Power battery temperature prediction method and device based on eVTOL typical flight characteristics

Abstract

The invention provides a power battery temperature prediction method and device based on eVTOL typical flight characteristics, and belongs to the technical field of aviation engineering such as an aircraft technology, a power technology, an avionics technology and an electromechanical system technology. The method comprises the following steps: collecting time sequence data of current and temperature in real time after the eVTOL takes off, calculating a time-current curve curvature through a high-precision non-equidistant five-point curvature method, and determining a flight state conversion time point; according to typical characteristics of different flight states, fitting a temperature-time change relationship between the take-off stage and the initial stage of the cruise stage through partial data of the take-off stage and the cruise stage; and predicting the temperature change of the remaining voyage in the flight process by using the obtained fitting parameters in combination with the remaining cruise duration and the landing duration. The method has the characteristics of simplicity, high efficiency and high practicability, can predict the temperature change in the later flight period in the initial flight period, provides effective data support for eVTOL power battery thermal management, and lays a foundation for safe flight.

Description

A method and device for predicting the temperature of a power battery based on typical eVTOL flight characteristics. Technical Field

[0001] This invention relates to the fields of aerospace engineering technology, including aircraft technology, power technology, avionics technology, and electromechanical system technology, and in particular to a method and device for predicting the temperature of a power battery based on typical flight characteristics of eVTOL. Background Technology

[0002] eVTOL (Electric Vertical Take-off and Landing) aircraft, as a new type of air transportation, relies entirely on batteries for power. The temperature characteristics of these batteries during flight directly affect their range and safety. Excessive battery temperature in eVTOLs poses several serious risks, directly threatening flight safety and equipment reliability. High temperatures can cause unstable battery output, leading to sudden power shortages and difficulty maintaining preset lift or descent speeds during takeoff or landing. High temperatures can also cause the battery casing to deform or crack, and electrolyte leakage can cause corrosive hazards, exacerbating equipment damage. When the temperature exceeds a safe threshold, the battery is highly susceptible to thermal runaway. The large amount of high-temperature gas and flames released during thermal runaway can trigger a chain reaction, leading to complete failure of the eVTOL power system and even catastrophic accidents such as crashes.

[0003] However, due to the significant differences in motor power and complex temperature fluctuations in eVTOLs at different stages of flight, accurately predicting the power battery temperature with sufficient lead time by combining the flight time and changes in battery physical characteristics at each flight stage in the flight profile is a prerequisite for effective thermal management functions such as thermal runaway alarms, and a key issue to ensure the reliable operation of eVTOLs. This is specifically reflected in the following three aspects.

[0004] Firstly, regarding the accuracy of temperature prediction: the different characteristics of typical flight states of eVTOL, such as takeoff, cruise, and landing, all significantly affect the temperature changes of the power battery, thus impacting the accuracy of temperature prediction. During the takeoff phase, eVTOL requires high power output to overcome its own gravity and achieve vertical ascent, resulting in high-rate discharge of the power battery and a rapid temperature rise. During the cruise phase, power demand is relatively stable, the battery discharge rate decreases, and the temperature slowly and slightly decreases under effective cooling conditions. During the landing phase, precise power control is required to achieve a smooth vertical or near-vertical landing without a runway buffer, demanding extremely high precision and response speed in power regulation, and the temperature also rises rapidly. If the power battery temperature prediction method does not fully consider the typical flight dynamics of eVTOL, the predicted results will deviate significantly from the actual temperature. In this case, effective temperature control measures cannot be taken in a timely manner during actual flight, directly affecting flight safety and battery performance. For example, electric vehicles primarily operate on the ground, and their load changes are relatively stable during operation. Fixed-wing aircraft, on the other hand, need to accumulate sufficient airspeed through ground taxiing before takeoff and undergo a relatively long runway buffer during landing. Overall, their power fluctuations are relatively mild, and the battery temperatures of both are relatively stable, fundamentally different from the characteristics of eVTOL flight. Therefore, related temperature prediction methods lack transferability in terms of adaptability and prediction completeness under eVTOL conditions. Thus, there is an urgent need to develop a battery temperature prediction method based on the typical flight characteristics of eVTOL.

