Aircraft tractor low-temperature self-starting energy management method and system, terminal and medium

Abstract

The invention belongs to the technical field of vehicle energy management, and particularly discloses an aircraft tractor low-temperature self-starting energy management method and system, a terminal and a medium. Comprising the following steps: collecting power battery overall temperature, environment temperature and residual electric quantity data; when the environment temperature or the battery temperature is lower than a preset low-temperature threshold value, entering a low-temperature self-starting energy management mode; based on a heating rate model and a charging efficiency model, respectively calculating the time required for heating the battery to a dischargeable temperature and the time required for charging the battery to a target electric quantity, and predicting the starting time and the advanced starting time of the next operation based on a starting time prediction model; and automatically starting an engine to drive the range extender to generate power when the advanced starting moment is reached, and distributing the generated power to a battery heating and charging system according to a calculation result to complete battery activation and energy compensation. According to the invention, autonomous starting and energy optimization management of the aircraft tractor can be realized under a low-temperature condition, and the starting reliability and the operation efficiency of the vehicle in a cold region are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of vehicle energy management technology, specifically relating to a method, system, terminal, and medium for low-temperature self-starting energy management of aircraft tractors. Background Technology

[0002] Aircraft towing vehicles are one of the ground operation support equipment at airports, mainly used for towing, moving, and parking aircraft. In recent years, with the trend of electrification of civil aviation ground vehicles, pure electric or range-extended driven aircraft towing vehicles have gradually replaced traditional fuel-powered models.

[0003] However, pure electric tractors suffer from significant performance degradation in low-temperature environments. Low temperatures lead to a decrease in the chemical reaction rate of the power battery, an increase in internal resistance, and a reduction in charge and discharge efficiency, resulting in insufficient battery output power, reduced usable capacity, and prolonged charging time. In frigid regions or during early winter shifts, if both battery temperature and charge are low, the tractor often cannot start immediately, requiring the driver to manually heat it or preheat it with an external charger. This not only increases waiting time but also affects the efficiency of ground operations.

[0004] To improve operational reliability in low-temperature environments, some technical solutions propose generating electricity from the engine-driven range extender before vehicle startup to heat the battery. However, existing solutions generally rely on fixed startup times or manually set schedules, lacking intelligent predictive capabilities based on historical operating patterns and environmental conditions. They cannot dynamically determine when to start the engine and range extender in advance to perform the heating and charging process, which can easily lead to low energy utilization efficiency or insufficient preheating. Summary of the Invention

[0005] This invention addresses the problems in the prior art by providing a method, system, terminal, and medium for low-temperature self-starting energy management of aircraft tractors. This solves the problem that existing solutions in the background generally rely on fixed start-up times or manually set schedules, lack intelligent prediction capabilities based on historical operating patterns and environmental conditions, and cannot dynamically determine when to start the engine and range extender in advance to perform heating and power replenishment processes, which easily leads to low energy utilization efficiency or insufficient preheating.

[0006] The technical solution adopted in this invention is as follows: In a first aspect, this application provides a method for low-temperature self-starting energy management of an aircraft tractor, the method comprising the following steps: Step S1: Collect overall temperature data of the power battery, ambient temperature data of the vehicle, and remaining battery charge data; Step S2: When the ambient temperature or the overall battery temperature is determined to be lower than the preset low temperature threshold, the low temperature self-starting energy management mode is entered to perform battery activation and energy compensation before operation. Step S3: Calculate the time required for the battery to heat up to the dischargeable temperature and the time required to replenish the battery to the target capacity based on the heating rate model and the charging efficiency model, respectively. The start time of the next operation and the corresponding advance start time are predicted based on the start time prediction model. Step S4: When the early start time is reached, start the engine and drive the range extender to generate electricity, and distribute the generated power to the battery for heating and charging to perform battery activation and energy compensation.

[0007] Furthermore, in step S3, the heating rate model is used to establish a heating function of battery temperature changing with time based on battery thermal characteristic parameters, ambient temperature, overall battery temperature data and heating power, and to predict the time required for the battery to heat up to the dischargeable temperature. The charging efficiency model is used to establish a charging function for battery capacity over time based on battery state of charge, voltage and current characteristics, power generation, and energy conversion efficiency during the charging process, and to predict the time required for the battery to be recharged to the target capacity. The start-up time prediction model is used to establish a predictive relationship for the operation time series based on the vehicle's historical operation start time, calendar time, parking duration, ambient temperature changes and battery temperature decay patterns, and output the expected start time of the next operation and the corresponding advance start time.

