Hydrogen fuel vehicle endurance performance prediction method and system

Abstract

The present application belongs to the technical field of safety monitoring of electric vehicles, and particularly relates to a hydrogen fuel vehicle endurance performance prediction method and system, which comprises the following steps: obtaining a compression factor at each time based on the absolute pressure and thermodynamic temperature at each time after collection and preprocessing, which is used to calculate the residual hydrogen mass at each time; constructing a road condition feature vector based on geographic information data, and jointly constructing a dynamic energy consumption model with the residual hydrogen mass, calculating an instantaneous hydrogen consumption rate based on the model, and calculating a unit mileage energy consumption benchmark value; dividing discrete road sections based on the unit mileage energy consumption benchmark value, the residual hydrogen mass and the road condition feature vector, predicting the maximum endurance mileage by using a segmented iteration algorithm, and obtaining the residual mileage of the current route; comparing the maximum endurance mileage with the residual mileage; setting an endurance safety margin for triggering a hierarchical energy management strategy. The present application improves the accuracy of hydrogen fuel vehicle endurance performance prediction.

Description

Technical Field

[0001] This invention relates to the field of safety monitoring technology for electric vehicles. More specifically, this invention relates to a method and system for predicting the range performance of hydrogen fuel cell vehicles. Background Technology

[0002] Hydrogen fuel cell vehicles, as an important type of electric vehicle, have the advantages of long driving range and rapid hydrogen refueling, and have been applied in urban public transportation, logistics and other fields. Unlike pure electric vehicles that rely on power battery energy storage, the energy supply path of hydrogen fuel cell vehicles is as follows: hydrogen stored in the on-board high-pressure hydrogen storage system is transported to the fuel cell system to undergo an electrochemical reaction with oxygen, directly converting chemical energy into electrical energy to drive the motor. Its actual driving range is affected by the coupling of three core factors: the physical characteristics of high-pressure hydrogen storage, the nonlinear operating characteristics of the fuel cell, and the dynamic changes of the road topology environment. The difficulty of accurately predicting this range is significantly higher than that of pure electric vehicles.

[0003] In urban public transport operations, accurate prediction of the driving range of hydrogen fuel cell vehicles is a key technological support for ensuring efficient capacity scheduling, eliminating range anxiety at the operational end, and reducing the construction costs of hydrogen refueling stations. Currently, the estimation method for the driving range of hydrogen fuel cell vehicles generally adopts a static linear extrapolation method. The core process of this method is as follows: based on the ideal gas law, the remaining hydrogen mass in the onboard hydrogen storage cylinder is calculated using the real-time pressure value; then, historical vehicle operating data, such as the average energy consumption value within the most recent 50 kilometers of driving, is retrieved; finally, the remaining hydrogen mass is divided by the average energy consumption value to obtain the vehicle's theoretical driving range.

[0004] However, existing methods have significant drawbacks in complex real-world operations: First, existing technologies ignore the inherent properties of hydrogen under high-pressure environments, such as the nonlinear fluctuations in mass caused by changes in temperature and cylinder pressure. The assumptions of the ideal gas law deviate from actual operating conditions, leading to a decrease in the accuracy of calculating the remaining hydrogen storage capacity. Second, the average energy consumption value in the vehicle's historical operating data can only reflect the energy consumption level under past steady-state conditions, failing to reflect the nonlinear relationship between the power and efficiency of the fuel cell system. It also cannot match the drastic fluctuations in real-time energy consumption caused by current and future road conditions such as long uphill driving, traffic congestion, and load changes, resulting in a large deviation between the predicted range and the actual driving mileage, thus leading to low accuracy in predicting the range performance of hydrogen fuel cell vehicles. Summary of the Invention

[0005] To address the technical problems of low accuracy in calculating remaining hydrogen mass, poor adaptability to dynamic operating conditions, and insufficient consideration of the coupling effects of multiple factors, which lead to low accuracy in predicting the range performance of hydrogen fuel cell vehicles, this invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for predicting the driving range of a hydrogen fuel cell vehicle, comprising: real-time acquisition and preprocessing of the absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage tank of a hydrogen fuel cell bus at various times; obtaining geographic information data and constructing a road condition feature vector based on the predetermined driving route of the hydrogen fuel cell bus and a GPS positioning system; obtaining the compressibility factor at each time based on the absolute pressure and thermodynamic temperature; correcting the real gas equation of state using the compressibility factor to obtain the remaining hydrogen mass in the high-pressure hydrogen storage tank at each time; acquiring the output current and operating temperature of the fuel cell stack; querying a polarization characteristic database to obtain the single-cell voltage and calculating the total output power; real-time acquisition of the auxiliary system power consumption and calculating the net output power and net efficiency factor; and combining the vehicle's cumulative mileage and aging sensitivity coefficient. The aging correction factor is calculated. Based on Faraday's law, and incorporating the net efficiency factor and the aging correction factor, a calculation model for instantaneous hydrogen consumption rate is constructed. This model is used to calculate the instantaneous hydrogen consumption rate, and the benchmark value for energy consumption per unit mileage is obtained by combining the road condition feature vector. Based on the remaining hydrogen mass, the benchmark value for energy consumption per unit mileage, and the road condition feature vector, the remaining journey is divided into discrete road segments. A piecewise iterative algorithm is used to calculate and accumulate the hydrogen consumption required for the vehicle to pass through each discrete road segment until the cumulative hydrogen consumption reaches the remaining hydrogen mass, thereby predicting the vehicle's maximum driving range. The maximum driving range is visualized and output, and the maximum driving range is compared with the remaining mileage of the route in real time. When a range risk is identified, a graded energy management strategy is automatically triggered to dynamically adjust the operating parameters of the fuel cell system.

