Control method and device of fuel cell system, vehicle and storage medium

Abstract

The invention provides a control method and device of a fuel cell system, a vehicle and a storage medium, the method is applied to the field of vehicles, and the method comprises the following steps: acquiring current driving data of the vehicle; determining a current driving condition of the vehicle based on the current driving data; determining a target maintaining temperature of the fuel cell system corresponding to the current driving working condition; and controlling the current temperature of the fuel cell system to be kept at the target maintaining temperature. According to the method, it can be ensured that the fuel cell system runs at the optimal temperature under different running working conditions of the vehicle, so that it is ensured that the output power of the fuel cell system meets the power requirement of the whole vehicle, the energy conversion efficiency of the fuel cell system can be improved, and energy loss is reduced.

Description

Technical Field

[0001] This application relates to the field of vehicles, and more specifically, to control methods, apparatus, vehicles, and storage media for fuel cell systems in the field of vehicles. Background Technology

[0002] Currently, new energy vehicles are gradually replacing traditional fuel vehicles and becoming people's first choice for vehicles. Among new energy vehicles, fuel cell vehicles are gradually gaining popularity due to their advantages such as zero emissions, high efficiency, and quiet operation.

[0003] However, in fuel cell vehicles, the liquid water inside the membrane electrode assembly (MEA) undergoes a phase change to form solid ice when the fuel cell system is below 0°C. This leads to problems such as proton exchange membrane (PEM) and catalyst layer separation, mechanical degradation of the PEM, and damage to the catalyst layer and microporous layer, ultimately causing a decline in fuel cell system performance. In existing technologies, one approach for starting the fuel cell system below 0°C is to use coolant heating. However, if the fuel cell system temperature is too low, this method may consume a significant amount of energy. Another approach is to maintain the fuel cell temperature at a certain threshold. While this can reduce energy loss to some extent, it may sometimes fail to meet the vehicle's power requirements. Summary of the Invention

[0004] This application provides a control method, apparatus, vehicle, and storage medium for a fuel cell system. The method can ensure that the fuel cell system operates at the optimal temperature under different driving conditions, thereby ensuring that the output power of the fuel cell system meets the power requirements of the vehicle, and can also improve the energy conversion efficiency of the fuel cell system and reduce energy loss.

[0005] In a first aspect, a control method for a fuel cell system is provided, the method comprising: acquiring current driving data of a vehicle; determining the current driving condition of the vehicle based on the current driving data; determining a target sustaining temperature of the fuel cell system corresponding to the current driving condition; and controlling the current temperature of the fuel cell system to be maintained at the target sustaining temperature.

[0006] The aforementioned technical solution, by acquiring the vehicle's current driving data, can more accurately determine the vehicle's current driving condition. Furthermore, by determining the target sustaining temperature corresponding to the current driving condition and controlling the fuel cell system's current temperature to maintain it at the target sustaining temperature, it ensures the fuel cell system operates at its optimal temperature. This guarantees that the fuel cell system's output power meets the vehicle's power requirements and also improves the fuel cell system's energy conversion efficiency, thereby reducing energy waste and increasing energy utilization efficiency. Adjusting the fuel cell system's current temperature based on this target sustaining temperature avoids unnecessary heating or cooling of the fuel cell system, reducing energy consumption. By controlling the fuel cell system's current temperature, it prevents the fuel cell system from being in an overheated or overcooled state for extended periods, reducing the risk of fuel cell system failure and extending its service life.

[0007] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining a target duration for shutdown purging of the fuel cell system corresponding to the current driving condition; and, if it is determined that shutdown purging of the fuel cell system is necessary, purging the interior of the fuel cell system according to the target duration.

[0008] The above-described technical solution addresses the issue that different driving conditions place the fuel cell system in varying states. By determining the target duration for fuel cell system shutdown and purging corresponding to the current driving condition, residual moisture, impurities, and reaction products can be more effectively removed, thus maintaining the fuel cell system's optimal performance. When the fuel cell receives appropriate purging treatment under different operating conditions, its operational reliability is significantly improved, reducing system failures and unexpected shutdowns caused by internal fuel cell problems and ensuring normal vehicle operation.

[0009] In conjunction with the first aspect and the above-described implementations, in some implementations of the first aspect, determining the target sustaining temperature of the fuel cell system corresponding to the current driving condition includes: determining the target sustaining temperature of the fuel cell system corresponding to the current driving condition based on a first preset correspondence; wherein the first preset correspondence is the correspondence between the driving condition of the vehicle and the sustaining temperature of the fuel cell system; the first preset correspondence is generated by: determining the vehicle's total power request range and the actual power output range of the vehicle's power battery system under different driving conditions; and determining the actual power output range of the fuel cell system under the different driving conditions based on the vehicle's total power request range and the actual power output range of the power battery system. The power output range is determined; based on the actual power output range of the fuel cell system under different driving conditions, the target temperature range of the fuel cell system under each driving condition is determined; for each driving condition, the temperature of the fuel cell system is adjusted within the target temperature range so that the vehicle's overall power output meets the vehicle's power request range corresponding to the driving condition; the temperature of the fuel cell system when the vehicle's overall power output meets the vehicle's power request range corresponding to the driving condition is recorded; the first preset correspondence is obtained by combining each driving condition and the temperature of the fuel cell system when the vehicle's overall power output meets the vehicle's power request range corresponding to the driving condition.

[0010] The above technical solution determines the vehicle's total power demand range under different driving conditions, records the temperature of the fuel cell system when the vehicle's total output power meets the demand range under different driving conditions, and establishes a first preset correspondence, enabling precise control of the fuel cell system temperature. A suitable temperature can improve the conversion efficiency of the fuel cell system, increase energy utilization, thereby reducing energy waste and increasing the vehicle's driving range.

[0011] In conjunction with the first aspect and the aforementioned implementation methods, in some implementation methods of the first aspect, determining the target duration for the fuel cell system shutdown purging corresponding to the current driving condition includes: determining the target duration for the fuel cell system shutdown purging corresponding to the current driving condition based on a second preset correspondence; wherein the second preset correspondence is the correspondence between the driving condition of the vehicle and the duration of the fuel cell system shutdown purging; determining the target purging requirement for the fuel cell system shutdown under different driving conditions; and determining the target purging requirement for the fuel cell system based on the target purging requirement under different driving conditions. The target purging time range for each driving condition; for each driving condition, the fuel cell system is purged within the target time range according to different purging times to meet the target purging requirements when the fuel cell system is shut down for that driving condition; the purging time spent by the fuel cell system to meet the target purging requirements for that driving condition is recorded; the second preset correspondence is obtained by combining each driving condition and the purging time spent by the fuel cell system to meet the target purging requirements for that driving condition.

[0012] The above technical solution takes into account that different driving conditions will cause the fuel cell system to be in different states when it is stopped. It records the purging time taken by the fuel cell system to reach the target purging requirement corresponding to the driving condition under different driving conditions, and establishes a second preset correspondence. It can accurately determine the target purging time according to the current driving conditions, protect the fuel cell system to the greatest extent, and avoid over-purging or under-purging of the fuel cell system.

[0013] In combination with the first aspect and the above implementation methods, in some implementation methods of the first aspect, determining the current driving condition of the vehicle based on the current driving data includes: inputting the current driving data into a preset neural network model to obtain an output result; wherein the preset neural network model is used to determine the driving condition of the vehicle based on the vehicle's driving data; and determining the output result as the current driving condition of the vehicle.

[0014] Combining the first aspect and the above implementation methods, in some implementation methods of the first aspect, the preset neural network model is obtained by: acquiring historical driving data and the driving conditions corresponding to the historical driving data; segmenting the historical driving data to obtain multiple kinematic segments; extracting feature parameters from the multiple kinematic segments, and performing principal component analysis on the feature parameters to obtain the main feature parameters; and constructing and training the preset neural network model based on the main feature parameters and the driving conditions corresponding to the main feature parameters.

