A coordination optimization method, system, device and medium for hydrogen fuel cell vehicle

Abstract

The present application relates to the field of fuel cell technology, and discloses a coordinated optimization method, system, device and medium for a hydrogen fuel cell vehicle, including: determining a target output voltage and a target output current corresponding to a stack in a hydrogen fuel cell vehicle; determining a sub-stack efficiency score corresponding to a sub-stack, and determining a sub-stack stability score corresponding to a sub-stack; comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining a main stack and a slave stack in a sub-stack according to the result of the comprehensive score; generating a main stack output parameter corresponding to the main stack according to the target output voltage and the target output current, and generating a slave stack output parameter corresponding to the slave stack; dynamically adjusting the working state of the main stack according to the main stack output parameter, and dynamically adjusting the working state of the slave stack according to the slave stack output parameter to meet the target load requirement. Its beneficial effect is to optimize and adjust the output of multiple battery stacks to ensure uniform sharing of the load.

Description

Technical Field

[0001] The present application relates to the field of fuel cell technology, and in particular to a coordination optimization method, system, equipment and medium for a hydrogen fuel cell vehicle. Background Art

[0002] Hydrogen fuel cell vehicles are an important way to protect the power system, and are mainly used for load protection in important meetings, large-scale events, important examinations, power maintenance, etc. At present, since a single fuel cell stack is difficult to meet the real-time power requirements of high-power vehicles, in order to meet the needs of hydrogen fuel cell vehicles, a hydrogen fuel cell group is composed of multiple hydrogen fuel cell reactors in parallel, with a power density of 700W / kg and a service life of up to 30,000h.

[0003] However, in the case of parallel battery stacks, the voltages of different battery stacks may be different, which will lead to uneven current distribution. One battery stack may output more current, while the other battery stack is less burdened. This voltage difference may cause unstable operation of the battery stack, affecting the overall efficiency and life. In addition, the internal resistance of the battery stack may vary due to manufacturing differences, service life and other factors. The difference in internal resistance will lead to uneven current distribution. Even at the same voltage, the power output of different battery stacks may be different. This difference may be due to factors such as aging of the battery stack and temperature changes.

[0004] Therefore, effective methods are needed to optimize and adjust the output of multiple battery stacks to ensure uniform sharing of the load and the overall stability of hydrogen fuel cell vehicles. Summary of the invention

[0005] The present application provides a coordinated optimization method, system, device and medium for a hydrogen fuel cell vehicle, which solves the technical problem of how to optimize and adjust the output of multiple battery stacks, and achieves the technical effect of ensuring uniform load sharing and the overall stability of the hydrogen fuel cell vehicle.

[0006] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0007] In a first aspect, an embodiment of the present application provides a coordination optimization method for a hydrogen fuel cell vehicle, the method comprising:

[0008] Based on the acquired target load demand of the hydrogen fuel cell vehicle, determining a target output voltage and a target output current corresponding to a battery stack in the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel;

[0009] Determining a sub-stack efficiency score corresponding to the sub-stack, and determining a sub-stack stability score corresponding to the sub-stack;

[0010] Comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining a main stack and a slave stack in the sub-stack according to the result of the comprehensive scoring;

[0011] According to the target output voltage and the target output current, using a preset output characteristic model to generate a main stack output parameter corresponding to the main stack, and to generate a slave stack output parameter corresponding to the slave stack;

[0012] The working state of the main fuel cell stack is dynamically adjusted according to the output parameter of the main fuel cell stack, and the working state of the slave fuel cell stack is dynamically adjusted according to the output parameter of the slave fuel cell stack to meet the target load demand.

[0013] The coordinated optimization method of a hydrogen fuel cell vehicle provided in this embodiment determines the target output voltage and target output current of the stack by the acquired target load demand, so that the stack can be dynamically adjusted according to the real-time load demand. This adjustment can optimize the power output of the stack under different operating conditions, thereby improving the overall performance and efficiency of the hydrogen fuel cell vehicle. Next, since the stack includes at least two sub-stacks in parallel, it is necessary to accurately evaluate the performance of each sub-stack by determining the efficiency score and stability score of the sub-stack. It is helpful to identify the sub-stacks with lower performance and optimize or replace them to ensure the reliability and stability of the entire stack. Then, the roles of the main stack and the slave stack are determined by comprehensive scoring, which helps to allocate resources to the stack with the best performance. The main stack undertakes the main energy conversion task, while the slave stack is auxiliary or standby. This allocation improves the overall efficiency and reliability of the hydrogen fuel cell vehicle. Based on the output parameters of the main stack and the slave stack generated by the preset output characteristic model, the working state can be accurately adjusted to ensure that the output of the stack meets the target load demand, improve the dynamic response capability and operating efficiency, and thus improve the overall performance of the hydrogen fuel cell vehicle.

[0014] Optionally, determining a target output voltage and a target output current corresponding to a fuel cell stack in the hydrogen fuel cell vehicle based on the acquired target load demand of the hydrogen fuel cell vehicle includes:

[0015] Obtaining the current load demand of the hydrogen fuel cell vehicle;

[0016] Using Kalman filtering to smooth the current load demand data to obtain the smoothed target load demand;

[0017] According to the target load demand, the target output voltage and the target output current corresponding to the battery stack are generated using a preset fuzzy rule base.

[0018] This embodiment obtains the current load demand, and the application of Kalman filtering can effectively smooth the load demand data and eliminate the influence of noise and outliers. The data sequence becomes more stable and reasonable. This processing can improve the reliability of the data, thereby improving the accuracy of the response of the stack to load changes. Then, through the preset fuzzy rule base, the target output voltage and target output current of the stack are generated according to the smoothed target load demand. The stack can optimize the output under various load conditions to ensure the performance and efficiency of hydrogen fuel cell vehicles.

[0019] Optionally, determining the sub-stack efficiency score corresponding to the sub-stack includes:

[0020] Obtaining the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period;

[0021] Determining an average output voltage of the output voltage within the preset time period, and determining an average output current of the output current within the preset time period;

[0022] Determining an average output power corresponding to the sub-stack according to the average output voltage and the average output current;

[0023] Inputting the hydrogen flow rate and the oxygen flow rate into a preset power conversion model to generate an average input power corresponding to the sub-stack;

[0024] The sub-stack efficiency score is determined based on the ratio of the average output power to the average input power.

[0025] This embodiment can reduce the impact of instantaneous fluctuations by obtaining the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period, and calculating the average value of the output voltage and output current, so that the evaluated voltage and current values ​​are more representative and better reflect the actual performance of the sub-stack. The average output power calculated based on accurate voltage and current data provides the necessary data for the performance evaluation of the sub-stack. By inputting hydrogen and oxygen flow data into the power conversion model, the energy demand of the sub-stack can be effectively estimated, thereby evaluating its energy efficiency and working status. Finally, by calculating the ratio of output power to input power, the efficiency of the sub-stack can be accurately evaluated. This efficiency score intuitively reflects the energy efficiency level of the sub-stack, which helps to optimize its performance and energy utilization efficiency.

[0026] Optionally, determining the sub-stack stability score corresponding to the sub-stack includes:

[0027] Obtaining the output voltage and output current of the sub-stack within a preset time period;

[0028] Determining a voltage standard deviation of the output voltage within the preset time period, and determining a current standard deviation of the output current within the preset time period;

[0029] The sub-stack stability score is determined based on the voltage standard deviation and the current standard deviation using a preset stability score model.

[0030] This embodiment measures the stability by obtaining the output voltage and output current of the sub-stack within a preset time period and calculating the standard deviation of the voltage and current. The standard deviation reflects the fluctuation of the data and further evaluates the performance of the sub-stack. Converting the standard deviation into a stability score makes the stability assessment of the battery more intuitive and quantitative, and facilitates comparison and decision-making.

[0031] Optionally, the comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining the main stack and the slave stack in the sub-stack according to the result of the comprehensive scoring, includes:

[0032] Weighting the sub-stack efficiency score and the sub-stack stability score to obtain a comprehensive score;

[0033] Clustering each of the sub-stacks to obtain a stack cluster including one or more sub-stacks;

[0034] Determine the representative features within each of the battery stack clusters, and for any battery stack cluster, determine the battery stack feature set to which the representative features within the cluster belong;

[0035] Obtaining a risk factor for each of the battery stack feature sets, and screening out a candidate battery stack feature set based on the risk factor;

[0036] In the battery stack cluster corresponding to the candidate battery stack feature set, the comprehensive scores of the various sub-battery stacks are sorted from high to low, and the sub-battery stack corresponding to the highest comprehensive score is determined as the main battery stack, and the remaining sub-battery stacks are determined as the slave battery stacks.

[0037] This embodiment first comprehensively considers the sub-stack efficiency score and the sub-stack stability score through a weighted summation method, and provides a comprehensive performance evaluation. This method can balance different performance indicators to ensure that the final score is more representative. Then, the sub-stacks are classified through a clustering algorithm, and sub-stacks with similar performance can be divided into the same cluster, thereby simplifying the subsequent analysis and decision-making process. Determining the representative features within the cluster can effectively reduce data complexity and improve the efficiency and accuracy of feature selection. By calculating and screening the risk coefficient, it is ensured that the selected stack feature set has the lowest risk, which enhances the safety and reliability of stack selection. According to the comprehensive score and risk assessment results, the sub-stack with the highest comprehensive score is selected as the main stack, and the rest are selected as slave stacks. It helps to optimize the configuration of the stack while ensuring performance.

[0038] Optionally, the preset output characteristic model includes a support vector machine, a decision tree and a random forest; the main stack output parameters include a main output voltage, a main output current and a main output power; the slave stack output parameters include a slave output voltage, a slave output current and a slave output power; the method of generating the main stack output parameters corresponding to the main stack and generating the slave stack output parameters corresponding to the slave stack using the preset output characteristic model according to the target output voltage and the target output current includes:

[0039] According to the target output voltage and the target output current, using the support vector machine to generate a master output voltage corresponding to the master stack and a slave output voltage corresponding to the slave stack;

[0040] According to the target output voltage and the target output current, using the decision tree to generate a main output current corresponding to the main battery stack and a slave output current corresponding to the slave battery stack;

[0041] According to the target output voltage and the target output current, the random forest is used to generate a main output power corresponding to the main fuel cell stack and a slave output power corresponding to the slave fuel cell stack.

[0042] This embodiment can accurately predict the main output voltage of the main stack and the slave output voltage of the slave stack by using a support vector machine. The decision tree can generate the main output current of the main stack and the slave output current of the slave stack by analyzing the target output voltage and the target output current. The random forest can generate the main output power of the main stack and the slave output power of the slave stack by training multiple decision trees and integrating their results. By using three different machine learning models, namely support vector machines, decision trees and random forests, the voltage, current and power of the main stack and the slave stack in hydrogen fuel cell vehicles can be comprehensively and accurately predicted. This method enables hydrogen fuel cell vehicles to optimize the performance of the stack according to the target output parameters in complex practical applications, thereby improving the overall efficiency and stability of hydrogen fuel cell vehicles.

[0043] Optionally, after dynamically adjusting the working state of the main fuel cell stack according to the output parameter of the main fuel cell stack, and dynamically adjusting the working state of the slave fuel cell stack according to the output parameter of the slave fuel cell stack, the method further includes:

[0044] Comparing the main output voltage with the target output voltage, and if the difference in the comparison result exceeds a voltage deviation threshold, re-adjusting the working state of the main fuel cell stack and the working state of the slave fuel cell stack;

[0045] The main output current is compared with the target output current, and when the difference in the comparison result exceeds a current deviation threshold, the working state of the main fuel cell stack and the working state of the slave fuel cell stack are readjusted.

[0046] This embodiment can ensure that the hydrogen fuel cell vehicle always remains within the expected performance range by continuously monitoring the main output voltage and main output current of the main stack and making adjustments when the deviation exceeds the set threshold. This can effectively deal with fluctuations caused by performance degradation of the main stack or load changes, thereby improving the overall operating stability and reliability of the hydrogen fuel cell vehicle. It can ensure the coordinated work of the main stack and the slave stack, optimize power output, ensure that the target load requirements are met, and reduce the potential risk of failure caused by deviations.

[0047] Optionally, the method further comprises:

[0048] When the battery stack is used in conjunction with a plurality of auxiliary power supplies, obtaining performance parameters of the auxiliary power supplies;

[0049] According to the performance parameters, a preset performance-power range model is used to determine the output power range corresponding to the auxiliary power supply;

[0050] With maximizing power supply efficiency, equipment power supply reliability and equipment life as objective functions, and the output power of the auxiliary power supply satisfying the output power range as a constraint, a multi-objective optimization algorithm is used to generate an optimized power allocation scheme; wherein, the equipment power supply reliability represents the proportion of time to maintain the target load demand.

[0051] This embodiment uses auxiliary power sources (generators, solar panels, and lithium battery packs) in combination, so that even if the main power source fails, the auxiliary power source can continue to supply power to ensure the normal operation of the hydrogen fuel cell vehicle. The power generation efficiency of the generator, the maximum output power of the solar panel, and the capacity of the lithium battery pack are monitored in real time. Through the preset performance-power range model, the output power range of the auxiliary power source is determined according to the performance parameters of the auxiliary power source to ensure that the hydrogen fuel cell vehicle can meet the real-time changing load requirements and optimize the efficiency of each auxiliary power source. The power allocation plan is generated by using a multi-objective optimization algorithm, which comprehensively considers power supply efficiency, equipment power supply reliability, and equipment life, and can find the best balance between the three to improve overall performance.

[0052] Optionally, the auxiliary power source includes a generator, a solar panel and a lithium battery pack;

[0053] The performance parameters include the power generation efficiency of the generator, the maximum output power of the solar panel and the capacity of the lithium battery pack.

[0054] Optionally, the generating an optimized power allocation scheme by using a multi-objective optimization algorithm further includes satisfying the following conditions:

[0055] The target load demand is equal to the sum of the output power of each battery stack and the output power of the auxiliary power supply;

[0056] The output power of each of the sub-stacks must be within the design limit.

[0057] Optionally, the objective function includes:

[0058]

[0059] Power supply efficiency = output power of battery stack or auxiliary power supply / target load demand

[0060] Among them, w1, w2, w3 are weight coefficients; a i is the power supply efficiency of the ith sub-stack or auxiliary power supply; b i The reliability of power supply for the i-th sub-stack or auxiliary power supply equipment; c i is the equipment life of the ith sub-stack or auxiliary power supply.

[0061] Optionally, the method further comprises:

[0062] Obtaining the temperature change rate and current load power of each sub-stack, and using a fuzzy logic algorithm to determine the temperature change trend membership corresponding to the sub-stack; wherein the temperature change trend membership is used to characterize the fuzzification degree of the temperature change trend;

[0063] Generate an adjustment power corresponding to the sub-stack according to the current load power and the temperature change trend membership;

[0064] According to the adjusted power, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

[0065] This embodiment uses a fuzzy logic algorithm to obtain the temperature change rate and load power of the sub-stack in real time, and fuzzifies them into membership values, which can accurately reflect the actual operating status of the sub-stack and its temperature change trend. Based on the fuzzified membership values ​​and preset rules, accurate adjustment power (including heating and cooling power) is generated to optimize the performance and stability of the sub-stack. The flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the adjustment power to ensure that the sub-stack can maintain the best working state under various load conditions, thereby improving overall efficiency and equipment life.