[0007] This method involves real-time acquisition and preprocessing of the absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage tank of a hydrogen fuel cell bus. A road condition feature vector is constructed by combining this data with the vehicle's planned route and geographic information obtained from the GPS positioning system. Based on the absolute pressure and thermodynamic temperature, the hydrogen compressibility factor is calculated at each moment. This compressibility factor is then used to correct the real gas equation of state to accurately obtain the remaining hydrogen mass in the high-pressure hydrogen storage tank at each moment. Finally, using the remaining hydrogen mass and the road condition feature vector as core inputs, a dynamic energy consumption model of the hydrogen fuel cell system is constructed. This model is then used to calculate the instantaneous hydrogen consumption. The system determines the energy consumption benchmark per unit mileage by combining the rate and road condition feature vectors. Then, based on the remaining hydrogen mass, the energy consumption benchmark per unit mileage, and the road condition feature vectors, the remaining journey is divided into discrete road segments. A segmented iterative algorithm is used to accumulate the hydrogen consumption of each discrete road segment until the cumulative hydrogen consumption reaches the remaining hydrogen mass, thereby achieving accurate prediction of the vehicle's maximum driving range. At the same time, by visualizing the maximum driving range and comparing it with the remaining mileage of the route in real time, a graded energy management strategy is automatically triggered when a range risk is identified, improving the accuracy of predicting the driving range performance of hydrogen fuel cell vehicles.

[0008] Preferably, the road condition feature vector is , It calculates the distance of the travel path to the next scheduled bus stop based on the current location and the route map; It extracts the average slope from the current location to the next station based on terrain data; The average speed is calculated based on the historical trajectory data of this road section during the same period. This is the index for the time.

[0009] Preferably, obtaining the compressibility factor at each moment based on the absolute pressure and thermodynamic temperature includes: pre-storing a data table of compressibility factors of hydrogen at different pressures and temperatures, and interpolating and querying the data table according to the absolute pressure and thermodynamic temperature to obtain the compressibility factor.

[0010] Preferably, obtaining the remaining hydrogen mass in the high-pressure hydrogen storage cylinder at each time point includes: In the formula, It is the first The mass of remaining hydrogen in the high-pressure hydrogen storage cylinder at any given time; The internal gas of the high-pressure hydrogen storage cylinder is in the first... The absolute pressure of every moment; It is the geometric volume of the high-pressure hydrogen storage cylinder; The internal gas of the high-pressure hydrogen storage cylinder is in the first... Thermodynamic temperature at any given moment; It is the specific gas constant of hydrogen; It is the first The compression factor of time; It is the safety redundancy factor; This is the index for the time.

[0011] This method introduces a formula for calculating the remaining hydrogen mass that includes key parameters such as absolute pressure, thermodynamic temperature, compressibility factor, and safety redundancy coefficient. It fully considers the real gas characteristics of hydrogen and the safety redundancy requirements under high-pressure scenarios. Combined with fixed parameters such as the geometric volume of the hydrogen storage cylinder and the hydrogen specific gas constant, the calculation process of the remaining hydrogen mass is more targeted and scientific, effectively improving the accuracy and reliability of the remaining hydrogen mass calculation at each time point. This provides high-precision data support for subsequent dynamic energy consumption modeling and maximum driving range prediction.

[0012] Preferably, the calculation of the aging correction factor includes: In the formula, It is an aging correction factor; It is the aging sensitivity coefficient; It is the cumulative mileage throughout history; That is the maximum driving range.

[0013] Preferably, the calculation of the instantaneous hydrogen consumption rate includes: In the formula, It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses at any given time; The fuel cell system is in the first The current output at all times; It is the total number of individual cells connected in series in the fuel cell system; It is the molar mass of hydrogen gas; It is Faraday's constant; The fuel cell system is in the first Net efficiency factor at any given time; It is an aging correction factor; This is the index for the time.

[0014] This method constructs an instantaneous hydrogen consumption rate calculation model that integrates multiple key parameters. It precisely couples core operating parameters such as the real-time output current of the fuel cell system and the total number of series-connected cells with fundamental physical quantities such as the molar mass of hydrogen and the Faraday constant. It also innovatively introduces a net efficiency factor and an aging correction factor to achieve dynamic correction of the hydrogen consumption rate across all scenarios. The net efficiency factor is calculated by integrating the total output power of the fuel cell system and the power consumption of the auxiliary system, effectively avoiding the bias caused by neglecting the energy consumption of the auxiliary system in traditional calculations. The aging correction factor is constructed based on the vehicle's cumulative mileage and aging sensitivity coefficient, fully covering the performance degradation loss of the fuel cell system after long-term operation. This solves the technical pain point of existing technologies that struggle to balance dynamic operating characteristics and the effects of long-term aging, significantly improving the accuracy of hydrogen consumption rate calculation. This provides highly reliable data support for the scientific derivation of subsequent energy consumption benchmarks per unit mileage and lays a core foundation for the accuracy of range prediction.

[0015] Preferably, obtaining the energy consumption benchmark value per unit mileage includes: In the formula, It is the first The baseline value of energy consumption per unit distance at any given time; The average speed is calculated based on the historical trajectory data of this road section during the same period. It extracts the average slope from the current location to the next station based on terrain data; It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses at any given time; This is the index for the time.

