A power supply control method and device, equipment and storage medium

Abstract

This application relates to the field of hydrogen monitoring and energy management technology, and discloses a collaborative power supply control method, device, equipment, and storage medium. The method includes: initializing the initial hydrogen quantity and hydrogen replacement judgment threshold of the solid-state hydrogen storage device to obtain initial operating baseline parameters; calibrating and mapping the operating condition test data to obtain a power-hydrogen consumption calibration parameter set; synchronously collecting the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time operating sequence dataset; combining the calibration parameter set to perform hydrogen consumption prediction calculation to obtain the cumulative total hydrogen consumption and real-time operating condition correction coefficient; converting the remaining hydrogen quantity data and theoretical remaining driving range data to obtain the remaining driving range data; and performing adaptive power allocation based on the real-time driving conditions, remaining hydrogen quantity, and remaining driving range data to obtain a collaborative power supply control strategy for the hydrogen fuel cell and lithium battery. This application significantly improves the accuracy of hydrogen quantity detection and driving range efficiency.

Description

Technical Field

[0001] This application relates to the field of hydrogen monitoring and energy management technology, and in particular to a collaborative power supply control method, device, equipment and storage medium. Background Technology

[0002] With the rapid development of the hydrogen energy industry and the growing demand for green short-distance travel, hydrogen-powered shared bicycles are gradually becoming an important development direction in the field of urban shared mobility, which puts forward higher application requirements for hydrogen storage safety, hydrogen quantity monitoring accuracy and vehicle energy management efficiency.

[0003] Currently, hydrogen content monitoring for hydrogen-powered two-wheeled vehicles mainly falls into two categories: high-pressure gaseous hydrogen storage pressure sensing and solid-state hydrogen storage weight sensing. High-pressure gaseous hydrogen storage relies on high-pressure cylinders and pressure sensors to infer the remaining hydrogen content. However, the high-pressure environment presents inherent safety risks, and the equipment manufacturing cost and maintenance threshold are high, making it unsuitable for the high-frequency, widespread civilian use scenarios of shared bicycles. Solid-state hydrogen storage weight sensing calculates the remaining hydrogen content by detecting the total weight of the device using a weight sensor. However, the rated hydrogen storage capacity is a very small percentage of the device's weight, and it is susceptible to interference from road bumps, vehicle load, and driving posture, resulting in large detection errors and inaccurate hydrogen content assessments. Furthermore, existing solutions generally suffer from a disconnect between hydrogen content monitoring and energy management, a simplistic hydrogen replacement logic, and static range estimation, making it difficult to guarantee vehicle operational reliability and large-scale maintenance efficiency.

[0004] Therefore, how to improve the accuracy of hydrogen monitoring under a low-pressure and safe hydrogen storage architecture, achieve synergistic optimization of hydrogen monitoring and energy management, and adapt to the large-scale operation and maintenance needs of shared bicycles are the technical problems that urgently need to be solved. Summary of the Invention

[0005] In view of this, the collaborative power supply control method, apparatus, device, and storage medium provided in this application can improve the accuracy of hydrogen quantity monitoring under a low-pressure and safe hydrogen storage architecture, achieve collaborative optimization of hydrogen quantity monitoring and energy management, and adapt to the large-scale operation and maintenance needs of shared bicycles. The collaborative power supply control method, apparatus, device, and storage medium provided in this application are implemented as follows: This application provides a cooperative power supply control method, including: Initialize the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters. The operating condition test data is calibrated and mapped to obtain a set of power-hydrogen consumption calibration parameters. The output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle are collected and processed synchronously to obtain a real-time runtime sequence dataset. The hydrogen consumption prediction calculation is performed on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient. The remaining hydrogen quantity is converted by the initial operating baseline parameters, the cumulative total hydrogen consumption and the real-time operating condition correction coefficient to obtain the remaining hydrogen quantity data and the theoretical remaining range data. Adaptive power allocation processing is performed on real-time driving condition data, remaining hydrogen quantity data, and theoretical remaining range data to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

[0006] In some embodiments, the calibration mapping process of the operating condition test data to obtain a power-hydrogen consumption calibration parameter set includes: The test data of hydrogen fuel cells are calibrated according to hydrogen consumption to obtain a first mapping relationship, which is the mapping relationship between fuel cell output power and hydrogen consumption per unit time. The test data of the drive motor are subjected to hydrogen consumption equivalent calibration to obtain a second mapping relationship, which is the mapping relationship between the motor input power and the hydrogen consumption per unit time. The test data under typical driving conditions are processed by range conversion and correction to obtain the range correction coefficient; The first mapping relationship, the second mapping relationship, and the range correction coefficient are integrated and stored to obtain a power-hydrogen consumption calibration parameter set.

[0007] In some embodiments, the synchronous acquisition and processing of the hydrogen fuel cell output power, drive motor input power, and actual vehicle mileage to obtain a real-time runtime sequence dataset includes: The electrical power of the hydrogen fuel cell output circuit is collected and processed at a fixed frequency to obtain the time-series data of the fuel cell output power. The electrical power of the drive motor power supply circuit is collected and processed synchronously at the same frequency to obtain the timing data of the motor input power; The vehicle's location and driving status data are cumulatively and statistically processed to obtain the actual mileage data; The time-series data of the fuel cell output power, the time-series data of the motor input power, and the actual driving mileage are time-aligned and integrated to obtain a real-time runtime timing dataset.

[0008] In some embodiments, the step of performing hydrogen consumption prediction calculations on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient includes: The real-time runtime sequence dataset is subjected to sliding filtering and feature splitting to obtain the fuel cell output power sequence and the motor input power sequence; The fuel cell output power sequence, the motor input power sequence, and the power-hydrogen consumption calibration parameter set are input into a preset hydrogen consumption prediction model for inference processing to obtain the total hydrogen consumption per unit time. The total hydrogen consumption per unit time is accumulated throughout the entire operation to obtain the cumulative total hydrogen consumption. The dynamic variation characteristics of the fuel cell output power sequence and the dynamic variation characteristics of the motor input power sequence are respectively processed by operating condition identification and coefficient matching to obtain real-time operating condition correction coefficients.

[0009] In some embodiments, the process of converting the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient into remaining hydrogen data to obtain remaining hydrogen data and theoretical remaining range data includes: The difference between the initial hydrogen quantity in the initial operating baseline parameters and the cumulative total hydrogen consumption is calculated to obtain the remaining hydrogen quantity data. The remaining hydrogen data and the real-time operating condition correction coefficient are dynamically converted into driving range data to obtain the theoretical remaining driving range data.