[0008] Furthermore, the battery heating rate model is defined as:

[0009] in, Let be the overall battery temperature at time t. For ambient temperature, This is the initial battery temperature. For battery heating power, The equivalent heat capacity of the battery. The overall heat transfer coefficient between the battery and the environment; Solve The battery temperature is raised to the target discharge temperature. Time required ; The battery charging efficiency model is defined as follows:

[0010] in, The percentage of battery state of charge at time t. The initial state of charge, For charging energy conversion efficiency, For charging power, Convert the battery's rated capacity into energy units; Solve The battery was recharged to the target capacity. Time required .

[0011] Furthermore, the start-up time prediction model constructs a training dataset by acquiring historical operation data, and trains the model based on this dataset to establish a mapping relationship between operation time and environmental factors; the training data includes historical operation start time, parking duration, ambient temperature, battery temperature, battery charge and holiday attribute information; Feature extraction and parameter fitting are performed on the training data to form a start-up time prediction model for predicting the start time of the next operation. Input the parking duration corresponding to the date to be predicted, the current ambient temperature, battery temperature, and battery level into the trained model, and output the start time of the next operation. and The relatively long time data is used as the corresponding advance start time margin. The advance start time margin is left forward at the start time of the next operation to obtain the automatic start time of the engine and range extender.

[0012] Furthermore, it also includes the following steps: Step S5: During execution, the parameters of the heating rate model, charging efficiency model, and start-up time prediction model are updated based on real-time feedback of temperature and power, and the heating power and charging power are rolled over and corrected.

[0013] Furthermore, during the real-time feedback update process, the parameters of the heating rate model, charging efficiency model, and start-up time prediction model are continuously corrected through online learning. During each execution of low-temperature self-start energy management, actual operating data such as battery temperature changes, battery charging and discharging processes, and start-up time are acquired. This data is compared with the model prediction results, and the model parameters are adjusted according to the deviation. The heating rate model is modified based on the actual heating curve to adjust the battery thermal conductivity and heating power sensitivity. The charging efficiency model corrects the charging power utilization rate and energy conversion efficiency based on the actual charging rate. The start-up time prediction model updates the weight parameters of operation time and environmental variables based on the difference between the predicted start-up time and the actual start-up time.

[0014] Secondly, this application provides a low-temperature self-starting energy management system for an aircraft towing vehicle, used to implement the low-temperature self-starting energy management method for an aircraft towing vehicle as described in the first aspect. The system includes a power battery, an engine, a range extender, a battery heating system, a charging system, an ambient temperature sensor, an energy management and control system, and signal and power connection lines. The output terminal of the power battery is electrically connected to the battery heating system and the charging system to provide electrical energy; The engine's output shaft is connected to the range extender's input shaft. The range extender's electrical output terminals are electrically connected to the battery heating system, charging system, and the power battery's input terminals, respectively, to supply power to the battery and heating system when the engine is running. An ambient temperature sensor is installed on the exterior of the vehicle to collect ambient temperature signals; The energy management and control system is connected to the ambient temperature sensor, power battery, battery heating system, charging system, engine and range extender signals respectively, and is used to monitor and control temperature, power and energy flow.

[0015] Furthermore, the energy management and control system includes: The data acquisition module is used to obtain the overall battery temperature, ambient temperature, and remaining battery power. The status determination module is used to trigger the low-temperature self-starting energy management process when the ambient temperature or battery temperature is detected to be lower than a preset threshold. The energy assessment module is used to execute the heating rate model and charging efficiency model to calculate the time required for battery heating and recharging. The timing prediction module is used to predict the start time of the next operation and determine the early start time based on the start time prediction model. The execution control module is used to control the engine to start and drive the range extender to generate electricity at the early start time, and distribute the generated power to the battery heating system and charging system according to the calculation results. The adaptive correction module is used to update the parameters of the heating rate model, charging efficiency model, and start-up time prediction model based on real-time feedback of temperature and power during execution, and to perform rolling corrections on heating power and charging power.