[0016] This method innovatively couples the instantaneous hydrogen consumption rate with the historical average speed and current average slope of the road segment by establishing a dynamic correlation mechanism between instantaneous hydrogen consumption rate and core road condition characteristics. This constructs a benchmark model for energy consumption per unit mileage that is adapted to actual driving scenarios. In this model, the historical average speed of the road segment is used to convert the instantaneous hydrogen consumption rate into hydrogen consumption per unit mileage, accurately reflecting the energy consumption differences at different driving speeds. The average slope of the road segment, through a coefficient correction, quantifies the additional impact of terrain undulations on energy consumption, solving the problem of insufficient scenario adaptability caused by ignoring the slope factor in traditional energy consumption benchmark calculations. The energy consumption benchmark value per unit mileage obtained in this way can dynamically respond to the differences in road condition characteristics of different road segments, significantly improving the scenario fit and accuracy of the energy consumption benchmark value. This provides accurate energy consumption basis for subsequent discretization analysis of the remaining journey and segmented iterative calculation of hydrogen consumption for each road segment, directly ensuring the reliability of the maximum driving range prediction.

[0017] Preferably, the graded energy management strategy includes: the system acquiring the remaining physical mileage of the vehicle from the terminal station in real time, and using the difference between the maximum range and the remaining mileage of the current route as the range safety margin; when the range safety margin is greater than or equal to 0 kilometers and less than or equal to 5 kilometers, a level one response is triggered to remind the driver that the hydrogen fuel is insufficient, and a recommended maximum cruising speed is generated to prompt the driver to drive smoothly; when the range safety margin is less than 0 kilometers, a level two response is triggered, and the vehicle controller immediately takes over the authority and executes a forced energy-saving strategy: forcibly reducing the maximum speed of the air compressor, prohibiting rapid acceleration, and forcing the hydrogen fuel cell bus to operate in a low-energy consumption state.

[0018] Secondly, the present invention provides a hydrogen fuel cell vehicle range prediction system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned hydrogen fuel cell vehicle range prediction method is implemented.

[0019] By adopting the above technical solution, a computer program is generated from the above-mentioned method for predicting the range performance of hydrogen fuel cell vehicles and stored in a memory so that it can be loaded and executed by a processor. A terminal device can then be made based on the memory and the processor for convenient use.

[0020] The beneficial effects of this invention are as follows: By real-time acquisition of the absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage cylinder and combining this with the compressibility factor to correct the real gas law, the errors of the ideal gas law under high-pressure scenarios are effectively avoided, significantly improving the calculation accuracy of the remaining hydrogen mass and providing reliable data support for range prediction; by integrating geographical information data of the predetermined driving route to construct a road condition feature vector and applying it throughout the entire process of dynamic energy consumption model construction, calculation of energy consumption benchmark value per unit mileage, and discretization analysis of remaining range, energy consumption prediction and range assessment are made more consistent with the actual driving scenarios of the vehicle, greatly improving the accuracy of maximum range prediction. The system demonstrates high performance and environmental adaptability. By using a segmented iterative algorithm to discretize the remaining range, it achieves refined prediction of driving range, providing drivers with an intuitive and reliable basis for trip planning. Furthermore, by visually displaying the maximum driving range and comparing it in real-time with the remaining mileage, it can identify the risk of insufficient range in advance. Then, through an automatically triggered tiered energy management strategy, it dynamically adjusts the operating parameters of the fuel cell system, effectively ensuring the safety and continuity of hydrogen fuel cell vehicle operation, optimizing the operating status of the fuel cell system, and improving the utilization efficiency of hydrogen energy. This provides key technical support for the large-scale promotion and commercial application of hydrogen fuel cell vehicles. Attached Figure Description

[0021] Figure 1 This is a flowchart illustrating a method for predicting the range performance of a hydrogen fuel cell vehicle according to the present invention.

[0022] Figure 2 This is a schematic diagram illustrating the range prediction results of a hydrogen fuel cell vehicle range prediction method according to the present invention.

[0023] Figure 3 This is a schematic diagram illustrating the range prediction comparison of a hydrogen fuel cell vehicle range performance prediction method according to the present invention. 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, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0026] This invention discloses a method for predicting the driving range of hydrogen fuel cell vehicles, referring to... Figure 1 This includes steps S1-S4:

[0027] S1. Real-time acquisition of the absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage cylinder in the hydrogen fuel cell bus at each moment, and preprocessing; acquisition of geographic information data to construct road condition feature vectors; acquisition of compressibility factor at each moment based on absolute pressure and thermodynamic temperature; and acquisition of the remaining hydrogen mass in the high-pressure hydrogen storage cylinder at each moment by correcting the real gas state equation with the compressibility factor.

[0028] It should be noted that hydrogen fuel cell buses typically use 35 MPa high-pressure hydrogen storage cylinders. Under this high-pressure environment, the volume effect and intermolecular forces of hydrogen molecules cannot be ignored. If the ideal gas law is used directly to calculate the remaining hydrogen mass, significant systematic errors will occur, potentially exceeding 10%, directly leading to incorrect baseline values ​​for predicted driving range. Furthermore, hydrogen fuel cell buses are characterized by fixed routes and frequent stops. Their energy consumption patterns are highly correlated with road gradients and stop spacing. Simple average energy consumption methods cannot reflect the energy fluctuations characterized by high consumption uphill and feedback downhill. Accurately obtaining the compressibility factor requires… This requires relying on real-time and pre-processed data on the absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage tank at various times. Only by ensuring the reliability of this basic data can the compressibility factor be used to accurately correct the equation of state for the real gas, thereby obtaining a physically accurate remaining hydrogen mass. At the same time, considering the fixed routes and frequent stops of hydrogen fuel cell buses, by obtaining geographical information data of the predetermined routes, a road condition feature vector containing geographical features can be constructed. This system can capture key geographical factors affecting energy consumption, such as road slope and station spacing, providing basic data support for subsequent accurate range prediction based on energy consumption patterns.