[0010] In some embodiments, the adaptive power allocation processing of real-time driving condition data, remaining hydrogen quantity data, and theoretical remaining range data to obtain a coordinated power supply control strategy for the hydrogen fuel cell and lithium battery includes: Load feature extraction and scene classification are performed on real-time driving condition data to obtain driving condition judgment results; The driving condition determination result and the remaining hydrogen data are processed to match the power supply mode, and an initial allocation scheme for fuel cell output power and lithium battery power supply and discharge is obtained. The theoretical remaining range data is subjected to low range threshold verification processing to obtain motor power limitation correction parameters; The initial allocation scheme and the motor power limitation correction parameters are integrated and optimized to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

[0011] In some embodiments, the initial configuration process for the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid-state hydrogen storage device to obtain initial operating baseline parameters includes: The initial hydrogen weight parameters of the solid hydrogen storage device are entered and configured to obtain the initial hydrogen quantity baseline parameters. The hydrogen exchange judgment threshold is classified, decomposed, and parameter set to obtain dual-index hydrogen exchange judgment parameters. The initial hydrogen content benchmark parameter is converted to the preset basic range standard to obtain the theoretical total range parameter; The initial hydrogen quantity baseline parameters, the dual-index hydrogen exchange determination parameters, and the theoretical total range parameters are integrated, stored, and processed to obtain the initial operating baseline parameters.

[0012] This application provides a cooperative power supply control device, comprising: The processing module is used to initialize and configure the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters. The processing module is also used to perform calibration mapping processing on the operating condition test data to obtain a power-hydrogen consumption calibration parameter set; The processing module is also used to synchronously collect and process the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time runtime sequence dataset. The processing module is also used to perform hydrogen consumption prediction calculation on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient. The conversion module is used to convert the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient into remaining hydrogen data to obtain remaining hydrogen data and theoretical remaining range data. The allocation module is used to perform adaptive power allocation processing on real-time driving condition data, the remaining hydrogen quantity data, and the theoretical remaining range data to obtain a coordinated power supply control strategy for the hydrogen fuel cell and the lithium battery.

[0013] The computer device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.

[0014] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method described in this application embodiment.

[0015] The collaborative power supply control method, device, equipment, and storage medium provided in this application embodiment initialize the initial hydrogen quantity and hydrogen replacement judgment threshold of the solid-state hydrogen storage device to obtain initial operating baseline parameters; calibrate and map the operating condition test data to obtain a power-hydrogen consumption calibration parameter set; synchronously collect the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time operating sequence dataset; combine the calibration parameter set to perform hydrogen consumption prediction calculation to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient; convert the remaining hydrogen quantity data and the theoretical remaining driving range data to obtain the remaining driving range data; and perform adaptive power allocation based on the real-time driving conditions, remaining hydrogen quantity, and remaining driving range data to obtain a collaborative power supply control strategy for the hydrogen fuel cell and lithium battery. This improves the accuracy of hydrogen quantity monitoring under a low-pressure and safe hydrogen storage architecture, achieves synergistic optimization of hydrogen quantity monitoring and energy management, and adapts to the large-scale operation and maintenance needs of shared bicycles, solving the technical problems mentioned in the background art. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A schematic diagram illustrating the implementation process of a coordinated power supply control method provided in this application embodiment; Figure 2 A schematic diagram illustrating the implementation process of obtaining a power-hydrogen consumption calibration parameter set provided in an embodiment of this application; Figure 3 This is a schematic diagram of a collaborative power supply control device provided in an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0019] The following description of some technologies involved in the embodiments of this application is provided to aid understanding and should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, some descriptions of well-known functions and structures are omitted in the following description.

[0020] This application applies to the energy management scenario of hydrogen-powered shared bicycles. The system consists of two parts: an on-board actuator and a cloud-based backend management system. The on-board actuator is equipped with a low-pressure solid-state hydrogen storage device, which weighs approximately 10 kg, has a rated hydrogen storage capacity of 80 g, and operates at a pressure not exceeding 2 MPa, thus requiring no high-pressure protection. The on-board actuator also includes a hydrogen fuel cell, a fuel cell output power sensor, a motor input power sensor, a lithium battery, a drive motor, an AI control module, a positioning and mileage statistics module, an on-board display screen, a power management module, and a 4G wireless data communication unit. The cloud-based backend management system includes a parameter configuration window, a data storage unit, and a hydrogen replacement reminder push unit. The gas outlet of the solid hydrogen storage device is connected to the gas inlet of the hydrogen fuel cell, providing hydrogen fuel for the fuel cell; the power output of the hydrogen fuel cell is divided into two paths, one connected to the charging end of the lithium battery, and the other connected to the input end of the power management module; the discharge end of the lithium battery is connected to the power supply end of the drive motor via the motor input power sensor; the AI ​​control module is bidirectionally connected to each sensor, the power management module, the vehicle display screen, and the wireless communication unit, and realizes data interaction with the cloud-based backend management terminal through the wireless communication unit.

[0021] Figure 1 This is a schematic diagram illustrating the implementation flow of a coordinated power supply control method provided in an embodiment of this application, including steps 101 to 106. Wherein, Figure 1 This is merely one execution order shown in the embodiments of this application and does not represent the only execution order of a cooperative power supply control method. Where the final result can be achieved, Figure 1 The steps shown can be performed in parallel or in reverse order.

[0022] Step 101: Initialize the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters.

[0023] In this embodiment, after replacing the solid-state hydrogen storage device, the initial hydrogen weight of the device installed in the vehicle is entered through the parameter configuration window of the cloud-based backend management terminal. The default value is 80 grams, which can be flexibly adjusted to different values ​​such as 75 grams or 80 grams based on the actual filling amount. Simultaneously, two types of threshold parameters are set for hydrogen replacement judgment: one is the threshold for the proportion of actual driving mileage to the theoretical total range, with a default value of 90%; the other is the lower limit threshold for the theoretical remaining range, with a default value of 5 kilometers. Both thresholds can be flexibly adjusted through the backend window according to operational needs. Based on the entered initial hydrogen weight and the preset basic range standard of one kilometer of range per gram of hydrogen, the system automatically calculates the theoretical total range corresponding to the device, which is 80 kilometers by default. The system integrates the initial hydrogen quantity parameters, the two types of hydrogen replacement judgment threshold parameters, and the theoretical total range parameters to generate initial operating baseline parameters, stores them in the cloud data storage unit, and simultaneously sends them to the corresponding vehicle's AI control module as the basis for all subsequent calculations and control logic.

[0024] Step 102: Perform calibration mapping processing on the operating condition test data to obtain a power-hydrogen consumption calibration parameter set.