[0016] Thirdly, this application provides a terminal, including: Memory for storing the aircraft tractor's low-temperature self-starting energy management program; A processor is configured to execute the steps of the aircraft tractor cryogenic self-starting energy management method as described in the first aspect when performing the aircraft tractor cryogenic self-starting energy management device.

[0017] Fourthly, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aircraft tractor low-temperature self-starting energy management method as described in the first aspect.

[0018] As can be seen from the above technical solutions, the advantages of the present invention are: By modeling and predicting the energy management of power batteries under low-temperature conditions, intelligent start-up and energy self-regulation of aircraft towing vehicles in cold environments have been achieved. Compared with existing technologies, this invention can automatically analyze the trends of ambient temperature, battery temperature, and charge change during vehicle parking, and determine the optimal start-up time of the engine and range extender without manual intervention. This allows the vehicle to complete the battery warm-up and recharging process before planned operations, significantly improving the start-up success rate and operational continuity under low-temperature conditions.

[0019] By establishing a heating rate model, battery thermal characteristic parameters, ambient temperature, and heating power are transformed into calculable temperature change functions. This allows the system to accurately predict the time required for the battery to reach its dischargeable temperature, thus avoiding overheating or underheating problems inherent in traditional heating control and improving energy utilization. The charging efficiency model, based on battery state of charge, voltage and current characteristics, and energy conversion efficiency, can accurately assess the duration of the charging process, enabling more rational allocation of the range extender's output power and reducing redundant charging and energy waste.

[0020] The start-up time prediction model is trained using historical operation patterns and environmental characteristic data. It can adaptively predict the start time of the next operation based on the parking time, changes in ambient temperature, battery temperature decay, and holiday patterns, and dynamically adjust the start-up time in advance to achieve intelligent coordinated start-up control of the engine and range extender, thereby effectively avoiding the uncertainty and inaccuracy caused by manually setting the start-up time.

[0021] By coupling the three types of models mentioned above into a unified energy management logic, the model parameters are continuously corrected based on real-time feedback of temperature and battery charge during execution. This enables the system to continuously adapt to environmental changes and battery state fluctuations, maintaining prediction accuracy and control stability. This method achieves integrated intelligent management of power battery preheating, energy compensation, and engine start-up control in low-temperature environments, significantly improving the reliability, energy efficiency, and automation level of aircraft towing vehicles, and has broad engineering application value. Attached Figure Description

[0022] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying 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 This is a flowchart illustrating the steps of the low-temperature self-starting energy management method for aircraft tractors in the embodiment. Detailed Implementation

[0024] 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, and 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] Please see Figure 1 As shown, the present invention provides a method for low-temperature self-starting energy management of an aircraft tractor, comprising the following steps: Step S1: Collect overall temperature data of the power battery, ambient temperature data of the vehicle, and remaining battery charge data; In practical implementation, the temperature values ​​of multiple points on the power battery module can be collected in real time through a temperature sensor array built into the vehicle. The overall battery temperature is obtained through weighted averaging or segmented statistics. The ambient temperature is collected by a temperature sensor installed on the outside of the vehicle. The remaining charge is calculated from the state of charge (SOC) parameter output by the battery management system. The vehicle performs this data collection process periodically in standby mode, with each collection interval set to 1 to 5 minutes to ensure accurate reflection of the battery's true thermal state and energy level under different climatic conditions. In this embodiment, the sampling period is 2 minutes, and the recorded data includes three parameters: battery pack temperature, ambient temperature, and SOC, which are used for subsequent model calculations.

[0026] Step S2: When the ambient temperature or the overall battery temperature is determined to be lower than the preset low temperature threshold, the low temperature self-starting energy management mode is entered to perform battery activation and energy compensation before operation. In practical applications, the low-temperature threshold can be set to 0°C or dynamically adjusted between -5°C and 5°C based on the battery material performance. When the detected temperature is below this threshold, the system automatically switches to low-temperature management mode. At this time, the energy management system is no longer in standby mode but enters the active calculation and scheduling phase. This mode can be automatically triggered at night or after long-term parking without driver intervention. In this embodiment, when the detected battery temperature is -8°C, the system immediately enters low-temperature mode, preparing to execute subsequent prediction and start-up decision processes.