[0029] Based on this, this method introduces a compressibility factor to modify the real gas equation of state in order to obtain a physically accurate remaining hydrogen mass, and simultaneously constructs a road condition feature vector containing geographical features.

[0030] Specifically, pressure and temperature sensors installed at the inlet of the high-pressure hydrogen storage cylinder in the hydrogen fuel cell bus are used to read the absolute pressure and thermodynamic temperature of the gas inside the cylinder at various times. Preprocessing is then performed, including: checking the validity and rationality of the pressure and temperature data, such as whether the pressure is within the 0-35 MPa range; accurately aligning time-series data from different sensors; using a low-pass digital filter to eliminate high-frequency noise interference; and using statistical methods, such as... The criteria identify and eliminate abnormal sampling points, and if necessary, repair them using interpolation to obtain the absolute pressure and thermodynamic temperature of the gas inside the pre-treated high-pressure hydrogen storage cylinder at each moment; [The last part, "Setting," appears to be an incomplete sentence or fragment.] Indexed by time, starting with the first Taking time as an example for analysis, the internal gas of the high-pressure hydrogen storage cylinder at the [time point] is [value]. The absolute pressure at any given moment is denoted as The unit is megapascal (MPa), and the thermodynamic temperature is denoted as . The unit is Kelvin.

[0031] Among them, low-pass digital filter, The criteria and interpolation methods are existing technologies and will not be elaborated upon here.

[0032] Furthermore, based on the predetermined route of the hydrogen fuel cell bus and the GPS positioning system, its geographic information data is obtained, and a road condition feature vector is constructed. The geographic information data includes road slope, station spacing, and speed limits. The GPS positioning system automatically extracts the distance of all road segments from the current location to the terminal station for the hydrogen fuel cell bus on that route, the average road slope, and the historical average travel speed. For example, the road condition feature vector of the hydrogen fuel cell bus on that route is denoted as... This is used to reflect the location of the hydrogen fuel cell bus or the road conditions of the next section it will travel on; among them, It calculates the distance of the travel path to the next scheduled bus stop based on the current location and the route map, in kilometers; It extracts the average slope from the current location to the next station based on terrain data, and the unit is percentage. The average speed is calculated based on the historical trajectory data of this road section during the same period, and the unit is kilometers per hour.

[0033] Specifically, based on the absolute pressure and thermodynamic temperature at each moment, the compressibility factor at each moment is obtained, with the first... Taking time as an example for analysis, according to the first... absolute pressure of time and thermodynamic temperature , obtained the Compression factor of time , used to characterize the first absolute pressure of time and thermodynamic temperature The degree of deviation of hydrogen from the behavior of an ideal gas, preferably, is determined by the compressibility factor. The compressibility factor of hydrogen is determined based on real gaseous property data or the equation of state for high-pressure hydrogen. Specifically, it can be obtained through methods such as: pre-stored tables of hydrogen compressibility factors at different pressures and temperatures, and based on absolute pressure... and thermodynamic temperature The compression factor is obtained by performing an interpolation query on the data table. The data table is sourced from the international standard physical property database.

[0034] It should be noted that this method uses high-precision experimental and equation data from international standard physical property databases, such as the REFPROP database, and pre-stores a compressibility factor data table covering the entire operating range. The compressibility factor is determined by a lookup table and interpolation calculation. This construction logic provides dual protection in engineering: it not only fundamentally ensures the accuracy of the compressibility factor acquisition, but also meets the reliability requirements of the vehicle system, thus providing a corrective basis for the subsequent high-precision estimation of the remaining hydrogen mass.

[0035] Furthermore, based on the structural drawings of the high-pressure hydrogen storage cylinder, the geometric volume of the high-pressure hydrogen storage cylinder is obtained. The unit is cubic meters; because the structure of a high-pressure hydrogen storage cylinder is fixed, its geometric volume is... To fix the physical constants; the physical property parameters of hydrogen are used to obtain the specific gas constant of hydrogen, which is set to a value of Physically, it represents the amount of heat required to raise the temperature by one unit per unit mass of hydrogen. Based on the compressibility factor at each moment, the real gas law is modified to obtain the remaining hydrogen mass in the high-pressure hydrogen storage tank at each moment. Taking time as an example for analysis, we obtain the first... The mass of remaining hydrogen in the high-pressure hydrogen storage cylinder at any given time is given by the following formula:

[0036] ;

[0037] In the formula, It is the first The mass of the remaining hydrogen gas in the high-pressure hydrogen storage cylinder at a given time, with dimensions of , This indicates the dimension of mass, and the unit is kilogram. The value ranges from 0 to the rated hydrogen storage capacity of the high-pressure hydrogen storage cylinder; The internal gas of the high-pressure hydrogen storage cylinder is in the first... The absolute pressure of a moment, with dimensions of , Represents the dimensions of length. The time dimension is expressed, and the unit is megapascal (MPa). ; It is the geometric volume of the high-pressure hydrogen storage cylinder, with dimensions of . The unit is cubic meters; The internal gas of the high-pressure hydrogen storage cylinder is in the first... Thermodynamic temperature at time , dimensionless , Temperature is a dimensionless quantity representing thermodynamic temperature, and its unit is Kelvin. It is the specific gas constant of hydrogen, with dimensions of . The unit is The value is ; It is the first The compressibility factor at time is dimensionless and is used to correct for non-ideal gas behavior. It is the safety redundancy coefficient, which is dimensionless and ranges from 0.90 to 0.98.