[0005] Secondly, regarding the timeliness of temperature prediction: Currently, most common battery temperature measurement and prediction methods rely on short-term predictions based on the battery's current usage patterns, significantly shortening the warning time for abnormal battery temperatures. For eVTOLs used in manned flights, predicting battery temperatures during the later stages of flight (takeoff and cruise phases) would improve prediction timeliness. This would allow for proactive cooling measures or adjustments to flight parameters when temperatures show a tendency to exceed safety thresholds, reducing the risk of thermal runaway from the outset. On one hand, the descent phase of eVTOLs is a high-risk segment of flight; predicting temperature changes during this phase allows sufficient time to respond before abnormal temperature trends occur, enabling timely adjustments to flight strategies or optimization of cooling measures to prevent flight accidents caused by temperature issues. On the other hand, such advance prediction provides a forward-looking basis for battery thermal management throughout the entire flight process, helping to optimize the operation of the thermal management system, improving the overall reliability and safety of eVTOLs, and meeting the risk warning requirements of relevant industry standards.

[0006] Thirdly, regarding the practicality of prediction algorithms: eVTOL airborne hardware and software algorithms need to balance high accuracy and lightweight design. Although cutting-edge theoretical research in recent years has developed high-precision battery temperature prediction algorithms based on artificial intelligence, these algorithms generally rely on massive computing power. However, eVTOLs are constrained by their own size and weight, and the computing resources of airborne electronic equipment are limited, making it difficult to support the operation requirements of complex artificial intelligence algorithms. Therefore, there is an urgent need for a battery temperature prediction method that can ensure high prediction accuracy while also being lightweight, in order to achieve efficient adaptation to airborne hardware platforms. Summary of the Invention

[0007] Purpose of the invention: To provide a method and device for predicting the temperature of a power battery based on typical flight characteristics of eVTOL. By distinguishing the flight phases through the curvature change characteristics of the current time series collected in real time after eVTOL takeoff, and performing piecewise fitting of the temperature change over time based on the temperature time series characteristics collected in the takeoff and early cruise phases of eVTOL, the method can accurately predict the temperature changes of the power battery in the later cruise and landing phases, providing strong support for the prevention of battery thermal runaway and the assurance of flight safety.

[0008] Technical Solution: A method for predicting the temperature of a power battery based on typical flight characteristics of eVTOL, comprising: S1, real-time acquisition of time-series data of current and temperature after eVTOL takeoff, and calculation of the curvature of the time-current curve using a high-precision non-equidistant five-point curvature method to determine the flight state transition time point; S2, based on the typical characteristics of different flight stages, using partial data from the takeoff and cruise stages, and differentially fitting the temperature-time change relationship between the takeoff stage and the initial stage of the cruise stage; S3, using the obtained fitting parameters, combined with the remaining cruise duration and landing duration, to predict the temperature change of the remaining flight distance during this flight.

[0009] Furthermore, the high-precision non-equidistant five-point curvature method described in S1 includes: S11, for time series... , And satisfy and ,calculate , S12, Calculation hour, exist Approximate value of the first derivative of a point S13, Calculation hour, exist Approximate value of the second derivative of a point S14, Calculation hour, exist Approximate curvature of a point .

[0010] Furthermore, the calculation of the time-current curve curvature described in S1 to determine the flight state transition time point includes: S15, real-time acquisition of the current sequence. , , The total number of data acquisitions at the current time is defined as negative for battery discharge current; S16, the curvature of the time-current curve is calculated using a high-precision non-equidistant five-point curvature method to dynamically distinguish flight phases: Phase 1 is the take-off phase, with the starting point being the initial data acquisition time point at takeoff. The endpoint is the curvature during the process where the first current is negative and its absolute value continuously decreases. Points that are negative and whose absolute values ​​change abruptly , For the first time to meet The point in time; when the unit of time is seconds and the unit of current is milliamperes. The range of values ​​is Phase 2 is the cruise phase, starting from the next point after the end of Phase 1. The endpoint is the next current that is negative and its absolute value continuously increases, during which the curvature... Points that are negative and whose absolute values ​​change abruptly ,satisfy and , The range of values ​​is Phase 3 is the landing phase, starting from the point following the end of Phase 1. ;end This marks the end of the flight phase, that is, the point where the current returns to 0 from a negative value.