[0027] Step S3: Calculate the time required for the battery to heat up to the dischargeable temperature and the time required to replenish the battery to the target capacity based on the heating rate model and the charging efficiency model, respectively. The start time of the next operation and the corresponding advance start time are predicted based on the start time prediction model. In practice, the system starts from the battery temperature and charge status obtained in the previous step, and calls the heating rate model and charging efficiency model stored in the control system to calculate the time required for heating and recharging, respectively. The heating model obtains the battery's thermal inertia parameters through offline calibration, and the heating power is automatically adjusted according to the temperature difference. The charging model estimates the time required to reach the target SOC by combining the current SOC and voltage curve. The start-up time prediction model extracts time series features from historical operation records, including the start time, parking duration, season, and ambient temperature information of past operations. After training, the model can output the expected start time of the next operation and the corresponding advance start time, enabling the system to complete start-up preparation without human intervention. In this example, by training the model with nearly a month's worth of operation data, the system predicts that the operation time for Monday morning shift is 8:00, and calculates that the engine should be started at 7:35 to complete the battery heating and recharging process.

[0028] Step S4: When the early start time is reached, start the engine and drive the range extender to generate electricity, and distribute the generated power to the battery for heating and charging to perform battery activation and energy compensation.

[0029] In practical implementation, the parameters of the heating rate model can be obtained through vehicle experiment calibration, such as recording battery heating curves under different ambient temperatures and fitting a heating rate constant; the charging efficiency model obtains the energy conversion coefficient by measuring the SOC rise curve under different charging powers; the start-up time prediction model can establish a mapping relationship using multiple regression or machine learning algorithms and be retrained periodically using the latest operating records. In the embodiment, the system automatically updates the model parameters after two weeks of operation in winter, reducing the heating prediction error from ±4 minutes to ±1 minute.

[0030] In some embodiments, in step S3, the heating rate model is used to establish a heating function of battery temperature changing with time based on battery thermal characteristic parameters, ambient temperature, overall battery temperature data and heating power, and to predict the time required for the battery to heat up to the dischargeable temperature. The charging efficiency model is used to establish a charging function for battery capacity over time based on battery state of charge, voltage and current characteristics, power generation, and energy conversion efficiency during the charging process, and to predict the time required for the battery to be recharged to the target capacity. The start-up time prediction model is used to establish a predictive relationship for the operation time series based on the vehicle's historical operation start time, calendar time, parking duration, ambient temperature changes and battery temperature decay patterns, and output the expected start time of the next operation and the corresponding advance start time.

[0031] In practical implementation, the parameters of the heating rate model can be obtained through vehicle experiment calibration, such as recording battery heating curves under different ambient temperatures and fitting a heating rate constant; the charging efficiency model obtains the energy conversion coefficient by measuring the SOC rise curve under different charging powers; the start-up time prediction model can establish a mapping relationship using multiple regression or machine learning algorithms and be retrained periodically using the latest operating records. In the embodiment, the system automatically updates the model parameters after two weeks of operation in winter, reducing the heating prediction error from ±4 minutes to ±1 minute.

[0032] In some embodiments, the battery temperature rise rate model is defined as:

[0033] in, Let be the overall battery temperature at time t. For ambient temperature, This is the initial battery temperature. For battery heating power, The equivalent heat capacity of the battery. The overall heat transfer coefficient between the battery and the environment; Solve The battery temperature is raised to the target discharge temperature. Time required ; The battery charging efficiency model is defined as follows:

[0034] in, The percentage of battery state of charge at time t. The initial state of charge, For charging energy conversion efficiency, For charging power, Convert the battery's rated capacity into energy units; Solve The battery was recharged to the target capacity. Time required .

[0035] During implementation, the control system calculates the required heating and charging time in real time based on the aforementioned model and dynamically corrects parameters by reading sensor data. For example, when the ambient temperature drops significantly or the battery's internal impedance increases, the system automatically adjusts the heating power and target time. In the embodiment, the vehicle was tested in an environment of -10°C. The heating model calculated an expected heating time of 24 minutes, and the actual measured completion time was 25 minutes, with the deviation controlled within 4%, verifying the reliability of the model.