[0038] Specifically, safety redundancy factor The value range is from 0.90 to 0.98, when the safety redundancy coefficient If the value is too large, the amount of unusable hydrogen deducted will be too small, which may result in the predicted remaining hydrogen mass including some that cannot be actually used. This would lead to an overly optimistic range prediction, affecting the reliability of operational scheduling decisions and increasing the risk of vehicles breaking down due to hydrogen depletion during operation. When the safety redundancy coefficient... If the value is too small, the amount of unusable hydrogen deducted will be too high, leading to an overly conservative prediction of the remaining hydrogen mass. This could result in a waste of hydrogen resources and unnecessary hydrogen refueling scheduling, increasing operating costs. For example, this method sets a safety redundancy coefficient. It can be adjusted according to actual needs.

[0039] When the gas inside the high-pressure hydrogen storage cylinder is at the The greater the absolute pressure at a given moment and the greater the geometric volume of the high-pressure hydrogen storage cylinder, the more likely the gas inside the high-pressure hydrogen storage cylinder will be at the first moment. Thermodynamic temperature at time and the first The smaller the compression factor at each time point, the better. The greater the amount of hydrogen remaining in the high-pressure hydrogen storage cylinder at any given time, the greater the mass of hydrogen.

[0040] It should be noted that setting a safety redundancy factor The aim is to ensure the practical usability of the range prediction results and avoid the impact of unusable hydrogen due to the structural limitations of the high-pressure hydrogen storage tank on the prediction accuracy. Specifically, the high-pressure hydrogen storage tank has a valve opening pressure threshold and a minimum safe retention pressure requirement. Hydrogen below this pressure range cannot be effectively extracted for use in the fuel cell, therefore a safety redundancy factor is required. Subtract the mass of this unusable hydrogen.

[0041] Furthermore, the remaining hydrogen mass in the high-pressure hydrogen storage cylinder at each moment and the road condition characteristic vector of the hydrogen fuel cell buses on this route are combined. Together, they serve as input data for subsequent steps.

[0042] S2. Based on the remaining hydrogen mass in the high-pressure hydrogen storage cylinder and the road condition feature vector at each time, a dynamic energy consumption model of the hydrogen fuel cell system is constructed. The instantaneous hydrogen consumption rate at each time is calculated using this model, and the energy consumption benchmark value per unit mileage is obtained by combining the road condition feature vector.

[0043] It should be noted that the actual energy consumption of a hydrogen fuel cell system is not constant, but rather governed by electrochemical polarization characteristics, exhibiting nonlinear variations under different current loads. Furthermore, the auxiliary systems such as air compressors and cooling pumps that maintain the operation of the hydrogen fuel cell system have relatively high energy consumption, which fluctuates dramatically with operating conditions. In addition, as the vehicle operates, the hydrogen fuel cell system gradually ages, requiring more hydrogen to produce the same power output. This life-cycle aging effect cannot be ignored in predicting long-term driving range. Traditional estimation methods based on average efficiency cannot characterize these dynamic characteristics, which is also a major reason for the significant deviation in driving range predictions.

[0044] Specifically, calculate the first The specific method for determining the instantaneous hydrogen consumption rate of a hydrogen fuel cell bus is as follows: The instantaneous hydrogen consumption rate of the fuel cell system at the specified time is obtained through a current sensor. Current output at all times The unit is amperes; the temperature sensor obtains the temperature data of the fuel cell system at the [number]th [unit]... Operating temperature at all times The unit is Kelvin; using a pre-stored database characterizing the polarization characteristics of this type of fuel cell system, based on the fuel cell system in the first... Current output at all times and operating temperature The first one is obtained through interpolation query. The average voltage of a single cell at time t is denoted as . Then, the total output power of the fuel cell system can be calculated. The relationship is as follows:

[0045] ;

[0046] In the formula, It is the total output electrical power of the fuel cell system; It is the total number of individual cells connected in series in the fuel cell system; The fuel cell system is in the first The current output at all times; It is the first The average voltage of a single cell at time t; the larger the total number of single cells connected in series in the fuel cell system, the greater the voltage of the fuel cell system at time t. The larger the output current at any given moment, the more... The higher the average voltage of a single cell at any given time, the greater the total output power of the fuel cell system, and vice versa.

[0047] Furthermore, the system synchronously and in real-time reads data from auxiliary systems such as air compressor speed and cooling fan power, and summarizes this data to obtain the total output power of the auxiliary systems. The total output power of the fuel cell system Total output power of auxiliary systems The difference is taken as the net output power of the fuel cell system, and the fuel cell system will be used in the first... The net efficiency factor at time t is defined as: It is used to reflect the efficiency loss caused by auxiliary systems such as air compressors and cooling fans in real time.