[0011] Furthermore, S2, based on the typical characteristics of different flight phases, fits the temperature-time variation relationship between the takeoff phase and the initial stage of the cruise phase using a small amount of differentiated data, including: S21, inputting the given estimated takeoff time. Cruise estimated time and the preset battery temperature sampling time interval After S22 and eVTOL takeoff, for ,collection , ,in, , The value range is 5 to 15 seconds. The value range is 5 to 12; S23, the value collected by S22. indivual Data points, as Fitting to obtain the rate of temperature rise and reference temperature S24, when ,for ,collection , ,in, , The value range is 5 to 15 seconds. The value range is 30 to 50. The value range is 1 to 100 seconds; S25, collected using S24. indivual Data points, as Fitting to obtain parameters and .

[0012] Furthermore, S3, using the obtained fitting parameters and combining the remaining cruise time and landing time, predicts the temperature change during the remaining flight distance, including: S31, for ,in Temperature forecast is ,calculate S32, Input the given estimated landing phase time. S33, for Temperature forecast is ,calculate ,in, The method for determining the value is as follows: For ,calculate ;for ,calculate ;in, , , This is a time constant related to the intrinsic characteristics of the battery.

[0013] A power battery temperature prediction device based on typical eVTOL flight characteristics includes: a flight phase determination module, used to collect time-series data of current and temperature in real time after eVTOL takeoff, and calculate the curvature of the time-current curve using a high-precision non-equidistant five-point curvature method to determine the flight state transition time point; a temperature-time change relationship determination module, used to fit the temperature-time change relationship between the takeoff phase and the early stage of the cruise phase using partial data from the takeoff phase and the cruise phase, based on the typical characteristics of different flight phases; and a prediction module, used to predict the temperature change of the remaining flight distance during this flight by using the obtained fitting parameters and combining the remaining cruise duration and landing duration.

[0014] Furthermore, the high-precision non-equidistant five-point curvature method in the flight phase determination module includes: S11, for time series... , And satisfy and ,calculate , S12, Calculation hour, exist Approximate value of the first derivative of a point S13, Calculation hour, exist Approximate value of the second derivative of a point S14, Calculation hour, exist Approximate curvature of a point .

[0015] Furthermore, the flight phase determination module calculates the curvature of the time-current curve to determine the flight state transition time point, specifically: S15, real-time acquisition of the current sequence. , , The total number of data acquisitions at the current time is defined as negative for battery discharge current; S16, the curvature of the time-current curve is calculated using a high-precision non-equidistant five-point curvature method to dynamically distinguish flight phases: Phase 1 is the take-off phase, with the starting point being the initial data acquisition time point at takeoff. The endpoint is the curvature during the process where the first current is negative and its absolute value continuously decreases. Points that are negative and whose absolute values ​​change abruptly , For the first time to meet The point in time; when the unit of time is seconds and the unit of current is milliamperes. The range of values ​​is Phase 2 is the cruise phase, starting from the next point after the end of Phase 1. The endpoint is the next current that is negative and its absolute value continuously increases, during which the curvature... Points that are negative and whose absolute values ​​change abruptly ,satisfy and , The range of values ​​is Phase 3 is the landing phase, starting from the point following the end of Phase 1. ;end This marks the end of the flight phase, that is, the point where the current returns to 0 from a negative value.

[0016] Furthermore, the temperature-time variation determination module is specifically used for: S21, inputting the given estimated takeoff time. Cruise estimated time and the preset battery temperature sampling time interval After S22 and eVTOL takeoff, for ,collection , ,in, , The value range is 5 to 15 seconds. The value range is 5 to 12; S23, the value collected by S22. indivual Data points, as Fitting to obtain the rate of temperature rise and reference temperature S24, when ,for ,collection , ,in, , The value range is 5 to 15 seconds. The value range is 30 to 50. The value range is 1 to 100 seconds; S25, collected using S24. indivual Data points, as Fitting to obtain parameters and .

[0017] Furthermore, the prediction module, specifically for: S31, for ,in Temperature forecast is ,calculate S32, Input the given estimated landing phase time. S33, for Temperature forecast is ,calculate ,in, The method for determining the value is as follows: For ,calculate ;for ,calculate ;in, , , This is a time constant related to the intrinsic characteristics of the battery.