[0025] In this embodiment, before the vehicles are put into mass operation, full-condition parameter calibration is completed in a laboratory bench environment. For the matching combination of solid-state hydrogen storage device, hydrogen fuel cell, lithium battery, and drive motor used in the target vehicle model, point-by-point tests are conducted covering the full power range of the hydrogen fuel cell from 0 watts to 500 watts and the full load range of the drive motor from 0 watts to 350 watts. The hydrogen consumption per unit time of the hydrogen fuel cell under different output power is recorded, establishing a corresponding mapping relationship between fuel cell output power and hydrogen consumption per unit time. Typical calibration values ​​include: 30 watts corresponding to 0.0015 grams per second, 50 watts corresponding to 0.0025 grams per second, 80 watts corresponding to 0.0040 grams per second, and 100 watts corresponding to 0.0050 grams per second. Interpolation calculation is supported for linear intervals. Simultaneously, the equivalent hydrogen consumption per unit time of the drive motor under different input power levels was recorded point by point, establishing a mapping relationship between motor input power and hydrogen consumption per unit time. Typical calibration values ​​include: 80 watts corresponding to 0.0024 grams per second, 100 watts to 0.0030 grams per second, 150 watts to 0.0045 grams per second, and 200 watts to 0.0060 grams per second. Interpolation calculation is supported within the linear interval. Furthermore, tests were conducted under various typical driving conditions, including constant speed on flat roads, acceleration uphill, coasting downhill, and idle start-stop, and range correction coefficients were calibrated for each condition. The correction coefficient for constant speed on flat roads was 1.0, for acceleration uphill was 1.2, and for descent was 0.8, used to correct the range estimation results under different road conditions. Finally, the two sets of power-hydrogen consumption mapping relationships and the range correction coefficients for each condition were integrated into a power-hydrogen consumption calibration parameter set and stored in the onboard AI control module.

[0026] Step 103: Synchronously collect and process the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time runtime sequence dataset.

[0027] In this embodiment, after the user unlocks the vehicle by scanning a code, the system powers on and starts. A dual power acquisition unit, consisting of a fuel cell output power sensor and a motor input power sensor, synchronously acquires data at the same frequency of 10 times per second. The fuel cell output power sensor is located in the power output circuit of the hydrogen fuel cell, acquiring the real-time electrical power value of the hydrogen fuel cell charging the lithium battery, generating continuous fuel cell output power time-series data. The motor input power sensor is located in the power supply circuit of the drive motor, acquiring the real-time electrical power value of the drive motor, generating continuous motor input power time-series data. Simultaneously, the positioning and mileage statistics module accumulates the vehicle's actual driving distance in real-time using BeiDou positioning signals, generating actual mileage data. The AI ​​control module performs time alignment and integration of the above three data streams every 0.1 seconds according to a unified timestamp, forming a complete real-time runtime sequence dataset with time tags, which is simultaneously used for hydrogen consumption calculation, operating condition identification, and mileage statistics.

[0028] Step 104: Perform hydrogen consumption prediction calculation on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient.

[0029] In this embodiment, the AI ​​control module inputs the real-time runtime time series dataset into the pre-trained AI hydrogen consumption prediction model and performs inference calculations based on the pre-stored power-hydrogen consumption calibration parameter set. First, the power time series data is processed using a moving average filter with three sampling points to remove high-frequency noise interference from road bumps and vehicle vibrations. Then, the filtered data is split into a fuel cell output power sequence and a motor input power sequence, while extracting power change rate and ambient temperature as auxiliary features. Based on the real-time values ​​of the two power sources, the model interpolates and matches the calibration mapping relationship. Simultaneously, it identifies vehicle acceleration, deceleration, start-stop, and other operating states based on the power change rate feature, outputting the total hydrogen consumption per unit time. The total hydrogen consumption is the sum of the hydrogen consumption at the fuel cell end and the equivalent hydrogen consumption at the motor load end. The system accumulates the hydrogen consumption per unit time every 0.1 seconds according to the vehicle's running time to obtain the cumulative total hydrogen consumption since the current hydrogen exchange. At the same time, the model identifies the current driving condition based on the dynamic change characteristics of the power sequence, matches the corresponding range correction coefficient, and outputs the real-time driving condition correction coefficient.

[0030] The AI ​​hydrogen consumption prediction model was trained using a combination of offline supervised pre-training and online incremental learning. In the offline phase, 120,000 labeled data points from laboratory bench tests were used as the basic training set, covering 12 typical driving conditions. Real-world driving data from 10 pilot vehicles were used as the validation set. The model was trained using a network structure with two layers of long short-term memory and two fully connected layers, and the relative prediction error on the test set was no higher than 3%. In the online phase, incremental fine-tuning was performed on a single vehicle using the actual total hydrogen consumption data from each hydrogen exchange. A full model update was performed monthly to correct systemic biases caused by fuel cell aging and individual device differences, ensuring that the hydrogen consumption calculation error remained stable at no higher than 5% throughout the entire lifecycle.

[0031] Step 105: Perform remaining hydrogen quantity conversion on the initial operating baseline parameters, cumulative total hydrogen consumption, and real-time operating condition correction coefficient to obtain remaining hydrogen quantity data and theoretical remaining range data.

[0032] In this embodiment, the AI ​​control module calls the initial hydrogen weight value from the initial operating baseline parameters, subtracts the cumulative total hydrogen consumption, and calculates the remaining hydrogen weight in the cylinder, i.e., the remaining hydrogen quantity. Then, based on the remaining hydrogen quantity, combined with the basic range standard of one kilometer per gram of hydrogen, it is multiplied by a real-time operating condition correction factor for dynamic calculation to obtain the theoretical remaining range data adapted to the current driving conditions. The calculated remaining hydrogen quantity data and the theoretical remaining range data are synchronously transmitted to the vehicle's display screen for real-time display, allowing riders to check at any time, and also serving as the core input parameters for adaptive energy management.

[0033] While calculating the remaining hydrogen capacity and driving range, the system simultaneously performs a dual-indicator fuzzy hydrogen swap judgment: The first indicator is the ratio of actual mileage to theoretical total range. This involves comparing the actual mileage value from the real-time runtime dataset with the mileage percentage threshold in the initial operating baseline parameters to determine if the actual mileage has reached 90% of the theoretical total range. The second indicator is the lower limit of the theoretical remaining range. This involves comparing the calculated theoretical remaining range data with the lower limit threshold in the initial operating baseline parameters to determine if the theoretical remaining range is less than or equal to 5 kilometers. When either indicator meets the trigger condition, the system immediately generates a hydrogen swap reminder message, including the vehicle number, real-time location, remaining hydrogen capacity, and remaining driving range data, and sends it to the maintenance personnel's terminal device via a cloud-based hydrogen swap reminder push unit.

[0034] Step 106: Adaptive power allocation processing is performed on real-time driving condition data, remaining hydrogen data, and theoretical remaining range data to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

[0035] In this embodiment, the AI ​​control module identifies the vehicle's current driving conditions in real time based on features such as load size and trend of real-time power data, including different scenarios such as constant speed on flat roads, acceleration while climbing hills, and deceleration and braking while descending hills. Combining the identified driving conditions, remaining hydrogen data, and theoretical remaining range data, the module matches corresponding power allocation rules, generates coordinated power supply control commands, and sends them to the power management module for execution.