[0048] It is important to note that the core logic behind constructing the net efficiency factor is to accurately quantify the actual impact of auxiliary system power consumption on the energy utilization efficiency of the fuel cell system, aligning with the frequent start-stop operating conditions of hydrogen fuel cell buses. During dynamic conditions such as bus stops and acceleration, the air compressor needs to maintain the oxygen supply required for the fuel cell stack reaction, and the cooling fan needs to ensure stable stack operating temperature. The power consumption of these auxiliary systems is not a constant value but fluctuates dynamically with the operating conditions, and is even higher under low-load conditions. This directly results in the total output power of the fuel cell system not being fully converted into effective power to drive the vehicle. Therefore, this method constructs a net efficiency factor, using the difference between the total output power and the auxiliary system power consumption—that is, the ratio of net output power to total output power—as the core quantitative indicator. This enables real-time dynamic characterization of auxiliary system efficiency losses. Essentially, by eliminating the influence of ineffective auxiliary power consumption, it restores the true energy utilization efficiency of the fuel cell system used to drive the vehicle, providing an efficiency benchmark that matches actual operating conditions for the subsequent accurate calculation of instantaneous hydrogen consumption rate, and avoiding errors in hydrogen consumption calculation due to neglecting auxiliary power consumption.

[0049] Specifically, the molar mass of hydrogen is obtained based on currently known technologies. The unit is grams per mole. and Faraday constant It reflects the total charge carried by 1 mole of electrons, and the unit is coulombs per mole. Based on the odometer readings of the hydrogen fuel cell bus, its historical cumulative mileage is obtained and recorded as follows: Based on the production nameplate of the fuel cell system inside the hydrogen fuel cell bus, its maximum driving range over its entire life cycle is obtained and denoted as _____. Set the aging sensitivity coefficient The specific process is as follows: A fuel cell stack sample with configurations identical to the target hydrogen fuel cell bus is selected, and aging conditions corresponding to different cumulative mileages are simulated in the laboratory to monitor the increase in hydrogen consumption rate under the same output power; long-term operational data of the target model are collected, and hydrogen consumption rate change data corresponding to different cumulative mileages are extracted and compared with laboratory data; based on the two types of data, a correlation model between the increase in hydrogen consumption rate and the proportion of cumulative mileage is established, and the correlation model is fitted using the least squares method to obtain the fitting parameters, which are then used as aging sensitivity coefficients. This value is used to reflect the sensitivity of hydrogen consumption rate to changes in aging degree, and typically ranges from 0.5 to 1.2. For example, this method sets... Based on this, an aging correction factor is constructed, with the following relationship:

[0050] ;

[0051] In the formula, It is an aging correction factor used to reflect the magnitude of hydrogen consumption rate caused by the aging performance degradation of the fuel cell system. It is the aging sensitivity coefficient; It is the cumulative mileage throughout history; It is the maximum driving range; the larger the historical cumulative driving range and the smaller the maximum driving range, the larger the aging correction factor, which reflects the greater hydrogen consumption rate caused by the aging performance degradation of the fuel cell system, and vice versa.

[0052] It should be noted that the instantaneous hydrogen consumption rate calculation model is built around Faraday's law, a well-known fundamental law in electrochemistry. The core principle of Faraday's law is that the mass of reactants consumed in an electrochemical reaction is positively correlated with the reaction current, reaction time, and molar mass of the reactants, and negatively correlated with the number of electrons transferred and the Faraday constant during the reaction. Considering the characteristics of electrochemical reactions involving hydrogen, where the number of electrons transferred is 2, this scheme incorporates the series single-cell structure of the fuel cell system, the net efficiency loss during actual system operation, and the performance degradation characteristics caused by fuel cell system aging to perform engineering modifications to Faraday's law, ultimately yielding a method for calculating the instantaneous hydrogen consumption rate suitable for hydrogen fuel cell buses.

[0053] Furthermore, the calculation yields the first... The instantaneous hydrogen consumption rate of a hydrogen fuel cell bus at any given time is expressed by the following formula:

[0054] ;

[0055] In the formula, It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses, in grams per second. ; The fuel cell system is in the first The current output at all times; It is the total number of individual cells connected in series in the fuel cell system; It is the molar mass of hydrogen gas; It is Faraday's constant; The fuel cell system is in the first Net efficiency factor at any given time; It is an aging correction factor; when the fuel cell system is in the aging correction factor; The larger the output current at any given time, the larger the total number of individual cells connected in series in the fuel cell system. The fuel cell system at the [missing information] time... When the net efficiency factor is smaller at time point and the aging correction factor is larger, the first... The faster the hydrogen fuel cell bus operates, the greater its instantaneous hydrogen consumption rate, and vice versa.

[0056] Specifically, to obtain the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses Then, combined with road condition feature vectors , obtained the The baseline value of energy consumption per unit distance at any given time is given by the following formula:

[0057] ;

[0058] In the formula, It is the first The baseline value for energy consumption per unit distance at any given time, expressed in grams per kilometer. This represents the estimated mass of hydrogen consumed by the vehicle when traveling one kilometer on the current road segment and at the current efficiency level. It is the average speed calculated based on the historical trajectory data of the same period of the road section, in kilometers per hour. In actual calculations, it can be converted into kilometers per 3600 seconds, which is used to convert the instantaneous hydrogen consumption rate in the time dimension into the energy consumption benchmark value per unit mileage in the distance dimension. It extracts the average slope from the current location to the next station based on terrain data, and the unit is percentage. It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses, in grams per second. When the first The higher the instantaneous hydrogen consumption rate of the hydrogen fuel cell bus, the lower the average speed calculated based on historical trajectory data for the same period on that road segment, and the greater the average gradient from the current location to the next stop, the better. The higher the baseline value of energy consumption per unit distance at any given time, the lower the baseline value, and vice versa.

[0059] It should be noted that this unit mileage energy consumption benchmark is a dynamic and refined prediction benchmark. It integrates the accurate remaining hydrogen mass, real-time fuel cell efficiency and aging status provided by step S1, and the specific road condition and geographical features extracted by step S2. This allows it to accurately capture the energy consumption fluctuation characteristics of high consumption uphill and low consumption downhill, providing key input parameters for subsequent accurate range prediction and fundamentally overcoming the prediction errors caused by the fixed average method.