[0018] Beneficial effects: (1) Highly targeted and adaptable to eVTOL operating conditions: It fully considers the unique operating conditions of eVTOL, such as power burst during takeoff, fluctuation during cruise, and fine adjustment during landing. Based on the high linear correlation between temperature and current during takeoff and landing, and the flight characteristics of rapid temperature change followed by slow temperature change during cruise, linear and exponential functions are used for data fitting respectively. The phased modeling avoids the problem of insufficient adaptation of traditional algorithms to complex operating conditions, and the prediction results are more in line with the actual flight scenario.

[0019] (2) Early warning to ensure flight safety: Through algorithm construction, the temperature during the landing phase depends on the time linear relationship by fitting parameter values ​​of the data from the takeoff and cruise phases. It can directly determine the temperature changes in the later stage of the cruise phase and the landing phase using the data from the takeoff and early cruise phases. The intercept is borrowed from the baseline temperature of the cruise phase, and the slope is borrowed from a certain scaling of the temperature rise rate (slope) during the takeoff phase. This can significantly extend the warning time, allow for early cooling or adjustment strategies, effectively reduce the risk of battery thermal runaway, and meet relevant safety standards.

[0020] (3) Easy to deploy and lightweight design: It abandons the huge computing power requirements of complex artificial intelligence algorithms, adopts a simplified phased model and numerical calculation method, with low computational complexity, and can be directly deployed on the limited airborne electronic equipment of eVTOL without increasing the size and weight of the equipment.

[0021] (4) Accurate prediction, aiding thermal management: By dynamically optimizing model parameters based on the temperature change characteristics of each stage, the prediction error is small, providing accurate data support for the real-time control of the battery thermal management system, and improving the endurance and operational efficiency of eVTOL. In addition, the high-precision non-equidistant five-point curvature method proposed in this method can achieve a second-order approximation in the calculation of the first derivative, and the second derivative has a first-order approximation, which can accurately distinguish the flight state transition point, providing support for fitting the temperature-time change relationship between the takeoff stage and the early stage of the cruise stage through differential data with a small amount of data. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 is a schematic diagram of the principle of a power battery temperature prediction method based on typical eVTOL flight characteristics according to an embodiment of the present invention; Figure 2 is a schematic diagram of the process of a power battery temperature prediction method based on typical eVTOL flight characteristics according to an embodiment of the present invention; Figure 3 is a schematic diagram of flight phase identification results for the same battery under different flight cycle numbers according to an embodiment of the present invention; Figure 4 is a schematic diagram of temperature prediction for the same battery under different flight cycle numbers according to an embodiment of the present invention; Figure 5 is a schematic diagram of flight phase identification for the first flight of a new battery of the same specification with only different cruise time according to an embodiment of the present invention; Figure 6 is a schematic diagram of temperature prediction for the first flight of a new battery of the same specification with only different cruise time according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] The features and illustrative embodiments of various aspects of the present invention will now be described in detail. Numerous specific details are set forth in the following detailed description to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention may be practiced without requiring some of these specific details. The following description of embodiments is merely intended to provide a better understanding of the invention by illustrating examples of the invention. The invention is by no means limited to any specific setups and methods set forth below, but covers any improvements, substitutions, and modifications to structures, methods, and devices without departing from the spirit of the invention. Well-known structures and techniques are not shown in the drawings and the following description to avoid unnecessarily obscuring the invention.

[0026] In the description of this invention, it should be noted that the directions or positional relationships indicated by terms such as "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing and simplifying the invention, and should not be construed as limiting the invention. Furthermore, the use of ordinal numbers (e.g., "first and second," etc.) is for distinguishing objects and is not limited to this order, and should not be construed as indicating or implying relative importance.

[0027] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly, encompassing both direct connection and indirect connection via an intermediate medium. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0028] It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other, and the various embodiments can be referenced and cited in each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0030] This patent develops a power battery temperature prediction method based on typical eVTOL flight characteristics. It is characterized by its simplicity, efficiency, and practicality. It can predict the highest temperature in the later stage of flight during the initial stage, providing effective data support for eVTOL power battery thermal management and laying the foundation for safe flight.