[0066] Optionally, the method further comprises:

[0067] When the temperature change rate exceeds a preset temperature change threshold, adjusting the membership function in the fuzzy logic algorithm to obtain an adjusted fuzzy logic algorithm;

[0068] Determining, according to the adjusted fuzzy logic algorithm, an updated temperature change trend membership corresponding to the sub-stack;

[0069] generating an updated adjusted power corresponding to the sub-stack according to the current load power and the updated temperature change trend membership;

[0070] According to the updated adjusted power, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

[0071] This embodiment can deal with situations where the temperature change rate exceeds the preset threshold by adjusting the membership function in the fuzzy logic algorithm. This adjustment is intended to improve the adaptability of the algorithm and ensure that a more accurate control strategy can be generated when the temperature change rate is fast, thereby optimizing the operation effect of the sub-stack.

[0072] Optionally, the method further comprises:

[0073] Determine the current running time corresponding to the sub-stack;

[0074] According to the target load demand, with the goal of extending the current operating time, a dynamic programming algorithm is used to determine the predicted load power demand corresponding to the sub-stack in a future period of time;

[0075] According to the predicted load power demand, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

[0076] This embodiment accurately calculates the current operating time of the sub-stack. Then, a dynamic programming algorithm is used to predict the future load power demand based on the target load demand. By modeling historical load data and current hydrogen inventory, future load conditions can be predicted and optimized to meet the goal of extending the sub-stack operating time. This prediction can not only improve the operating efficiency of the stack, but also make adjustments when the load fluctuates to ensure the stability of the stack. The flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the predicted load power demand. This dynamic adjustment can accurately match the output power demand of the sub-stack and optimize the operating performance of the hydrogen fuel cell. This adjustment method can adapt to different load conditions, thereby improving the overall efficiency and stability of hydrogen fuel cell vehicles.

[0077] Optionally, determining the current operating time corresponding to the sub-stack includes:

[0078] Obtaining the current hydrogen inventory, sub-stack efficiency and peak power demand of each of the sub-stacks;

[0079] Determining a required amount of hydrogen corresponding to the sub-stack according to the peak power demand and the sub-stack efficiency;

[0080] The current operating time corresponding to the sub-stack is determined according to the current hydrogen inventory and the required hydrogen quantity.

[0081] This embodiment can accurately calculate the required amount of hydrogen by obtaining the current hydrogen inventory, sub-stack efficiency and peak power demand of the sub-stack, thereby accurately determining the hydrogen demand of the sub-stack under various operating conditions. Furthermore, based on the ratio of the current hydrogen inventory to the required hydrogen volume, the current operating time of the sub-stack can be estimated, which provides an important basis for reasonable operation and maintenance planning.

[0082] Optionally, the dynamic programming algorithm includes:

[0083] Determining a predicted required amount of hydrogen corresponding to the sub-stack according to the predicted load power demand and the sub-stack efficiency;

[0084] Determining a predicted operating time according to the current hydrogen inventory and the predicted required hydrogen quantity;

[0085] When the predicted running time is lower than the current running time, the dynamic programming algorithm is continuously iterated until the predicted running time exceeds the current running time, thereby obtaining the predicted load power demand corresponding to the sub-stack.

[0086] This embodiment combines the predicted load power demand and the sub-stack efficiency to accurately calculate the amount of hydrogen required by the sub-stack under future load conditions. Then, by calculating the ratio of the current hydrogen inventory to the predicted required hydrogen amount, the predicted operation time of the sub-stack is accurately estimated. Finally, by continuously iterating and optimizing the dynamic programming algorithm until the predicted operation time exceeds the current operation time, the accuracy of the predicted load power demand is ensured.

[0087] Optionally, the method further comprises:

[0088] Obtaining the current operating temperature and current ambient temperature of the sub-stack;

[0089] When the current working temperature is lower than a preset working temperature threshold and / or the current ambient temperature is lower than a preset ambient temperature threshold, starting a drainage heating function and a water storage return function;

[0090] Monitor the liquid flow rate during drainage heating and the liquid level during storage water return;

[0091] The adjusted heating power and water storage recovery rate are determined according to the liquid flow and the liquid level, and dynamic adjustments are made according to the heating power and the water storage recovery rate.

[0092] This embodiment monitors the working temperature and ambient temperature in real time. When it detects that the temperature is lower than the preset threshold, it automatically starts the drainage heating and water storage return function to effectively prevent the freezing of water in the drainage pipe and the battery stack, thereby protecting the battery stack from the influence of low temperature. The liquid flow and liquid level are monitored in real time, and the heating power and return rate are dynamically adjusted according to the actual data to ensure the normal operation of the battery stack, prevent excessive or insufficient water, and optimize the humidity inside the battery stack.

[0093] Optionally, the method further comprises:

[0094] Obtaining the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and determining the load power demand corresponding to the sub-stack by using a preset first fuzzy control algorithm in combination with the target load demand;

[0095] According to the power demand and the temperature gradient, determining the adjusted current density corresponding to the sub-stack by a preset second fuzzy control algorithm;

[0096] According to the adjustment of current density, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

[0097] This embodiment obtains the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and uses the first fuzzy control algorithm to process these data. It can accurately evaluate the working state of the sub-stack and predict its power demand. Then, the second fuzzy control algorithm determines the adjustment current density according to the power demand and the temperature change gradient. It can dynamically adjust the current density during the operation of the sub-stack to maintain the optimal working state and efficiency of the stack. Finally, the flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the adjusted current density. It can optimize the gas and liquid flow in the sub-stack in real time to keep the sub-stack under the best operating conditions, ensure the operating stability and efficiency of the sub-stack, and thus improve the overall performance and responsiveness of the sub-stack.

[0098] Optionally, the method further comprises:

[0099] Obtaining weight distribution data of a hydrogen fuel cell vehicle box, and constructing a weight distribution matrix according to the weight distribution data; wherein the weight distribution matrix is ​​used to characterize weight data of different areas of the box;

[0100] According to the weight distribution matrix, the box is analyzed using finite element software to obtain an overweight area;

[0101] According to the overweight area, the structural design parameters of the box are adjusted by finite element software, and the structure of the box is adjusted according to the structural design parameters.

[0102] This embodiment obtains the weight distribution data of the hydrogen fuel cell vehicle box in real time, and constructs a weight distribution matrix based on the weight distribution data. Each element in the matrix represents the weight of the corresponding area. Then, the box is analyzed using finite element software to identify the overweight area of ​​the box, evaluate its stress and load-bearing capacity in actual use, and provide a basis for design optimization. The analysis results can reveal potential overweight areas, which helps to discover and solve structural problems in advance. According to the analysis results of the overweight area, the structural design parameters of the box, such as material type, thickness, geometry, etc., are adjusted. Through optimized design, the load-bearing capacity and stability of the box are enhanced, the load in the overweight area is reduced, and the potential risk of failure caused by insufficient design is reduced, thereby improving the reliability and durability of the overall structure.

[0103] Optionally, the structural design parameters include redistributing loads; and adjusting the structure of the box according to the structural design parameters includes:

[0104] Obtain the weight, size and position of each device in the box, and determine the center of gravity position of each device;

[0105] Weighting the center of gravity position to obtain the overall center of gravity position;

[0106] Determining the offset between the overall center of gravity position and the geometric center of the box, and if the determination result shows that the offset is greater than a preset offset threshold, inputting the weight, the size, the position, the center of gravity position and the geometric center into a dynamic balancing algorithm to generate a load adjustment plan;

[0107] The equipment in the box is adjusted according to the load adjustment scheme.

[0108] This embodiment obtains the weight, size and position of each device in the box to provide basic data for further calculation of the center of gravity position. The overall center of gravity position is obtained by weighted calculation of the center of gravity positions of all devices. This weighted method combines the mass and position data of all devices so that the overall center of gravity position can truly reflect the mass distribution of the equipment in the entire box. The offset between the overall center of gravity position and the geometric center of the box is calculated and compared with the preset threshold to ensure the stability and safety of the box during transportation. If the offset exceeds the preset threshold, the dynamic balancing algorithm will generate a load adjustment plan to optimize the equipment layout to reduce the center of gravity offset, thereby improving the transportation stability of the box. Finally, the equipment is actually adjusted according to the load adjustment plan to ensure that the overall center of gravity position is aligned with the geometric center. This not only improves the stability during transportation, but also effectively avoids potential safety hazards caused by center of gravity offset.

[0109] In a second aspect, an embodiment of the present application provides a coordination optimization system for a hydrogen fuel cell vehicle, the system comprising:

[0110] A target output determination module, used to determine the target output voltage and target output current corresponding to the battery stack in the hydrogen fuel cell vehicle based on the acquired target load demand of the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel;

[0111] An efficiency scoring and stability scoring module, used to determine a sub-stack efficiency score corresponding to the sub-stack, and to determine a sub-stack stability score corresponding to the sub-stack;

[0112] A comprehensive scoring module, used for comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining the main stack and the slave stack in the sub-stack according to the result of the comprehensive scoring;

[0113] an output parameter determination module, configured to generate a main stack output parameter corresponding to the main stack and a slave stack output parameter corresponding to the slave stack using a preset output characteristic model according to the target output voltage and the target output current;

[0114] A dynamic adjustment module is used to dynamically adjust the working state of the main fuel cell stack according to the output parameters of the main fuel cell stack, and dynamically adjust the working state of the slave fuel cell stack according to the output parameters of the slave fuel cell stack to meet the target load demand.

[0115] The coordinated optimization system of a hydrogen fuel cell vehicle provided in this embodiment determines the target output voltage and target output current of the stack by the acquired target load demand, so that the stack can be dynamically adjusted according to the real-time load demand. This adjustment can optimize the power output of the stack under different operating conditions, thereby improving the overall performance and efficiency of the hydrogen fuel cell vehicle. Next, since the stack includes at least two sub-stacks in parallel, it is necessary to accurately evaluate the performance of each sub-stack by determining the efficiency score and stability score of the sub-stack. It is helpful to identify the sub-stacks with lower performance and optimize or replace them to ensure the reliability and stability of the entire stack. Then, the roles of the main stack and the slave stack are determined by comprehensive scoring, which helps to allocate resources to the stack with the best performance. The main stack undertakes the main energy conversion task, while the slave stack serves as an auxiliary or standby. This allocation improves the overall efficiency and reliability of the hydrogen fuel cell vehicle. Based on the output parameters of the main stack and the slave stack generated by the preset output characteristic model, the working state can be accurately adjusted to ensure that the output of the stack meets the target load demand, improve the dynamic response capability and operating efficiency, and thus improve the overall performance of the hydrogen fuel cell vehicle.

[0116] In a third aspect, an embodiment of the present application provides a computer device, including:

[0117] A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above-mentioned coordination optimization method for hydrogen fuel cell vehicles by executing the computer instructions.

[0118] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above-mentioned coordinated optimization method for hydrogen fuel cell vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0119] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0120] Figure 1 A flow chart of a coordination optimization method for a hydrogen fuel cell vehicle provided in an embodiment of the present application;

[0121] Figure 2 A flowchart of step S101 provided in an embodiment of the present application;

[0122] Figure 3 A flowchart of determining a sub-stack efficiency score corresponding to a sub-stack in step S103 provided in an embodiment of the present application;

[0123] Figure 4 A flowchart of determining a sub-stack stability score corresponding to a sub-stack in step S103 provided in an embodiment of the present application;

[0124] Figure 5 A flowchart of step S105 provided in an embodiment of the present application;

[0125] Figure 6 A flowchart of step S107 provided in an embodiment of the present application;

[0126] Figure 7 A flowchart of the use of an auxiliary power supply provided in an embodiment of the present application;

[0127] Figure 8 A flow chart of temperature change adjustment provided in an embodiment of the present application;

[0128] Fig. 9 A flow chart of updating temperature change adjustment provided in an embodiment of the present application;

[0129] Fig.10 A flowchart of extending the running time provided by an embodiment of the present application;

[0130] Fig.11 A flowchart of step S501 provided in an embodiment of the present application;

[0131] Fig.12 A flow chart of a dynamic programming algorithm provided in an embodiment of the present application;

[0132] Fig.13 A flow chart of the heating and water storage function provided in an embodiment of the present application;

[0133] Fig.14A flow chart for adjusting current density provided in an embodiment of the present application;

[0134] Fig.15 A flow chart for adjusting weight distribution provided in an embodiment of the present application;

[0135] Fig.16 A flow chart of adjusting the structure of the box according to the structural design parameters provided in the embodiment of the present application;

[0136] Fig.17 A block diagram of a coordination optimization system for a hydrogen fuel cell vehicle provided in an embodiment of the present application;

[0137] Fig.18 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0138] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0139] As a tool for power system protection, hydrogen fuel cell vehicles mainly play a role in important meetings, large-scale events, important examinations, power maintenance and other scenarios. These application scenarios usually require a stable and reliable power supply, and hydrogen fuel cell vehicles can provide the necessary load support to ensure the normal operation of the power system at critical moments. A single hydrogen fuel cell stack cannot meet the real-time power requirements of high-power vehicles, so multiple battery stacks are required to be used in parallel to form a hydrogen fuel cell group. This configuration has a power density of 700W / kg and a long service life (up to 30,000 hours), which can meet the needs of high-power applications. In a parallel configuration, the voltage of different battery stacks may be different. The voltage difference will lead to uneven current distribution, that is, some battery stacks may output more current, while others are less burdened. This uneven current distribution will affect the stability, overall efficiency and service life of the battery stack. The internal resistance of the battery stack may also vary due to manufacturing differences, usage time and other factors. The difference in internal resistance further exacerbates the uneven current distribution, and even at the same voltage, the power output of different battery stacks may be different. These differences may be affected by factors such as battery stack aging and temperature changes.

[0140] In order to ensure the stability and efficiency of hydrogen fuel cell vehicles, effective optimization and adjustment methods are needed to achieve uniform load sharing, thereby ensuring the overall stability of the multi-battery stack system.

[0141] According to an embodiment of the present application, an embodiment of a coordinated optimization method for a hydrogen fuel cell vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0142] In this embodiment, a coordination optimization method for a hydrogen fuel cell vehicle is provided. Figure 1 A flow chart of a coordinated optimization method for a hydrogen fuel cell vehicle provided in an embodiment of the present application, such as Figure 1 As shown, the process includes the following steps:

[0143] Step S101, based on the acquired target load demand of the hydrogen fuel cell vehicle, determine the target output voltage and target output current corresponding to the battery stack in the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel.

[0144] Specifically, in order to accurately determine the load power demand required by the motor when the hydrogen fuel cell vehicle is supplying power to the outside, it is first necessary to select a high-precision sensor to obtain the motor load data in real time. Since the sensor data may be interfered by noise, it is necessary to filter and filter these data in the subsequent processing process to eliminate unnecessary high-frequency interference. Next, outlier detection is used to identify and process abnormal points in the data to ensure the accuracy and reliability of the data. Finally, data verification is used to verify the consistency of the data to obtain an accurate target load demand. This series of preprocessing steps ensures the accuracy and availability of the final load power demand data, thereby obtaining the target load demand.