[0036] In some embodiments, the start-up time prediction model constructs a training dataset by acquiring historical operation data, and trains the model based on the dataset to establish a mapping relationship between operation time and environmental factors; the training data includes historical operation start time, parking duration, ambient temperature, battery temperature, battery charge and holiday attribute information; Feature extraction and parameter fitting are performed on the training data to form a start-up time prediction model for predicting the start time of the next operation. Input the parking duration corresponding to the date to be predicted, the current ambient temperature, battery temperature, and battery level into the trained model, and output the start time of the next operation. and The relatively long time data is used as the corresponding advance start time margin. The advance start time margin is left forward at the start time of the next operation to obtain the automatic start time of the engine and range extender.

[0037] In practical implementation, historical data can be automatically recorded and periodically uploaded through the vehicle management system for model training. The training phase can be performed on a backend server, using least squares regression or gradient learning algorithms to obtain weight parameters. The inference phase is executed on the vehicle, taking current environmental and battery status data as input and outputting startup prediction results. In this example, the system uses the most recent 60 days of operational data for training, and the model's prediction error on the validation set is less than ±5 minutes, achieving high-precision prediction of operating time.

[0038] In some embodiments, the following steps are also included: Step S5: During execution, the parameters of the heating rate model, charging efficiency model, and start-up time prediction model are updated based on real-time feedback of temperature and power, and the heating power and charging power are rolled over and corrected.

[0039] During implementation, the vehicle continuously collects temperature and power change curves while in operation. When a deviation is detected between the model's predicted value and the actual measured value, the system automatically adjusts relevant parameters, such as correcting the heating rate constant or energy efficiency factor, thereby achieving real-time adaptive control. In this embodiment, when the actual heating rate is detected to be 10% lower than the predicted value, the system automatically increases the heating power to 1.1 times the original setting and simultaneously updates the model parameters to ensure more accurate predictions in the next iteration.

[0040] In some embodiments, during the real-time feedback update process, the parameters of the heating rate model, the charging efficiency model, and the start-up time prediction model are continuously corrected through online learning. During each execution of low-temperature self-start energy management, actual operating data such as battery temperature changes, battery charging and discharging processes, and start-up time are acquired. This data is compared with the model prediction results, and the model parameters are adjusted according to the deviation. The heating rate model is modified based on the actual heating curve to adjust the battery thermal conductivity and heating power sensitivity. The charging efficiency model corrects the charging power utilization rate and energy conversion efficiency based on the actual charging rate. The start-up time prediction model updates the weight parameters of operation time and environmental variables based on the difference between the predicted start-up time and the actual start-up time.

[0041] In practical implementation, the system can use a sliding window to save the most recent running data. After each low-temperature start-up task is completed, the system automatically calls the update algorithm to correct the parameters, realizing the self-evolution of the model. In the example, after the vehicle has been running continuously for ten working days, the system model has completed five parameter updates through an online learning mechanism, which has gradually reduced the start-up prediction error from the initial ±6 minutes to ±2 minutes, significantly improving the adaptive accuracy of energy management.

[0042] In some embodiments, this application provides a cryogenic self-starting energy management system for aircraft towing vehicles, used to implement a cryogenic self-starting energy management method for aircraft towing vehicles, the system comprising: Power battery, engine, range extender, battery heating system, charging system, ambient temperature sensor, energy management and control system, and signal and power connection lines; In practical implementation, the system is installed on a range-extended aircraft tractor. The power battery is a high-energy-density lithium-ion battery pack, and its rated capacity can be configured according to the traction power requirements. The engine and range extender together constitute an auxiliary power generation unit, used to provide energy support for the battery in low-temperature or low-charge conditions. The battery heating system includes a heating film, a liquid-cooled heating circuit, or a PTC heating unit, which can automatically select the operating mode according to the ambient temperature. The charging system is connected in parallel with the vehicle's DC bus to achieve bidirectional energy flow. The signal and power connection lines include a high-voltage DC bus, a CAN communication line, and a safety relay control line, used to realize energy transmission and signal interaction. In this embodiment, the vehicle is equipped with a 120kWh rated capacity power battery, a 60kW range extender, and a liquid heating circuit, and its overall layout takes into account both low-temperature operation and safety isolation requirements.

