Temperature control method, device and equipment for fuel cell stack, medium and product

Abstract

The invention discloses a temperature control method, device and equipment for a fuel cell stack, a medium and a product, and relates to the field of temperature control, and the method comprises the steps: obtaining the actual measurement temperature of the fuel cell stack in real time; when the actually-measured temperature is smaller than or equal to the temperature safety threshold value, the current load working condition sequence and the trained prediction model are used for obtaining the predicted refrigerating capacity requirement; the target opening degree of the liquid cooling valve is determined according to the predicted refrigerating capacity demand; when the actually measured temperature is larger than a temperature safety threshold value, an alarm signal is sent out, and an actual opening feedback signal of the liquid cooling valve and a flow feedback signal of a coolant are obtained; determining the target opening degree of the liquid cooling valve based on the actual opening degree feedback signal, the opening degree threshold value, the flow feedback signal of the coolant and the flow safety range; and the liquid cooling valve is controlled based on the target opening degree, and temperature control over the fuel cell stack is achieved. According to the invention, the refrigeration range of the flat plate type heat pipe is expanded so as to adapt to the dynamic heat dissipation requirements of the fuel cell under different load working conditions.

Description

Technical Field

[0001] This application relates to the field of temperature control, and in particular to a method, apparatus, equipment, medium, and product for temperature control of a fuel cell stack. Background Technology

[0002] Fuel cells generate a significant amount of heat during operation. If this heat cannot be dissipated promptly and effectively, it can lead to performance degradation, shortened lifespan, and even safety risks. Flat-plate heat pipes, a typical passive cooling method, utilize the internal working fluid to absorb heat and vaporize at the evaporation end, carrying the heat to the condensation end. After condensation and liquefaction, the fluid flows back to the evaporation end through the capillary structure within the pipe wall, achieving phase change heat transfer and circulation, thus dissipating heat. This method requires no moving mechanical parts, offering advantages such as high heat transfer efficiency, simple structure, and low operating energy consumption, and also helps achieve uniform heat distribution within the fuel cell. However, because the amount of working fluid inside a flat-plate heat pipe is fixed, the evaporation temperature is relatively constant when using it for cooling, limiting the achievable cooling range and making it difficult to adapt to the dynamic heat dissipation requirements of fuel cells under different load conditions. Summary of the Invention

[0003] The purpose of this application is to provide a temperature control method, device, equipment, medium, and product for fuel cell stacks, which expands the cooling range of flat plate heat pipes to adapt to the dynamic heat dissipation requirements of fuel cells under different load conditions.

[0004] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a temperature control method for a fuel cell stack, comprising: Real-time acquisition of the measured temperature of the fuel cell stack; When the measured temperature is less than or equal to the temperature safety threshold, the current load condition sequence of the fuel cell stack is obtained; The current load condition sequence is input into the trained prediction model to predict the cooling demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences; The target opening degree of the liquid-cooled valve is determined based on the predicted cooling capacity requirement; When the measured temperature exceeds the temperature safety threshold, an alarm signal is issued and the actual opening degree feedback signal of the liquid cooling valve and the flow rate feedback signal of the coolant are obtained. The target opening degree of the liquid-cooled valve is determined based on the actual opening degree feedback signal, the opening degree threshold, the flow rate feedback signal of the coolant, and the flow rate safety range. The liquid-cooled valve is controlled based on the target opening degree to achieve temperature control of the fuel cell stack.

[0005] Secondly, this application provides a temperature control device for a fuel cell stack, comprising: Temperature acquisition module, used to acquire the measured temperature of fuel cell stack in real time; The first data acquisition module is used to acquire the current load condition sequence of the fuel cell stack when the measured temperature is less than or equal to the temperature safety threshold. The cooling capacity prediction module is used to input the current load condition sequence into the trained prediction model to predict the cooling capacity demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences; The first target opening degree determination module is used to determine the target opening degree of the liquid-cooled valve based on the predicted cooling capacity requirement; The second data acquisition module is used to issue an alarm signal and acquire the actual opening feedback signal of the liquid cooling valve and the flow feedback signal of the coolant when the measured temperature is greater than the temperature safety threshold. The second target opening determination module is used to determine the target opening of the liquid-cooled valve based on the actual opening feedback signal of the liquid-cooled valve, the opening threshold, the flow feedback signal of the coolant, and the flow safety range. The control module is used to control the liquid-cooled valve based on the target opening degree to achieve temperature control of the fuel cell stack.