[0145] In response to the target load demand, the fuel cell stack of the hydrogen fuel cell vehicle needs to meet a specific output voltage and output current to meet the power supply demand. Accordingly, this can be achieved by building a fuzzy rule base. The fuzzy rule base establishes a mapping relationship between the target load demand and the target output voltage and current of the fuel cell stack based on expert experience and historical operating data. In this fuzzy rule base, the input variable is the target load demand, and the output variable is the target output voltage and current of the fuel cell stack. Through this rule base, the output of the fuel cell stack can be dynamically adjusted according to the real-time changing load demand, thereby meeting the power demand of the hydrogen fuel cell vehicle under different circumstances. This approach ensures that the fuel cell stack can flexibly adapt to various load conditions and optimize the performance of hydrogen fuel cell vehicles.

[0146] Step S103, determining a sub-stack efficiency score corresponding to the sub-stack, and determining a sub-stack stability score corresponding to the sub-stack.

[0147] The sub-stack efficiency score is used to characterize the ratio of the average output power of the sub-stack to the average input power in a specific time period to reflect the energy conversion efficiency of the sub-stack. The sub-stack stability score is used to characterize the degree of fluctuation of the output voltage and output current of the sub-stack in a specific time period to reflect the operating stability of the sub-stack. The main purpose of determining the sub-stack efficiency score and the sub-stack stability score is to accurately evaluate the performance of the stack in order to effectively manage, control and optimize the stack. For example, if the sub-stack efficiency score or sub-stack stability score of a sub-stack is low, it may need to be optimized or replaced to ensure the performance and reliability of the entire stack. In addition, these scores can also be used to adjust the working conditions of the stack, such as gas flow, pressure and temperature, to achieve better performance and longer service life.

[0148] Specifically, the parameters of the sub-stack during operation, such as hydrogen flow, oxygen flow, output current, output voltage, temperature, relative humidity, etc., can be obtained, and the sub-stack efficiency score and sub-stack stability score corresponding to the sub-stack can be predicted by the machine learning model. For example, in order to determine the sub-stack efficiency score and sub-stack stability score, it is first necessary to collect parameter data under different operating conditions, such as hydrogen flow, oxygen flow, output current, voltage, temperature and relative humidity. Next, the missing values, outliers and noise in the data are processed, and the data is normalized or standardized. The data set is divided into a training set and a test set by extracting time series features and applying models such as linear regression, support vector regression (SVR), random forest regression or gradient boosting regression. The cross-validation technique is used to optimize the model hyperparameters and improve its generalization ability. When evaluating the model performance in the training and validation stages, the efficiency scoring model is evaluated using indicators such as mean square error (MSE) and root mean square error (RMSE), and similar regression indicators or classification accuracy and F1 score are used for the stability scoring model. Finally, by acquiring parameter data in real time, the trained model is used to determine the sub-stack efficiency score and sub-stack stability score.

[0149] Step S105, comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining the main stack and the slave stack in the sub-stack according to the result of the comprehensive scoring.

[0150] The comprehensive score is used to characterize the evaluation and ranking of sub-stacks by weighted sub-stack efficiency scores and sub-stack stability scores to reflect the overall performance of the sub-stacks.

[0151] Specifically, the sub-stack efficiency score and the sub-stack stability score are comprehensively scored, different weights can be assigned, and then the weighted average is calculated to evaluate the overall performance of the sub-stack. According to the results of the comprehensive score, the sub-stacks can be sorted and classified to distinguish the main stack and the sub-stack. The main stack usually refers to the stack that undertakes the main energy conversion task in the stack, which needs to have high efficiency and stability. The sub-stack may assume an auxiliary or backup role, and its performance requirements are slightly lower than the main stack. For example, first, in order to evaluate the comprehensive score of each sub-stack, a weight of 0.6 for the sub-stack efficiency score and a weight of 0.4 for the sub-stack stability score can be assigned to calculate the comprehensive score of each sub-stack. Then, a clustering algorithm such as K-means or hierarchical clustering is used to group the sub-stacks and identify clusters of stacks with similar performance. In each cluster, the overall performance of the cluster is summarized by calculating the average comprehensive score of the sub-stacks in the cluster and representative features such as performance stability. Subsequently, based on these representative features, the stack feature set of each cluster is determined, that is, the stack feature set that best matches the performance characteristics of the cluster is selected. The risk factor of each stack feature set is evaluated, taking into account factors such as long-term stability and failure risk. By screening the candidate stack feature set with the smallest risk factor, the best performance or lowest risk is ensured. Finally, among the screened candidate stack feature sets, the comprehensive scores of each sub-stack are sorted from high to low, and the sub-stack with the highest comprehensive score is selected as the main stack, and the remaining sub-stacks are used as slave stacks.

[0152] Step S107, based on the target output voltage and the target output current, using a preset output characteristic model to generate a main stack output parameter corresponding to the main stack, and to generate a slave stack output parameter corresponding to the slave stack.

[0153] Specifically, the output parameters of the stack are generated using a preset output characteristic model based on the target output voltage and target output current as the benchmark for operating the sub-stack. The model simulates the behavior of the stack under different current and voltage conditions based on the operating characteristics and performance data of the stack. The model calculates the output parameters of the main stack under these conditions, such as the corresponding output voltage, output current, and output power, and derives the theoretical expected performance. Similarly, the model also generates the output parameters of the slave stack, which may reflect a lower power output because the performance of the slave stack is slightly inferior to that of the main stack. The main stack is responsible for providing the main power output, and the slave stack can be auxiliary adjusted according to the status of the main stack to balance the overall load of the hydrogen fuel cell vehicle and avoid overloading or inefficient operation of the main stack.

[0154] In order to build the model, it is necessary to collect the performance data of the main and slave stacks under different voltage and current conditions, including current-voltage characteristics, power output, efficiency, and design parameters of the stack. The model is established through a polynomial regression model, a neural network model, or empirical data, and historical data (such as target output voltage, target output current, and known design parameters) are used to input the model to generate the output parameters of the main and slave stacks. Subsequently, the parameters generated by the model are compared with the actual measurement results to verify the accuracy of the model, and the model parameters are adjusted according to the actual performance data to improve the prediction accuracy. Finally, the trained model is used to obtain the output parameters of the main and slave stacks in real time.

[0155] Step S109, dynamically adjusting the working state of the main fuel cell stack according to the output parameters of the main fuel cell stack, and dynamically adjusting the working state of the slave fuel cell stack according to the output parameters of the slave fuel cell stack to meet the target load demand.

[0156] Specifically, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water of the main stack are dynamically adjusted according to the output parameters of the main stack; the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water of the slave stack are dynamically adjusted according to the output parameters of the slave stack; to meet the target load requirements. For example, increasing the flow rate of hydrogen, oxygen and water, increasing their pressure, or increasing the temperature can increase the reaction rate, thereby increasing the output current and voltage. During the adjustment process, the actual output voltage, actual output current and actual output power must be monitored in real time to ensure that they meet the output parameters of the main stack or the slave stack, and to ensure that the adjusted parameters can meet the target load requirements. By adjusting the flow rate, pressure and temperature of the main stack and the slave stack respectively, the reaction rate can be optimized, thereby improving the output efficiency of the entire hydrogen fuel cell vehicle. The main stack can focus on providing efficient output, while the slave stack can assist in maintaining stable operating conditions.

[0157] The coordinated optimization method of a hydrogen fuel cell vehicle provided in this embodiment determines the target output voltage and target output current of the stack by the acquired target load demand, so that the stack can be dynamically adjusted according to the real-time load demand. This adjustment can optimize the power output of the stack under different operating conditions, thereby improving the overall performance and efficiency of the hydrogen fuel cell vehicle. Next, since the stack includes at least two sub-stacks in parallel, it is necessary to accurately evaluate the performance of each sub-stack by determining the efficiency score and stability score of the sub-stack. It is helpful to identify the sub-stacks with lower performance and optimize or replace them to ensure the reliability and stability of the entire stack. Then, the roles of the main stack and the slave stack are determined by comprehensive scoring, which helps to allocate resources to the stack with the best performance. The main stack undertakes the main energy conversion task, while the slave stack is auxiliary or standby. This allocation improves the overall efficiency and reliability of the hydrogen fuel cell vehicle. Based on the output parameters of the main stack and the slave stack generated by the preset output characteristic model, the working state can be accurately adjusted to ensure that the output of the stack meets the target load demand, improve the dynamic response capability and operating efficiency, and thus improve the overall performance of the hydrogen fuel cell vehicle.

[0158] Figure 2 The flowchart of step S101 provided in the embodiment of the present application may include the following steps:

[0159] Step S1, obtaining the current load demand of the hydrogen fuel cell vehicle.

[0160] Specifically, in order to ensure the accuracy of the data, high-precision sensors can be used to obtain the load demand of hydrogen fuel cell vehicles in real time. First, the power is obtained by measuring the voltage and current flowing through the battery stack and calculating their product. Secondly, the operation of the vehicle and the load power required by the external power supply motor are obtained. In addition, the power consumption of equipment such as air compressors and water pumps in the vehicle needs to be considered. Finally, all load power requirements are added together to obtain the real-time current load demand.

[0161] Step S3: Kalman filtering is used to smooth the current load demand data to obtain a smoothed target load demand.

[0162] Specifically, since the sensor data may be affected by noise, it is necessary to filter and filter the data in the subsequent processing to eliminate unnecessary high-frequency interference. For example, Kalman filtering is used to smooth the current load demand data. Assume that the dynamics of the current load power demand at each time step k is described by the following linear state equation: k =x k-1 +w k , where x k is the load demand at step k, w kis process noise. Construct observation model: z k =x k +v k , where z k is the observed load demand, v k is the observation noise. The initial state estimate, when the time is not long k=0, is And the initial estimation error covariance P0, for each time step k, first predict the current state , prediction error covariance , where Q is the covariance of the process noise. Then according to the observed data z k Update state estimate and calculate Kalman gain , where R is the covariance of the observation noise, and the estimated state is updated , update error covariance .

[0163] Take the obtained load demand sequence [100, 105, 110, 500, 115] as an example, where 500 may be caused by some abnormality. Assuming the initial estimate The first observation value is 100, and the initial estimation error covariance P0 is usually selected to be a relatively large value, such as 1000. The covariance Q of the process noise is a small constant, such as 10. The covariance R of the observation noise is assumed to be a small constant, such as 5. Kalman filtering is used for data smoothing, and the output data is [100, 104, 108, 110, 113], eliminating the influence of the outlier 500, which makes the entire data look more stable and reasonable.

[0164] Step S5, based on the target load requirement, using a preset fuzzy rule base to generate a target output voltage and a target output current corresponding to the battery stack.

[0165] Specifically, a preset fuzzy rule base is used to determine the target output voltage and current of the battery stack. The rule base is a set of predefined rules, each of which corresponds to different input conditions and output decisions.

[0166] Assume the following fuzzy rule base:

[0167] Rule 1: If the load power is "low", the target output voltage of the stack is "42V" and the target current is "2A".

[0168] Rule 2: If the load power is "medium", the target output voltage of the battery stack is "48V" and the target current is "3A".

[0169] Rule 3: If the load power is "high", the target output voltage of the stack is "54V" and the target current is "4A".

[0170] According to the pre-processed target load power (for example, 110W), it is first fuzzified to "medium". Then, according to Rule 2, the target output voltage of the battery stack can be determined to be 48V and the target output current to be 3A.

[0171] and Figure 1 Compared with the embodiment shown in the figure, this embodiment obtains the current load demand, and the application of Kalman filtering can effectively smooth the load demand data and eliminate the influence of noise and outliers. Make the data sequence more stable and reasonable. This processing can improve the reliability of the data, and thus improve the accuracy of the response of the stack to load changes. Then, through the preset fuzzy rule base, the target output voltage and target output current of the stack are generated according to the smoothed target load demand. The stack can optimize the output under various load conditions to ensure the performance and efficiency of the hydrogen fuel cell vehicle.

[0172] Figure 3 A flowchart of determining the sub-stack efficiency score corresponding to the sub-stack in step S103 provided in an embodiment of the present application may include the following steps:

[0173] Step S311, obtaining the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period.

[0174] Specifically, high-precision voltage and current sensors are used to directly measure the output voltage and output current of the sub-stack. These sensors are usually connected to the battery management system (BMS) to monitor the electrical parameters of the sub-stack in real time. The output voltage and output current data collected by the sensors are recorded within a preset time period. A data acquisition system (such as a data logger or embedded system) can be set up to read and store this data regularly. The flow rates of hydrogen and oxygen are measured using mass flow meters or volume flow meters. Hydrogen flow rates are usually measured in standard liters per minute (SLM) or liters per hour (L / h). Oxygen flow rates are also measured in SLM or L / h. Flow meters usually provide real-time flow data, which can be transmitted to the battery management system (BMS) via an electronic interface (such as an analog signal, a digital signal, or a communication bus). The flow data of hydrogen and oxygen are recorded within a preset time period. At the same time, ensure that the data acquisition time of all sensors and flow meters is synchronized to facilitate subsequent data analysis. For example, use a timestamp to record the acquisition time of each data point to ensure the time consistency of different types of data.

[0175] Step S313, determining an average output voltage of the output voltage within a preset time period, and determining an average output current of the output current within the preset time period.

[0176] Specifically, data points of output voltage and output current are recorded within a preset time period. For example, the voltage and current are recorded once every second. All recorded voltage values ​​within the preset time period are added together, and then divided by the total number of records to obtain an average output voltage. All recorded current values ​​within the preset time period are added together, and then divided by the total number of records to obtain an average output current.

[0177] Step S315, determining the average output power corresponding to the sub-stack according to the average output voltage and the average output current.

[0178] Specifically, the corresponding average output power is obtained by multiplying the average output voltage and the average output current.

[0179] Step S317, inputting the hydrogen flow rate and the oxygen flow rate into a preset power conversion model to generate an average input power corresponding to the sub-stack.

[0180] Specifically, the power conversion model is trained based on the collected historical data, including hydrogen flow, oxygen flow, and the corresponding average output power of the stack and other related parameters (such as stack operating temperature, pressure, etc.). The collected data is preprocessed, including cleaning (removing outliers and missing values), standardization or normalization (making the data have a uniform scale and range). Use appropriate algorithms (such as regression analysis, neural networks, support vector machines, etc.) to train the power conversion model based on features and targets (input power). The accuracy and generalization ability of the power conversion model are verified by cross-validation, test set evaluation and other methods. The trained power conversion model is used for the prediction of real-time data. The real-time hydrogen flow and oxygen flow are input, and the power conversion model will generate the corresponding average input power.

[0181] Step S319, determining the sub-stack efficiency score based on the ratio of the average output power to the average input power.

[0182] Specifically, the efficiency score is calculated by dividing the average output power by the average input power and converted into a corresponding score. For example, the average input power is 15,000 watts and the average output power is 12,000 watts. The efficiency is usually expressed as a percentage, so the ratio is multiplied by 100 to get the percentage form of the efficiency. According to the calculated efficiency percentage, it can be directly used as the sub-stack efficiency score. Therefore, the sub-stack efficiency score is 80 points.

[0183] and Figure 1Compared with the embodiment shown in the figure, this embodiment can reduce the impact of instantaneous fluctuations by obtaining the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period, and calculating the average value of the output voltage and output current, so that the evaluated voltage and current values ​​are more representative and better reflect the actual performance of the sub-stack. The average output power calculated based on the precise voltage and current data provides the necessary data for the performance evaluation of the sub-stack. By inputting the hydrogen and oxygen flow data into the power conversion model, the energy demand of the sub-stack can be effectively estimated, thereby evaluating its energy efficiency and working status. Finally, by calculating the ratio of output power to input power, the efficiency of the sub-stack can be accurately evaluated. This efficiency score intuitively reflects the energy efficiency level of the sub-stack, which helps to optimize its performance and energy utilization efficiency.