[0043] The output terminal of the power battery is electrically connected to the battery heating system and the charging system to provide electrical energy; In practical applications, the output terminal of the power battery is connected in parallel with the heating and charging systems via a high-voltage bus. The control system can adjust the current distribution ratio according to the operating mode. During normal operation, the battery supplies power to the drive system; in low-temperature management mode, the battery prioritizes supplying power to the heating system to maintain its own temperature within a safe range. In this embodiment, when the battery temperature is below 0°C, the control system automatically switches to preheating mode, and the current distribution ratio is adjusted from drive:heating = 1:3 to 0:1 to ensure rapid battery heating.

[0044] The engine's output shaft is connected to the range extender's input shaft. The range extender's electrical output terminals are electrically connected to the battery heating system, charging system, and the power battery's input terminals, respectively, to supply power to the battery and heating system when the engine is running. In implementation, a low-temperature easy-start diesel engine is used, and its output shaft is connected to the input shaft of a permanent magnet synchronous generator via a flexible coupling, forming a mechanical-to-electrical energy conversion chain. The DC power output from the range extender is regulated by a power conversion module and simultaneously fed into the battery heating and charging systems, achieving power generation and energy recycling. In this embodiment, after the engine starts, it drives the generator to provide a rated power of 40kW, of which 25kW is used for battery charging and 15kW for battery heating. The system can dynamically adjust the distribution ratio according to the real-time temperature.

[0045] An ambient temperature sensor is installed on the exterior of the vehicle to collect ambient temperature signals; In practical implementation, the ambient temperature sensor can be deployed on the front protective cover or the outer side of the chassis of the vehicle, employing a digital temperature sampling module and communicating with the control system via CAN or LIN bus. To prevent thermal radiation interference, the sensor housing is coated with a heat-insulating coating and equipped with a windproof cover. In this embodiment, the sensor sampling accuracy is ±0.3℃, the refresh cycle is 1 second, and it can stably provide ambient temperature data to support the calculation of the heating rate model.

[0046] The energy management and control system is connected to the ambient temperature sensor, power battery, battery heating system, charging system, engine and range extender signals respectively, and is used to monitor and control temperature, power and energy flow.

[0047] In practical applications, the energy management and control system, acting as a central control unit, contains a multi-core processor and a data bus interface, enabling it to simultaneously process sensor data and control commands. Its software architecture comprises four core threads: data acquisition, decision logic, model calculation, and execution control, used to achieve real-time temperature and power monitoring and energy distribution adjustment. In this embodiment, the system performs data refresh and control output with a 100ms cycle, ensuring that the response time of each subsystem does not exceed 500ms, thereby meeting the rapid self-starting requirements in low-temperature startup scenarios.

[0048] In some embodiments, the energy management and control system includes: The data acquisition module is used to obtain the overall battery temperature, ambient temperature, and remaining battery power. During implementation, the data acquisition module aggregates information through a multi-channel temperature acquisition interface, SOC sensing unit, and communication bus, and performs filtering and correction on the raw data to ensure the accuracy of the model input. In this embodiment, the acquisition module updates the data every 2 seconds and writes the results to the system cache for subsequent modeling calculations.

[0049] The status determination module is used to trigger the low-temperature self-starting energy management process when the ambient temperature or battery temperature is detected to be lower than a preset threshold. This module invokes judgment logic to automatically activate the low-temperature mode when the ambient temperature is below a threshold or the battery temperature is below a set lower limit. Simultaneously, it freezes non-essential power-consuming devices and initiates the startup decision process. In this embodiment, the threshold is set to 2°C. When the vehicle's parking temperature drops to 0°C, the system automatically enters a self-starting preparation state without manual intervention.

[0050] The energy assessment module is used to execute the heating rate model and charging efficiency model to calculate the time required for battery heating and recharging. During implementation, this module calls a calibrated mathematical model to calculate the estimated time for completing the heating and recharging tasks based on the battery's current temperature, charge level, and environmental parameters, providing a decision-making basis for the timing prediction module. In this embodiment, the module outputs a heating time of 18 minutes and a recharging time of 20 minutes, and the system selects the maximum value as the overall preheating duration.