[0006] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the temperature control method for the fuel cell stack described in any one of the above.

[0007] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the temperature control method for the fuel cell stack described above.

[0008] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the temperature control method for the fuel cell stack described above.

[0009] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, apparatus, device, medium, and product for temperature control of a fuel cell stack. The measured temperature of the fuel cell stack characterizes its load conditions. When the temperature safety threshold is not exceeded, the predicted cooling capacity demand is obtained using the current load condition sequence, and the target opening degree of the liquid-cooled valve is determined based on this. This adjusts the flow rate of the coolant in the liquid-cooled housing, allowing the coolant to remove heat exceeding the cooling capacity of the flat-plate heat pipe, thus expanding the heat dissipation temperature limit of the flat-plate heat pipe and achieving temperature control of the fuel cell stack. When the temperature safety threshold is exceeded, the target opening degree of the liquid-cooled valve is determined based on the opening threshold and flow safety range, and an alarm signal is issued to ensure the safety of the fuel cell stack cooling device. Throughout the process, the determination of the target opening degree of the liquid-cooled valve is divided into two cases based on the temperature safety threshold to achieve different temperature regulation. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 This is an application environment diagram of a temperature control method for a fuel cell stack according to an embodiment of this application.

[0012] Figure 2 This is a schematic flowchart of a temperature control method for a fuel cell stack provided in an embodiment of this application.

[0013] Figure 3 for Figure 2 A detailed flowchart illustrating the steps of the temperature control method for fuel cell stacks.

[0014] Figure 4 This is a simulation diagram of a fuel cell stack cooling device provided in one embodiment of this application.

[0015] Figure 5 This is a schematic diagram of the network structure of the hidden layer in a temporal convolutional network provided in an embodiment of this application, as well as a schematic diagram of the processing procedure of the prediction model.

[0016] Figure 6 This is a schematic diagram of the functional modules of a temperature control device for a fuel cell stack provided in an embodiment of this application.

[0017] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

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

[0019] To make the objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] The temperature control method for fuel cell stacks provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on another server. Terminal 101 can send the real-time measured temperature of the fuel cell stack to server 102. Server 102 receives the measured temperature of the fuel cell stack. When the measured temperature is less than or equal to a temperature safety threshold, the current load condition sequence of the fuel cell stack is obtained. The current load condition sequence is input into a trained prediction model to predict the predicted cooling capacity requirement. The prediction model includes a temporal convolutional network and an attention mechanism network, and is trained using historical sample load condition sequences. The target opening degree of the liquid-cooled valve is determined based on the predicted cooling capacity requirement. When the measured temperature is greater than the temperature safety threshold, an alarm signal is issued and the actual opening degree feedback signal of the liquid-cooled valve and the coolant flow feedback signal are obtained. The target opening degree of the liquid-cooled valve is determined based on the actual opening degree feedback signal, the opening threshold, the coolant flow feedback signal, and the flow safety range. The liquid-cooled valve is controlled based on the target opening degree to achieve temperature control of the fuel cell stack. Server 102 can feed back the obtained target opening degree of the liquid-cooled valve to terminal 101. In addition, in some embodiments, the temperature control method of the fuel cell stack can also be implemented by the server 102 or the terminal 101 separately. For example, the terminal 101 can directly process the measured temperature of the fuel cell stack to be processed, or the server 102 can obtain the measured temperature of the fuel cell stack from the data storage system and process it.

[0021] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 102 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0022] In one exemplary embodiment, such as Figure 2 and Figure 3 As shown, a temperature control method for a fuel cell stack is provided. This method is executed by a computer device, specifically a terminal or server, or both. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps 201 to 207. Wherein: Step 201: Obtain the measured temperature of the fuel cell stack in real time.

[0023] Step 202: When the measured temperature is less than or equal to the temperature safety threshold, obtain the current load condition sequence of the fuel cell stack.

[0024] Step 203: Input the current load condition sequence into the trained prediction model to predict the predicted cooling demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences.