[0036] When the system detects a flat, constant-speed, low-load condition, a low-power charging strategy is employed, controlling the hydrogen fuel cell to continuously charge the lithium battery at a low power of approximately 50 watts. The lithium battery then prioritizes powering the drive motor, reducing the additional hydrogen consumption caused by frequent start-stop cycles of the fuel cell. When the system detects a hill-climbing, high-load condition, a full-power output strategy is employed, controlling the hydrogen fuel cell to output at its full power of 100 watts. Simultaneously, the lithium battery assists in discharging to supply power, jointly meeting the drive motor's peak power requirement of up to 200 watts and ensuring driving power. When the system detects a downhill, deceleration, and braking condition, an energy recovery strategy is employed, controlling the hydrogen fuel cell to stop power output and switching the lithium battery to braking energy recovery mode to recover braking energy and replenish the battery. The system continuously verifies the theoretical remaining range data. When the theoretical remaining range falls below the protection threshold of 10 kilometers, a power limiting protection strategy is implemented, limiting the maximum output power of the drive motor to no more than 60% of its rated power. This prioritizes ensuring the vehicle's basic range capability, and simultaneously, a "Insufficient remaining range, service will be discontinued soon" message is displayed to the user on the vehicle's screen. Ultimately, a collaborative power supply control strategy for hydrogen fuel cells and lithium batteries was developed, adapting to real-time operating conditions and remaining hydrogen levels, to achieve a balanced optimization of hydrogen consumption efficiency and driving performance.

[0037] This application's embodiments abandon traditional solid-state hydrogen storage weight detection and high-pressure hydrogen storage pressure detection schemes. Instead, it indirectly calculates hydrogen consumption through electrical power, adapting to low-pressure solid-state hydrogen storage architecture. This fundamentally avoids high-pressure safety risks and overcomes the drawbacks of weight sensors being susceptible to bumps and load interference, significantly improving the accuracy and stability of hydrogen quantity monitoring. It achieves end-to-end linkage between hydrogen quantity monitoring and energy management, directly using hydrogen quantity calculation results as the core basis for power allocation. This breaks down the technical barriers of independent hydrogen quantity detection and energy supply control in traditional solutions, allowing for dynamic energy allocation based on remaining hydrogen quantity and driving status, effectively improving hydrogen utilization efficiency and vehicle range. The solution covers the entire process of parameter configuration, calibration, data acquisition, prediction, conversion, and control, with complete logic and strong feasibility. It adapts to the needs of large-scale operation of hydrogen-powered shared bicycles, reducing maintenance costs and improving vehicle operational reliability.

[0038] In the above Figure 1 Based on the above, this application embodiment also provides a schematic diagram of the implementation process for obtaining a power-hydrogen consumption calibration parameter set. For example... Figure 2 As shown, steps 201 to 204 are included: Step 201: performing hydrogen consumption corresponding calibration processing on test data of a hydrogen fuel cell to obtain a first mapping relationship, wherein the first mapping relationship is a mapping relationship between output power of the fuel cell and hydrogen consumption per unit time.

[0039] In the embodiment of the present application, for a hydrogen fuel cell matched with a target vehicle model, a test loop is built in a bench environment, a hydrogen mass flowmeter with 0.1-level accuracy is connected, covering a full power output range from 0 W to 500 W, a plurality of typical power points are selected for steady-state test, and the hydrogen consumption per unit time when the fuel cell operates stably at each power point is recorded, wherein typical calibration values include 30 W corresponding to 0.0015 g per second, 50 W corresponding to 0.0025 g per second, 80 W corresponding to 0.0040 g per second, and 100 W corresponding to 0.0050 g per second; for a linear interval between adjacent power points, a linear interpolation method is used to calculate corresponding hydrogen consumption, and finally the first mapping relationship in which the output power of the fuel cell corresponds to hydrogen consumption per unit time one by one is formed.

[0040] Step 202: performing hydrogen consumption equivalent calibration processing on test data of a driving motor to obtain a second mapping relationship, wherein the second mapping relationship is a mapping relationship between input power of the motor and hydrogen consumption per unit time.

[0041] In the embodiment of the present application, for the driving motor matched with the target vehicle model, different load working conditions are simulated in a bench environment, covering a full input power range from 0 W to 350 W, a plurality of typical power points are selected for testing, and the vehicle hydrogen consumption per unit time corresponding to different motor input powers is equivalently converted by combining the power generation efficiency of the hydrogen fuel cell and energy transmission loss, wherein typical calibration values include 80 W corresponding to 0.0024 g per second, 100 W corresponding to 0.0030 g per second, 150 W corresponding to 0.0045 g per second, and 200 W corresponding to 0.0060 g per second; linear interpolation calculation is also supported between adjacent power points, and finally the second mapping relationship in which the input power of the motor corresponds to hydrogen consumption per unit time one by one is formed.

[0042] Step 203: performing driving range conversion correction processing on test data of typical driving working conditions to obtain a driving range correction coefficient.

[0043] In the embodiment of the present application, various typical driving working conditions such as constant speed on flat road, climbing acceleration and downhill coasting are simulated in a bench environment, actual hydrogen consumption rates under various working conditions are tested respectively, the measured hydrogen consumption rate is compared with a basic driving range standard of "1 gram of hydrogen corresponding to 1 kilometer of driving range" for calculation, and the driving range correction coefficient corresponding to each working condition is calibrated respectively, wherein the correction coefficient for constant speed working condition on flat road is 1.0, the correction coefficient for climbing working condition is 1.2, and the correction coefficient for downhill working condition is 0.8, which is used for dynamically correcting the estimation result of remaining driving range subsequently.

[0044] Step 204: Integrate and store the first mapping relationship, the second mapping relationship, and the range correction coefficient to obtain the power-hydrogen consumption calibration parameter set.

[0045] In this embodiment, the first mapping relationship, the second mapping relationship, and the range correction coefficients for each operating condition are structurally integrated according to a unified data format to form a complete power-hydrogen consumption calibration parameter set, which is then stored in the built-in storage unit of the vehicle AI control module as a reference parameter for real-time hydrogen consumption calculation and range conversion during vehicle operation.

