preparation time, longer flight duration, and lower battery replacement frequency and maintenance cost. Especially in harsh environmental conditions or high-intensity task scenarios, this method can significantly improve the reliability and task execution capability of the unmanned aerial vehicle system.

[0198] The embodiment divides the charging strategy into three modes of protective charging, standard charging and fast charging according to the battery health status, and makes a comprehensive decision in combination with the urgency of the flight task. Through real-time monitoring and dynamic adjustment, the balance between charging efficiency and battery life can be maximized under the premise of ensuring the safety of the battery, which significantly enhances the adaptability and reliability of the unmanned aerial vehicle in various complex task scenarios, and provides a strong guarantee for long-time, efficient and safe and reliable flight tasks of the unmanned aerial vehicle.

[0199] The embodiment of the application also provides an electronic device, comprising:

[0200] a memory configured to store instructions; and

[0201] a processor configured to call the instructions from the memory and capable of realizing the above-mentioned artificial intelligence-based charging parameter optimization method when executing the instructions.

[0202] Referring to Figure 3 , the embodiment of the application also provides an artificial intelligence-based charging parameter optimization system, comprising:

[0203] an electronic device;

[0204] an unmanned aerial vehicle connected with the electronic device.

[0205] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.

[0206] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.

[0207] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.

[0208] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. Figure 1 In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. Figure 1 In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.

[0209] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. Figure 1 In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. Figure 1 In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device. In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.

[0210] In this embodiment, the electronic device can be a tablet computer, a desktop computer, a laptop computer, a handheld computer, a wearable device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, or the like device with a processor. Of course, the electronic device can also be a server. The embodiments of the present application do not specially limit the specific form of the electronic device.​​​​​​​​These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1

[0211] In one typical configuration, the computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0212] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) about which the processor can execute instructions. The memory can also include non-volatile memory, such as read only memory (ROM), electrically programmable read only memory (EPROM), electrically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), flash memory, or a combination of non-volatile memories in different types. The memory can also include a compact disk read only memory (CD-ROM), digital versatile disk (DVD), Blu-ray, or another non-transitory computer readable medium, which is non-volatile and non-transitory in nature, but volatile in that it can lose its content if the power to the computer is turned off or if the computer crashes. The memory is an example of a computer readable medium.

[0213] Computer readable media includes permanent and non-permanent, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD), or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer readable media does not include transitory media such as modulated data signals and carriers.

[0214] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0215] ​​The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. An artificial intelligence-based charging parameter optimization method, characterized by, The method comprises the following steps: acquiring the battery type, current charge level and remaining flight task of the unmanned aerial vehicle; acquiring the corresponding battery safety parameter threshold from the preset battery parameter database according to the battery type of the unmanned aerial vehicle, wherein the battery safety parameter threshold comprises a safety current threshold and a safety voltage threshold; judging the charging stage of the battery according to the current charge level; determining the flight emergency level according to the remaining flight task, wherein the flight emergency level comprises high, medium and low; in the case that the charging stage is the first charging stage and the flight emergency level is high, determining that the charging mode is the constant-current constant-voltage combined charging mode, and setting the initial charging current value as the first preset percentage of the safety current threshold; in the case that the charging stage is the first charging stage and the flight emergency level is medium or low, determining that the charging mode is the constant-current charging mode, and setting the initial charging current value as the second preset percentage of the safety current threshold, wherein the second preset percentage is smaller than the first preset percentage; in the case that the charging stage is the second charging stage, determining that the charging mode is the constant-voltage charging mode, and setting the initial charging voltage value as the third preset percentage of the safety voltage threshold; monitoring the battery charging curve of the unmanned aerial vehicle in real time in response to the charging signal of the unmanned aerial vehicle, wherein the battery charging curve is constructed based on the real-time charging voltage, real-time charging current and real-time battery temperature; analyzing the change trend of the battery charging curve through the artificial intelligence model to obtain an analysis result, wherein the analysis result comprises the battery health degree and the optimal charging parameter; based on the battery health degree and the optimal charging parameter, dynamically adjusting the charging parameter of the unmanned aerial vehicle battery in the next preset time period at the end time of the current time period, wherein the charging parameter comprises the charging current and the charging voltage; charging the unmanned aerial vehicle battery according to the charging parameter at the start time of the next preset time period.

2. The method of claim 1, wherein, The remaining flight task comprises the task type and the estimated flight time, and the flight emergency level is determined according to the remaining flight task, comprising: in the case that the task type is the preset first task type, determining that the flight emergency level is high; in the case that the task type is not the first task type, determining that the flight emergency level is medium or low based on the estimated flight time; in the case that the estimated flight time is less than the preset time threshold, determining that the flight emergency level is medium, and in the case that the estimated flight time is not less than the preset time threshold, determining that the flight emergency level is low.

3. The method of claim 1, wherein, The artificial intelligence model is a deep reinforcement learning model, comprising a convolutional neural network layer for extracting the features of the battery charging curve, a long short-term memory network layer for learning the time sequence change rule of the battery charging state, and a policy network and a value network for predicting the optimal charging parameter.

4. The method of claim 3, wherein, The analysis result comprises the battery health degree and the optimal charging parameter, comprising: collecting the battery charging curve data in the current time period, wherein the battery charging curve data is time sequence data comprising the charging voltage, the charging current and the battery temperature; preprocessing the time sequence data; inputting the preprocessed time sequence data into the convolutional neural network layer to extract the local features of the battery charging curve; The local features are input into a long short-term memory network layer to learn a time sequence variation rule of the battery charging state; Based on the deviation of the battery charging curve from the standard charging curve, a battery internal resistance change rate, a capacity attenuation rate and a temperature sensitivity index are calculated; According to the internal resistance change rate, the capacity attenuation rate and the temperature sensitivity index, a preset battery health degree function is used to calculate the battery health degree; The local features and the time sequence variation rule are input into a policy network and a value network to predict the charging efficiency and the battery life under different charging parameters, and the optimal charging parameters are obtained.

5. The method of claim 1, wherein, Based on the battery health degree and the optimal charging parameters, the charging parameters of the unmanned aerial vehicle battery in the next preset time period are dynamically adjusted at the end of the current time period, including: In the case that the battery health degree is lower than a first preset threshold, the charging current in the next preset time period is reduced to a first preset proportion of the optimal charging parameters, and the charging voltage is reduced to a second preset proportion of the optimal charging parameters at the end of the current time period; In the case that the battery health degree is not lower than the first preset threshold and not higher than a second preset threshold, the charging parameters in the next preset time period are set to the optimal charging parameters at the end of the current time period; In the case that the battery health degree is higher than the second preset threshold and the flight emergency degree is high, the charging current in the next preset time period is increased to a third preset proportion of the optimal charging parameters, and does not exceed the battery safety parameter threshold at the end of the current time period.

6. An electronic device, comprising: comprising: a memory configured to store instructions; and a processor configured to call the instructions from the memory and enable the artificial intelligence-based charging parameter optimization method according to any one of claims 1 to 5 when the instructions are executed.

7. An artificial intelligence-based charging parameter optimization system, characterized by, comprising: the electronic device according to claim 6; an unmanned aerial vehicle connected with the electronic device.

Images