[0184] Figure 4 A flowchart of determining a sub-stack stability score corresponding to a sub-stack in step S103 provided in an embodiment of the present application may include the following steps:

[0185] Step S321, obtaining the output voltage and output current of the sub-stack within a preset time period.

[0186] Specifically, high-precision voltage and current sensors are used to directly measure the output voltage and output current of the sub-stack. These sensors are usually connected to the battery management system (BMS) to monitor the electrical parameters of the stack in real time. The output voltage and output current data collected by the sensor are recorded within a preset time period. A data acquisition system (such as a data logger or embedded system) can be set up to read and store this data regularly. At the same time, ensure that all sensor acquisition times are synchronized to facilitate subsequent data analysis. For example, use a timestamp to record the acquisition time of each data point to ensure the time consistency of different types of data.

[0187] Step S323, determining a voltage standard deviation of the output voltage within a preset time period, and determining a current standard deviation of the output current within a preset time period.

[0188] Specifically, the standard deviation is a statistical indicator to measure the volatility of data, which is used to describe the degree of dispersion of data points relative to their mean. The smaller the standard deviation, the more concentrated the data points are near the mean; the larger the standard deviation, the more dispersed the distribution of the data points. Within the preset time period, first calculate the mean (i.e., average value) of the output voltage or output current. For each data point, calculate its difference (deviation) from the mean. Square each deviation value to obtain the square deviation. Average all square deviations to obtain the variance. The standard deviation is the square root of the variance. The voltage standard deviation and the current standard deviation can reflect the stability of the sub-stack output during operation. If the standard deviation is small, it means that the voltage and current are relatively stable; if the standard deviation is large, it means that the voltage and current fluctuate greatly, which may affect the performance or safety of the sub-stack.

[0189] Step S325, determining the sub-stack stability score using a preset stability score model based on the voltage standard deviation and the current standard deviation.

[0190] Specifically, the preset stability scoring model can be expressed as a stability scoring formula:

[0191] Substack stability score = 100-(voltage standard deviation + current standard deviation)

[0192] Assuming the calculated voltage standard deviation is 2 volts and the current standard deviation is 3 amps, the calculated sub-stack stability score is 95 points, which means that the sub-stack is very stable, because the score is close to 100, indicating that the fluctuations in voltage and current are very small. A lower standard deviation value will result in a score close to 100, reflecting the stability of the sub-stack.

[0193] and Figure 1 Compared with the embodiment shown in the figure, this embodiment measures the stability by obtaining the output voltage and output current of the sub-stack within a preset time period and calculating the standard deviation of the voltage and current. The standard deviation reflects the fluctuation of the data, and then evaluates the performance of the sub-stack. Converting the standard deviation into a stability score makes the stability evaluation of the battery more intuitive and quantitative, which is convenient for comparison and decision-making.

[0194] Figure 5 The flowchart of step S105 provided in the embodiment of the present application may include the following steps:

[0195] Step S511, weighting the sub-stack efficiency score and the sub-stack stability score to obtain a comprehensive score.

[0196] Specifically, different weights can be assigned to the sub-stack efficiency score and the sub-stack stability score, and then the weighted sum can be performed to obtain the corresponding comprehensive score. For example, the weights of the sub-stack efficiency score and the sub-stack stability score are given as 0.6 and 0.4, respectively. This means that the sub-stack efficiency score has a larger proportion in the comprehensive score. Add the two weighted values ​​to get the comprehensive score: Comprehensive score = (80×0.6) + (95×0.4) = 86. This comprehensive score not only reflects the single indicator of the sub-stack, but also comprehensively considers the performance of different dimensions, thereby providing a more comprehensive performance evaluation.

[0197] Step S513: clustering each sub-stack to obtain a stack cluster including one or more sub-stacks.

[0198] Specifically, first, it is necessary to collect performance data on each sub-stack, including but not limited to sub-stack efficiency score, sub-stack stability score, output voltage, output current, hydrogen flow rate, oxygen flow rate, current density, mass / volume power density (measures the power generated by the stack per unit mass or unit volume, reflecting the compactness of the stack's energy conversion), fuel utilization rate (measures the proportion of hydrogen effectively converted into electrical energy), operating life, gas permeability (the sealing performance of the bipolar plate material in the stack for hydrogen or oxygen), etc. Then, according to the characteristics of the data and the clustering target, clustering algorithms including but not limited to K-means, hierarchical clustering, DBSCAN, spectral clustering, Gaussian mixture model, fuzzy C-means, K-medoids, MeanShift, OPTICS and BIRCH are used to perform cluster analysis on the sub-stacks, and the sub-stacks are assigned to different clustering clusters to obtain a stack cluster containing one or more sub-stacks.

[0199] Step S515, determining the representative features within each battery stack cluster, and for any battery stack cluster, determining the battery stack feature set to which the representative features within the cluster belong.

[0200] Specifically, once the clustering results are obtained, the next step is to determine the representative features within each battery stack cluster. Feature selection techniques (such as principal component analysis PCA, feature importance ranking, etc.) can be used to evaluate which features are most important for distinguishing clusters. For example, using principal component analysis PCA, these features can be converted into a set of new, orthogonal principal components, which are arranged from large to small according to variance contribution. In this way, fewer principal components can be used to approximate most of the information in the original data set, while reducing the complexity of the data and improving the efficiency of analysis, so as to determine the representative features within the cluster that best represent the battery stack cluster. According to these representative features within the cluster, they can be classified according to the corresponding characteristics or attributes to obtain the battery stack feature set to which the representative features within the cluster belong.

[0201] Step S517, obtaining the risk coefficient of each battery stack feature set, and screening out candidate battery stack feature sets based on the risk coefficient.

[0202] Specifically, the risk coefficient is calculated for each battery stack feature set. The risk coefficient corresponding to the battery stack feature set can be predicted based on a preset machine learning model, and then sorted from high to low according to the risk coefficient to screen out the candidate battery stack feature set with the lowest risk coefficient.

[0203] Step S519, in the battery stack cluster corresponding to the candidate battery stack feature set, the comprehensive scores of each sub-battery stack are sorted from high to low, and the sub-battery stack corresponding to the highest comprehensive score is determined as the main battery stack, and the remaining sub-battery stacks are determined as slave battery stacks.

[0204] Specifically, in the battery stack cluster corresponding to the candidate battery stack feature set, the comprehensive scores of all sub-batteries are sorted from high to low, and the sub-battery with the highest comprehensive score is selected as the main battery stack, and the other sub-batteries are determined as slave battery stacks. Ensure that the main battery stack and slave battery stack finally selected are representative and reliable.

[0205] Taking 5 sub-stacks as an example, the performance parameters of each sub-stack are obtained: output voltage (V), output current (A), hydrogen flow rate (SLM), oxygen flow rate (SLM), current density (mA / cm 2 ), mass / volume power density (W / kg), fuel utilization rate (%), operating life (hours), gas permeability (%); then standardize the data, select the K-means algorithm for clustering, and obtain 3 clusters. Use PCA to analyze the characteristics of each cluster, convert the original features into several principal components, determine the representative features within each battery stack cluster, such as the representative features within the first cluster are mass / volume power density and operating life, the representative features within the second cluster are oxygen flow and hydrogen flow, and the representative features within the third cluster are operating life and current density, and determine the battery stack feature set to which the representative features within the cluster belong. For example, the battery stack feature set corresponding to the first battery stack cluster includes mass / volume power density and operating life, the battery stack feature set corresponding to the second battery stack cluster includes oxygen flow and hydrogen flow, and the battery stack feature set corresponding to the third battery stack cluster includes operating life and current density. Build or use an existing machine learning model to predict the risk of each battery stack feature set. Calculate the risk coefficient for the battery stack feature set within each cluster. Select the battery stack feature set with the lowest risk coefficient as the candidate battery stack feature set. Then, in the battery stack cluster corresponding to the candidate battery stack feature set, the comprehensive scores of each sub-battery stack are sorted from high to low, and the sub-battery stack corresponding to the highest comprehensive score is determined as the main battery stack, and the remaining sub-battery stacks are determined as slave battery stacks.

[0206] and Figure 1 Compared with the embodiment shown in the figure, this embodiment first comprehensively considers the sub-stack efficiency score and the sub-stack stability score through a weighted summation method to provide a comprehensive performance evaluation. This method can balance different performance indicators to ensure that the final score is more representative. Then, the sub-stacks are classified through a clustering algorithm, and sub-stacks with similar performance can be divided into the same cluster, thereby simplifying the subsequent analysis and decision-making process. Determining the representative features within the cluster can effectively reduce data complexity and improve the efficiency and accuracy of feature selection. By calculating and screening the risk coefficient, it is ensured that the selected stack feature set has the lowest risk, which enhances the safety and reliability of stack selection. According to the comprehensive score and risk assessment results, the sub-stack with the highest comprehensive score is selected as the main stack, and the rest are selected as slave stacks. It helps to optimize the configuration of the stack while ensuring performance.

[0207] Figure 6 The flowchart of step S107 provided in the embodiment of the present application, the preset output characteristic model includes a support vector machine, a decision tree and a random forest; the main battery stack output parameters include the main output voltage, the main output current and the main output power; the slave battery stack output parameters include the slave output voltage, the slave output current and the slave output power; the process may include the following steps:

[0208] Step S71, using a support vector machine to generate a main output voltage corresponding to the main battery stack and a slave output voltage corresponding to the slave battery stack according to the target output voltage and the target output current.

[0209] Specifically, the support vector machine (SVM) is used as a supervised learning model for classification and regression analysis. Here it is used to predict the main output voltage of the main stack and the slave output voltage of the slave stack based on the target output voltage and target output current. The SVM model will be trained based on historical data (including target output voltage, target output current, performance parameters of the main stack, and performance parameters of the slave stack). During the training process, the model will learn how to allocate the distribution relationship between the output voltage and output current corresponding to the main stack and each sub-stack, and generate the main output voltage of the main stack and the slave output voltage of the slave stack through this relationship.

[0210] Step S73, based on the target output voltage and the target output current, use a decision tree to generate a main output current corresponding to the main battery stack and a slave output current corresponding to the slave battery stack.

[0211] Specifically, a training data set including a target output voltage, a target output current, a main stack performance parameter, a slave stack performance parameter, and a corresponding stack output current is first prepared. The decision tree model is trained using these data. The model constructs a tree structure to capture the relationship between input and output by segmenting the features in the data set (such as the target output voltage and current). The decision tree splits at each node according to certain features (such as the target output voltage or current) and gradually constructs a decision path. Through the tree path, the decision tree maps the input target output voltage and current to the main output current of the main stack and the slave output current of the slave stack. Through the decision tree, after inputting the target output voltage and the target output current, the main output current prediction value and the slave output current prediction value of the main stack are obtained. The output current value generated by the decision tree can optimize the working state of the main stack and the slave stack to ensure that the hydrogen fuel cell vehicle can achieve the expected performance and stability under specified conditions. It is also possible to use a decision tree to generate the main output current corresponding to the main stack according to the target output voltage and the target output current. According to the target output voltage and the target output current, another decision tree is used to generate the slave output current corresponding to the slave stack.

[0212] Step S75, using random forest to generate a main output power corresponding to the main battery stack and a slave output power corresponding to the slave battery stack according to the target output voltage and the target output current.

[0213] Specifically, collect a data set containing the target output voltage, target output current, performance parameters of the master and slave stacks, and the corresponding stack output power. The data set should contain the output power values ​​of the master and slave stacks. Use the training data set to train the random forest regression model. The random forest model creates multiple decision trees and averages the results of these trees to get the final prediction value.

[0214] and Figure 1 Compared with the embodiment shown, this embodiment can accurately predict the main output voltage of the main stack and the slave output voltage of the slave stack by using a support vector machine. The decision tree can generate the main output current of the main stack and the slave output current of the slave stack by analyzing the target output voltage and the target output current. The random forest can generate the main output power of the main stack and the slave output power of the slave stack by training multiple decision trees and integrating their results. By using three different machine learning models, namely support vector machines, decision trees and random forests, the voltage, current and power of the main stack and the slave stack in hydrogen fuel cell vehicles can be comprehensively and accurately predicted. This method enables hydrogen fuel cell vehicles to optimize the performance of the stack according to the target output parameters in complex practical applications, thereby improving the overall efficiency and stability of hydrogen fuel cell vehicles.

[0215] In some embodiments, after step S107, the process may further include the following steps:

[0216] The main output voltage is compared with the target output voltage. When the difference in the comparison result exceeds the voltage deviation threshold, the working state of the main battery stack and the working state of the slave battery stack are readjusted.

[0217] The main output current is compared with the target output current. When the difference in the comparison result exceeds the current deviation threshold, the working state of the main battery stack and the working state of the slave battery stack are readjusted.

[0218] Specifically, since the main stack and the slave stack are set in parallel, their main output voltage and slave output voltage are actually consistent, and the main stack is the main power supply, while the slave stack is used to assist the main stack. This configuration allows the slave stack to replenish energy when the performance of the main stack decreases or the load demand increases. Therefore, it is only necessary to monitor whether the main output voltage and the target output voltage are deviated. If the deviation exceeds the voltage deviation threshold, preferably set to 2%, it is necessary to readjust the working state of the main stack and the working state of the slave stack so that the deviation between the main output voltage and the target output voltage remains within the range of the voltage deviation threshold. Similarly, although the main stack is the main current source, the current of the slave stack does affect the total current. Therefore, if the deviation between the main output current and the target output current exceeds the current deviation threshold, preferably set to 2%, corresponding adjustments are also required to keep the deviation between the main output current and the target output current within the range of the current deviation threshold. The adjustment may be performed on both the main stack and the slave stack at the same time. For example, if the output current needs to be increased, it may be necessary to increase the load of the main stack or increase the output of the slave stack, and vice versa. The ultimate goal is to ensure that the entire stack, including the main stack and the slave stack, can stably provide the required voltage and current to meet the target load requirements.

[0219] and Figure 1 Compared with the embodiment shown in the figure, this embodiment can ensure that the hydrogen fuel cell vehicle always remains within the expected performance range by continuously monitoring the main output voltage and main output current of the main stack and making adjustments when the deviation exceeds the set threshold. This can effectively deal with the fluctuation problem caused by the performance degradation of the main stack or load changes, thereby improving the overall operating stability and reliability of the hydrogen fuel cell vehicle. It can ensure the coordinated work of the main stack and the slave stack, optimize the power output, ensure that the target load requirements are met, and reduce the potential failure risks caused by deviations.

[0220] Figure 7 A flowchart of the use of an auxiliary power supply provided in an embodiment of the present application may include the following steps:

[0221] Step S201 : when the fuel cell stack is used in conjunction with a plurality of auxiliary power supplies, obtaining performance parameters of the auxiliary power supplies.

[0222] Auxiliary power sources include generators, solar panels and lithium battery packs;

[0223] Performance parameters include the generator's power generation efficiency, the solar panel's maximum output power and the capacity of the lithium battery pack.