[0015] Combining the first aspect and the above implementation methods, in some implementation methods of the first aspect, the preset neural network model is constructed and trained based on the main feature parameters and the driving conditions corresponding to the main feature parameters, including: dividing the main feature parameters into a training set and a validation set according to a preset ratio; determining the model parameters corresponding to the preset neural network model, and constructing the preset neural network model based on the model parameters; inputting the training set into the preset neural network model for iterative training until the current mean square error of the preset neural network model is less than a preset error or the number of iterations of the neural network model is greater than a preset number, and determining that the preset neural network model training is complete; wherein, the current mean square error is the mean square error between the driving conditions corresponding to the input content of the preset neural network model and the actual driving conditions output by the preset neural network model; inputting the validation set into the preset neural network model to validate the preset neural network model; and determining that the preset neural network model has passed validation when it is determined that the actual driving conditions output by the preset neural network model are consistent with the driving conditions corresponding to the input content of the preset neural network model.

[0016] The above technical solution involves pre-training a preset neural network model. Since this preset neural network is trained based on a large amount of historical driving data, it can more accurately identify the current driving conditions of the vehicle. During actual vehicle operation, the current driving data is input into the trained preset neural network model in real time, which can quickly determine the current driving conditions of the vehicle, facilitating timely adjustments to the vehicle's control strategy and optimization of energy management.

[0017] In a second aspect, a control device for a fuel cell system is provided, the device comprising: an acquisition module for acquiring current driving data of a vehicle; a first determination module for determining the current driving condition of the vehicle based on the current driving data; a second determination module for determining a target maintenance temperature of the fuel cell system corresponding to the current driving condition; and a control module for controlling the current temperature of the fuel cell system to be maintained at the target maintenance temperature.

[0018] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes a purging module, which is specifically used to: determine the target duration for shutdown purging of the fuel cell system corresponding to the current driving condition; and, when it is determined that shutdown purging of the fuel cell system is required, purge the interior of the fuel cell system according to the target duration.

[0019] In conjunction with the second aspect and the above-described implementations, in some implementations of the second aspect, the second determining module is specifically used to: determine the target sustaining temperature of the fuel cell system corresponding to the current driving condition based on a first preset correspondence; wherein the first preset correspondence is the correspondence between the driving condition of the vehicle and the sustaining temperature of the fuel cell system; the device further includes a first preset correspondence generation module, which is specifically used to: determine the vehicle's total power request range and the actual power output range of the vehicle's power battery system under different driving conditions; and, based on the vehicle's total power request range and the actual power output range of the power battery system, determine the actual power output range of the fuel cell system under the different driving conditions. Power output range; based on the actual power output range of the fuel cell system under different driving conditions, determine the target temperature range of the fuel cell system under each driving condition; for each driving condition, adjust the temperature of the fuel cell system within the target temperature range so that the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition; record the temperature of the fuel cell system when the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition under each driving condition; combine each driving condition and the temperature of the fuel cell system when the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition to obtain the first preset correspondence.

[0020] In conjunction with the second aspect and the above-described implementations, in some implementations of the second aspect, the purging module includes a determining unit, which is specifically used to: determine the target duration of the fuel cell system shutdown purging corresponding to the current driving condition based on a second preset correspondence; wherein, the second preset correspondence is the correspondence between the driving condition of the vehicle and the duration of the fuel cell system shutdown purging; the second preset correspondence generation module is specifically used to: determine the target purging requirement when the fuel cell system shuts down under different driving conditions; and, based on the target purging requirement under different driving conditions, determine the target purging duration of the fuel cell system shutdown purging. The target purging time range for the fuel cell system under each driving condition; for each driving condition, the fuel cell system is purged within the target purging time range according to different purging times to meet the target purging requirements when the fuel cell system is shut down under the corresponding driving condition; the purging time spent by the fuel cell system to meet the target purging requirements under each driving condition is recorded; the second preset correspondence is obtained by combining each driving condition and the purging time spent by the fuel cell system to meet the target purging requirements under each driving condition.

[0021] In conjunction with the second aspect and the above implementation methods, in some implementation methods of the second aspect, the first determining module is specifically used to: input the current driving data into a preset neural network model to obtain an output result; wherein, the preset neural network model is used to determine the driving condition of the vehicle based on the vehicle's driving data; and to determine the output result as the current driving condition of the vehicle.

[0022] In conjunction with the second aspect and the above-described implementation methods, in some implementation methods of the second aspect, the device further includes a preset neural network model generation module, which is specifically used for: acquiring historical driving data and the driving conditions corresponding to the historical driving data; segmenting the historical driving data to obtain multiple kinematic segments; extracting feature parameters from the multiple kinematic segments and performing principal component analysis on the feature parameters to obtain principal feature parameters; and constructing and training the preset neural network model based on the principal feature parameters and the driving conditions corresponding to the principal feature parameters.

[0023] In conjunction with the second aspect and the above implementation methods, in some implementation methods of the second aspect, the preset neural network model generation module includes a model building unit, which is specifically used for: dividing the main feature parameters into a training set and a validation set according to a preset ratio; determining the model parameters corresponding to the preset neural network model, and constructing the preset neural network model based on the model parameters; inputting the training set into the preset neural network model for iterative training until the current mean square error of the preset neural network model is less than a preset error or the number of iterations of the neural network model is greater than a preset number, and determining that the preset neural network model training is complete; wherein, the current mean square error is the mean square error between the driving conditions corresponding to the input content of the preset neural network model and the actual driving conditions output by the preset neural network model; inputting the validation set into the preset neural network model to validate the preset neural network model; and determining that the preset neural network model has passed validation when it is determined that the actual driving conditions output by the preset neural network model are consistent with the driving conditions corresponding to the input content of the preset neural network model.

[0024] Thirdly, a vehicle is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the vehicle to perform the control method of the fuel cell system in the first aspect and any possible implementation of the first aspect.

[0025] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer, causes the computer to perform the control method for the fuel cell system described in the first aspect and any possible implementation thereof.

[0026] Fifthly, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the control method for the fuel cell system described in the first aspect and any possible implementation thereof. Attached Figure Description

[0027] Figure 1 This is a schematic flowchart of a control method for a fuel cell system provided in an embodiment of this application;

[0028] Figure 2 This is a schematic flowchart illustrating a method for generating a preset neural network model provided in an embodiment of this application;

[0029] Figure 3 This is a schematic diagram of the structure of a control device for a fuel cell system provided in an embodiment of this application;

[0030] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0031] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0032] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0033] Currently, new energy vehicles are gradually replacing traditional fuel vehicles and becoming people's first choice for vehicles. Among new energy vehicles, fuel cell vehicles are gradually gaining popularity due to their advantages such as zero emissions, high efficiency, and quiet operation.

[0034] However, in fuel cell vehicles, the liquid water inside the membrane electrode assembly (MEA) undergoes a phase change to form solid ice when the fuel cell system is below 0°C. This leads to problems such as proton exchange membrane (PEM) and catalyst layer separation, mechanical degradation of the PEM, and damage to the catalyst layer and microporous layer, ultimately causing a decline in fuel cell system performance. In existing technologies, one approach for starting the fuel cell system below 0°C is to use coolant heating. However, if the fuel cell system temperature is too low, this method may consume a significant amount of energy. Another approach is to maintain the fuel cell temperature at a certain threshold. While this can reduce energy loss to some extent, it may sometimes fail to meet the vehicle's power requirements.

[0035] Specifically, in the existing technology, when the ambient temperature is too low, the temperature of the coolant inside the fuel cell may continue to drop. When the temperature of the coolant drops to -20°C, if the required temperature of the coolant is 0°C, the coolant needs to be heated for at least 5 minutes, resulting in high energy consumption.

[0036] To reduce energy loss to some extent, the fuel cell system can be controlled to maintain the coolant temperature above a certain set value in low-temperature environments. When the coolant temperature drops below the set value, the fuel cell system immediately heats the coolant. However, since the output power of the fuel cell system is affected by the coolant temperature, if the coolant temperature is always kept below 65°C, the fuel cell system will be unable to output sufficient power, thus failing to meet the vehicle's power requirements in a timely manner.

[0037] Based on this, this application provides a control method for a fuel cell system. The subject executing this method can be a vehicle, specifically a controller within the vehicle.