[0046] This application establishes two independent hydrogen consumption mapping relationships from the fuel cell power generation side and the motor load side, respectively. This covers both the hydrogen consumption of the fuel cell itself and the equivalent hydrogen consumption corresponding to the vehicle load. Point-by-point calibration across the entire power range allows for finer granularity and higher accuracy in hydrogen consumption calculation. A multi-condition range correction coefficient is added to adapt to the differences in hydrogen consumption rates under different driving scenarios such as flat roads, inclines, and declines. This solves the problem of the fixed conversion standard being out of sync with actual driving conditions, making subsequent range estimations more consistent with real-world usage scenarios. The two types of mapping relationships and correction coefficients are integrated into a unified calibration parameter set, which can be directly stored and accessed on the vehicle, eliminating the need for complex real-time calculations and balancing computational accuracy with on-board operating efficiency.

[0047] In some embodiments, the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle are synchronously collected and processed to obtain a real-time runtime timing dataset, including: performing fixed-frequency acquisition and processing on the electrical power of the hydrogen fuel cell output circuit to obtain fuel cell output power timing data.

[0048] Specifically, a fuel cell output power sensor is installed in the power output circuit of the hydrogen fuel cell, i.e. the power supply branch that charges the lithium battery. After the vehicle is powered on and started, the sensor continuously collects the real-time power value in the circuit at a fixed sampling frequency of 10 Hz. Each sampled data is accompanied by a corresponding system timestamp. As the vehicle runs, a power data sequence with time stamps is continuously generated, forming fuel cell output power time-series data. This data directly corresponds to the hydrogen consumption rate during the fuel cell power generation process.

[0049] Furthermore, the electrical power of the drive motor power supply circuit is collected and processed synchronously at the same frequency to obtain the timing data of the motor input power.

[0050] Specifically, a motor input power sensor is installed in the lithium battery discharge circuit, specifically on the branch supplying power to the drive motor. This sensor and the fuel cell output power sensor are triggered by the same clock source, synchronously acquiring the real-time input power of the drive motor at the exact same 10 Hz frequency. Each sampling point is accompanied by a unified system timestamp, continuously generating time-series data of the motor input power. This data directly corresponds to the equivalent hydrogen consumption rate of the vehicle's driving load. The two power acquisition paths are strictly synchronized to avoid errors in subsequent hydrogen consumption calculations due to time deviations.

[0051] Furthermore, the vehicle's location and driving status data are cumulatively statistically processed to obtain actual mileage data.

[0052] Specifically, the vehicle positioning and mileage statistics module obtains the vehicle's location information in real time through satellite positioning signals, continuously accumulates the vehicle's cumulative driving distance based on the location difference between adjacent sampling times, and generates real-time updated actual driving mileage data; at the same time, it records the system timestamp corresponding to each mileage update to ensure that the mileage data and power data can be matched in the time dimension. This data is used to verify the actual driving mileage ratio index in the subsequent hydrogen replacement judgment.

[0053] Furthermore, the time-series data of fuel cell output power, motor input power, and actual driving mileage are time-aligned and integrated to obtain a real-time runtime timing dataset.

[0054] Specifically, the onboard AI control module uses a unified system timestamp as a benchmark to align and match the fuel cell output power time-series data, motor input power time-series data, and actual driving mileage data at 0.1-second intervals. It corrects the sampling time deviation of the three data sources to ensure that the fuel cell power, motor power, and driving mileage data at the same time node correspond one-to-one. The aligned three types of data are then encapsulated into a structured real-time runtime time-series dataset and synchronously output to the subsequent hydrogen consumption prediction calculation stage, serving as the basic data source for hydrogen consumption calculation and operating condition identification.

[0055] This application embodiment uses dual-channel power data to be synchronously acquired at the same frequency using the same source clock, ensuring a strict correspondence between the sampling times of fuel cell power and motor power. This avoids cumulative errors in subsequent hydrogen consumption calculations due to timing deviations, guaranteeing measurement accuracy from the data source. Synchronously acquiring mileage data and matching it with a unified timestamp forms a multi-source fused time-series dataset, which supports hydrogen consumption calculations and provides a data foundation for subsequent hydrogen replacement judgments and operation and maintenance scheduling, enabling the reuse of a single set of data across multiple scenarios. The unified time-aligned integration processing method outputs a structured standard dataset that can be directly input into subsequent prediction models and calculations, reducing data preprocessing overhead at the vehicle end and improving computational efficiency.

[0056] In some embodiments, hydrogen consumption prediction calculations are performed on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient. This includes: performing sliding filtering and feature splitting on the real-time runtime sequence dataset to obtain the fuel cell output power sequence and the motor input power sequence.

[0057] Specifically, the onboard AI control module uses a moving average filtering algorithm to denoise the two power data streams in the real-time runtime time series dataset. It selects multiple consecutive sampling points for averaging, filtering out high-frequency noise interference caused by road bumps and vehicle vibrations during vehicle operation, thus avoiding deviations in hydrogen consumption calculations due to random power fluctuations. After filtering, the time-aligned fuel cell output power sequence and motor input power sequence are extracted from the time series dataset, corresponding to the fuel cell's power generation data and the motor's load power data, respectively.

[0058] Furthermore, the fuel cell output power sequence, the motor input power sequence, and the power-hydrogen consumption calibration parameter set are input into a preset hydrogen consumption prediction model for inference processing to obtain the total hydrogen consumption per unit time.

[0059] Specifically, the fuel cell output power sequence, the motor input power sequence, and the power-hydrogen consumption calibration parameter set are input into a pre-trained AI hydrogen consumption prediction model for inference processing. Based on the power-hydrogen consumption mapping relationship in the calibration parameter set, the model interpolates and matches the real-time power values ​​to calculate the hydrogen consumption per unit time at the fuel cell end and the equivalent hydrogen consumption per unit time at the motor load end. The two hydrogen consumption values ​​are then added together to obtain the total hydrogen consumption per unit time. The model maintains the same output frequency as the data acquisition, ensuring that the corresponding hydrogen consumption value per unit time is output for each sampling period.

[0060] Furthermore, the total hydrogen consumption per unit time is accumulated over the entire operation to obtain the cumulative total hydrogen consumption.

[0061] Specifically, the total hydrogen consumption per unit time is accumulated throughout the entire operation. Taking the completion of this hydrogen exchange and the first power-on of the vehicle as the starting point for accumulation, after the on-board AI control module completes the calculation of hydrogen consumption per unit time in each sampling cycle, the hydrogen consumption of that cycle is added to the historical cumulative value. The hydrogen consumption throughout the entire operation of the vehicle is continuously accumulated to obtain the cumulative total hydrogen consumption since this hydrogen exchange. This value is updated in real time as the vehicle operates.

[0062] Furthermore, the dynamic variation characteristics of the fuel cell output power sequence and the dynamic variation characteristics of the motor input power sequence are respectively processed by operating condition identification and coefficient matching to obtain real-time operating condition correction coefficients.