[0051] The timing prediction module is used to predict the start time of the next operation and determine the early start time based on the start time prediction model. In practice, this module reads the vehicle's historical operation records, combines the current date, parking duration, and battery temperature decay patterns to predict the start time of the next operation, and calculates the corresponding advance start point. In this example, the system predicts the first start time of the next day to be 7:50 based on data from the previous 60 days, and determines the advance start time to be 7:30.

[0052] The execution control module is used to control the engine to start and drive the range extender to generate electricity at the early start time, and distribute the generated power to the battery heating system and charging system according to the calculation results. In practice, after the control module issues a start signal, the engine automatically ignites and enters the range-extending working state. The control system determines the power allocation ratio based on the calculation results of the temperature rise rate model and the charging efficiency model, and adjusts the current output under real-time feedback. In this embodiment, the initial power allocation ratio is 1:1. When the battery temperature rises to the target value, the system automatically transfers all power to the charging path to complete energy compensation.

[0053] The adaptive correction module is used to update the parameters of the heating rate model, charging efficiency model, and start-up time prediction model based on real-time feedback of temperature and power during execution, and to perform rolling corrections on heating power and charging power.

[0054] During implementation, the adaptive correction module compares the data collected during operation with the model's predicted values. When the error exceeds a set threshold, it automatically updates the model parameters, ensuring the system maintains prediction accuracy under different temperatures and usage frequencies. In this embodiment, the system automatically records operational data after each task, and completes a model iteration update after five consecutive tasks, reducing the battery temperature rise prediction error from ±5 minutes to ±1 minute, significantly improving the stability and energy utilization of low-temperature self-starting.

[0055] In some embodiments, this application provides a terminal, including: Memory for storing the aircraft tractor's low-temperature self-starting energy management program; A processor is used to execute the steps of the aircraft tractor's cryogenic self-starting energy management method when performing the aircraft tractor cryogenic self-starting energy management system.

[0056] In some embodiments, this application provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the aircraft tractor low-temperature self-starting energy management method.

[0057] The above description is merely a preferred embodiment of one or more embodiments of this specification and is not intended to limit the scope of one or more embodiments of this specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this specification should be included within the protection scope of one or more embodiments of this specification.

Claims

1. A method for low-temperature self-starting energy management of an aircraft tractor, characterized in that, Includes the following steps: Step S1: Collect overall temperature data of the power battery, ambient temperature data of the vehicle, and remaining battery charge data; Step S2: When the ambient temperature or the overall battery temperature is determined to be lower than the preset low temperature threshold, the low temperature self-starting energy management mode is entered to perform battery activation and energy compensation before operation. Step S3: Calculate the time required for the battery to heat up to the dischargeable temperature and the time required to replenish the battery to the target capacity based on the heating rate model and the charging efficiency model, respectively. The start time of the next operation and the corresponding advance start time are predicted based on the start time prediction model. Step S4: When the early start time is reached, start the engine and drive the range extender to generate electricity, and distribute the generated power to the battery for heating and charging to perform battery activation and energy compensation.

2. The method for low-temperature self-starting energy management of aircraft tractors according to claim 1, characterized in that, In step S3, the heating rate model is used to establish a heating function of battery temperature changing with time based on battery thermal characteristic parameters, ambient temperature, overall battery temperature data and heating power, and to predict the time required for the battery to heat up to the dischargeable temperature. The charging efficiency model is used to establish a charging function for battery capacity over time based on battery state of charge, voltage and current characteristics, power generation, and energy conversion efficiency during the charging process, and to predict the time required for the battery to be recharged to the target capacity. The start-up time prediction model is used to establish a predictive relationship for the operation time series based on the vehicle's historical operation start time, calendar time, parking duration, ambient temperature changes and battery temperature decay patterns, and output the expected start time of the next operation and the corresponding advance start time.

3. The method for low-temperature self-starting energy management of an aircraft tractor according to claim 1 or 2, characterized in that, The battery heating rate model is defined as follows: in, Let be the overall battery temperature at time t. For ambient temperature, This is the initial battery temperature. For battery heating power, The equivalent heat capacity of the battery. The overall heat transfer coefficient between the battery and the environment; Solve The battery temperature is raised to the target discharge temperature. Time required ; The battery charging efficiency model is defined as follows: in, The percentage of battery state of charge at time t. The initial state of charge, For charging energy conversion efficiency, For charging power, Convert the battery's rated capacity into energy units; Solve The battery was recharged to the target capacity. Time required .