[0060] S3. Based on the remaining hydrogen mass in the high-pressure hydrogen storage cylinder at each time point, the energy consumption benchmark value per unit mileage, and the road condition feature vector, a piecewise iterative algorithm is used to predict the maximum driving range of the hydrogen fuel cell bus.

[0061] It should be noted that the traditional average energy consumption method treats the energy consumption benchmark value per unit mileage as a constant and applies it to the remaining mileage, which cannot respond to fluctuations in road conditions ahead, resulting in large deviations in the prediction results. However, the topology of the planned route of the hydrogen fuel cell bus is known, which makes it possible to make accurate predictions based on the feedforward model. The core of this step is to use the energy consumption benchmark value per unit mileage obtained in step S2, which changes dynamically with road conditions, to perform virtual driving simulation of the future journey, and calculate the hydrogen consumption segment by segment until the limit of the remaining hydrogen mass at the current moment is reached.

[0062] Specifically, the process for predicting the maximum driving range is as follows: First, based on the digital map and route information, the remaining distance from the current location of the hydrogen fuel cell bus to the end of the route is divided into a continuous sequence of discrete road segments of fixed length, such as 100 meters. The index of each discrete road segment in this sequence is denoted as... ; Regarding the first For each discrete road segment, its corresponding road condition characteristics are extracted, mainly including average gradient and historical average travel speed. Based on the road condition characteristics of this discrete road segment, the dynamic energy consumption model of the hydrogen fuel cell system constructed in step S2 is called to calculate the energy consumption of the hydrogen fuel cell bus when it passes through the first discrete road segment. Dynamic unit mileage energy consumption benchmark value for each discrete road segment Then the fixed length and the energy consumption per unit mileage benchmark value will be used. The product of the two is used as the hydrogen fuel cell bus through the first The estimated hydrogen consumption for each discrete road segment is denoted as . .

[0063] Furthermore, the estimated hydrogen consumption mass for each discrete road segment is obtained through iteration, and a virtual consumption cycle is executed, based on the current remaining hydrogen mass obtained in step S1. The estimated hydrogen consumption of each discrete road segment is deducted segment by segment; this process is iterated until the sum of the cumulative deducted hydrogen consumption is close to or equal to the current remaining hydrogen mass. At this point, the total length of all the discrete road segments that have been covered is calculated, and this total length is the maximum driving range of the hydrogen fuel cell bus, thus determining the farthest distance that it can physically cover.

[0064] S4. Visualize the maximum driving range and trigger a hierarchical closed-loop control strategy based on the real-time comparison between the maximum driving range and the remaining range of the current route.

[0065] It's important to note that the ultimate goal of accurate forecasting is to ensure operational safety and achieve proactive energy management. For buses on fixed routes, when forecasts indicate insufficient range, relying solely on driver experience for energy-saving measures is limited and inconsistent. This step establishes a closed loop between forecasting and control, with the vehicle controller proactively intervening to optimize system operation, thereby transforming predicted risks into controllable strategies.

[0066] Specifically, firstly, the system obtains the remaining physical mileage of the vehicle to the destination in real time, and uses the difference between the maximum range and the remaining mileage of the current route as the range safety margin. Finally, based on the range safety margin value, the system automatically executes the following graded adjustment measures: when the range safety margin is greater than or equal to 0 kilometers and less than or equal to 5 kilometers, a level 1 response is triggered, reminding the driver that the hydrogen fuel is insufficient, and generating a recommended maximum cruising speed to prompt the driver to drive smoothly; when the range safety margin is less than 0 kilometers, a level 2 response is triggered, at which point it is predicted that the hydrogen fuel is insufficient to reach the destination, and the vehicle controller immediately takes over the authority and executes a forced energy-saving strategy: forcibly reducing the maximum speed of the air compressor, prohibiting rapid acceleration, and forcing the hydrogen fuel cell bus to operate in a low-energy consumption state.

[0067] Through the above adjustments, this method can reduce the actual instantaneous hydrogen consumption rate, thereby increasing the physical mileage while keeping the remaining hydrogen mass constant, and achieving accurate prediction of the driving range performance of hydrogen fuel cell vehicles.

[0068] Based on the above steps, a prediction result for the driving range of hydrogen fuel cell vehicles can be obtained, resulting in a driving range prediction result chart and a driving range prediction comparison chart. Figure 2 This is a graph showing the predicted range. Figure 3 This is a comparison chart of predicted battery life.

[0069] in, Figure 2 By simultaneously presenting the dynamic fluctuation curve of the maximum driving range, the linear decrease curve of the remaining route length, and the driving range safety margin curve corresponding to the difference between the two, this method reflects that during the operation of hydrogen fuel cell buses, the maximum driving range will dynamically change with hydrogen consumption and road energy consumption fluctuations. The driving range safety margin can quantify the matching risk between the current hydrogen supply and the remaining route in real time. This demonstrates that this method can not only output accurate dynamic driving range results adapted to actual operating conditions, but also intuitively characterize the driving range risk status, providing a reliable real-time basis for triggering subsequent graded energy management strategies. This effectively makes up for the shortcomings of traditional driving range prediction, which only outputs fixed values ​​and cannot perceive dynamic risks.