[0063] Specifically, the dynamic variation characteristics of the fuel cell output power sequence and the motor input power sequence are processed by operating condition identification and coefficient matching. The AI ​​control module extracts dynamic features such as the power change rate, average load level, and power fluctuation amplitude of the two power sequences to identify the current driving conditions of the vehicle, including typical scenarios such as flat road constant speed, uphill acceleration, downhill coasting, and idle start-stop. Based on the identified operating condition type, the corresponding range correction coefficient is matched to the power-hydrogen consumption calibration parameter set, and finally the real-time operating condition correction coefficient is output for the dynamic calculation of the remaining driving range.

[0064] This application embodiment uses sliding filtering to denoise the power data, effectively filtering out high-frequency power noise caused by road bumps and vehicle vibrations, avoiding random power fluctuations from interfering with hydrogen consumption calculation results, and improving the reliability of data in dynamic driving scenarios. Combining calibration parameter sets with AI prediction models to calculate hydrogen consumption per unit time, compared to simple table lookup interpolation, it is more adaptable to dynamically changing power driving conditions and can more accurately match the hydrogen consumption rate under real-time load. The full-process time-series accumulation calculation method ensures the continuity and real-time nature of the cumulative hydrogen consumption, which can be dynamically updated as the vehicle runs, truly reflecting the progress of hydrogen consumption; based on power dynamic characteristics to identify driving conditions and match correction coefficients, no additional driving condition detection sensors are needed, improving the adaptability of range estimation without increasing hardware costs.

[0065] In some embodiments, the remaining hydrogen quantity is converted from the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient to obtain the remaining hydrogen quantity data and the theoretical remaining range data. This includes: performing a difference calculation on the initial hydrogen quantity and the cumulative total hydrogen consumption in the initial operating baseline parameters to obtain the remaining hydrogen quantity data.

[0066] Specifically, the initial operating baseline parameters include the pre-configured initial hydrogen weight (initial hydrogen quantity) of the solid-state hydrogen storage device. This value is entered by maintenance personnel via the cloud backend after hydrogen exchange, with a default value of 80 grams, which can be flexibly adjusted according to the actual filling volume. The onboard AI control module retrieves this initial hydrogen quantity value and performs a difference calculation with the total hydrogen consumption accumulated since this hydrogen exchange, calculated in real time. The difference between the initial hydrogen quantity and the accumulated total hydrogen consumption is used to calculate the current remaining hydrogen weight in the solid-state hydrogen storage device, i.e., the remaining hydrogen quantity. This data is updated in real time as the vehicle operates, accurately reflecting the remaining hydrogen status of the hydrogen storage device.

[0067] Furthermore, the remaining hydrogen data and the real-time operating condition correction coefficient are dynamically converted into driving range data to obtain the theoretical remaining driving range data.

[0068] Specifically, firstly, based on a preset baseline range standard—that is, one kilometer of range per gram of hydrogen—an initial range estimate is calculated using the remaining hydrogen quantity data. Then, this initial estimate is dynamically adjusted using real-time matching correction coefficients. The correction coefficient is 1.0 for flat, constant-speed driving, 1.2 for climbing, and 0.8 for downhill driving, thus adapting to the different hydrogen consumption rates under various road conditions. Finally, a theoretical remaining range data that fits the current driving state is obtained. The calculated remaining hydrogen quantity data and the theoretical remaining range data are simultaneously transmitted to the onboard display for real-time viewing by the rider, and also serve as core input parameters for subsequent adaptive power allocation.

[0069] This application's embodiments calculate the remaining hydrogen quantity using the difference between the initial hydrogen quantity and the cumulative hydrogen consumption. The principle is clear, the calculation is efficient, and no additional weight or pressure detection hardware is required, reducing the hardware cost and structural complexity of the vehicle. Combining a real-time operating condition correction coefficient for dynamic range calculation replaces the traditional fixed-ratio range estimation method. This allows for real-time adjustment of the range prediction result according to driving conditions, significantly improving the accuracy of remaining range estimation and reducing users' range anxiety.

[0070] In some embodiments, adaptive power allocation processing is performed on real-time driving condition data, remaining hydrogen quantity data, and theoretical remaining range data to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries, including: extracting load features and classifying scenarios from real-time driving condition data to obtain driving condition determination results.

[0071] Specifically, the onboard AI control module extracts dynamic load features such as power load level, power change rate, and power fluctuation amplitude from real-time operating data, and combines them with vehicle driving status data to perform scene classification and recognition. When the power load is stable at a medium level and the power change rate is gradual, it is determined to be a flat road constant speed condition; when the power load continues to rise, is in a high range, and the power change rate is a large positive value, it is determined to be a hill climbing acceleration condition; when the power load drops rapidly and negative power feedback characteristics appear, it is determined to be a downhill deceleration and braking condition, and finally outputs a clear driving condition judgment result.

[0072] Furthermore, the power supply mode matching process is performed on the driving condition determination results and the remaining hydrogen data to obtain the initial allocation scheme of fuel cell output power and lithium battery power supply and discharge.

[0073] Specifically, based on the driving condition determination results and the current remaining hydrogen data, a preset power supply operation mode is matched: If the driving condition is determined to be a flat road constant speed condition, a low-power charging mode is matched, setting the hydrogen fuel cell to output a stable power of about 50 watts to continuously replenish the lithium battery. The driving load is primarily borne by the lithium battery, forming an initial allocation scheme of low-power charging of the fuel cell and discharging of the lithium battery; If the driving condition is determined to be a hill-climbing acceleration condition, a full-power output mode is matched, setting the hydrogen fuel cell to output a full power of 100 watts, while controlling the lithium battery to enter an auxiliary discharge state, jointly supporting the peak power demand of the drive motor, forming an initial allocation scheme of full-power output of the fuel cell and auxiliary discharge of the lithium battery; If the driving condition is determined to be a downhill deceleration and braking condition, an energy recovery mode is matched, setting the hydrogen fuel cell to stop power output, and the lithium battery to switch to a charging state to recover braking energy, forming an initial allocation scheme of fuel cell shutdown and lithium battery energy recovery.

[0074] Furthermore, the theoretical remaining range data is subjected to low range threshold verification processing to obtain motor power limitation correction parameters.

[0075] Specifically, the system retrieves a preset low range protection threshold, with a default value of 10 kilometers, and compares the current theoretical remaining range data with this threshold for verification. When the theoretical remaining range is lower than this threshold, a power limit correction parameter is generated, setting the maximum output power of the drive motor to 60% of the rated power, and an on-board warning command is generated. When the theoretical remaining range is higher than this threshold, an unlimited correction parameter is generated, without interfering with the rated power output of the motor.

[0076] Furthermore, the initial allocation scheme and motor power limitation correction parameters are integrated and optimized to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

[0077] Specifically, the initial allocation scheme obtained from the matching of operating conditions is superimposed and integrated with the motor power limit correction parameters. The fuel cell output power setpoint, lithium battery charging and discharging status, and motor power limit are uniformly adjusted and optimized to form the final executable collaborative power supply control strategy. This strategy is then sent to the power management module for implementation. While ensuring basic driving power, the hydrogen consumption rate is optimized to extend the driving range and adapt to the energy management needs of different driving scenarios and remaining hydrogen status.