[0038] Figure 1 This is a schematic flowchart of a control method for a fuel cell system provided in an embodiment of this application.

[0039] For example, such as Figure 1 As shown, the method 100 includes:

[0040] S101, Obtain the vehicle's current driving data.

[0041] S102, based on the current driving data, determine the current driving condition of the vehicle.

[0042] S103, determine the target maintenance temperature of the fuel cell system corresponding to the current driving conditions.

[0043] S104 controls the current temperature of the fuel cell system to be maintained at the target sustaining temperature.

[0044] In this embodiment, by acquiring the vehicle's current driving data, the current driving condition of the vehicle can be determined more accurately based on this data. Furthermore, by determining the target sustaining temperature corresponding to the current driving condition and controlling the current temperature of the fuel cell system to remain at the target sustaining temperature, the fuel cell system can be ensured to operate at the optimal temperature. This guarantees that the output power of the fuel cell system meets the power requirements of the entire vehicle and also improves the energy conversion efficiency of the fuel cell system, thereby reducing energy waste and increasing energy utilization efficiency. Adjusting the current temperature of the fuel cell system based on this target sustaining temperature also avoids unnecessary heating or cooling of the fuel cell system, reducing energy consumption. By controlling the current temperature of the fuel cell system, prolonged overheating or overcooling is avoided, reducing the risk of fuel cell system failure and extending the service life of the fuel cell system.

[0045] The following is about Figure 1 The specific implementation methods of each step in the illustrated embodiment are explained below:

[0046] Regarding S101 above, it is understood that the current driving data can be used to determine the current driving condition of the vehicle.

[0047] For example, the aforementioned current driving data may include the vehicle's average driving speed, maximum driving speed, percentage of constant speed time, percentage of idling time, percentage of acceleration time, percentage of deceleration time, average acceleration, maximum acceleration, average deceleration, minimum deceleration, speed standard deviation, running time, average output power of the drive motor, and average recharge power of the drive motor, etc.

[0048] Regarding S102 above, it is understood that after obtaining the current driving data, the current driving condition of the vehicle can be determined based on the current driving data.

[0049] Currently, for heavy-duty trucks that use fuel cell technology as their main power source (i.e., fuel cell heavy-duty trucks), their operating environment and routes are relatively fixed. Road conditions typically include highways, national roads, and short-distance transport. The load capacity of the vehicle typically includes fully loaded, half-loaded, and empty.

[0050] Based on this, the current driving conditions of the vehicle can be distinguished according to road conditions and load, resulting in 9 driving conditions: highway fully loaded driving condition, highway half-loaded driving condition, highway empty driving condition, national highway fully loaded driving condition, national highway half-loaded driving condition, national highway empty driving condition, short-haul fully loaded driving condition, short-haul half-loaded driving condition, and short-haul empty driving condition.

[0051] Furthermore, it is usually possible to determine which of the above-mentioned driving conditions the vehicle is in based on the vehicle's current driving data.

[0052] For example, a low average acceleration and a low maximum acceleration usually indicate that the vehicle is heavily loaded, that is, the vehicle is fully loaded, because a fully loaded vehicle has poor acceleration performance; a high average deceleration usually indicates that the vehicle is lightly loaded, and the vehicle may be half-loaded or unloaded, because a half-loaded or unloaded vehicle decelerates more when braking.

[0053] A higher average driving speed usually indicates that the vehicle is on a highway; a high idling time usually indicates that the vehicle is on a national highway or short-distance road, because national highways or short-distance road conditions may frequently require stopping or slowing down; a higher average output power of the drive motor usually indicates that the vehicle is on a highway, because high-speed driving requires higher power output; a higher average recharge power of the drive motor usually indicates that the vehicle is on a national highway or short-distance road, because frequent braking in urban traffic will bring more opportunities for recharge.

[0054] In order to more accurately determine the current driving condition of a vehicle based on its current driving data, embodiments of this application may pre-train a preset neural network model for determining the driving condition of a vehicle based on its driving data. The input of this model is the current driving data of the vehicle, and the output is the current driving condition of the vehicle.

[0055] In one possible implementation, determining the current driving condition of the vehicle based on the current driving data includes: inputting the current driving data into a preset neural network model to obtain an output result; wherein the preset neural network model is used to determine the driving condition of the vehicle based on the vehicle's driving data; and determining the output result as the current driving condition of the vehicle.

[0056] It is understandable that the aforementioned preset neural network model is a trained neural network that can predict the vehicle's driving conditions based on the input driving data.

[0057] Neural network models typically contain multiple layers, each with several nodes (neurons) connected by weights.

[0058] For example, the aforementioned preset neural network model can be a back propagation neural network (BPNN). A BP neural network is a multi-layer feedforward neural network, which typically includes an input layer, hidden layers, and an output layer.

[0059] The input layer receives external input data; the hidden layer extracts features from the input data. A BP neural network can contain multiple hidden layers, each containing several neurons (nodes); and the output layer outputs the final prediction result of the BP neural network.

[0060] Furthermore, the aforementioned preset neural network model can be trained based on the vehicle's historical driving data and the corresponding driving conditions.

[0061] One possible implementation is, such as Figure 2 As shown, the generation method of the above-mentioned preset neural network model may include the following steps S21 to S24:

[0062] S21, obtain historical driving data and the driving conditions corresponding to the historical driving data.

[0063] Understandably, this involves collecting historical driving data of the vehicle under different driving conditions, including data such as vehicle speed, acceleration, braking frequency, and steering frequency. The collected historical driving data is then labeled, indicating the driving conditions corresponding to each segment of data.

[0064] S22, the historical driving data is segmented to obtain multiple kinematic segments.

[0065] Understandably, historical driving data can be segmented into multiple kinematic segments to facilitate subsequent processing and analysis.

[0066] For example, continuous historical driving data can be divided into multiple kinematic segments according to a certain length or time interval. For instance, the data can be divided into small segments of 5 seconds or 10 seconds.

[0067] S23. Extract feature parameters from multiple kinematic segments and perform principal component analysis on the feature parameters to obtain the main feature parameters.

[0068] It is understandable that useful feature parameters can be extracted from the segmented kinematic segments, such as average driving speed, maximum driving speed, constant speed time percentage, idling time percentage, acceleration time percentage, deceleration time percentage, average acceleration, maximum acceleration, average deceleration, minimum deceleration, speed standard deviation, running time, average output power of the drive motor, and average recharge power of the drive motor.

[0069] Furthermore, principal component analysis is performed on the extracted feature parameters to obtain the main feature parameters.

[0070] For example, principal component analysis (PCA) can be used to perform principal component analysis on the extracted feature parameters.

[0071] Specifically, the extracted feature parameters are first standardized to ensure they all have the same scale. Then, the covariance matrix of the standardized feature parameters is calculated, and eigenvalue decomposition is performed on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors. The eigenvectors are then sorted according to their eigenvalues, and the first few eigenvectors with the largest eigenvalues ​​are selected as the principal eigenvectors. Finally, the original feature parameters are projected onto the principal eigenvectors to obtain the principal feature parameters.

[0072] S24. Based on the main feature parameters and the driving conditions corresponding to the main feature parameters, a preset neural network model is constructed and trained.

[0073] Understandably, since the original historical driving data and its corresponding driving condition labels are in one-to-one correspondence, segmenting and extracting features from the historical driving data will not change the correspondence between feature parameters and labels; that is, the correspondence between the main feature parameters and their corresponding driving conditions will not change. Based on this, a pre-defined neural network model can be constructed and trained based on the main feature parameters and their corresponding driving conditions.

[0074] In one possible implementation, a preset neural network model is constructed and trained based on the main feature parameters and the corresponding driving conditions, as described above. Figure 2 Specifically, S24 can include the following S31 to S35:

[0075] S31, the main feature parameters are divided into training set and validation set according to a preset ratio.

[0076] Understandably, the above preset ratio can be set according to actual needs. For example, the preset ratio can be set to 8:2, that is, 80% of the data in the main feature parameters is used as the training set, and 20% of the data in the main feature parameters is used as the validation set.