[0025] Step 204: Determine the target opening degree of the liquid-cooled valve based on the predicted cooling capacity requirement.

[0026] Step 205: When the measured temperature is greater than the temperature safety threshold, an alarm signal is issued and the actual opening degree feedback signal of the liquid cooling valve and the flow rate feedback signal of the coolant are obtained.

[0027] Step 206: Determine the target opening degree of the liquid cooling valve based on the actual opening degree feedback signal of the liquid cooling valve, the opening degree threshold, the flow rate feedback signal of the coolant, and the flow rate safety range.

[0028] Step 207: Control the liquid-cooled valve based on the target opening degree to achieve temperature control of the fuel cell stack.

[0029] In an exemplary embodiment, the method of steps 201-207 is applied to a fuel cell stack cooling device, such as... Figure 4As shown, the fuel cell stack cooling device includes a flat-plate heat pipe 1 and a liquid-cooled housing 2. The flat-plate heat pipe 1 is disposed on the side of the fuel cell stack 3 and inside the liquid-cooled housing 2. The flat-plate heat pipe 1 is used to absorb the heat generated by the fuel cell stack during operation and release the absorbed heat into the liquid-cooled housing. In this embodiment, the fuel cell stack 3 includes multiple fuel cells. Specifically, when the fuel cell stack 3 generates heat during operation, the working fluid in the flat-plate heat pipe 1 absorbs heat from the fuel cell at the evaporation end, which is the end closer to the fuel cell (high temperature), to cool it down. Inside the flat-plate heat pipe 1, the working fluid absorbs heat at the evaporation end and undergoes a phase change evaporation. The vapor flows to the cold end of the flat-plate heat pipe 1, which is the liquid-cooled side (low temperature), under the action of pressure difference. It condenses at the cold end and releases heat into the liquid-cooled housing. The working fluid in the flat-plate heat pipe 1 at the cold end dissipates the absorbed heat to the low-temperature air or coolant, thereby achieving cooling. Heat dissipation is achieved by contacting the low-temperature air or coolant. The internal structure of the flat plate heat pipe 1 includes a capillary structure 4 tightly wrapped around the pipe wall and an internal evaporating medium channel 5 filled with evaporating working fluid. The direction of heat conduction is as indicated by the arrow inside the evaporating medium channel 5. The condensed working fluid flows back to the evaporation end under the capillary force of the capillary structure 4 in the flat plate heat pipe 1, thus forming a closed phase change heat transfer cycle. In this embodiment, the capillary structure 4 is at least one of sintered powder, metal mesh, or a grooved structure.

[0030] In this embodiment, flat heat pipes 1 are provided on three sides of the fuel cell stack 3. The flat heat pipes 1 absorb the heat from the fuel cell stack 3 and conduct it along the thickness direction of the flat heat pipes 1, releasing the heat into the liquid-cooled housing 2.

[0031] A liquid cooling valve 7 is installed at the inlet 6 of the liquid-cooled housing 2. The liquid cooling valve 7 is used to control the flow rate of coolant into the interior of the liquid-cooled housing 2, and the coolant flows out through the outlet 8 of the liquid-cooled housing 2 to form an active liquid cooling circuit. In this embodiment, the liquid cooling valve 7 is selected as a proportional regulating valve, whose opening degree can be continuously adjusted or controlled in stages to achieve precise regulation of the coolant flow rate.

[0032] In an exemplary embodiment, step 201 specifically includes using a sensor to acquire the measured temperature d of the fuel cell stack in real time, and determining the relationship between the measured temperature d and the temperature safety threshold.

[0033] In an exemplary embodiment, step 202 specifically includes: when the measured temperature is less than or equal to the temperature safety threshold, the fuel cell stack is under normal operating conditions. At this time, the current load condition sequence of the fuel cell stack is obtained. The current load condition sequence includes the current a, voltage b, measured temperature d, and output power of the fuel cell stack at the current moment. and current density The load condition sequence includes the output power of the fuel cell stack. and current density It is calculated based on the current a and voltage b of the fuel cell stack at the current moment.

[0034] In an exemplary embodiment, step 203 specifically includes steps 2031-2032: Step 2031: Input the current load condition sequence into a temporal convolutional network to extract features and obtain multi-scale temporal features.