[0078] This application's embodiments automatically identify driving conditions based on load characteristics and match corresponding power supply modes. In flat road scenarios, priority is given to hydrogen economy; in uphill scenarios, priority is given to power output; and in downhill scenarios, braking energy is recovered, balancing vehicle power performance and hydrogen utilization efficiency. A low-range threshold verification and power limitation correction mechanism is added. When the remaining range is too low, the peak power of the motor is automatically limited, preventing the vehicle from breaking down mid-journey due to hydrogen depletion, improving vehicle reliability, and maximizing the remaining driving range. A two-level allocation logic of "initial scheme for driving conditions matching + low-range correction optimization" ensures adaptability to different driving scenarios while also addressing protection needs in low-battery states, resulting in greater strategy flexibility and practicality.

[0079] In some embodiments, initial configuration processing is performed on the initial hydrogen quantity and hydrogen replacement judgment threshold of the solid hydrogen storage device to obtain initial operating baseline parameters, including: inputting and configuring the initial hydrogen weight parameters of the solid hydrogen storage device to obtain initial hydrogen quantity baseline parameters.

[0080] Specifically, after the maintenance personnel complete the replacement of the vehicle's solid hydrogen storage device, they log into the parameter configuration interface of the cloud-based backend management system and enter the initial hydrogen weight parameter of the newly installed solid hydrogen storage device. The default value of this parameter is 80 grams, and it can be flexibly adjusted to different values ​​such as 75 grams and 80 grams according to the actual filling volume. After the system verifies the validity of the entered parameters, it generates the initial hydrogen quantity benchmark parameter, which serves as the basis for subsequent hydrogen quantity difference calculations.

[0081] Furthermore, the hydrogen exchange judgment threshold is classified, decomposed, and parameter set to obtain dual-index hydrogen exchange judgment parameters.

[0082] Specifically, the system breaks down the unified hydrogen swap judgment threshold into two categories based on judgment dimensions: the mileage percentage judgment threshold and the remaining range minimum threshold. Operation and maintenance personnel can set parameters for the two types of thresholds in the configuration interface. The mileage percentage judgment threshold is set to 90% by default, and the remaining range minimum threshold is set to 5 kilometers by default. Both types of thresholds can be flexibly adjusted according to operational scheduling needs. After the parameters are set and confirmed, the system generates structured dual-index hydrogen swap judgment parameters for dual-dimensional verification of the subsequent hydrogen swap triggering logic.

[0083] Furthermore, the initial hydrogen quantity benchmark parameter is converted to the preset basic range standard to obtain the theoretical total range parameter.

[0084] Specifically, the system retrieves a preset baseline range standard, which is the range conversion benchmark of one kilometer per gram of hydrogen. It then converts the initial hydrogen weight corresponding to the initial hydrogen quantity benchmark parameter with this conversion benchmark to obtain the theoretical total range of the solid hydrogen storage device in a fully loaded state, generating a theoretical total range parameter. For example, when the initial hydrogen quantity is 80 grams, the corresponding theoretical total range parameter is 80 kilometers. This parameter is used to determine the hydrogen replacement ratio for subsequent driving mileage.

[0085] Furthermore, the initial hydrogen quantity baseline parameters, dual-index hydrogen exchange judgment parameters, and theoretical total range parameters are integrated, stored, and processed to obtain the initial operating baseline parameters.

[0086] Specifically, the system integrates the initial hydrogen quantity benchmark parameters, dual-index hydrogen swapping judgment parameters, and theoretical total range parameters in a structured manner according to a unified data format to form complete initial operating benchmark parameters. On the one hand, these parameters are stored in the cloud data storage unit for record-keeping, and on the other hand, they are simultaneously transmitted to the corresponding vehicle's onboard AI control module via a wireless communication link, serving as unified benchmark parameters for hydrogen quantity calculation, hydrogen swapping judgment, and energy management throughout the vehicle's subsequent entire operating cycle.

[0087] This application's embodiments support flexible input of initial hydrogen weights with varying filling volumes, making it adaptable to solid-state hydrogen storage devices of different specifications and filling levels. This enhances versatility and meets diverse filling needs in actual operation and maintenance. The hydrogen replacement judgment threshold is broken down into two independent parameters: mileage percentage and remaining range minimum. A dual-indicator judgment system is constructed from two dimensions: usage time and remaining status. This system is more comprehensive than a single judgment indicator and can effectively reduce the false judgment rate of hydrogen replacement triggering. The theoretical total range is automatically calculated based on the initial hydrogen quantity, eliminating the need for manual calculation and input, reducing the configuration workload for maintenance personnel and improving operational efficiency. The integrated initial operating benchmark parameters are synchronously distributed to the vehicle terminal, ensuring the consistency and accuracy of benchmark parameters throughout the vehicle's entire operating cycle.

[0088] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in this embodiment is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in this embodiment or the accompanying drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0089] like Figure 3 As shown in the illustration, this application also provides a cooperative power supply control device 300. The device includes: The processing module 301 is used to initialize and configure the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters.

[0090] The processing module 301 is also used to perform calibration mapping processing on the operating condition test data to obtain a power-hydrogen consumption calibration parameter set.

[0091] The processing module 301 is also used to synchronously collect and process the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time runtime sequence dataset.

[0092] The processing module 301 is also used to perform hydrogen consumption prediction calculation on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient.

[0093] The conversion module 302 is used to convert the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient to the remaining hydrogen quantity, so as to obtain the remaining hydrogen quantity data and the theoretical remaining range data.

[0094] The allocation module 303 is used to perform adaptive power allocation processing on real-time driving condition data, remaining hydrogen data and theoretical remaining range data to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

[0095] Some modules in the apparatus described in this application can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0096] The apparatus or module described in the above embodiments can be implemented by a computer chip or physical entity, or by a product with a certain function. For ease of description, the above apparatus is described by dividing it into various modules according to their functions. When implementing the embodiments of this application, the functions of each module can be implemented in one or more software and / or hardware. Of course, a module that implements a certain function can also be implemented by combining multiple sub-modules or sub-units.

[0097] The methods, apparatus, or modules described in this application can be implemented in a computer-readable program code manner. The controller can be implemented in any suitable manner, such as a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of a memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code manner, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included within it for implementing various functions can also be considered as structures within the hardware component. Alternatively, the device used to implement various functions can be viewed as either a software module that implements the method or a structure within a hardware component.

[0098] This application also provides an apparatus, the apparatus comprising: a processor; a memory for storing processor-executable instructions; wherein, when the processor executes the executable instructions, it implements the method described in this application.