[0077] S32, determine the model parameters corresponding to the preset neural network model, and construct the preset neural network model based on the model parameters.

[0078] It is understandable that the model parameters corresponding to the above-mentioned preset neural network model may include the input sample dimension, the output result dimension, the number of hidden layers and nodes, the learning rate, the initial weights, and the initial bias values.

[0079] Here, the input sample dimension refers to the number of features in each input sample, i.e., the number of the aforementioned main feature parameters. In a neural network, the number of nodes in the input layer matches the input sample dimension. For example, if 10 main feature parameters are extracted, the input sample dimension is 10.

[0080] The output dimension refers to the number of nodes in the output layer of a neural network. The output dimension is usually determined by the dimension of the target value output by the neural network model. For example, if the output of the neural network model is to predict a driving condition, then the output dimension is 1.

[0081] The number of hidden layers can usually be determined based on the number of input samples. For example, if the number of input samples is large, the number of hidden layers can be set to 2, meaning the neural network model contains two hidden layers.

[0082] The number of nodes in a hidden layer refers to the number of neurons in each hidden layer. The number of nodes in a hidden layer typically depends on the complexity of the model and the difficulty of the task. Generally, the number of nodes in a hidden layer can be estimated using rules of thumb, such as the geometric mean of the number of nodes in the input and output layers. Then, cross-validation can be used to determine the optimal number of nodes in the hidden layers.

[0083] For example, if the number of nodes in the input layer is 10 and the number of nodes in the output layer is 3, the calculated geometric mean is approximately 5.477. Taking the geometric mean as an integer, we can determine that the number of nodes in the hidden layer is 5 or 6.

[0084] The learning rate refers to the speed at which the weights are adjusted during model training; it can also be called the maximum stable learning rate. A learning rate that is too large may lead to model instability or even divergence during training, while a learning rate that is too small may result in slow training or an inability to escape local optima. A suitable learning rate is typically set, such as 0.001 or 0.01. Then, observe the changes in the model's loss during training to determine if the learning rate needs adjustment. For example, if the loss value decreases rapidly, the learning rate is appropriate; if the loss value fluctuates significantly or does not decrease, the learning rate is either too high or too low.

[0085] Initial weights refer to the initial weight values ​​of a neural network. These initial weight values ​​are typically set to random numbers between 0 and 1. The weight values ​​define the relationship between the input samples and the output results, and their magnitude affects the accuracy of the neural network model's output.

[0086] The initial bias value is used to adjust the output of the neuron's activation function, helping the neural network better fit the data. The initial bias value can be set to a random number between 0 and 1.

[0087] After determining the above model parameters, a preset neural network model can be constructed based on the determined model parameters.

[0088] S33, input the training set into the preset neural network model for iterative training until the current mean square error of the preset neural network model is less than the preset error or the number of iterations of the neural network model is greater than the preset number, and determine that the preset neural network model training is complete.

[0089] The aforementioned mean square error is the mean square error between the driving conditions corresponding to the input content of the preset neural network model and the actual driving conditions output by the preset neural network model.

[0090] In some embodiments, in order to reduce the impact of differences in different types of data on the number of training iterations of the preset neural network model, the data in the training set can be normalized before being input into the preset neural network model for iterative training.

[0091] Furthermore, the mean squared error mentioned above is a loss function that measures the difference between the model's predicted value and the actual value. If the mean squared error of the preset neural network model is lower than the preset error at a certain moment during the iterative training process, it can be considered that the preset neural network model has reached an acceptable level of accuracy, and the training of the preset neural network model is considered complete.

[0092] A maximum number of iterations can also be set, namely the preset number mentioned above. Even if the mean square error of the preset neural network model does not fall below the preset error during the iterative training process, if the number of iterations of the preset neural network model has exceeded the maximum number of iterations, then the training will stop and the preset neural network model will be determined to be completed.

[0093] It is understandable that during the iterative training of the aforementioned preset neural network model, the weights and biases of the preset neural network model may also change continuously.

[0094] In some embodiments, the difference between the output of the constructed pre-defined neural network model and the driving conditions corresponding to the input content is calculated, typically quantified by a loss function such as mean squared error. Then, the gradient of the loss function with respect to each weight and bias value is calculated using a backpropagation algorithm. Finally, an optimization algorithm (such as gradient descent) is used to update the weight and bias values.

[0095] For example, the change in weight value for each time can be calculated using the following formula (1).

[0096] ΔW m (k)=γΔW m (k-1)-(1-γ)αs m (a m-1 ) T Formula (1)

[0097] Wherein, ΔW m(k) represents the change in weight value W of layer m in the k-th iteration; γ is a coefficient between 0 and 1, used to adjust the influence of the previous weight change on the current weight change; ΔW m (k-1) represents the change in the weight value of the m-th layer during the previous iteration (k-1th iteration); α represents the learning rate mentioned above; s m This refers to the output value of the m-th layer; (a m-1 ) T This refers to the transpose of the output value of the (m-1)th layer.

[0098] The change in the bias value for each time can also be calculated using the following formula (2).

[0099] Δb m (k)=γΔb m (k-1)-(1-γ)αs m Formula (2)

[0100] Where, Δb m (k) represents the change in bias value of the m-th layer in the k-th iteration; γ is a coefficient between 0 and 1, used to adjust the influence of the previous bias change on the current bias change; Δb m (k-1) represents the change in the bias value of the m-th layer during the previous iteration (k-1); α represents the learning rate mentioned above; s m This refers to the output value of the m-th layer.

[0101] Furthermore, based on the current weight values ​​of the preset neural network model and the calculated changes in the weight values, the updated weight values ​​are determined; and based on the current bias values ​​of the preset neural network model and the calculated changes in the bias values, the updated bias values ​​are determined.

[0102] S34. Input the validation set into the preset neural network model to validate the preset neural network model.

[0103] Understandably, after confirming that the preset neural network model has been trained, a validation set can be used to test and validate the trained model. Specifically, the validation success of the preset neural network model can be determined by analyzing whether the output of the preset neural network model matches the driving conditions corresponding to the input content.

[0104] S35, if it is determined that the actual driving conditions output by the preset neural network model are consistent with the driving conditions corresponding to the input content of the preset neural network model, the preset neural network model is verified as successful.

[0105] Understandably, if the preset neural network model passes the verification, it means that the preset neural network model can predict the current driving conditions of the vehicle based on the input vehicle driving data.

[0106] In some embodiments, if the preset neural network model is determined to be validated, the weight values ​​and bias values ​​of the preset neural network model can be obtained, and a Simulink model can be constructed based on the weight values ​​and bias values ​​of the preset neural network model.

[0107] Understandably, in practical applications, it is often necessary to integrate the generated pre-defined neural network model with other physical systems or control modules. However, directly using the pre-defined neural network model may make it difficult to integrate it seamlessly with these complex systems.

[0108] Simulink models can be connected to hardware platforms to enable real-time control and testing of actual hardware systems. Therefore, converting the above-mentioned preset neural network models into Simulink models makes it easier to perform real-time simulation and hardware-in-the-loop testing, ensuring the reliability and performance of the models in actual operation.

[0109] Furthermore, after the Simulink model is built, it can be integrated into the vehicle so that, after obtaining the vehicle's current driving data, the vehicle's current driving condition can be predicted based on the current driving data and the Simulink model.

[0110] The above method involves pre-training a preset neural network model. Since this preset neural network is trained based on a large amount of historical driving data, it can more accurately identify the current driving conditions of the vehicle. During actual vehicle operation, the current driving data is input into the trained preset neural network model in real time, which can quickly determine the current driving conditions of the vehicle, facilitating timely adjustments to the vehicle's control strategy and optimization of energy management.

[0111] Regarding S103 above, it is understood that, as mentioned earlier, in order to reduce energy loss to a certain extent, the temperature of the coolant in the fuel cell system can be controlled to be higher than a certain set temperature value in low-temperature environments. Since the temperature of the fuel cell system may affect its output power, and the vehicle's overall power demand varies under different driving conditions, the target maintenance temperature of the fuel cell system also differs under different driving conditions. Based on this, the target maintenance temperature of the fuel cell system corresponding to the current driving condition can be determined.