4. The low-temperature self-starting energy management method for aircraft tractors according to claim 3, characterized in that, The start-up time prediction model constructs a training dataset by acquiring historical operation data, and trains the model based on this dataset to establish the mapping relationship between operation time and environmental factors. The training data includes historical operation start time, parking duration, ambient temperature, battery temperature, battery charge, and holiday attribute information. Feature extraction and parameter fitting are performed on the training data to form a start-up time prediction model for predicting the start time of the next operation. Input the parking duration corresponding to the date to be predicted, the current ambient temperature, battery temperature, and battery level into the trained model, and output the start time of the next operation. and The relatively long time data is used as the corresponding advance start time margin. The advance start time margin is left forward at the start time of the next operation to obtain the automatic start time of the engine and range extender.

5. The method for low-temperature self-starting energy management of aircraft tractors according to claim 1, characterized in that, It also includes the following steps: Step S5: During execution, the parameters of the heating rate model, charging efficiency model, and start-up time prediction model are updated based on real-time feedback of temperature and power, and the heating power and charging power are rolled over and corrected.

6. The method for low-temperature self-starting energy management of an aircraft tractor according to claim 5, characterized in that, During the real-time feedback update process, the parameters of the heating rate model, charging efficiency model, and start-up time prediction model are continuously corrected through online learning. During each execution of low-temperature self-start energy management, actual operating data such as battery temperature changes, battery charging and discharging processes, and start-up time are acquired. This data is compared with the model prediction results, and the model parameters are adjusted according to the deviation. The heating rate model is modified based on the actual heating curve to adjust the battery thermal conductivity and heating power sensitivity. The charging efficiency model corrects the charging power utilization rate and energy conversion efficiency based on the actual charging rate. The start-up time prediction model updates the weight parameters of operation time and environmental variables based on the difference between the predicted start-up time and the actual start-up time.

7. A low-temperature self-starting energy management system for aircraft tractors, used to implement the low-temperature self-starting energy management method for aircraft tractors as described in claim 1, characterized in that, The system includes a power battery, an engine, a range extender, a battery heating system, a charging system, an ambient temperature sensor, an energy management and control system, and signal and power connection lines. The output terminal of the power battery is electrically connected to the battery heating system and the charging system to provide electrical energy; The engine's output shaft is connected to the range extender's input shaft. The range extender's electrical output terminals are electrically connected to the battery heating system, charging system, and the power battery's input terminals, respectively, to supply power to the battery and heating system when the engine is running. An ambient temperature sensor is installed on the exterior of the vehicle to collect ambient temperature signals; The energy management and control system is connected to the ambient temperature sensor, power battery, battery heating system, charging system, engine and range extender signals respectively, and is used to monitor and control temperature, power and energy flow.

8. The aircraft tractor low-temperature self-starting energy management system according to claim 7, characterized in that, The energy management and control system includes: The data acquisition module is used to obtain the overall battery temperature, ambient temperature, and remaining battery power. The status determination module is used to trigger the low-temperature self-starting energy management process when the ambient temperature or battery temperature is detected to be lower than a preset threshold. The energy assessment module is used to execute the heating rate model and charging efficiency model to calculate the time required for battery heating and recharging. The timing prediction module is used to predict the start time of the next operation and determine the early start time based on the start time prediction model. The execution control module is used to control the engine to start and drive the range extender to generate electricity at the early start time, and distribute the generated power to the battery heating system and charging system according to the calculation results. The adaptive correction module is used to update the parameters of the heating rate model, charging efficiency model, and start-up time prediction model based on real-time feedback of temperature and power during execution, and to perform rolling corrections on heating power and charging power.

9. A terminal, characterized in that, include: Memory for storing the aircraft tractor's low-temperature self-starting energy management program; A processor is configured to implement the steps of the aircraft tractor low-temperature self-starting energy management method as described in claim 1 when executing the aircraft tractor low-temperature self-starting energy management device.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the low-temperature self-starting energy management method for aircraft tractors as described in claim 1.

Images