[0031] Figure 1 is a schematic diagram of the principle of a power battery temperature prediction method based on typical flight characteristics of eVTOL according to an embodiment of the present invention. As shown in Figure 1, the method may include the following steps: S1, after the eVTOL takes off, real-time time series data of current and temperature are collected, and the curvature of the time-current curve is calculated by using the high-precision non-equidistant five-point curvature method to determine the flight state transition time point; S2, based on the typical characteristics of different flight stages, the temperature-time change relationship between the takeoff stage and the early stage of the cruise stage is fitted using partial data from the takeoff stage and the cruise stage; S3, using the obtained fitting parameters, combined with the remaining cruise duration and landing duration, the temperature change of the remaining flight distance during this flight is predicted.

[0032] Figure 2 is a schematic flowchart of a power battery temperature prediction method based on typical flight characteristics of eVTOL according to an embodiment of the present invention; as shown in Figure 2, the method may include the following steps: Step 1: Execute

[101] , estimated takeoff time Cruise estimated time Expected landing time Preset battery temperature sampling time interval ; Proceed to execution

[102] ; Step 2: Execute

[102] , set , , ;definition ;for ,calculate ; Proceed to execution

[103] ; Step 3: Execute

[103] , for ,collection ; ;for ,collection ;calculate , , ;for ,collection ;set up ; Proceed to execution

[104] ; Step 4: Execute

[104] , and set , ;collection ; Proceed to execution

[105] ; Step 5: Execute

[105] , high-precision non-equidistant five-point curvature method calculation The method is as follows: First calculate , , ; then set ,calculate , ; Proceed to execution

[106] ; Step 6: Execute

[106] , determine If the condition is true, execute

[107] ; otherwise, execute

[111] . Step 7: Execute

[107] to determine the condition. If the condition is true, execute

[108] ; if not, execute

[104] . Step 8: Execute

[108] , and set... , , ; Proceed to execution

[109] ; Step 9: Execute

[109] , determine If the condition is true, execute

[110] ; if not, execute

[104] . Step 10: Execute

[110] , using... Data set, perform linear fitting To obtain the rate of temperature rise and reference temperature ; Proceed to execution

[104] ; Step 11: Execute

[111] , set , , ;definition , , ;for ,calculate ; Proceed to execution

[112] ; Step 12: Execute

[112] , let , ;collection ; Proceed to execution

[113] ; Step 13: Execute

[113] , high-precision non-equidistant five-point curvature method calculation The method is as follows: First calculate , , ; then set ,calculate , ; Proceed to execution

[114] ; Step 14: Execute

[114] , determine If the condition is true, execute

[115] ; otherwise, execute

[112] . Step 15: Execute

[115] . , , ; Proceed to execution

[116] ; Step 16: Execute

[116] , determine If the condition is true, execute

[117] ; otherwise, execute

[112] . Step 17: Execute

[117] , using... Data set, perform exponential fitting Obtain parameters and ; Proceed to execution

[118] ; Step 18: Execute

[118] , for Temperature forecast is ,calculate ; Proceed to execution

[119] ; Step 19: Execute

[119] , set ,calculate , ; Proceed to execution

[119] ; Step 20: Execute

[120] , determine If the condition is true, execute

[121] ; otherwise, execute

[122] . Step 21: Execute

[121] to calculate... ; Proceed to execution

[123] ; Step 22: Execute

[122] , calculate ; Proceed to execution

[123] ; Step 23: Execute

[123] , for Temperature forecast is ,calculate ; Proceed to execution

[124] ; Step 24: Execute

[124] , output the prediction curve, output the predicted maximum temperature value and the corresponding time.

[0033] In some embodiments, the parameter settings and implementation effects of the power battery temperature prediction method based on typical eVTOL flight characteristics are described in detail.