[0070] in, Figure 3By comparing the prediction curves of the method of this invention with the prediction curves of the existing static linear method and the fitting relationship with the actual remaining route, it is reflected that the prediction results of the existing static linear method deviate significantly from the actual remaining route and cannot adapt to dynamic operating conditions. In contrast, the prediction curve of the method of this invention is closer to the dynamic changes of the actual remaining route and intuitively presents the accuracy advantage of this method over the existing methods. This proves that compared with the existing static linear extrapolation method, the method of this invention can accurately adapt to the dynamic energy consumption fluctuations and road condition characteristics of hydrogen fuel cell buses, and significantly improve the accuracy and reliability of range prediction.

[0071] This invention also discloses a hydrogen fuel cell vehicle range prediction system, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a hydrogen fuel cell vehicle range prediction method according to the present invention.

[0072] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

Claims

1. A method for predicting the driving range of a hydrogen fuel cell vehicle, characterized in that, include: The absolute pressure and thermodynamic temperature of the gas inside the high-pressure hydrogen storage tank of the hydrogen fuel cell bus are collected in real time and preprocessed. Geographic information data is obtained based on the planned route of the hydrogen fuel cell bus and the GPS positioning system, and a road condition feature vector is constructed. The road condition feature vector is... , It calculates the distance of the travel path to the next scheduled bus stop based on the current location and the route map; It extracts the average slope from the current location to the next station based on terrain data; The average speed is calculated based on the historical trajectory data of this road section during the same period. For indexing time; Based on the absolute pressure and thermodynamic temperature at each moment, the compressibility factor is obtained. Using this compressibility factor, the equation of state for a real gas is corrected to obtain the remaining hydrogen mass in the high-pressure hydrogen storage tank at each moment, including: ； In the formula, It is the first The mass of remaining hydrogen in the high-pressure hydrogen storage cylinder at any given time; The internal gas of the high-pressure hydrogen storage cylinder is in the first... The absolute pressure of every moment; It is the geometric volume of the high-pressure hydrogen storage cylinder; The internal gas of the high-pressure hydrogen storage cylinder is in the first... Thermodynamic temperature at any given moment; It is the specific gas constant of hydrogen; It is the first The compression factor of time; It is the safety redundancy factor; For indexing time; The system acquires the output current and operating temperature of the fuel cell stack, queries the polarization characteristic database to obtain the single-cell voltage, and calculates the total output power; it also acquires the auxiliary system power consumption in real time and calculates the net output power and net efficiency factor; and it calculates the aging correction factor by combining the vehicle's cumulative mileage and aging sensitivity coefficient, including: ； In the formula, It is an aging correction factor; It is the aging sensitivity coefficient; It is the cumulative mileage throughout history; It is the maximum driving range; Based on Faraday's law and introducing net efficiency factors and aging correction factors, a calculation model for instantaneous hydrogen consumption rate is constructed. This model is used to calculate the instantaneous hydrogen consumption rate, including: ； In the formula, It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses at any given time; The fuel cell system is in the first The current output at all times; It is the total number of individual cells connected in series in the fuel cell system; It is the molar mass of hydrogen gas; It is Faraday's constant; The fuel cell system is in the first Net efficiency factor at any given time; It is an aging correction factor; For indexing time; The benchmark value of energy consumption per unit mileage is obtained by combining the road condition feature vector; based on the remaining hydrogen mass, the benchmark value of energy consumption per unit mileage and the road condition feature vector, the remaining journey is divided into discrete road segments. The hydrogen consumption required by the vehicle to pass through each discrete road segment is calculated by a segmented iterative algorithm and accumulated until the cumulative hydrogen consumption reaches the remaining hydrogen mass, thereby predicting the maximum driving range of the vehicle. The maximum driving range is visualized and output, and the maximum driving range is compared with the remaining driving range in real time. When a driving range risk is identified, a graded energy management strategy is automatically triggered to dynamically adjust the operating parameters of the fuel cell system.

2. The method for predicting the driving range of a hydrogen fuel cell vehicle according to claim 1, characterized in that, The method of obtaining the compressibility factor at each moment based on the absolute pressure and thermodynamic temperature includes: A pre-stored table of compressibility factors for hydrogen at different pressures and temperatures is used to interpolate and look up the compressibility factor in the table based on the absolute pressure and thermodynamic temperature.

3. The method for predicting the driving range of a hydrogen fuel cell vehicle according to claim 1, characterized in that, The process of obtaining the energy consumption benchmark value per unit mileage includes: ； In the formula, It is the first The baseline value of energy consumption per unit distance at any given time; The average speed is calculated based on the historical trajectory data of this road section during the same period. It extracts the average slope from the current location to the next station based on terrain data; It is the first Instantaneous hydrogen consumption rate of hydrogen fuel cell buses at any given time; This is the index for the time.

4. The method for predicting the driving range of a hydrogen fuel cell vehicle according to claim 1, characterized in that, The tiered energy management strategy includes: The system obtains the remaining physical mileage of the vehicle from the terminal station in real time and uses the difference between the maximum range and the remaining mileage of the current route as the range safety margin. When the range safety margin is greater than or equal to 0 kilometers and less than or equal to 5 kilometers, a level 1 response is triggered to remind the driver that the hydrogen fuel is low and a recommended maximum cruising speed is generated to prompt the driver to drive smoothly. When the range safety margin is less than 0 kilometers, a level 2 response is triggered, and the vehicle controller immediately takes over the authority and executes a forced energy-saving strategy: forcibly reducing the maximum speed of the air compressor, prohibiting rapid acceleration, and forcing the hydrogen fuel cell bus to operate in a low-energy consumption state.

5. A hydrogen fuel cell vehicle range prediction system, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a method for predicting the range performance of a hydrogen fuel cell vehicle according to any one of claims 1-4.

Images