[0224] Specifically, the use of auxiliary power supplies can improve the reliability and flexibility of hydrogen fuel cell vehicles. Auxiliary power supplies provide backup power to ensure that power can continue to be supplied when the main power supply fails. At the same time, according to the advantages and disadvantages of different power sources, energy use can be optimized, operating costs can be reduced, and the overall efficiency of energy utilization can be improved. By monitoring the power generation efficiency of the generator, its operating status can be dynamically adjusted to ensure that it works at optimal efficiency, thereby reducing fuel consumption and operating costs. Real-time knowledge of the maximum output power of solar panels can help optimize the use of solar energy, adjust load distribution, ensure maximum use of solar energy resources, and reduce dependence on other power sources. Monitoring the capacity of lithium battery packs can help manage the charge and discharge status of the battery, avoid over-discharge or overcharging, thereby extending battery life and ensuring that the battery can provide sufficient power when needed.

[0225] Step S203: According to the performance parameters, a preset performance-power range model is used to determine the output power range corresponding to the auxiliary power supply.

[0226] Specifically, a mapping model is established based on performance parameters and load requirements to determine the output power range of each auxiliary power source, which is used to ensure that the hydrogen fuel cell vehicle can meet the real-time changing load requirements while optimizing the use efficiency of each auxiliary power source.

[0227] For example, the power generation efficiency of the generator is obtained, such as 90%; the maximum output power of the solar panel is obtained, such as 100 kilowatts (kW); the capacity of the lithium battery pack is obtained, such as 200 kilowatt-hours (kWh); assuming that the current target load demand is 500kW, the preset performance-power range model can be used to determine that the output power range of the generator is 450 to 500 kW, the output power range of the lithium battery pack is 0 to 200 kW, and the output power range of the solar panel is 0 to 100 kW.

[0228] Step S205, with maximizing power supply efficiency, equipment power supply reliability and equipment life as objective functions, and the output power of the auxiliary power supply meeting the output power range as a constraint condition, a multi-objective optimization algorithm is used to generate an optimized power allocation plan; wherein, the equipment power supply reliability represents the proportion of time to maintain the target load demand.

[0229] Power supply efficiency = input power / output power = (output power of generator, output power of solar panel and output power of lithium battery pack) / target load demand

[0230] Equipment power supply reliability = the proportion of time that the output power of the equipment can maintain the target load demand.

[0231] The effective life of equipment (such as generators, lithium battery packs, solar panels) can usually be measured in years or operating hours of the equipment.

[0232] The reliability of equipment power supply can be obtained in the following ways: record the operating status and output power of the auxiliary power supply within a certain period of time. Set a time window (for example, 1 hour, 1 day or 1 week) and evaluate the performance of the auxiliary power supply within this time window. Monitor and record whether the auxiliary power supply can continue to provide the power required by the load within this time window. Train the machine model based on the obtained data, and finally the trained model can obtain the time proportion corresponding to the output power of the auxiliary power supply.

[0233] In some embodiments, using a multi-objective optimization algorithm to generate an optimized power allocation solution also includes satisfying the following conditions:

[0234] The target load demand is equal to the sum of the output power of each battery stack and the output power of the auxiliary power supply.

[0235] Specifically, the total output power (including the output power of all battery stacks and auxiliary power supplies) must be equal to the target load demand. This means that the combined output of all power supplies must be able to meet the power demand of the load.

[0236] The output power of each sub-stack must be within the design limit.

[0237] Specifically, the output power of each sub-stack must be within its design limits. This is to ensure that the stack will not be damaged or its efficiency will be reduced due to overload.

[0238] In some embodiments, the objective function includes:

[0239]

[0240] Power supply efficiency = output power of battery stack or auxiliary power supply / target load demand

[0241] Among them, w1, w2, w3 are weight coefficients; a i is the power supply efficiency of the ith sub-stack or auxiliary power supply; b i The reliability of power supply for the i-th sub-stack or auxiliary power supply equipment; c i is the equipment life of the ith sub-stack or auxiliary power supply.

[0242] Specifically, a multi-objective optimization algorithm is used to search for the optimal power allocation solution based on the objective function and constraints. From the multiple solutions found by the multi-objective optimization algorithm, a solution is selected that achieves the best balance between power supply efficiency, system reliability and power supply life.

[0243] and Figure 1Compared with the embodiment shown in the figure, this embodiment uses auxiliary power sources (generators, solar panels and lithium battery packs) in combination, so that even if the main power source fails, the auxiliary power source can continue to supply power to ensure the normal operation of the hydrogen fuel cell vehicle. The power generation efficiency of the generator, the maximum output power of the solar panel, and the capacity of the lithium battery pack are monitored in real time. Through the preset performance-power range model, the output power range of the auxiliary power source is determined according to the performance parameters of the auxiliary power source to ensure that the hydrogen fuel cell vehicle can meet the real-time changing load requirements and optimize the use efficiency of each auxiliary power source. The power allocation plan is generated by using a multi-objective optimization algorithm, which comprehensively considers power supply efficiency, equipment power supply reliability and equipment life, and can find the best balance between the three to improve overall performance.

[0244] Figure 8 A flow chart of temperature change adjustment provided in an embodiment of the present application may include the following steps:

[0245] Step S301, obtaining the temperature change rate and current load power of each sub-stack, and using a fuzzy logic algorithm to determine the temperature change trend membership corresponding to the sub-stack; wherein the temperature change trend membership is used to characterize the degree of fuzzification of the temperature change trend.

[0246] Specifically, the membership of the temperature change trend is used to characterize the degree of fuzzification of the temperature change trend. Usually, the exact value is mapped to the interval [0,1], where 0 means that the value does not belong to a fuzzy set at all, and 1 means that the value belongs to the fuzzy set completely. Values ​​between 0 and 1 indicate that the value has a partial degree of membership to the fuzzy set. The temperature change rate and current load power of each sub-stack are collected in real time by sensors. Fuzzy sets and membership functions are defined for the temperature change rate and load power. For example, the temperature change rate can be defined as "low", "medium", and "high", and membership functions are assigned to these sets. For example: low temperature change rate (for example: 0℃ / min to 3℃ / min), medium temperature change rate (for example: 3℃ / min to 8℃ / min), high temperature change rate (for example: 8℃ / min to 15℃ / min). Low load power (for example: 0kW to 30kW), medium load power (for example: 30kW to 70kW), high load power (for example: 70kW to 100kW). In the fuzzy logic algorithm, a fuzzy rule base is constructed based on domain knowledge or expert experience. For example, Rule 1: If the temperature change rate is "medium" and the load power is "low load", the temperature change trend is "low". Rule 2: If the temperature change rate is "medium" and the load power is "medium load", the temperature change trend is "medium". Rule 3: If the temperature change rate is "medium" and the load power is "high load", the temperature change trend is "high".

[0247] Taking the obtained sub-stack temperature change rate of 6°C / min and the current load power of 50kW as an example, if the temperature change rate is between 3°C / min and 8°C / min, the temperature change trend is considered to be "medium", and the corresponding membership function is:

[0248]

[0249] Among them, x is the obtained temperature change rate. When the temperature change rate x is between 3℃ / min and 8℃ / min, the membership increases linearly from 0 to 1. Therefore, the membership value of 6℃ / min is 0.6, indicating that the membership degree of this temperature change rate in the "medium temperature change rate" fuzzy set is medium. This value reflects the membership relationship of 6℃ / min relative to the "medium" set and can be used for subsequent fuzzy logic reasoning and decision making.

[0250] If the load power is between 30kW and 70kW, the load power is considered to be "medium", and the corresponding membership function is:

[0251]

[0252] Among them, P is the load power. Therefore, the membership value of 50kW is 0.5, which means that the membership degree of this load power in the "medium load" fuzzy set is medium.

[0253] Finally, the results are aggregated and averaged to obtain the temperature change trend membership corresponding to the sub-stack = (0.6+0.5) / 2=0.55.

[0254] Step S303, generating an adjustment power corresponding to the sub-stack according to the current load power and the degree of membership of the temperature change trend.

[0255] Specifically, the load power and temperature change rate are fuzzified into membership values. For example, the membership of the load power may be low (0.2), medium (0.5), and high (0.1), and the membership of the temperature change rate may be low (0.3), medium (0.6), and high (0.1). The fuzzified load power and temperature change rate membership values ​​are sent as inputs to the trained neural network module. After processing these inputs, the neural network outputs the required heating power and cooling power. For example, the corresponding adjustment power of the sub-stack is 10kW for heating power and 5kW for cooling power.

[0256] Step S305, dynamically adjusting the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the adjusted power.

[0257] Specifically, according to the adjusted power, a PID controller is used to accurately adjust the parameters of hydrogen, oxygen and water. Actuators (such as valves, pumps, etc.) are used to adjust the flow, pressure and temperature of hydrogen, oxygen and water according to the adjusted power. The operating status of the sub-stack is monitored in real time to ensure that the adjusted operating status can meet the performance requirements. The data obtained from the monitoring is fed back to the control system to form a closed loop, and the control parameters are dynamically adjusted according to the feedback signal.

[0258] For example, assume that a sub-stack requires 10kW of heating power to increase the temperature or maintain a specific temperature, and 5kW of cooling power to prevent overheating. Based on this requirement: Increase the flow of hydrogen and oxygen to provide more chemical reactants to increase the power output of the sub-stack. Adjust the gas pressure to ensure that the gas inside the sub-stack is evenly distributed when the flow rate is increased. Adjust the temperature of the gas as needed to optimize the rate of the electrochemical reaction. Adjust the flow of cooling water to provide sufficient cooling capacity to absorb the heat generated by the stack. Adjust the water pressure to ensure that the cooling water can effectively flow through the cooling channels of the stack. Monitor the temperature of the water to ensure that it maintains a suitable temperature range when entering and leaving the stack. This dynamic adjustment helps improve the efficiency, stability and life of the sub-stack.

[0259] It should be noted that the embodiments of step S301 to step S305 can be implemented after step S109. After adjusting the parameters of the main stack and the slave stack, monitoring and adjustment are performed during the operation of the fuel cell vehicle to further improve the efficiency, stability and life of the slave stack.

[0260] and Figure 1 Compared with the embodiment shown in the figure, this embodiment uses a fuzzy logic algorithm to obtain the temperature change rate and load power of the sub-stack in real time, and fuzzifies them into membership values, which can accurately reflect the actual operating status of the sub-stack and its temperature change trend. Based on the fuzzified membership values ​​and preset rules, accurate adjustment power (including heating and cooling power) is generated to optimize the performance and stability of the sub-stack. The flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the adjustment power to ensure that the sub-stack can maintain the best working state under various load conditions, thereby improving overall efficiency and equipment life.

[0261] Fig. 9 The flowchart of updating temperature change adjustment provided in the embodiment of the present application may include the following steps:

[0262] Step S401, when the temperature change rate exceeds a preset temperature change threshold, adjusting the membership function in the fuzzy logic algorithm to obtain an adjusted fuzzy logic algorithm.

[0263] Specifically, a temperature change rate threshold (e.g., 15°C / min) is set. If the actual temperature change rate exceeds this threshold, the membership function needs to be adjusted. For situations where the threshold is exceeded, the shape and range of the original membership function are adjusted. For example, if the original membership function of the temperature change rate is defined as "low", "medium", and "high", it can be expanded or redefined to adapt to the new temperature change rate range. The new membership function may require the addition of a new fuzzy set, such as "very high", and a new membership function is defined for it. For example: low temperature change rate (0°C / min to 3°C / min), medium temperature change rate (3°C / min to 8°C / min), high temperature change rate (8°C / min to 15°C / min), and very high temperature change rate (15°C / min and above). According to the new membership function, the fuzzy logic rule base is updated. For example, if the temperature change rate is "very high" and the load power is "high load", new fuzzy rules may need to be generated to cope with the challenges brought by the high temperature change rate. Implement the adjusted fuzzy logic algorithm and verify its effect through actual testing. Ensure that the adjusted membership functions and rule base can effectively cope with new temperature change conditions and optimize system performance.

[0264] Step S403, determining the updated temperature change trend membership corresponding to the sub-stack according to the adjusted fuzzy logic algorithm.

[0265] Step S405, generating an updated adjusted power corresponding to the sub-stack according to the current load power and the updated temperature change trend membership.

[0266] Step S407, dynamically adjusting the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the updated adjustment power.

[0267] For the adjusted fuzzy logic algorithm, the implementation of steps S403 to S407 is consistent with steps S301 to S305, and will not be repeated here. By continuously collecting data and training neural networks, optimal decisions can be made under various working conditions to ensure safe and efficient operation of the sub-stack.

[0268] It should be noted that the embodiments of step S401 to step S407 can be implemented after step S109. After adjusting the parameters of the main stack and the slave stack, monitoring and adjustment are performed during the operation of the fuel cell vehicle to further ensure the safe and efficient operation of the slave stack.

[0269] and Figure 1Compared with the embodiment shown, this embodiment can deal with the situation that exceeds the preset temperature change rate threshold by adjusting the membership function in the fuzzy logic algorithm. This adjustment is intended to improve the adaptability of the algorithm and ensure that a more accurate control strategy can be generated when the temperature change rate is fast, thereby optimizing the operation effect of the sub-stack.

[0270] Fig.10 A flowchart of extending the running time provided in an embodiment of the present application may include the following steps:

[0271] Step S501, determining the current operating time corresponding to the sub-stack.

[0272] Specifically, high-precision hydrogen sensors and measuring equipment, such as gas flow meters, can be used to monitor the hydrogen flow in real time. The hydrogen input and consumption are usually recorded to obtain the hydrogen inventory. The sub-stack efficiency can be calculated by measuring the amount of hydrogen input and the electrical energy output by the sub-stack. Peak power demand refers to the maximum power required by the sub-stack at maximum load. This can be determined through performance testing, in which the sub-stack is operated under different load conditions until its maximum output power is reached. Required hydrogen = peak power demand / (sub-stack efficiency×33.333×10 -6 ), where 33.333×10 -6 It converts the lower heating value of hydrogen (expressed in kilowatt-hours per kilogram) into a unit that matches the power demand. Current operating time = current hydrogen inventory / required hydrogen volume.

[0273] Step S503, based on the target load demand and with the goal of extending the current operating time, a dynamic programming algorithm is used to determine the predicted load power demand corresponding to the sub-stack within a period of time in the future.

[0274] Specifically, a dynamic programming algorithm is used for modeling, and the state variables include the current hydrogen inventory, the current load power of the sub-stack, historical load data, etc. The load power demand is predicted, that is, how the load should be set in the future time period in order to achieve the goal of extending the operating time. The main goal is to extend the operating time of the sub-stack. The remaining constraints are that the output power of all sub-stacks meets the target load demand and that the sub-stack meets its own design parameter requirements. That is, after step S109, parameters are continued to be obtained, and the adjusted main stack and slave stack are further predicted to obtain their corresponding predicted load demands, which are also the corresponding output powers that need to be adjusted.

[0275] Step S505, dynamically adjusting the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the predicted load power demand.

[0276] Specifically, based on the predicted load power demand obtained in the previous step, that is, the output power of the sub-stack that needs to be further adjusted, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted in the same manner as in step S305 and will not be repeated here.

[0277] It should be noted that the embodiments of step S501 to step S507 can be implemented after step S109. After adjusting the parameters of the main stack and the slave stack, monitoring and adjustment are performed during the operation of the fuel cell vehicle to further optimize the operating performance of the hydrogen fuel cell.