[0034] In one embodiment that uses an 18650 cylindrical lithium battery as the test object to simulate the eVTOL flight power supply cycle, a full life cycle eVTOL flight power supply simulation test is conducted on a certain battery, with parameters set... , , , , , , The flight stages of the same battery at the 1st, 450th, and 900th cycles were identified. The results are shown in Figure 3. The six points on each current curve, from left to right, represent: takeoff start point, takeoff end point, cruise start point, cruise end point, landing start point, and landing end point. The temperature changes during the later stages of flight at the 1st, 450th, and 900th cycles of the same battery were predicted, and the results are shown in Figure 4. As can be seen from the figures, the high-precision non-equidistant five-point curvature method proposed in this invention can effectively and accurately distinguish the typical flight stages of eVTOL for batteries at different aging stages, and the temperature prediction error throughout the process is only within 2℃, achieving the invention's objective.

[0035] In one embodiment of simulating eVTOL flight power supply cycles using 18650 cylindrical lithium batteries as the test object, multiple new batteries of the same specification were used to conduct eVTOL flight power supply cycle simulation tests with different cruise phase durations; for a cycle with a cruise time of 800 seconds, parameters were set... , , , , , , For a cycle with a cruise time of 600 seconds, set the parameters... , , , , , , For a cycle with a cruise time of 400 seconds, set the parameters... , , , , , , The first flight of new batteries of the same specification, differing only in cruise time, was identified for each flight stage, as shown in Figure 5. The six points corresponding to each current curve, from left to right, are: takeoff start point, takeoff end point, cruise start point, cruise end point, landing start point, and landing end point. The temperature changes in the later stages of flight of new batteries of the same specification, differing only in cruise time, were predicted, as shown in Figure 6. As can be seen from the figure, for batteries with different cycle durations, the high-precision non-equidistant five-point curvature method proposed in this invention can effectively and accurately distinguish the typical flight stages of eVTOL, and the temperature prediction error throughout the process is only within 1℃, achieving the invention's objective.

[0036] It should be noted that the above process operations can be combined to varying degrees. For the sake of simplicity, the implementation methods of various combinations will not be elaborated further. Those skilled in the art can flexibly adjust or combine the order of the steps of the above method (or the position of the product components) according to the actual situation.

[0037] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting the temperature of a power battery based on typical eVTOL flight characteristics, characterized in that, include: S1. After takeoff, the eVTOL collects real-time time-series data of current and temperature. Using a high-precision non-equidistant five-point curvature method, the curvature of the time-current curve is calculated to determine the flight state transition time point. S2. Based on the typical characteristics of different flight phases, the temperature-time change relationship between the takeoff phase and the early stage of the cruise phase is fitted using partial data from the takeoff and cruise phases. S3. Using the obtained fitting parameters, combined with the remaining cruise duration and landing duration, the temperature change of the remaining flight distance is predicted.

2. The method according to claim 1, characterized in that, The high-precision non-equidistant five-point curvature method described in S1 includes: S11, for time series... ， And satisfy and ,calculate ， S12, Calculation hour, exist Approximate value of the first derivative of a point S13, Calculation hour, exist Approximate value of the second derivative of a point S14, Calculation hour, exist Approximate curvature of a point 。 3. The method according to claim 1, characterized in that, The calculation of the time-current curve curvature described in S1 to determine the flight state transition time point includes: S15, real-time acquisition of current sequence. ， ， The total number of data acquisitions at the current time is defined as negative for battery discharge current; S16, the curvature of the time-current curve is calculated using a high-precision non-equidistant five-point curvature method to dynamically distinguish flight phases: Phase 1 is the take-off phase, with the starting point being the initial data acquisition time point at takeoff. The endpoint is the curvature during the process where the first current is negative and its absolute value continuously decreases. Points that are negative and whose absolute values ​​change abruptly ， For the first time to meet The point in time; when the unit of time is seconds and the unit of current is milliamperes. The range of values ​​is Phase 2 is the cruise phase, starting from the point following the endpoint of Phase 1. The endpoint is the next current that is negative and its absolute value continuously increases, during which the curvature... Points that are negative and whose absolute values ​​change abruptly ,satisfy and ， The range of values ​​is Phase 3 is the landing phase, starting from the point following the end of Phase 1. ;end This marks the end of the flight phase, that is, the point where the current returns to 0 from a negative value.