[0035] Input a timing window of length N: ; in, Let τ be the current of the fuel cell stack at time τ. Let τ be the voltage of the fuel cell stack at time τ. Let be the output power of the fuel cell stack at time τ, and , Let τ be the temperature of the fuel cell stack at time τ. Let τ be the current density of the fuel cell stack at time τ.

[0036] like Figure 5 As shown, the temporal convolutional network includes multiple hidden layers connected in sequence. Each hidden layer includes a feature extraction unit and a residual connection unit. The feature extraction unit includes dilated convolution, batch normalization, ReLU, and Dropout connected in sequence. The input to the residual connection unit is the output feature of the previous hidden layer and the output feature of the feature extraction unit. The output feature of the previous hidden layer is processed by a 1×1 convolution and then residually processed with the output feature of the feature extraction unit to obtain the output feature of the hidden layer. The expression for feature extraction by the hidden layer is as follows: ; in, For the first The input feature tensor of the hidden layer, when l When = 1, the input sequence of the first causal convolutional layer is , For the first The output feature tensor of the hidden layer For the first The convolutional kernel weights of the hidden layers For the first The bias vector of the hidden layer. The activation function is a non-linear activation function, such as ReLU, where L is the total number of hidden layers. This is a 1×1 convolution operation.

[0037] The Temporal Convolutional Network (TCN) extracts features from the input sequence, capturing local and long-term temporal dependencies in the sequence through its multi-layer dilated convolutional structure, and outputting multi-scale temporal features. for: in, For multi-scale temporal features, it is a d-dimensional vector containing all temporal features extracted at time t.

[0038] Step 2031: Input the multi-scale temporal features into the attention mechanism network for feature weighting and aggregation to obtain the predicted cooling demand.

[0039] See you again Figure 5 ,like Figure 5 As shown, the temporal convolutional network processes the input current load condition sequence and finally outputs the features of the last time step. , The query vector q is used in the attention mechanism network. Simultaneously, the entire feature sequence output by the last layer of the TCN... The sequence is linearly mapped to key vector k and value vector v, respectively. The attention mechanism network calculates the weights at each historical time step. This weight reflects the importance of each historical moment to the current prediction; the value vector of all historical moments... According to weight Perform a weighted summation to obtain a context vector. . This can be understood as the model "reviewing" the entire historical sequence and then focusing on the comprehensive context formed by the most important information.

[0040] Weighted aggregation via attention mechanism network: ; Where q is the query vector (derived from the features output by the TCN at the most recent time step). (obtained by linear mapping) The key vector (derived from the TCN output features at each time step) (obtained by linear mapping) Value vector (features output by TCN at each time step) (obtained by linear mapping) The dimension of the key vector; The attention weight at time t satisfies ; The context vector obtained by attention aggregation, This represents the transpose of a matrix.

[0041] The features of the current time step output by TCN Context vectors generated by attention mechanism networks By splicing them together, a more powerful comprehensive feature vector is formed. =[ , ].Will Linearization, outputting the predicted temperature separately. and forecasting cooling demand .

[0042] Output predicted values: ; in, For the predicted temperature of the fuel cell stack, To predict cooling demand, It is based on the characteristics of the current time step With context vector c t A composite feature formed by piecing together elements; These are the regression weights for predicted temperature and predicted cooling demand, respectively. This is the regression bias.

[0043] Predictive models also include data acquisition and data preprocessing before training: Data Acquisition: Collect a large amount of historical operating data of the fuel cell stack. Use a sensor set to collect the current, voltage and measured temperature of the fuel cell stack for a preset period of time, and calculate the output power and current density of the fuel cell stack. The sensor set includes current sensors, voltage sensors and temperature sensors.

[0044] Data preprocessing: Based on the various historical data collected over a preset time period, a historical sample load condition sequence is obtained. This historical sample load condition sequence is then used to train the prediction model. The data for each time point in the historical sample load condition sequence includes the fuel cell stack's current, voltage, measured temperature, output power, and current density. The true label corresponding to the historical sample load condition sequence is the actual temperature at the next time point. and actual cooling capacity requirements .