[0112] In one possible implementation, determining the target maintenance temperature of the fuel cell system corresponding to the current driving condition includes: determining the target maintenance temperature of the fuel cell system corresponding to the current driving condition based on a first preset correspondence; wherein the first preset correspondence is the correspondence between the driving condition of the vehicle and the maintenance temperature of the fuel cell system.

[0113] It is understood that the aforementioned first preset correspondence refers to a pre-set mapping relationship, which is used to determine the target maintenance temperature that the fuel cell system should maintain under different driving conditions. This first preset correspondence can be stored in the vehicle.

[0114] The aforementioned first pre-defined correspondence is usually generated by summarizing a large amount of experimental data and simulation results.

[0115] In one possible implementation, the method for generating the aforementioned first preset correspondence may specifically include the following steps S41 to S46:

[0116] S41, determine the vehicle's total power request range and the actual power output range of the vehicle's power battery system under different driving conditions.

[0117] It is understandable that the range of vehicle power requests under the different driving conditions mentioned above can be obtained by simulating the vehicle based on different road types and different load conditions.

[0118] The aforementioned different road types can include highways, national roads, and urban roads. These road types represent different driving environments and conditions, and have different requirements for vehicle output power.

[0119] The different load conditions mentioned above typically include: no load, half load, and full load.

[0120] The aforementioned vehicle power request range refers to the power range that the vehicle needs to provide under different driving conditions. However, the required vehicle output power varies depending on the driving conditions, meaning the vehicle's total power request range differs.

[0121] The total output power required by the vehicle can be provided by both the power battery system and the fuel cell system.

[0122] Specifically, one can first acquire road spectrum data obtained when the vehicle is actually driven on different road types, then classify the acquired road spectrum data according to road type, and then input the road spectrum data under different road types into simulation software, define different load conditions, and perform simulation.

[0123] Simulations can yield different driving conditions, including: high-speed fully loaded driving condition, high-speed half-load driving condition, high-speed unloaded driving condition, national highway fully loaded driving condition, national highway half-loaded driving condition, national highway unloaded driving condition, short-distance fully loaded driving condition, short-distance half-loaded driving condition, and short-distance unloaded driving condition.

[0124] Furthermore, simulation software or simulation programs can be used to establish a mathematical model of the vehicle's powertrain system. After obtaining different driving conditions through the above simulations, the data of these different driving conditions are input into the established model. The simulation model calculates the output power required by the vehicle under each driving condition and outputs the range of the total vehicle output power required under each of the above driving conditions.

[0125] Similarly, the actual power output range of the vehicle's power battery system under the above-mentioned different driving conditions can be obtained through simulation based on different road types, different load conditions, and the rated power and peak power of the power battery system.

[0126] The actual power output range of the aforementioned power battery system refers to the range of power that the power battery system can provide under different driving conditions.

[0127] The rated power of the aforementioned power battery system refers to the power that the power battery system can continuously output under specified operating conditions. Under normal circumstances, when the vehicle is driving at a constant speed or cruising at a constant speed, the power output of the power battery system is close to the rated power.

[0128] The peak power of the aforementioned power battery refers to the maximum power that the power battery system can output within a short period of time, which is usually higher than the rated power. Under normal circumstances, when a vehicle needs to accelerate rapidly, the power battery system will output peak power for a short period of time to provide sufficient power.

[0129] Since the rated power and peak power of the power battery system may be affected by factors such as ambient temperature, remaining battery charge, and battery state, the output power of the power battery system may also vary due to these factors. Therefore, simulation can be used to determine the actual power output range of the vehicle's power battery system under each driving condition.

[0130] Specifically, different driving condition data, the rated power and peak power of the power battery system can be input into the simulation model, and the simulation model can calculate the actual power output range of the vehicle's power battery system under each driving condition.

[0131] For example, load simulation is performed on a vehicle traveling at high speed, simulating a fully loaded high-speed driving condition. The simulation model calculates the required output power of the vehicle under this condition, determining that the total vehicle power demand range is 50kW to 80kW. If the rated power of the power battery is 30kW and the peak power is 40kW, the simulation model can calculate that the actual power output range of the power battery system under full load high-speed driving conditions is 25kW to 40kW.

[0132] S42 determines the actual power output range of the fuel cell system under different driving conditions based on the vehicle's power request range and the actual power output range of the power battery system.

[0133] It is understandable that when the actual power output range of the power battery system cannot meet the power demand range of the vehicle, the fuel cell system can work together with the power battery system to output power so that the vehicle output power meets the vehicle power demand range.

[0134] For example, if the vehicle's total power demand range under high-speed, fully loaded driving conditions is 50KW to 80KW, and the actual power output range of the power battery system under high-speed, fully loaded driving conditions is 25KW to 40KW, and it is determined that the actual power output range of the power battery system cannot meet the vehicle's total power demand range, the actual power output range of the fuel cell system can be calculated to be 25KW to 40KW based on the total vehicle power demand range and the actual power output range of the power battery system.

[0135] S43, based on the actual power output range of the fuel cell system under different driving conditions, determines the target temperature range of the fuel cell system under each driving condition.

[0136] It is understandable that, for fuel cell systems, as the temperature increases, the rate of the chemical reaction between fuel and oxygen inside the system also accelerates, thereby increasing the output power of the fuel cell system. Based on this, the target temperature range of the fuel cell system can be determined based on its actual power output range.

[0137] For example, through experiments and theoretical analysis, a model relating temperature and power output of a fuel cell system can be established. Based on this model, the target temperature range corresponding to the actual power output range of the fuel cell system under different driving conditions can be determined.

[0138] For example, by inputting the actual power output range of the fuel cell system, from 25KW to 40KW, into the model, the target temperature range of the fuel cell system can be obtained as 55℃ to 70℃.

[0139] S44, for each driving condition, adjust the temperature of the fuel cell system within the target temperature range so that the vehicle's overall output power meets the vehicle power request range corresponding to that driving condition.

[0140] It is understandable that, for each driving condition, continuously adjusting the temperature of the fuel cell system within the aforementioned target temperature range can change the output power of the fuel cell system, thereby changing the overall vehicle output power and ensuring that the overall vehicle output power meets the power request range corresponding to that driving condition.

[0141] For example, when the vehicle is driving at high speed and under full load, the temperature of the fuel cell system is adjusted within the range of 55°C to 70°C so that the vehicle's total output power meets the range of 50KW to 80KW.

[0142] S45 records the temperature of the fuel cell system when the vehicle's total output power meets the required range for that driving condition under each driving condition.

[0143] Understandably, for each driving condition, by continuously adjusting the temperature of the fuel cell system within the target temperature range, the optimal temperature of the fuel cell system can be obtained when the vehicle's output power meets the vehicle's power demand range.

[0144] By recording the temperature of the fuel cell system when the vehicle's total output power meets the required range for that driving condition under each driving condition, a series of temperature values ​​can be obtained. These temperature values ​​ensure that the fuel cell system's total output power meets the requirements under different driving conditions, meaning that the vehicle's total output power meets the required range for that driving condition.

[0145] For example, if the vehicle's total output power is recorded to be between 50KW and 80KW when the vehicle is in a high-speed, fully loaded driving condition, and the temperature of the fuel cell system is 65℃, then the target maintenance temperature of the fuel cell system corresponding to the high-speed, fully loaded driving condition is determined to be 65℃.

[0146] S46, combine the temperature of the fuel cell system when the vehicle's total output power meets the total power request range corresponding to each driving condition, to obtain a first preset correspondence.

[0147] It is understandable that the temperature of the fuel cell system is combined with the vehicle's total output power under each driving condition, as recorded in S45 above, when the total vehicle power demand for that driving condition meets the corresponding range. For example, the high-speed full-load driving condition mentioned above can be combined with 65°C.