4. The method according to claim 1, characterized in that, S2, based on the typical characteristics of different flight phases, fits the temperature-time variation relationship between the takeoff phase and the initial stage of the cruise phase using a small amount of differentiated data, including: S21, inputting the given estimated takeoff time. Cruise estimated time and the preset battery temperature sampling time interval After S22 and eVTOL takeoff, for ,collection ， ,in, ， The value range is 5 to 15 seconds. The value range is 5 to 12; S23, the value collected by S22. indivual Data points, as Fitting to obtain the rate of temperature rise and reference temperature S24, when ,for ,collection ， ,in, ， The value range is 5 to 15 seconds. The value range is 30 to 50. The value range is 1 to 100 seconds; S25, collected using S24. indivual Data points, as Fitting to obtain parameters and 。 5. The method according to claim 1, characterized in that, S3, using the obtained fitting parameters and combining the remaining cruise time and landing time, predicts the temperature change during the remaining flight distance, including: S31, for ,in Temperature forecast is ,calculate S32, Input the given estimated landing phase time. S33, for Temperature forecast is ,calculate ,in, The method for determining the value is as follows: For ,calculate ;for ,calculate ;in, ， ， This is a time constant related to the intrinsic characteristics of the battery.

6. A power battery temperature prediction device based on typical eVTOL flight characteristics, characterized in that, Includes the following steps: The flight phase determination module is used to collect time series data of current and temperature in real time after eVTOL takeoff. It calculates the curvature of the time-current curve using a high-precision non-equidistant five-point curvature method to determine the flight state transition time point. The temperature-time change relationship determination module is used to fit the temperature-time change relationship between the takeoff phase and the early stage of the cruise phase based on the typical characteristics of different flight phases and by using partial data from the takeoff phase and the cruise phase. The prediction module is used to predict the temperature change during the remaining flight distance by using the obtained fitted parameters and combining the remaining cruise time and landing time.

7. The apparatus according to claim 6, characterized in that, The high-precision non-equidistant five-point curvature method in the flight phase determination module includes: S11, for time series... ， And satisfy and ,calculate ， S12, Calculation hour, exist Approximate value of the first derivative of a point S13, Calculation hour, exist Approximate value of the second derivative of a point S14, Calculation hour, exist Approximate curvature of a point 。 8. The apparatus according to claim 7, characterized in that, The flight phase determination module calculates the curvature of the time-current curve to determine the flight state transition time point, specifically: S15, where the current sequence is acquired in real time. ， ， The total number of data acquisitions at the current time is defined as negative for battery discharge current; S16, the curvature of the time-current curve is calculated using a high-precision non-equidistant five-point curvature method to dynamically distinguish flight phases: Phase 1 is the take-off phase, with the starting point being the initial data acquisition time point at takeoff. The endpoint is the curvature during the process where the first current is negative and its absolute value continuously decreases. Points that are negative and whose absolute values ​​change abruptly ， For the first time to meet The point in time; when the unit of time is seconds and the unit of current is milliamperes. The range of values ​​is ； Phase 2 is the cruise phase, starting from the next point after the end of Phase 1. The endpoint is the next current that is negative and its absolute value continuously increases, during which the curvature... Points that are negative and whose absolute values ​​change abruptly ,satisfy and ， The range of values ​​is Phase 3 is the landing phase, starting from the point following the end of Phase 1. ;end This marks the end of the flight phase, that is, the point where the current returns to 0 from a negative value.

9. The apparatus according to claim 8, characterized in that, The temperature-time variation determination module is specifically used for: S21, inputting the given estimated takeoff time. Cruise estimated time and the preset battery temperature sampling time interval After S22 and eVTOL takeoff, for ,collection ， ,in, ， The value range is 5 to 15 seconds. The value range is 5 to 12; S23, the value collected by S22. indivual Data points, as Fitting to obtain the rate of temperature rise and reference temperature S24, when ,for ,collection ， ,in, ， The value range is 5 to 15 seconds. The value range is 30 to 50. The value range is 1 to 100 seconds; S25, collected using S24. indivual Data points, as Fitting to obtain parameters and 。 10. The apparatus according to claim 9, characterized in that, The prediction module, specifically used for: S31, for ,in Temperature forecast is ,calculate S32, Input the given estimated landing phase time. S33, for Temperature forecast is ,calculate ,in, The method for determining the value is as follows: For ,calculate ;for ,calculate ;in, ， ， This is a time constant related to the intrinsic characteristics of the battery.

Images