[0045] The loss calculated during the training process of the prediction model includes: 1. The model's predicted values ​​( , ) and the actual label value ( , (Compare)

[0046] 2. Use a loss function (mean squared error) to calculate the difference between the predicted and actual values. This difference (loss value) quantifies the "error" of the model's current prediction.

[0047] The prediction model undergoes backpropagation and optimization during training.

[0048] 1. Using the backpropagation algorithm, the calculated loss value is traced back layer by layer from the output of the prediction model to the input. In this process, the algorithm calculates the "contribution" (i.e., gradient) of each parameter in the prediction model (such as the convolutional kernel weights of TCN, the linear mapping weights in the attention mechanism, the weights of the final regression layer, etc.) to the total loss.

[0049] 2. Use an optimizer (such as Adam or SGD) to update all parameters in the prediction model based on the calculated gradients. The update direction is to fine-tune these parameters so that the loss value calculated on similar data in the next iteration can be reduced.

[0050] The predictive model undergoes iterative training.

[0051] The training dataset is used to perform tens of thousands of iterations on a large number of historical load condition sequences. Through this process, the predictive model parameters are continuously tuned and optimized, ultimately enabling the model to learn how to extract multi-scale time-series features from historical sequences and use these features to accurately predict future temperature and cooling capacity requirements. The training process continues until the model's performance on the validation set no longer shows significant improvement, in order to prevent overfitting.

[0052] The trained prediction model is set in the ECU (Engine Control Unit) to predict the cooling demand and obtain the predicted cooling demand.

[0053] In an exemplary embodiment, step 204 specifically includes steps 211-213: Step 211: Obtain the cooling difference based on the predicted cooling demand.

[0054] The specific expression is: ; in, Q represents the cooling difference. hp Q represents the maximum cooling capacity of a flat-plate heat pipe. pred To predict cooling demand.

[0055] Step 212: Obtain the coolant mass flow rate based on the cooling difference.

[0056] Based on the law of conservation of energy, the required cooling capacity (i.e., the cooling difference) is converted into the refrigerant mass flow rate, expressed as: ; in, This is the coolant mass flow rate. The average temperature difference between the inlet and outlet of the coolant. This refers to the specific heat capacity of the coolant.

[0057] Step 213: Obtain the target opening of the liquid-cooled valve based on the relationship between the opening degree of the liquid-cooled valve and the mass flow rate of the coolant.

[0058] The expression for the relationship between the opening degree of the liquid-cooled valve and the mass flow rate is: ; in, For liquid cooling valve opening The corresponding coolant mass flow rate, For coolant density, Let be the equivalent maximum flow area of ​​the liquid-cooled valve at its maximum opening, and k be the nonlinear exponential coefficient between the opening and the flow area of ​​the liquid-cooled valve. This represents the pressure difference across the liquid cooling circuit.

[0059] Therefore, the expression for the target opening degree of the liquid-cooled valve can be obtained by inverse solving as follows: ; ; in, This represents the target opening degree of the liquid-cooled valve. is a constant parameter representing the flow capacity coefficient of the liquid-cooled valve at its maximum opening.

[0060] In another exemplary embodiment, step 204 includes steps 221-222: Step 221: Determine the cooling difference based on the predicted cooling capacity demand. The method for determining the cooling difference in this process is the same as that in step 211, and will not be repeated here.

[0061] Step 222, determining the target opening degree of the liquid-cooled valve based on the cooling difference, specifically: When ΔQ≤0, the target opening degree of the liquid-cooled valve is determined to be 0.

[0062] When 0 < ΔQ ≤ ΔQ1, the target opening degree of the liquid-cooled valve is determined to be 25% of the maximum opening degree of the liquid-cooled valve.

[0063] When ΔQ1 < ΔQ ≤ ΔQ2, the target opening degree of the liquid-cooled valve is determined to be 75% of the maximum opening degree of the liquid-cooled valve.

[0064] When ΔQ>ΔQ2, the target opening degree of the liquid-cooled valve is determined to be the maximum opening degree of the liquid-cooled valve.

[0065] Wherein, ΔQ is the cooling difference, ΔQ1 is the first preset cooling difference, ΔQ2 is the second preset cooling difference, and the second preset cooling difference is greater than the first preset cooling difference. ΔQ1 and ΔQ2 are the grading thresholds preset according to the performance of the liquid cooling system.