[0148] For example, the aforementioned first preset correspondence can be a correspondence table. Through this correspondence table, the target sustaining temperature of the fuel cell system corresponding to the driving conditions (including road type and load) can be queried. This correspondence table can be shown in Table 1 below:

[0149] Table 1

[0150]

[0151] As shown in Table 1, under the same road type, the target sustaining temperature of the fuel cell system increases with the increase of load; under the same load, the target sustaining temperature under reverse short road conditions is lower than that under national road conditions, and the target sustaining temperature under national road conditions is lower than that under highway conditions.

[0152] As can be understood, as mentioned above, the vehicle's overall output power can be provided jointly by the power battery system and the fuel cell system. The vehicle in this application primarily uses the power battery system to drive the electric motor, while the fuel cell system is mainly used to charge the power battery system. Only when the output power of the power battery system cannot meet the vehicle's needs will the power battery system and the fuel cell system jointly drive the electric motor.

[0153] For example, when the vehicle is in a short-term unloaded driving condition, the rated output power of the vehicle's power battery system can fully meet the vehicle's power requirements for this condition. There is no need for the fuel cell system to output power to the electric motor; however, it may be necessary to charge the power battery when its remaining charge is insufficient. Therefore, when the vehicle is in a short-term unloaded driving condition, the temperature that the fuel cell system needs to maintain can be set relatively low, for example, to 15°C.

[0154] When a vehicle is traveling half-load on a national highway, the rated output power of the vehicle's power battery system can usually meet the vehicle's power requirements for most of these conditions (i.e., meeting more than 80% of the maximum value within the range of vehicle power requirements for half-load driving on national highways). Furthermore, the peak power of the power battery system can usually fully meet the vehicle's power requirements for half-load driving on national highways (i.e., meeting the maximum value within the range of vehicle power requirements for half-load driving on national highways). There is no need for the fuel cell system to continuously output significant power to the electric motor. Power output from the fuel cell system to the electric motor is only required when the remaining charge of the power battery is insufficient or when the vehicle has prolonged high power demands. Therefore, when the vehicle is traveling half-load on a national highway, the temperature that the fuel cell system needs to maintain can be set slightly higher, for example, to 45°C.

[0155] When a vehicle is traveling at high speed and under full load, the rated output power of the vehicle's battery system is insufficient to meet the overall vehicle power requirements for most high-speed, full-load driving conditions (i.e., it cannot meet 80% of the maximum value of the overall vehicle power requirements for high-speed, full-load driving conditions). Therefore, the fuel cell system needs to output a larger amount of power to the electric motor. Thus, when the vehicle is traveling at high speed and under full load, the temperature that the fuel cell system needs to maintain can be set higher, for example, to 65°C.

[0156] Furthermore, after generating the first preset correspondence, the first preset correspondence can be stored in the vehicle so as to determine the target maintenance temperature of the fuel cell system corresponding to the current driving conditions based on the first preset correspondence.

[0157] For example, if the current driving condition is determined to be a high-speed, fully loaded driving condition, the target maintenance temperature of the fuel cell system corresponding to the high-speed, fully loaded driving condition can be determined to be 65°C by querying the first preset correspondence (i.e., Table 1 above).

[0158] The above method, by accurately identifying the current driving conditions and determining the corresponding target sustainment temperature, enables the fuel cell system to operate optimally under various conditions. For example, under high-speed driving conditions, the fuel cell system may require higher power output. Adjusting the target sustainment temperature to a more suitable higher value can improve the fuel cell system's response rate and output performance, meeting the vehicle's power demands. Furthermore, it ensures the fuel cell system always operates within a highly efficient temperature range, thereby reducing energy waste, improving energy utilization efficiency, and extending the vehicle's driving range. It also prevents the fuel cell from operating at extreme temperatures, reducing damage from extreme temperatures and extending the fuel cell system's lifespan. Determining the target sustainment temperature based on driving conditions also better balances heat generation and dissipation, keeping the fuel cell system's temperature within a relatively stable range and reducing the impact of temperature fluctuations on the fuel cell system's lifespan.

[0159] Regarding the above S104, it can be understood that the current temperature of the fuel cell system is first monitored in real time by a temperature sensor, and then the current temperature is transmitted to the fuel cell system controller. When the fuel cell system controller determines that the current temperature is not equal to the target maintenance temperature, it adjusts the temperature of the fuel cell system through a heating or cooling device according to the difference between the current temperature and the target maintenance temperature, so as to keep the current temperature of the fuel cell system at the target maintenance temperature.

[0160] In some embodiments, when the current temperature of the fuel cell system is lower than the target sustaining temperature, the heat input can be increased to raise the temperature of the fuel cell system; when the current temperature of the fuel cell system is higher than the target sustaining temperature, the heat input can be reduced or the heat dissipation can be increased to lower the temperature of the fuel cell system.

[0161] For example, the temperature of a fuel cell system can be increased by the heat generated by the resistive element, or the fuel cell system can be heated by an additional heating device.

[0162] Coolant can be used to remove heat from the fuel cell system through a heat exchanger, and a fan can be used to accelerate airflow and remove heat from the area around the fuel cell system.

[0163] Furthermore, when a fuel cell system is shut down for an extended period in a low-temperature environment, residual moisture within the system may freeze, affecting its lifespan. Therefore, it is necessary to shut down the system and purge any residual moisture.

[0164] The amount of heat and moisture generated by the fuel cell system varies under different driving conditions. Therefore, embodiments of this application can also determine the duration of fuel cell system shutdown and purging based on the current driving conditions of the vehicle.

[0165] In one possible implementation, the method further includes: determining a target duration for the fuel cell system shutdown and purging corresponding to the current driving condition; and, if it is determined that the fuel cell system needs to be shut down and purged, purging the inside of the fuel cell system according to the target duration.

[0166] Understandably, as mentioned earlier, the heat and moisture generated by the fuel cell system vary under different driving conditions. To avoid over-purging or ineffective purging, a target purging duration for the fuel cell system corresponding to the vehicle's current driving conditions can be predetermined.

[0167] In one possible implementation, determining the target duration for the fuel cell system shutdown and purging corresponding to the current driving condition includes: determining the target duration for the fuel cell system shutdown and purging corresponding to the current driving condition based on a second preset correspondence; wherein the second preset correspondence is the correspondence between the driving condition of the vehicle and the duration of the fuel cell system shutdown and purging.

[0168] It is understood that the aforementioned second preset correspondence refers to a pre-set mapping relationship, which is used to determine the optimal purging time when the fuel cell system is shut down for purging under different driving conditions. This second preset correspondence can also be stored in the vehicle.

[0169] The aforementioned second pre-defined correspondence is usually generated by summarizing a large amount of experimental data and simulation results.

[0170] In one possible implementation, the generation method of the aforementioned second preset correspondence may specifically include the following steps S51 to S55:

[0171] S51, determine the target purging requirements when the fuel cell system is shut down under different driving conditions.

[0172] It is understandable that the target purging requirements when the fuel cell system shuts down under the above-mentioned different driving conditions can also be obtained by simulating the vehicle based on different road types and different load conditions.

[0173] The aforementioned different road types can include highways, national roads, and urban roads. These road types represent different driving environments and conditions, and have different requirements for vehicle output power.

[0174] The different load conditions mentioned above typically include: no load, half load, and full load.

[0175] The target purging requirement for the aforementioned fuel cell system shutdown refers to the expected state of the fuel cell system after shutdown purging.

[0176] Specifically, one can first acquire road spectrum data obtained when the vehicle is actually driven on different road types, then classify the acquired road spectrum data according to road type, and then input the road spectrum data under different road types into simulation software, define different load conditions, and perform simulation.

[0177] Simulations can yield different driving conditions, including: high-speed fully loaded driving condition, high-speed half-load driving condition, high-speed unloaded driving condition, national highway fully loaded driving condition, national highway half-loaded driving condition, national highway unloaded driving condition, short-distance fully loaded driving condition, short-distance half-loaded driving condition, and short-distance unloaded driving condition.

[0178] Furthermore, after obtaining different driving conditions through the above simulations, the target purging requirements for each driving condition can be determined. For example, the target purging requirement for the high-speed, fully loaded driving condition is determined to be to keep the fuel cell system in a dry state (humidity value of 0%).