[0278] and Figure 1 Compared with the embodiment shown, this embodiment accurately calculates the current operating time of the sub-stack. Then, a dynamic programming algorithm is used to predict the future load power demand based on the target load demand. By modeling historical load data and current hydrogen inventory, future load conditions can be predicted and optimized to meet the goal of extending the operating time of the sub-stack. This prediction can not only improve the operating efficiency of the stack, but also make adjustments when the load fluctuates to ensure the stability of the stack. The flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the predicted load power demand. This dynamic adjustment can accurately match the output power demand of the sub-stack and optimize the operating performance of the hydrogen fuel cell. This adjustment method can adapt to different load conditions, thereby improving the overall efficiency and stability of hydrogen fuel cell vehicles.

[0279] Fig.11 The flowchart of step S501 provided in the embodiment of the present application may include the following steps:

[0280] Step S5011, obtaining the current hydrogen inventory, sub-stack efficiency and peak power demand of each sub-stack.

[0281] Specifically, high-precision hydrogen sensors and measuring equipment, such as gas flow meters, can be used to monitor hydrogen flow in real time. The hydrogen input and consumption are usually recorded to obtain the hydrogen inventory. The sub-stack efficiency can be calculated by measuring the amount of hydrogen input and the electrical energy output by the sub-stack. Peak power demand refers to the maximum power required by the sub-stack at maximum load. This can be determined through performance testing, in which the sub-stack is operated under different load conditions until its maximum output power is reached.

[0282] Step S5013, determining the required amount of hydrogen corresponding to the sub-stack according to the peak power demand and the sub-stack efficiency.

[0283] Specifically, required hydrogen = peak power demand / (sub-stack efficiency × 33.333 × 10 -6 ), where 33.333×10 -6It is the conversion of the lower heating value of hydrogen (expressed in kilowatt-hours per kilogram) into units that match the power demand.

[0284] Step S5015, determining the current operating time corresponding to the sub-stack based on the current hydrogen inventory and the required hydrogen quantity.

[0285] Specifically, current operating time = current hydrogen inventory / required hydrogen amount.

[0286] and Fig.10 Compared with the embodiment shown in the figure, this embodiment can accurately calculate the required amount of hydrogen by obtaining the current hydrogen inventory of the sub-stack, the sub-stack efficiency and the peak power demand, thereby accurately determining the hydrogen demand of the sub-stack under various operating conditions. Furthermore, according to the ratio of the current hydrogen inventory to the required hydrogen volume, the current operating time of the sub-stack can be estimated, which provides an important basis for reasonable operation and maintenance planning.

[0287] Fig.12 A flow chart of a dynamic programming algorithm provided in an embodiment of the present application, which may include the following steps:

[0288] Step S5051, determining the predicted required hydrogen amount corresponding to the sub-stack based on the predicted load power demand and the sub-stack efficiency.

[0289] Specifically, the predicted amount of hydrogen required = predicted load power demand / sub-stack efficiency.

[0290] Step S5053, determining the predicted operating time based on the current hydrogen inventory and the predicted required hydrogen volume.

[0291] Specifically, predicted operating time = current hydrogen inventory / predicted required hydrogen volume.

[0292] Step S5055, when the predicted running time is lower than the current running time, continue to iterate the dynamic programming algorithm until the predicted running time exceeds the current running time, and obtain the predicted load power demand corresponding to the sub-stack.

[0293] Specifically, when the predicted running time is lower than the current running time, the dynamic programming algorithm should be iterated and executed repeatedly until the predicted running time exceeds the current running time. This process will enable the final predicted load power demand to accurately reflect the actual demand of the sub-stack.

[0294] and Fig.10Compared with the embodiment shown in the figure, this embodiment combines the predicted load power demand and the sub-stack efficiency to accurately calculate the amount of hydrogen required by the sub-stack under future load conditions. Then, by calculating the ratio of the current hydrogen inventory to the predicted required hydrogen amount, the predicted operation time of the sub-stack is accurately estimated. Finally, by continuously iterating and optimizing the dynamic programming algorithm until the predicted operation time exceeds the current operation time, the accuracy of the predicted load power demand is ensured.

[0295] Fig.13 A flow chart of the heating and water storage function provided in an embodiment of the present application, which may include the following steps:

[0296] Step S601, obtaining the current operating temperature and current ambient temperature of the sub-stack.

[0297] Step S603, when the current working temperature is lower than the preset working temperature threshold and / or the current ambient temperature is lower than the preset ambient temperature threshold, the drainage heating function and the water storage and return function are started.

[0298] Step S605, monitoring the liquid flow rate during the drainage heating process and the liquid level during the water storage and return process.

[0299] Step S607, determining the adjusted heating power and water storage recovery rate according to the liquid flow and liquid level, and dynamically adjusting the heating power and water storage recovery rate.

[0300] Specifically, in step S601 to step S607, the current operating temperature and ambient temperature of the sub-stack are collected in real time using a sensor network. When the operating temperature is lower than a preset threshold (e.g., 2°C) or the ambient temperature is close to zero, the drainage heating function is started to prevent the drainage pipe from freezing. At the same time, the water storage return function is started to ensure that the water inside the stack will not freeze. The flow sensor and the liquid level sensor are used to monitor the liquid flow during the drainage heating process and the liquid level during the water storage return process. According to the real-time monitored flow and liquid level data, the heating power and the water storage recovery rate are dynamically adjusted to ensure that the stack operates in the best state. For example, if the liquid level is too high, the water storage recovery rate needs to be reduced to avoid excessive water flowing back to the stack, which may cause excessive humidity inside the stack. Conversely, if the liquid level is too low, the recovery rate can be increased to ensure that the stack maintains proper moisture. If the displayed flow rate is too high, the drainage rate may need to be reduced to avoid excessive loss of moisture inside the stack. If the flow rate is too low, the flow rate may need to be increased to ensure that the moisture inside the stack is discharged in time. Through the above adjustments, it is possible to automatically respond to environmental changes and the operation requirements of the fuel cell stack, ensuring that the fuel cell stack operates in a safe and efficient state. This intelligent control strategy helps to improve the performance and life of the fuel cell stack while reducing maintenance costs.

[0301] It should be noted that the embodiments of step S601 to step S607 can be implemented after step S109. After adjusting the parameters of the main stack and the slave stack, monitoring and adjustment are performed during the operation of the fuel cell vehicle to further improve the performance and life of the stack.

[0302] and Figure 1 Compared with the embodiment shown in the figure, this embodiment monitors the working temperature and ambient temperature in real time. When it is detected that the temperature is lower than the preset threshold, the drainage heating and water storage return function are automatically started to effectively prevent the freezing of water in the drainage pipe and the battery stack, thereby protecting the battery stack from the influence of low temperature. The liquid flow and liquid level are monitored in real time, and the heating power and return rate are dynamically adjusted according to the actual data to ensure the normal operation of the battery stack, prevent excessive or insufficient water, and optimize the humidity inside the battery stack.

[0303] Fig.14 A flow chart for adjusting current density provided in an embodiment of the present application may include the following steps:

[0304] Step S701, obtaining the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and determining the corresponding load power demand of the sub-stack through a preset first fuzzy control algorithm in combination with the target load demand.

[0305] Specifically, a high-precision sensor is used to measure the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and fuzzy sets (such as "low", "medium", and "high") are defined for the current density, operating temperature, temperature change rate and temperature change gradient. A membership function is created for each fuzzy set. The measured precise numerical values ​​are converted into fuzzy values, and their membership in each fuzzy set is calculated. Fuzzy control rules are defined according to the operating characteristics and performance requirements of the sub-stack. For example: current density: low, medium, and high; operating temperature: low, medium, and high; temperature change rate: slow, medium, and fast; temperature change gradient: low, medium, and high. A membership function is created for each fuzzy set. The membership function is used to convert precise numerical data into fuzzy values, usually in the form of a triangle, trapezoid or Gaussian function. For example, for the "high" set of current density, a membership function above a threshold can be defined, in which the part above the threshold has a higher membership. The real-time measured data is converted into fuzzy values. Using the defined membership function, the actual data is mapped to the fuzzy set to obtain the membership values ​​of current density, temperature, rate of change and gradient. The first fuzzy control algorithm uses a fuzzy inference system (such as Mamdani or Sugeno reasoning) to process fuzzy control rules and fuzzy values ​​to derive the power demand. The inference system calculates the fuzzy control output based on the weight and membership value of the rule. The fuzzy inference result is converted into the actual power demand value. This process is called defuzzification, and methods such as the Centroid Method can be used to obtain a clear output value. The final power demand value is stored in the database, and a mapping relationship between current density, operating temperature, temperature change rate, temperature change gradient and power demand is established to facilitate subsequent automatic adjustment and optimization.

[0306] Step S703, according to the load power demand and the temperature change gradient, the adjusted current density corresponding to the sub-stack is determined by a preset second fuzzy control algorithm.

[0307] Specifically, fuzzy sets and membership functions are defined for the power demand, temperature change gradient, and adjusted current density. For example, the power demand and temperature change gradient can be defined as "low", "medium", and "high", and the current density can be defined as "low", "medium", "high", and "very high". The second fuzzy control algorithm is able to convert the actually measured power demand and temperature change gradient into fuzzy values ​​and calculate their membership in each fuzzy set. Assumption: If the temperature change gradient is "high", the current density should be adjusted to "low". If the power demand is "high" and the temperature change gradient is "medium", the current density should be adjusted to "medium". Reasoning is performed using fuzzy control rules and fuzzified data to determine the adjusted current density. The result of fuzzy reasoning is converted into a specific current density value. This is usually achieved through a defuzzification method, such as the centroid method. According to the defuzzified current density value, the operating parameters of the stack are adjusted, such as adjusting the fuel supply or the air supply, to achieve the desired current density.

[0308] For example, assuming the power demand of the sub-stack is 50kW and the temperature gradient is 3℃ / cm, the temperature gradient is considered "high" because it exceeds the preset threshold of 2℃ / cm. According to the fuzzy control rules, the algorithm recommends reducing the current density to 6A / cm 2 , so as to control the temperature rise rate within 3℃ / s. Convert the load power demand and temperature change gradient into fuzzy values. According to the fuzzy control rules, calculate the specific adjustment current density, such as 6A / cm².

[0309] Step S705, dynamically adjusting the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the adjusted current density.

[0310] Specifically, a mathematical model describing the operating state of the battery stack can be established, which usually includes the following parts: electrochemical reaction model: describing the process of generating water and electric energy by the reaction of hydrogen and oxygen; thermodynamic model: considering the influence of temperature change of the battery stack on the reaction; fluid dynamics model: involving the relationship between gas flow, pressure and flow rate. According to the established model, a control strategy is designed to adjust the flow, pressure and temperature of gas and liquid. These strategies usually include: feedback control: by real-time monitoring of the actual current density and other performance parameters of the battery stack, the flow, pressure and temperature of hydrogen, oxygen and water are adjusted to keep the battery stack running at the expected current density. Feedforward control: based on the prediction of the change in the state of the battery stack, the parameters of the gas and liquid are adjusted in advance to prevent performance fluctuations caused by delays. Based on the sensor data, the controller automatically adjusts the flow, pressure and temperature of the gas and water to ensure that the battery stack meets the set current density under the optimized operating state. It can also be the same as step S305, which will not be repeated here.

[0311] It should be noted that the embodiments of steps S701 to S705 can be implemented after step S109. After adjusting the parameters of the main stack and the slave stack, monitoring and adjustment are performed during the operation of the fuel cell vehicle to further ensure the operating stability and efficiency of each sub-stack.

[0312] and Figure 1 Compared with the embodiment shown in the figure, this embodiment obtains the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and uses the first fuzzy control algorithm to process these data. It can accurately evaluate the working state of the sub-stack and predict its power demand. Then, the second fuzzy control algorithm determines the adjustment current density according to the power demand and the temperature change gradient. The current density can be dynamically adjusted during the operation of the sub-stack to maintain the optimal working state and efficiency of the stack. Finally, the flow, pressure and temperature of hydrogen, oxygen and water are dynamically adjusted according to the adjusted current density. It is possible to optimize the gas and liquid flow in the sub-stack in real time to keep the sub-stack under optimal operating conditions, ensure the operating stability and efficiency of the sub-stack, and thus improve the overall performance and responsiveness of the sub-stack.

[0313] Fig.15 A flowchart for adjusting weight distribution provided in an embodiment of the present application may include the following steps:

[0314] Step S801, obtaining weight distribution data of the hydrogen fuel cell vehicle body, and constructing a weight distribution matrix according to the weight distribution data; wherein the weight distribution matrix is ​​used to characterize the weight data of different areas of the body.

[0315] Specifically, since hydrogen fuel cell vehicles are equipped with battery stacks, lithium battery packs, various auxiliary power supplies, cooling systems, heating systems, air conditioners, air intake and exhaust, and centralized control cabinets, the stability of hydrogen fuel cell vehicles will be poor. For this reason, this embodiment arranges a high-precision sensor in each square meter of the box to ensure full coverage of the entire surface of the box. Ensure that the sensor can accurately measure and record the weight of its location. The sensor network is used to obtain the weight distribution data of the box in real time, and the collected data can be preprocessed, including removing outliers, filtering and calibration to ensure the accuracy of the data. The preprocessed data is constructed into a matrix according to the layout of the box, and each element in the matrix represents the weight of the corresponding area. For example, if the total area of ​​the box is 20 square meters, it can be divided into a grid of 3 rows × 6 columns, each grid corresponding to the position of a sensor, then the weight distribution matrix may be a 3 × 6 matrix.

[0316] Step S803: Analyze the box body using finite element software according to the weight distribution matrix to obtain the overweight area.

[0317] Specifically, a geometric model of the box is constructed in the finite element software to ensure that the size and shape of the model match the actual box. Assign corresponding physical and mechanical properties to the box material, such as density (such as 7800kg / m³ steel), elastic modulus (such as 200GPa steel), Poisson's ratio (such as 0.3 steel), etc. The geometric model is meshed to generate a finite element mesh for analysis. The density of the mesh should be adjusted according to the accuracy requirements of the weight distribution. The data in the weight distribution matrix is ​​converted into appropriate load conditions (such as distributed loads, concentrated loads). At the same time, the constraints under the actual working state are simulated. Perform finite element analysis, and the software will calculate and provide results such as stress, strain, and displacement of the box. After the analysis is completed, use the post-processing tools of the finite element software to view and evaluate the results and obtain the overweight area.

[0318] Step S805, adjusting the structural design parameters of the box body through finite element software according to the overweight area, and adjusting the structure of the box body according to the structural design parameters.

[0319] Specifically, analyze the current load capacity of the overweight area and compare it with the design load capacity to determine whether design adjustments are needed. Determine the structural design parameters that need to be adjusted, such as material type, thickness, geometry, and rib layout. Create a parametric box model in the finite element software to quickly adjust the design parameters and reanalyze. Based on the analysis results, adjust the structural design parameters of the box. For example, if the weight of a certain area exceeds 600 kg, it may be necessary to increase the material thickness of the area or add ribs.

[0320] It should be noted that the embodiments of step S801 to step S805 may be implemented before step S101 to ensure the reliability and durability of the box.