[0099] This application also provides a non-volatile computer-readable storage medium storing a computer program or instructions thereon, which, when executed, enables the method described in this application embodiment to be implemented.

[0100] Furthermore, in the various embodiments of the present invention, each functional module can be integrated into a processing module, or each module can exist independently, or two or more modules can be integrated into a single module.

[0101] The aforementioned storage media include, but are not limited to, Random Access Memory (RAM), Read-Only Memory (ROM), Cache, Hard Disk Drive (HDD), or Memory Card. The memory can be used to store computer program instructions.

[0102] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary hardware. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, or it can be embodied in the process of data migration. The computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0103] The various embodiments described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. All or part of this application can be used in numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, mobile communication terminals, multiprocessor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices, etc.

[0104] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of this application.

Claims

1. A method of coordinated power supply control, characterized by, include: Initialize the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters. The operating condition test data is calibrated and mapped to obtain a set of power-hydrogen consumption calibration parameters. The output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle are collected and processed synchronously to obtain a real-time runtime sequence dataset. The hydrogen consumption prediction calculation is performed on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient. The remaining hydrogen quantity is converted by the initial operating baseline parameters, the cumulative total hydrogen consumption and the real-time operating condition correction coefficient to obtain the remaining hydrogen quantity data and the theoretical remaining range data. Adaptive power allocation processing is performed on real-time driving condition data, remaining hydrogen quantity data, and theoretical remaining range data to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

2. The method according to claim 1, characterized in that, The calibration mapping process performed on the operating condition test data yields a power-hydrogen consumption calibration parameter set, including: The test data of hydrogen fuel cells are calibrated according to hydrogen consumption to obtain a first mapping relationship, which is the mapping relationship between fuel cell output power and hydrogen consumption per unit time. The test data of the drive motor are subjected to hydrogen consumption equivalent calibration to obtain a second mapping relationship, which is the mapping relationship between the motor input power and the hydrogen consumption per unit time. The test data under typical driving conditions are processed by range conversion and correction to obtain the range correction coefficient; The first mapping relationship, the second mapping relationship, and the range correction coefficient are integrated and stored to obtain a power-hydrogen consumption calibration parameter set.

3. The method according to claim 1, characterized in that, The process of synchronously collecting and processing the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time runtime sequence dataset includes: The electrical power of the hydrogen fuel cell output circuit is collected and processed at a fixed frequency to obtain the time-series data of the fuel cell output power. The electrical power of the drive motor power supply circuit is collected and processed synchronously at the same frequency to obtain the timing data of the motor input power; The vehicle's location and driving status data are cumulatively and statistically processed to obtain the actual mileage data; The time-series data of the fuel cell output power, the time-series data of the motor input power, and the actual driving mileage are time-aligned and integrated to obtain a real-time runtime timing dataset.

4. The method according to claim 1, characterized in that, The step of performing hydrogen consumption prediction calculations on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient includes: The real-time runtime sequence dataset is subjected to sliding filtering and feature splitting to obtain the fuel cell output power sequence and the motor input power sequence; The fuel cell output power sequence, the motor input power sequence, and the power-hydrogen consumption calibration parameter set are input into a preset hydrogen consumption prediction model for inference processing to obtain the total hydrogen consumption per unit time. The total hydrogen consumption per unit time is accumulated throughout the entire operation to obtain the cumulative total hydrogen consumption. The dynamic variation characteristics of the fuel cell output power sequence and the dynamic variation characteristics of the motor input power sequence are respectively processed by operating condition identification and coefficient matching to obtain real-time operating condition correction coefficients.

5. The method according to claim 1, characterized in that, The process of converting the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient into remaining hydrogen quantity data to obtain remaining hydrogen quantity data and theoretical remaining range data includes: The difference between the initial hydrogen quantity in the initial operating baseline parameters and the cumulative total hydrogen consumption is calculated to obtain the remaining hydrogen quantity data. The remaining hydrogen data and the real-time operating condition correction coefficient are dynamically converted into driving range data to obtain the theoretical remaining driving range data.

6. The method according to claim 1, characterized in that, The adaptive power allocation processing of real-time driving condition data, remaining hydrogen quantity data, and theoretical remaining range data yields a coordinated power supply control strategy for the hydrogen fuel cell and lithium battery, including: Load feature extraction and scene classification are performed on real-time driving condition data to obtain driving condition judgment results; The driving condition determination result and the remaining hydrogen data are processed to match the power supply mode, and an initial allocation scheme for fuel cell output power and lithium battery power supply and discharge is obtained. The theoretical remaining range data is subjected to low range threshold verification processing to obtain motor power limitation correction parameters; The initial allocation scheme and the motor power limitation correction parameters are integrated and optimized to obtain a coordinated power supply control strategy for hydrogen fuel cells and lithium batteries.

7. The method according to claim 1, characterized in that, The initial configuration process for the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid-state hydrogen storage device is performed to obtain the initial operating baseline parameters, including: The initial hydrogen weight parameters of the solid hydrogen storage device are entered and configured to obtain the initial hydrogen quantity baseline parameters. The hydrogen exchange judgment threshold is classified, decomposed, and parameter set to obtain dual-index hydrogen exchange judgment parameters. The initial hydrogen content benchmark parameter is converted to the preset basic range standard to obtain the theoretical total range parameter; The initial hydrogen quantity baseline parameters, the dual-index hydrogen exchange determination parameters, and the theoretical total range parameters are integrated, stored, and processed to obtain the initial operating baseline parameters.

8. A cooperative power supply control device, characterized in that, include: The processing module is used to initialize and configure the initial hydrogen quantity and hydrogen exchange judgment threshold of the solid hydrogen storage device to obtain the initial operating baseline parameters. The processing module is also used to perform calibration mapping processing on the operating condition test data to obtain a power-hydrogen consumption calibration parameter set; The processing module is also used to synchronously collect and process the output power of the hydrogen fuel cell, the input power of the drive motor, and the actual driving mileage of the vehicle to obtain a real-time runtime sequence dataset. The processing module is also used to perform hydrogen consumption prediction calculation on the real-time runtime sequence dataset and the power-hydrogen consumption calibration parameter set to obtain the cumulative total hydrogen consumption and the real-time operating condition correction coefficient. The conversion module is used to convert the initial operating baseline parameters, the cumulative total hydrogen consumption, and the real-time operating condition correction coefficient into remaining hydrogen data to obtain remaining hydrogen data and theoretical remaining range data. The allocation module is used to perform adaptive power allocation processing on real-time driving condition data, the remaining hydrogen quantity data, and the theoretical remaining range data to obtain a coordinated power supply control strategy for the hydrogen fuel cell and the lithium battery.

9. A computer device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.

Images