[0179] S52, based on the target purging requirements under different driving conditions, determines the target duration range for purging the fuel cell system under each driving condition.

[0180] Understandably, the operating state and residual substances produced by the fuel cell may differ under different driving conditions, thus affecting purging requirements and the required purging time. Based on this, the target purging time range for the fuel cell system under each driving condition can be determined according to the target purging requirements.

[0181] For example, a purging experiment is conducted on a fuel cell system, and the purging effect of the fuel cell system, such as residual moisture content and impurity gas concentration, is measured under different purging durations. Based on the experimental data, a relationship model between purging duration and target purging requirements is established. By inputting the target purging requirements under different driving conditions into the established relationship model, the target purging duration range for each driving condition can be obtained.

[0182] For example, by inputting the target purging requirement (to keep the fuel cell system in a dry state) corresponding to the high-speed full-load driving condition into the relationship model between purging time and target purging requirement, the target purging time range under the high-speed full-load driving condition can be obtained as 2.5 min to 3.5 min.

[0183] S53, for each driving condition, the fuel cell system is purged with different purging durations within the target time range to meet the target purging requirements when the fuel cell system is shut down for that driving condition.

[0184] Understandably, for each driving condition, the fuel cell system is purged by gradually increasing the purging time within the target duration, and the status of the fuel cell system after purging is monitored in real time until the target purging requirement is met.

[0185] For example, when the vehicle is driving at high speed and fully loaded, the fuel cell is purged by gradually increasing the purging time within a range of 2.5 minutes to 3.5 minutes until the fuel cell system reaches a dry state.

[0186] S54 records the purging time required for the fuel cell system to reach the target purging requirement corresponding to each driving condition.

[0187] It is understandable that the purging time required for the fuel cell system to reach the target purging requirement for each driving condition can be used to obtain multiple purging times.

[0188] For example, if the purging time is gradually increased within the range of 2.5 min to 3.5 min, and the time taken for the fuel cell system to reach a dry state is 3 min, and the purging time taken for the fuel cell system to reach a dry state under high-speed full-load driving conditions is recorded as 3 min, then the target purging time for the fuel cell system to stop and purge under high-speed full-load conditions can be determined to be 3 min.

[0189] S55, combine each driving condition and the purging time required for the fuel cell system to reach the target purging requirement corresponding to that driving condition to obtain a second preset correspondence.

[0190] It is understandable that each driving condition is combined with the purging time recorded in S53 above, which is the time required for the fuel cell system to reach the target purging requirement corresponding to that driving condition. For example, the high-speed full-load driving condition mentioned above can be combined with 3 minutes.

[0191] For example, the aforementioned second preset correspondence can be a correspondence table. Through this table, the target duration for fuel cell system shutdown and purging corresponding to driving conditions (including road type and load) can be queried. This correspondence table can be shown in Table 2 below:

[0192] Table 2

[0193]

[0194] As shown in Table 2, under the same road type, the target duration of fuel cell system shutdown purging gradually increases with the increase of load; under the same load, the target duration of fuel cell system shutdown purging under reverse short road conditions is higher than that under national road conditions, and the target duration of fuel cell system shutdown purging under national road conditions is higher than that under expressway conditions.

[0195] Understandably, on highways, vehicles typically travel at relatively high, constant speeds, traffic flow is relatively low, and travel is relatively smooth. Under these conditions, the fuel cell system operates in a relatively stable state, producing relatively little moisture and hydrogen, thus allowing for a shorter target downtime for purging.

[0196] National highways typically refer to major roads connecting cities, with high traffic volume and slower speeds compared to expressways, often involving frequent acceleration and deceleration. Under these conditions, the operating state of the fuel cell system varies considerably, resulting in relatively higher levels of moisture and hydrogen production. Therefore, the target duration for shutdown purging needs to be appropriately increased.

[0197] Short-circuit conditions typically refer to urban roads where traffic congestion is more severe, vehicles frequently start and stop, and travel at low and unstable speeds. Under these conditions, the fuel cell system operates very unstablely, producing the most moisture and hydrogen, thus requiring the longest possible shutdown and purging time.

[0198] Fuel cells generate moisture during operation. Increased load means the fuel cell system needs to operate for longer periods or at higher power, resulting in even more moisture production and requiring longer purging times to ensure the fuel cell system remains dry. Therefore, under the same road conditions, the target downtime for purging gradually increases with increasing load.

[0199] Furthermore, after generating the aforementioned second preset correspondence, the aforementioned second preset correspondence can be stored in the vehicle so as to determine the target duration for the fuel cell system shutdown and purging corresponding to the current driving conditions based on the second preset correspondence.

[0200] For example, if the current driving condition is determined to be a high-speed, fully loaded driving condition, by querying the second preset correspondence (i.e., Table 2 above), the target duration for the fuel cell system shutdown and purging corresponding to the high-speed, fully loaded driving condition can be determined to be 3 minutes.

[0201] Furthermore, after determining the target duration for the fuel cell system shutdown and purging corresponding to the current driving conditions, the fuel cell system can be shut down and purged according to the target duration when shutdown and purging are required.

[0202] In some embodiments, it can be determined whether the fuel cell system needs to be shut down and purged based on its current state.

[0203] For example, when the fuel cell system has accumulated a preset running time, it is usually necessary to shut down and purge it.

[0204] The above method, by identifying the current driving conditions and determining the corresponding target purging duration, can more effectively remove impurities and moisture accumulated inside the fuel cell system under specific operating conditions, thereby maintaining the good performance of the fuel cell system. It can also effectively reduce damage to the fuel cell system caused by improper or insufficient purging. When the fuel cell receives proper purging treatment under different operating conditions, its operational reliability will be greatly improved, reducing system failures and unexpected shutdowns caused by internal fuel cell problems, and ensuring normal vehicle operation.

[0205] Figure 3 This is a schematic diagram of the structure of a control device for a fuel cell system provided in an embodiment of this application.

[0206] For example, such as Figure 3 As shown, the device 300 includes:

[0207] The acquisition module 301 is used to acquire the current driving data of the vehicle.

[0208] The first determining module 302 is used to determine the current driving condition of the vehicle based on the current driving data.

[0209] The second determining module 303 is used to determine the target maintenance temperature of the fuel cell system corresponding to the current driving condition.

[0210] The control module 303 is used to control the current temperature of the fuel cell system to maintain the target sustaining temperature.

[0211] Optionally, the device further includes a purging module, which is specifically used to: determine the target duration for shutdown purging of the fuel cell system corresponding to the current driving condition; and, if it is determined that the fuel cell system needs to be shut down for purging, purge the inside of the fuel cell system according to the target duration.

[0212] In one possible implementation, the second determining module is specifically used to: determine the target sustaining temperature of the fuel cell system corresponding to the current driving condition based on a first preset correspondence; wherein the first preset correspondence is the correspondence between the driving condition of the vehicle and the sustaining temperature of the fuel cell system; the device further includes a first preset correspondence generation module, which is specifically used to: determine the vehicle's total power request range and the actual power output range of the vehicle's power battery system under different driving conditions; and, based on the vehicle's total power request range and the actual power output range of the power battery system, determine the actual power output range of the fuel cell system under the different driving conditions; based on The actual power output range of the fuel cell system under different driving conditions is determined, and the target temperature range of the fuel cell system under each driving condition is determined. For each driving condition, the temperature of the fuel cell system is adjusted within the target temperature range so that the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition. The temperature of the fuel cell system when the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition is recorded. The first preset correspondence is obtained by combining each driving condition and the temperature of the fuel cell system when the vehicle's overall output power meets the vehicle's power request range corresponding to the driving condition.

[0213] In one possible implementation, the purging module includes a determining unit, which is specifically used to: determine the target duration of the fuel cell system shutdown purging corresponding to the current driving condition based on a second preset correspondence; wherein the second preset correspondence is the correspondence between the driving condition of the vehicle and the duration of the fuel cell system shutdown purging; the second preset correspondence generation module is specifically used to: determine the target purging requirement of the fuel cell system shutdown under different driving conditions; and based on the target purging requirement under different driving conditions, determine the duration of the fuel cell system shutdown purging under each driving condition. The target purging time range under each driving condition; for each driving condition, the fuel cell system is purged within the target time range according to different purging times to meet the target purging requirements when the fuel cell system is shut down under the corresponding driving condition; the purging time spent by the fuel cell system to meet the target purging requirements under each driving condition is recorded; the second preset correspondence is obtained by combining each driving condition and the purging time spent by the fuel cell system to meet the target purging requirements under each driving condition.