[0321] and Figure 1 Compared with the embodiment shown in the figure, this embodiment obtains the weight distribution data of the hydrogen fuel cell vehicle box in real time, and constructs a weight distribution matrix based on the weight distribution data. Each element in the matrix represents the weight of the corresponding area. Then, the box is analyzed using finite element software to identify the overweight area of ​​the box, evaluate its stress and load-bearing capacity in actual use, and provide a basis for design optimization. The analysis results can reveal potential overweight areas, which helps to discover and solve structural problems in advance. According to the analysis results of the overweight area, the structural design parameters of the box, such as material type, thickness, geometry, etc., are adjusted. Through optimized design, the load-bearing capacity and stability of the box are enhanced, the load in the overweight area is reduced, and the potential risk of failure caused by insufficient design is reduced, thereby improving the reliability and durability of the overall structure.

[0322] Fig.16A flowchart of adjusting the structure of a box according to structural design parameters provided in an embodiment of the present application, wherein the structural design parameters include redistributing loads; the flow may include the following steps:

[0323] Step S8051, obtain the weight, size and position of each device in the box, and determine the center of gravity position of each device.

[0324] Specifically, use high-precision weighing equipment to weigh each device and record its exact weight. Use a laser rangefinder or caliper to measure the size of each device and record its length, width, height and other data. Use a three-dimensional coordinate measurement tool (such as a laser scanner or total station) to determine the exact position coordinates of each device in the box. Based on the geometric shape and mass distribution of the device, use a formula to calculate the center of gravity of each device.

[0325] For example: the device is a uniform cuboid, the center of gravity position (x c ,y c ,z c ), x c =L / 2,y c =W / 2, z c =H / 2, L, W and H are the length, width and height of the cuboid respectively.

[0326] The device is a uniform cylinder, the center of gravity position (x c ,y c ,z c ), x c =D / 2,y c =D / 2, z c =H / 2, D is the diameter of the cylinder, H is the height of the cylinder.

[0327] The device is a uniform cone, the center of gravity position (x c ,y c ,z c ), x c =D / 2,y c =D / 2, z c =H / 2, D is the diameter of the cone, H is the height of the cone.

[0328] The device is irregular in shape, and the center of gravity (x c ,y c ,z c ), , , , M is the total mass of the device, ρ(x,y,z) is the mass density distribution, and dV is the volume element.

[0329] The equipment is distributed at different densities, and the center of gravity position (x c ,y c ,zc ), , ,

[0330] , m i is the mass of each block, x i ,y i 、z i are the centroid coordinates of each small block.

[0331] Step S8053, weighting the center of gravity position to obtain the overall center of gravity position.

[0332] Specifically, for each device, the contribution of its center of gravity position to the overall center of gravity in the x, y, and z directions is calculated, and then the contributions of all devices in the x, y, and z directions are summed, and the result is used as the overall center of gravity position.

[0333] For example: The mass of the battery stack is m1 = 10kg, and the coordinates of the center of gravity are (x1, y1, z1) = (1, 2, 3) m. The mass of the cooling system is m2 = 20kg, and the coordinates of the center of gravity are (x2, y2, z2) = (4, 5, 6) m. The mass of the heating system is m3 = 30kg, and the coordinates of the center of gravity are (x3, y3, z3) = (7, 8, 9) m. The overall center of gravity position is:

[0334] x cg,total =(10×1+20×4+30×7) / (10+20+30)=310 / 60=5.17m;

[0335] y cg,total =(10×2+20×5+30×8) / (10+20+30)=340 / 60=5.67m;

[0336] z cg,total =(10×3+20×6+30×9) / (10+20+30)=390 / 60=6.50m.

[0337] Step S8055, determine the offset between the overall center of gravity position and the geometric center of the box. If the offset is greater than a preset offset threshold, input the weight, size, position, center of gravity position and geometric center into the dynamic balancing algorithm to generate a load adjustment plan.

[0338] Step S8057: adjust the equipment in the box according to the load adjustment plan.

[0339] Specifically, during the mobile layout, it is crucial to ensure that the overall center of gravity of the box is aligned with the geometric center, which helps maintain stability and safety during transportation. The distance between the overall center of gravity and the geometric center, that is, the offset, can be calculated using the Euclidean distance formula. Determine a preset offset threshold, which is the maximum allowable offset, exceeding which may require load adjustment. Here, the preset offset threshold is set to 2 meters, and parameters such as weight, size, position, center of gravity position, and geometric center are input into the dynamic balancing algorithm. The algorithm calculates a load adjustment plan to reduce the center of gravity offset. The dynamic balancing algorithm can be trained based on historical data.

[0340] Assume that the geometric center of the box is (2,1,1.5), the current overall center of gravity calculation result is (2.5,1.2,1.8), and the offset is 0.62 meters. If the threshold is set to 2 meters, the offset is within the threshold and no adjustment is required; otherwise, the algorithm will suggest moving some objects to the geometric center or adjusting their weight to reduce the offset.

[0341] and Fig.15 Compared with the embodiment shown in the figure, this embodiment provides basic data for further calculating the center of gravity position by obtaining the weight, size and position of each device in the box. The overall center of gravity position is obtained by weighted calculation of the center of gravity position of all devices. This weighted method combines the mass and position data of all devices so that the overall center of gravity position can truly reflect the mass distribution of the equipment in the entire box. The offset between the overall center of gravity position and the geometric center of the box is calculated and compared with the preset threshold to ensure the stability and safety of the box during transportation. If the offset exceeds the preset threshold, the dynamic balancing algorithm will generate a load adjustment plan to optimize the equipment layout to reduce the center of gravity offset, thereby improving the transportation stability of the box. Finally, the equipment is actually adjusted according to the load adjustment plan to ensure that the overall center of gravity position is aligned with the geometric center. This not only improves the stability during transportation, but also effectively avoids potential safety hazards caused by center of gravity offset.

[0342] Accordingly, please refer to Fig.17 A block diagram of a coordinated optimization system for a hydrogen fuel cell vehicle provided in an embodiment of the present application, the system comprising:

[0343] The target output determination module S001 is used to determine the target output voltage and target output current corresponding to the battery stack in the hydrogen fuel cell vehicle based on the acquired target load demand of the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel;

[0344] The efficiency scoring and stability scoring module S003 is used to determine the sub-stack efficiency score corresponding to the sub-stack, and determine the sub-stack stability score corresponding to the sub-stack;

[0345] A comprehensive scoring module S005 is used to comprehensively score the sub-stack efficiency score and the sub-stack stability score, and determine the main stack and the slave stack in the sub-stack according to the result of the comprehensive scoring;

[0346] An output parameter determination module S007, configured to generate a main stack output parameter corresponding to the main stack and a slave stack output parameter corresponding to the slave stack using a preset output characteristic model according to the target output voltage and the target output current;

[0347] The dynamic adjustment module S009 is used to dynamically adjust the working state of the main fuel cell stack according to the output parameters of the main fuel cell stack, and dynamically adjust the working state of the slave fuel cell stack according to the output parameters of the slave fuel cell stack to meet the target load demand.

[0348] Optionally, the target output determination module S001 includes:

[0349] A load demand acquisition unit, used to acquire the current load demand of the hydrogen fuel cell vehicle;

[0350] A data smoothing unit, configured to use a Kalman filter to perform data smoothing on the current load demand to obtain the smoothed target load demand;

[0351] A target output determination unit is used to generate the target output voltage and the target output current corresponding to the battery stack according to the target load demand using a preset fuzzy rule base.

[0352] Optionally, the efficiency scoring and stability scoring module S003 determines the sub-stack efficiency score corresponding to the sub-stack, including:

[0353] An acquisition unit, used to acquire the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period;

[0354] an average output voltage and average output current determining unit, configured to determine an average output voltage of the output voltage within the preset time period, and determine an average output current of the output current within the preset time period;

[0355] an average output power determination unit, configured to determine an average output power corresponding to the sub-stack according to the average output voltage and the average output current;

[0356] An average input power generation unit, used for inputting the hydrogen flow rate and the oxygen flow rate into a preset power conversion model to generate an average input power corresponding to the sub-stack;

[0357] An efficiency score determination unit is used to determine the sub-stack efficiency score according to the ratio of the average output power to the average input power.

[0358] Optionally, the efficiency scoring and stability scoring module S003 determines the sub-stack stability score corresponding to the sub-stack, including:

[0359] An output voltage and output current acquisition unit, used to acquire the output voltage and output current of the sub-stack within a preset time period;

[0360] a voltage standard deviation and current standard deviation determining unit, configured to determine a voltage standard deviation of the output voltage within the preset time period, and determine a current standard deviation of the output current within the preset time period;

[0361] A stability score determination unit is used to determine the stability score of the sub-stack according to the voltage standard deviation and the current standard deviation using a preset stability score model.

[0362] Optionally, the comprehensive scoring module S005 includes:

[0363] A comprehensive scoring unit, used for weighting the sub-stack efficiency score and the sub-stack stability score to obtain a comprehensive score;

[0364] A clustering unit, used for clustering each of the sub-stacks to obtain a stack cluster including one or more sub-stacks;

[0365] A representative feature determination unit, used to determine the intra-cluster representative features of each of the battery stack clusters, and for any battery stack cluster, determine the battery stack feature set to which the intra-cluster representative features belong;

[0366] A candidate battery stack determination unit, configured to obtain a risk factor of each of the battery stack feature sets, and screen out a candidate battery stack feature set based on the risk factor;

[0367] The master-slave battery stack determination unit is used to sort the comprehensive scores of each sub-battery stack from high to low in the battery stack cluster corresponding to the candidate battery stack feature set, and determine the sub-battery stack corresponding to the highest comprehensive score as the master battery stack, and the remaining sub-battery stacks as the slave battery stacks.

[0368] Optionally, the preset output characteristic model includes a support vector machine, a decision tree and a random forest; the main battery stack output parameters include a main output voltage, a main output current and a main output power; the slave battery stack output parameters include a slave output voltage, a slave output current and a slave output power; the output parameter determination module S007 includes:

[0369] an output voltage unit, configured to generate a main output voltage corresponding to the main battery stack and a slave output voltage corresponding to the slave battery stack using the support vector machine according to the target output voltage and the target output current;

[0370] an output current unit, configured to generate a main output current corresponding to the main battery stack and a slave output current corresponding to the slave battery stack using the decision tree according to the target output voltage and the target output current;

[0371] An output power unit is used to generate a main output power corresponding to the main battery stack and a slave output power corresponding to the slave battery stack using the random forest according to the target output voltage and the target output current.

[0372] Optionally, after the dynamic adjustment module S009, the system further includes:

[0373] Comparing the main output voltage with the target output voltage, and if the difference in the comparison result exceeds a voltage deviation threshold, re-adjusting the working state of the main fuel cell stack and the working state of the slave fuel cell stack;

[0374] The main output current is compared with the target output current, and when the difference in the comparison result exceeds a current deviation threshold, the working state of the main fuel cell stack and the working state of the slave fuel cell stack are readjusted.

[0375] Optionally, the system further comprises:

[0376] A performance parameter acquisition module, used for acquiring performance parameters of the auxiliary power supplies when the battery stack is used in conjunction with multiple auxiliary power supplies;

[0377] An output power range determination module, used to determine the output power range corresponding to the auxiliary power supply according to the performance parameters using a preset performance-power range model;

[0378] The power allocation scheme generation module is used to generate an optimized power allocation scheme using a multi-objective optimization algorithm with maximizing power supply efficiency, equipment power supply reliability and equipment life as objective functions and the output power of the auxiliary power supply satisfying the output power range as a constraint condition; wherein the equipment power supply reliability represents the proportion of time to maintain the target load demand.

[0379] Optionally, the auxiliary power source includes a generator, a solar panel and a lithium battery pack;

[0380] The performance parameters include the power generation efficiency of the generator, the maximum output power of the solar panel and the capacity of the lithium battery pack.

[0381] Optionally, the generating an optimized power allocation scheme by using a multi-objective optimization algorithm further includes satisfying the following conditions:

[0382] The target load demand is equal to the sum of the output power of each battery stack and the output power of the auxiliary power supply;

[0383] The output power of each of the sub-stacks must be within the design limit.

[0384] Optionally, the objective function includes:

[0385]

[0386] Power supply efficiency = output power of battery stack or auxiliary power supply / target load demand

[0387] Among them, w1, w2, w3 are weight coefficients; a i is the power supply efficiency of the ith sub-stack or auxiliary power supply; b i The reliability of power supply for the i-th sub-stack or auxiliary power supply equipment; c i is the equipment life of the ith sub-stack or auxiliary power supply.

[0388] Optionally, the system further comprises:

[0389] A membership determination module is used to obtain the temperature change rate and current load power of each sub-stack, and use a fuzzy logic algorithm to determine the temperature change trend membership corresponding to the sub-stack; wherein the temperature change trend membership is used to characterize the fuzzification degree of the temperature change trend;

[0390] An adjustment power generation module, used to generate an adjustment power corresponding to the sub-stack according to the current load power and the temperature change trend membership;

[0391] The power adjustment module is used to dynamically adjust the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the adjusted power.

[0392] Optionally, the system further comprises:

[0393] A function adjustment module, used for adjusting the membership function in the fuzzy logic algorithm to obtain an adjusted fuzzy logic algorithm when the temperature change rate exceeds a preset temperature change threshold;

[0394] An updated membership determination module, used to determine the updated temperature change trend membership corresponding to the sub-stack according to the adjusted fuzzy logic algorithm;

[0395] An updated adjustment power generation module, used to generate an updated adjustment power corresponding to the sub-stack according to the current load power and the updated temperature change trend membership;

[0396] The power adjustment module is updated and adjusted, and is used to dynamically adjust the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the updated adjusted power.

[0397] Optionally, the system further comprises:

[0398] A current running time determination module, used to determine the current running time corresponding to the sub-stack;

[0399] A predicted load power demand determination module is used to determine the predicted load power demand corresponding to the sub-stack within a period of time in the future using a dynamic programming algorithm based on the target load demand and with the goal of extending the current operating time;

[0400] A dynamic adjustment module is used to dynamically adjust the flow, pressure and temperature of hydrogen, the flow, pressure and temperature of oxygen, and the flow, pressure and temperature of water in the sub-stack according to the predicted load power demand.

[0401] Optionally, the current running time determination module includes:

[0402] Obtaining the current hydrogen inventory, sub-stack efficiency and peak power demand of each of the sub-stacks;

[0403] Determining a required amount of hydrogen corresponding to the sub-stack according to the peak power demand and the sub-stack efficiency;

[0404] The current operating time corresponding to the sub-stack is determined according to the current hydrogen inventory and the required hydrogen quantity.

[0405] Optionally, the dynamic programming algorithm includes:

[0406] Determining a predicted required amount of hydrogen corresponding to the sub-stack according to the predicted load power demand and the sub-stack efficiency;

[0407] Determining a predicted operating time according to the current hydrogen inventory and the predicted required hydrogen quantity;

[0408] When the predicted running time is lower than the current running time, the dynamic programming algorithm is continuously iterated until the predicted running time exceeds the current running time, thereby obtaining the predicted load power demand corresponding to the sub-stack.