[0214] In one possible implementation, the first determining module is specifically used to: input the current driving data into a preset neural network model to obtain an output result; wherein the preset neural network model is used to determine the driving condition of the vehicle based on the vehicle's driving data; and to determine the output result as the current driving condition of the vehicle.

[0215] Optionally, the device further includes a preset neural network model generation module, which is specifically used for: acquiring historical driving data and the driving conditions corresponding to the historical driving data; segmenting the historical driving data to obtain multiple kinematic segments; extracting feature parameters from the multiple kinematic segments and performing principal component analysis on the feature parameters to obtain principal feature parameters; and constructing and training the preset neural network model based on the principal feature parameters and the driving conditions corresponding to the principal feature parameters.

[0216] In one possible implementation, the preset neural network model generation module includes a model building unit, which is specifically used for: dividing the main feature parameters into a training set and a validation set according to a preset ratio; determining the model parameters corresponding to the preset neural network model, and building the preset neural network model based on the model parameters; inputting the training set into the preset neural network model for iterative training until the current mean square error of the preset neural network model is less than a preset error or the number of iterations of the neural network model is greater than a preset number, and determining that the preset neural network model training is complete; wherein, the current mean square error is the mean square error between the driving conditions corresponding to the input content of the preset neural network model and the actual driving conditions output by the preset neural network model; inputting the validation set into the preset neural network model to validate the preset neural network model; and determining that the preset neural network model has passed validation when it is determined that the actual driving conditions output by the preset neural network model are consistent with the driving conditions corresponding to the input content of the preset neural network model.

[0217] Figure 4 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0218] For example, such as Figure 4 As shown, the vehicle 400 includes a memory 401 and a processor 402. The memory 401 stores executable program code 4011, and the processor 402 is used to call and execute the executable program code 4011 to perform a control method for a fuel cell system.

[0219] Furthermore, embodiments of this application also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform a control method for a fuel cell system provided in embodiments of this application.

[0220] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0221] When each functional module is divided according to its corresponding function, the device may further include an acquisition module, a first determination module, a second determination module, and a control module. It should be noted that all relevant content regarding the steps involved in the above method embodiments can be referenced to the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0222] It should be understood that the device provided in this embodiment is used to execute the control method of the fuel cell system described above, and therefore can achieve the same effect as the above implementation method.

[0223] When using an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module can be used to control and manage the vehicle's movements. The storage module can be used to support the vehicle in executing relevant program code and data.

[0224] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits shown in conjunction with the disclosure of this application. The processor may also be a combination of functions that implement computing capabilities, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0225] In addition, the device provided in the embodiments of this application may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a control method for a fuel cell system provided in the above embodiments.

[0226] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement the control method for a fuel cell system provided in the above embodiment.

[0227] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement a control method for a fuel cell system provided in the above embodiment.

[0228] In this embodiment, the device, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0229] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0230] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0231] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A control method for a fuel cell system, characterized in that, The method includes: Obtain the vehicle's current driving data; Based on the current driving data, the current driving condition of the vehicle is determined; Determine the target maintenance temperature of the fuel cell system corresponding to the current driving conditions; The current temperature of the fuel cell system is controlled to remain at the target maintenance temperature.

2. The method according to claim 1, characterized in that, The method further includes: Determine the target duration for the fuel cell system shutdown and purging corresponding to the current driving condition; If it is determined that the fuel cell system needs to be shut down and purged, the internal components of the fuel cell system shall be purged for the target duration.

3. The method according to claim 1, characterized in that, Determining the target maintenance temperature of the fuel cell system corresponding to the current driving condition includes: Based on a first preset correspondence, the target maintenance temperature of the fuel cell system corresponding to the current driving condition is determined; wherein, the first preset correspondence is the correspondence between the driving condition of the vehicle and the maintenance temperature of the fuel cell system; The first preset correspondence is generated as follows: The vehicle's total power request range and the actual power output range of the vehicle's power battery system under different driving conditions are determined; based on the total power request range and the actual power output range of the power battery system, the actual power output range of the fuel cell system under different driving conditions is determined; based on the actual power output range of the fuel cell system under different driving conditions, the target temperature range of the fuel cell system under each driving condition is determined; for each driving condition, the temperature of the fuel cell system is adjusted within the target temperature range so that the vehicle's total power output meets the total power request range corresponding to the driving condition; the temperature of the fuel cell system is recorded when the vehicle's total power output meets the total power request range corresponding to the driving condition under each driving condition; the first preset correspondence is obtained by combining the temperature of the fuel cell system under each driving condition and the temperature of the fuel cell system when the vehicle's total power output meets the total power request range corresponding to the driving condition.

4. The method according to claim 2, characterized in that, The determination of the target duration for the fuel cell system shutdown and purging corresponding to the current driving condition includes: Based on the second preset correspondence, the target duration of the fuel cell system shutdown and purging corresponding to the current driving condition is determined; wherein, the second preset correspondence is the correspondence between the driving condition of the vehicle and the duration of the fuel cell system shutdown and purging; The second preset correspondence is generated as follows: The target purging requirement for the fuel cell system during shutdown is determined under different driving conditions; based on the target purging requirement under different driving conditions, the target duration range for purging the fuel cell system under each driving condition is determined; for each driving condition, the fuel cell system is purged within the target duration range according to different purging durations to achieve the target purging requirement for the fuel cell system during shutdown corresponding to that driving condition; the purging duration taken by the fuel cell system to achieve the target purging requirement under each driving condition is recorded; and the second preset correspondence is obtained by combining each driving condition and the purging duration taken by the fuel cell system to achieve the target purging requirement under each driving condition.

5. The method according to claim 1 or 2, characterized in that, Determining the current driving condition of the vehicle based on the current driving data includes: The current driving data is input into a preset neural network model to obtain the output result; wherein, the preset neural network model is used to determine the driving condition of the vehicle based on the vehicle's driving data; The output result is determined as the current driving condition of the vehicle.

6. The method according to claim 5, characterized in that, The preset neural network model is obtained through the following method: Acquire historical driving data and the driving conditions corresponding to the historical driving data; The historical driving data is segmented to obtain multiple kinematic segments; Feature parameters are extracted from the multiple kinematic segments, and principal component analysis is performed on the feature parameters to obtain the main feature parameters; Based on the main feature parameters and the driving conditions corresponding to the main feature parameters, the preset neural network model is constructed and trained.

7. The method according to claim 6, characterized in that, The process of constructing and training the preset neural network model based on the main feature parameters and the corresponding driving conditions includes: The main feature parameters are divided into a training set and a validation set according to a preset ratio; Determine the model parameters corresponding to the preset neural network model, and construct the preset neural network model based on the model parameters; The training set is input into the preset neural network model for iterative training until the current mean square error of the preset neural network model is less than the preset error or the number of iterations of the neural network model is greater than the preset number, at which point the training of the preset neural network model is determined to be complete; wherein, the current mean square error is the mean square error between the driving condition corresponding to the input content of the preset neural network model and the actual driving condition output by the preset neural network model. The validation set is input into the preset neural network model to validate the preset neural network model; If the actual driving conditions output by the preset neural network model are consistent with the driving conditions corresponding to the input content of the preset neural network model, then the preset neural network model is deemed to have passed verification.

8. A control device for a fuel cell system, characterized in that, The device includes: The acquisition module is used to acquire the vehicle's current driving data; The first determining module is used to determine the current driving condition of the vehicle based on the current driving data; The second determining module is used to determine the target maintenance temperature of the fuel cell system corresponding to the current driving condition; A control module is used to control the current temperature of the fuel cell system to maintain it at the target sustaining temperature.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the method as described in any one of claims 1 to 7.

Images