[0409] Optionally, the system further comprises:

[0410] A temperature acquisition module, used to acquire the current operating temperature and current ambient temperature of the sub-stack;

[0411] A heating and water storage module, used to start the drainage heating function and the water storage and return function when the current working temperature is lower than a preset working temperature threshold and / or the current ambient temperature is lower than a preset ambient temperature threshold;

[0412] Monitoring module, used to monitor the liquid flow rate during drainage heating and the liquid level during water storage and return;

[0413] The heating power and water storage recovery rate determination and adjustment module is used to determine the adjusted heating power and water storage recovery rate according to the liquid flow and the liquid level, and dynamically adjust the heating power and the water storage recovery rate according to the heating power and the water storage recovery rate.

[0414] Optionally, the system further comprises:

[0415] A load power demand determination module is used to obtain the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and determine the load power demand corresponding to the sub-stack through a preset first fuzzy control algorithm in combination with the target load demand;

[0416] An adjustment current density determination module, used to determine the adjustment current density corresponding to the sub-stack through a preset second fuzzy control algorithm according to the load power requirement and the temperature change gradient;

[0417] The current density adjustment module is used to dynamically adjust the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack according to the adjusted current density.

[0418] Optionally, the system further comprises:

[0419] A matrix construction module, used to obtain weight distribution data of a hydrogen fuel cell vehicle box, and to construct a weight distribution matrix according to the weight distribution data; wherein the weight distribution matrix is ​​used to characterize weight data of different areas of the box;

[0420] An analysis module, used to analyze the box body according to the weight distribution matrix using finite element software to obtain an overweight area;

[0421] A parameter adjustment module is used to adjust the structural design parameters of the box body according to the overweight area through finite element software, and adjust the structure of the box body according to the structural design parameters.

[0422] Optionally, the structural design parameters include redistributing loads; and adjusting the structure of the box according to the structural design parameters includes:

[0423] Obtain the weight, size and position of each device in the box, and determine the center of gravity position of each device;

[0424] Weighting the center of gravity position to obtain the overall center of gravity position;

[0425] Determining the offset between the overall center of gravity position and the geometric center of the box, and if the determination result shows that the offset is greater than a preset offset threshold, inputting the weight, the size, the position, the center of gravity position and the geometric center into a dynamic balancing algorithm to generate a load adjustment plan;

[0426] The equipment in the box is adjusted according to the load adjustment scheme.

[0427] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0428] In this embodiment, a coordinated optimization system for a hydrogen fuel cell vehicle is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0429] See also Fig.18 , Fig.18 A schematic diagram of the structure of a computer device provided in an embodiment of the present application is shown in FIG. Fig.18 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.18 A processor 10 is taken as an example.

[0430] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0431] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0432] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0433] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0434] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0435] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0436] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0437] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0438] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0439] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0440] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0441] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0442] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0443] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0444] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0445] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A coordination optimization method for a hydrogen fuel cell vehicle, characterized in that: The method comprises: Based on the acquired target load demand of the hydrogen fuel cell vehicle, determining a target output voltage and a target output current corresponding to a battery stack in the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel; Determine a sub-stack efficiency score corresponding to the sub-stack, and determine a sub-stack stability score corresponding to the sub-stack; wherein the sub-stack efficiency score is used to characterize the ratio of the average output power to the average input power of the sub-stack in a specific time period; and the sub-stack stability score is used to characterize the degree of fluctuation of the output voltage and output current of the sub-stack in a specific time period; Perform a comprehensive score on the sub-stack efficiency score and the sub-stack stability score; cluster each of the sub-stacks to obtain a stack cluster containing one or more sub-stacks; determine the representative features within each of the stack clusters, and for any stack cluster, determine the stack feature set to which the representative features within the cluster belong; obtain the risk coefficient of each stack feature set, and screen out a candidate stack feature set based on the risk coefficient; in the stack cluster corresponding to the candidate stack feature set, sort the comprehensive scores of each sub-stack from high to low; and determine the main stack and slave stack in the sub-stack based on the result of the comprehensive score; wherein, based on stability and failure risk factors, the stack feature set is evaluated for risk coefficient; According to the target output voltage and the target output current, using a preset output characteristic model to generate a main stack output parameter corresponding to the main stack, and to generate a slave stack output parameter corresponding to the slave stack; The working state of the main fuel cell stack is dynamically adjusted according to the output parameter of the main fuel cell stack, and the working state of the slave fuel cell stack is dynamically adjusted according to the output parameter of the slave fuel cell stack to meet the target load demand.

2. The method according to claim 1, characterized in that The step of determining a target output voltage and a target output current corresponding to a fuel cell stack in the hydrogen fuel cell vehicle based on the acquired target load demand of the hydrogen fuel cell vehicle includes: Obtaining the current load demand of the hydrogen fuel cell vehicle; Using Kalman filtering to smooth the current load demand data to obtain the smoothed target load demand; According to the target load demand, the target output voltage and the target output current corresponding to the battery stack are generated using a preset fuzzy rule base.

3. The method according to claim 1, characterized in that The determining of the sub-stack efficiency score corresponding to the sub-stack includes: Obtaining the output voltage, output current, hydrogen flow rate and oxygen flow rate of the sub-stack within a preset time period; Determining an average output voltage of the output voltage within the preset time period, and determining an average output current of the output current within the preset time period; Determining an average output power corresponding to the sub-stack according to the average output voltage and the average output current; Inputting the hydrogen flow rate and the oxygen flow rate into a preset power conversion model to generate an average input power corresponding to the sub-stack; The sub-stack efficiency score is determined based on the ratio of the average output power to the average input power.

4. The method according to claim 1, characterized in that: The determining of the sub-stack stability score corresponding to the sub-stack includes: Obtaining the output voltage and output current of the sub-stack within a preset time period; Determining a voltage standard deviation of the output voltage within the preset time period, and determining a current standard deviation of the output current within the preset time period; The sub-stack stability score is determined based on the voltage standard deviation and the current standard deviation using a preset stability score model.

5. The method according to claim 1, characterized in that The step of comprehensively scoring the sub-stack efficiency score and the sub-stack stability score, and determining the main stack and the slave stack in the sub-stack according to the result of the comprehensive scoring, includes: Weighting the sub-stack efficiency score and the sub-stack stability score to obtain a comprehensive score; The sub-stack corresponding to the highest comprehensive score is determined as the main stack, and the remaining sub-stacks are determined as the slave stacks.

6. The method according to claim 1, characterized in that The preset output characteristic model includes a support vector machine, a decision tree and a random forest; the main stack output parameters include a main output voltage, a main output current and a main output power; the slave stack output parameters include a slave output voltage, a slave output current and a slave output power; the method of generating the main stack output parameters corresponding to the main stack and generating the slave stack output parameters corresponding to the slave stack using the preset output characteristic model according to the target output voltage and the target output current includes: According to the target output voltage and the target output current, using the support vector machine to generate a master output voltage corresponding to the master stack and a slave output voltage corresponding to the slave stack; According to the target output voltage and the target output current, using the decision tree to generate a main output current corresponding to the main battery stack and a slave output current corresponding to the slave battery stack; According to the target output voltage and the target output current, the random forest is used to generate a main output power corresponding to the main fuel cell stack and a slave output power corresponding to the slave fuel cell stack.

7. The method according to claim 6, characterized in that After dynamically adjusting the working state of the main battery stack according to the output parameter of the main battery stack, and dynamically adjusting the working state of the slave battery stack according to the output parameter of the slave battery stack, the method further includes: Comparing the main output voltage with the target output voltage, and if the difference in the comparison result exceeds a voltage deviation threshold, re-adjusting the working state of the main fuel cell stack and the working state of the slave fuel cell stack; The main output current is compared with the target output current, and when the difference in the comparison result exceeds a current deviation threshold, the working state of the main fuel cell stack and the working state of the slave fuel cell stack are readjusted.

8. The method according to claim 1, characterized in that The method further comprises: When the battery stack is used in conjunction with a plurality of auxiliary power supplies, obtaining performance parameters of the auxiliary power supplies; According to the performance parameters, a preset performance-power range model is used to determine the output power range corresponding to the auxiliary power supply; With maximizing power supply efficiency, equipment power supply reliability and equipment life as objective functions, and the output power of the auxiliary power supply satisfying the output power range as a constraint, a multi-objective optimization algorithm is used to generate an optimized power allocation scheme; wherein, the equipment power supply reliability represents the proportion of time to maintain the target load demand.

9. The method according to claim 8, characterized in that The auxiliary power source includes a generator, a solar panel and a lithium battery pack; The performance parameters include the power generation efficiency of the generator, the maximum output power of the solar panel and the capacity of the lithium battery pack.

10. The method according to claim 8, characterized in that The use of a multi-objective optimization algorithm to generate an optimized power allocation solution also includes satisfying the following conditions: The target load demand is equal to the sum of the output power of each battery stack and the output power of the auxiliary power supply; The output power of each of the sub-stacks must be within the design limit.

11. The method according to claim 8, characterized in that The objective function includes: Power supply efficiency = output power of battery stack or auxiliary power supply / target load demand Among them, w1, w2, w3 are weight coefficients; a i is the power supply efficiency of the ith sub-stack or auxiliary power supply; b i The reliability of power supply for the i-th sub-stack or auxiliary power supply equipment; c i is the equipment life of the ith sub-stack or auxiliary power supply.

12. The method according to claim 1, characterized in that The method further comprises: Obtaining the temperature change rate and current load power of each sub-stack, and using a fuzzy logic algorithm to determine the temperature change trend membership corresponding to the sub-stack; wherein the temperature change trend membership is used to characterize the fuzzification degree of the temperature change trend; Generate an adjustment power corresponding to the sub-stack according to the current load power and the temperature change trend membership; According to the adjusted power, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

13. The method according to claim 12, characterized in that The method further comprises: When the temperature change rate exceeds a preset temperature change threshold, adjusting the membership function in the fuzzy logic algorithm to obtain an adjusted fuzzy logic algorithm; Determining, according to the adjusted fuzzy logic algorithm, an updated temperature change trend membership corresponding to the sub-stack; generating an updated adjusted power corresponding to the sub-stack according to the current load power and the updated temperature change trend membership; According to the updated adjusted power, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

14. The method according to claim 1, characterized in that The method further comprises: Determine the current running time corresponding to the sub-stack; According to the target load demand, with the goal of extending the current operating time, a dynamic programming algorithm is used to determine the predicted load power demand corresponding to the sub-stack in a future period of time; According to the predicted load power demand, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

15. The method according to claim 14, characterized in that The determining the current operating time corresponding to the sub-stack includes: Obtaining the current hydrogen inventory, sub-stack efficiency and peak power demand of each of the sub-stacks; Determining a required amount of hydrogen corresponding to the sub-stack according to the peak power demand and the sub-stack efficiency; The current operating time corresponding to the sub-stack is determined according to the current hydrogen inventory and the required hydrogen quantity.

16. The method according to claim 14, characterized in that The dynamic programming algorithm includes: Determining a predicted required amount of hydrogen corresponding to the sub-stack according to the predicted load power demand and the sub-stack efficiency; Determining a predicted operating time according to the current hydrogen inventory and the predicted required hydrogen quantity; When the predicted running time is lower than the current running time, the dynamic programming algorithm is continuously iterated until the predicted running time exceeds the current running time, thereby obtaining the predicted load power demand corresponding to the sub-stack.

17. The method according to claim 1, characterized in that The method further comprises: Obtaining the current operating temperature and current ambient temperature of the sub-stack; When the current working temperature is lower than a preset working temperature threshold and / or the current ambient temperature is lower than a preset ambient temperature threshold, starting a drainage heating function and a water storage return function; Monitor the liquid flow rate during drainage heating and the liquid level during storage water return; The adjusted heating power and water storage recovery rate are determined according to the liquid flow and the liquid level, and dynamic adjustments are made according to the heating power and the water storage recovery rate.

18. The method according to claim 1, characterized in that The method further comprises: Obtaining the current current density, current operating temperature, temperature change rate and temperature change gradient of the sub-stack, and determining the load power demand corresponding to the sub-stack by using a preset first fuzzy control algorithm in combination with the target load demand; According to the power demand and the temperature gradient, determining the adjusted current density corresponding to the sub-stack by a preset second fuzzy control algorithm; According to the adjusted current density, the flow rate, pressure and temperature of hydrogen, the flow rate, pressure and temperature of oxygen, and the flow rate, pressure and temperature of water in the sub-stack are dynamically adjusted.

19. The method according to claim 1, characterized in that The method further comprises: Obtaining weight distribution data of a hydrogen fuel cell vehicle box, and constructing a weight distribution matrix according to the weight distribution data; wherein the weight distribution matrix is ​​used to characterize weight data of different areas of the box; According to the weight distribution matrix, the box is analyzed using finite element software to obtain an overweight area; According to the overweight area, the structural design parameters of the box are adjusted by finite element software, and the structure of the box is adjusted according to the structural design parameters.

20. The method according to claim 19, characterized in that The structural design parameters include redistributing loads; and adjusting the structure of the box according to the structural design parameters includes: Obtain the weight, size and position of each device in the box, and determine the center of gravity position of each device; Weighting the center of gravity position to obtain the overall center of gravity position; Determining the offset between the overall center of gravity position and the geometric center of the box, and if the determination result shows that the offset is greater than a preset offset threshold, inputting the weight, the size, the position, the center of gravity position and the geometric center into a dynamic balancing algorithm to generate a load adjustment plan; The equipment in the box is adjusted according to the load adjustment scheme.

21. A coordination optimization system for a hydrogen fuel cell vehicle, characterized in that: The system comprises: A target output determination module, used to determine the target output voltage and target output current corresponding to the battery stack in the hydrogen fuel cell vehicle based on the acquired target load demand of the hydrogen fuel cell vehicle; wherein the battery stack includes at least two sub-battery stacks connected in parallel; An efficiency scoring and stability scoring module, used to determine the sub-stack efficiency score corresponding to the sub-stack, and to determine the sub-stack stability score corresponding to the sub-stack; wherein the sub-stack efficiency score is used to characterize the ratio of the average output power to the average input power of the sub-stack in a specific time period; and the sub-stack stability score is used to characterize the degree of fluctuation of the output voltage and output current of the sub-stack in a specific time period; A comprehensive scoring module is used to comprehensively score the sub-stack efficiency score and the sub-stack stability score; cluster each of the sub-stacks to obtain a stack cluster containing one or more sub-stacks; determine the representative features within each of the stack clusters, and for any stack cluster, determine the stack feature set to which the representative features within the cluster belong; obtain the risk coefficient of each stack feature set, and screen out a candidate stack feature set based on the risk coefficient; in the stack cluster corresponding to the candidate stack feature set, sort the comprehensive scores of each sub-stack from high to low; and determine the main stack and slave stack in the sub-stack based on the result of the comprehensive scoring; wherein, based on stability and failure risk factors, the stack feature set is evaluated for risk coefficient; an output parameter determination module, configured to generate a main stack output parameter corresponding to the main stack and a slave stack output parameter corresponding to the slave stack using a preset output characteristic model according to the target output voltage and the target output current; A dynamic adjustment module is used to dynamically adjust the working state of the main fuel cell stack according to the output parameters of the main fuel cell stack, and dynamically adjust the working state of the slave fuel cell stack according to the output parameters of the slave fuel cell stack to meet the target load demand.

22. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the coordinated optimization method for a hydrogen fuel cell vehicle according to any one of claims 1 to 20 by executing the computer instructions.

23. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the coordinated optimization method for a hydrogen fuel cell vehicle according to any one of claims 1 to 20.

Images