[0066] Under abnormal operating conditions, that is, when the measured temperature d is greater than the temperature safety threshold, the ECU triggers an alarm signal f and starts auxiliary safety control methods.

[0067] In an exemplary embodiment, the auxiliary safety control method is a method for determining the target opening degree of the liquid-cooled valve in step 206, specifically including steps 231-234: Step 231: Determine whether the difference between the actual opening feedback signal of the liquid-cooled valve and the opening threshold is within the preset opening range. If the difference exceeds the preset opening range, then determine the target opening of the liquid-cooled valve as the opening threshold.

[0068] Specifically, the valve stem of the liquid-cooled valve 7 is directly coaxially connected to the output shaft of the stepper motor via a coupling; the stepper motor is electrically connected to the ECU and is used to receive pulse control signals from the ECU.

[0069] Based on the target opening degree and the actual opening degree feedback signal i, the opening degree deviation e is calculated, and the target stepping angle of the stepper motor is determined based on the opening degree deviation e.

[0070] Subsequently, based on the target stepper motor step angle, a corresponding pulse sequence and direction signal are generated to drive the stepper motor to rotate. The stepper motor directly drives the valve stem of the liquid-cooled valve 7 to rotate via a coupling, thereby positioning the valve core to the position corresponding to the target opening degree.

[0071] Step 232: When the difference does not exceed the preset opening range, determine whether the coolant flow feedback signal is within the safe flow range.

[0072] Step 233: When the flow feedback signal of the coolant does not exceed the safe flow range, the target opening of the liquid cooling valve is determined to be the current liquid cooling valve opening.

[0073] Step 234: When the flow feedback signal of the coolant exceeds the safe flow range, the opening of the liquid cooling valve is gradually adjusted with a preset amplitude and a preset period until the measured temperature is within the preset temperature range or the opening of the liquid cooling valve reaches the limit value, and the adjusted opening of the liquid cooling valve is determined as the target opening of the liquid cooling valve; wherein, the adjustment operation includes increasing operation and decreasing operation.

[0074] In this embodiment, the preset amplitude is 5% of the maximum opening of the liquid-cooled valve, and the preset period is 5 seconds, but other values ​​are also possible.

[0075] Step 234 specifically includes steps 1-2: Step 1: When the coolant flow feedback signal is less than the minimum flow safety threshold, and the opening of the liquid cooling valve remains unchanged, and the measured temperature continues to decrease within a judgment step of M consecutive preset cycles, the opening of the liquid cooling valve is increased by a preset amount. The measured temperature of the fuel cell stack after increasing the liquid cooling valve opening is re-acquired, and it is determined whether the measured temperature after increasing the liquid cooling valve opening is within a preset temperature range. If yes, the increased liquid cooling valve opening is determined as the target opening of the liquid cooling valve; if not, the increased liquid cooling valve opening is increased again by a preset amount, and the increased liquid cooling valve opening is taken as the opening of the liquid cooling valve, until the measured temperature is within the preset temperature range or the liquid cooling valve opening is at its maximum opening. In this embodiment, M is an integer greater than or equal to 2.

[0076] Specifically, when the coolant flow feedback signal j is less than the minimum flow safety threshold, and the measured temperature continues to decrease for several consecutive preset cycles (e.g., two consecutive cycles of 5 seconds) while the valve opening remains unchanged, the system enters the incremental adjustment mode, which means gradually increasing the opening of the liquid cooling valve by a preset amplitude and preset cycle. in, This is to adjust and increase the opening of the liquid cooling valve.

[0077] With a 5-second cycle, the maximum opening of the liquid cooling valve is increased by 5% each time until the measured temperature rises to the preset temperature range or the liquid cooling valve opening reaches its maximum.

[0078] Step 2: When the coolant flow feedback signal is greater than or equal to the maximum flow safety threshold, and the opening of the liquid cooling valve remains unchanged, and the measured temperature continues to rise within a judgment step of M consecutive fixed cycles, the opening of the liquid cooling valve is reduced by a preset amount. The measured temperature of the fuel cell stack after reducing the liquid cooling valve opening is re-acquired, and it is determined whether the measured temperature after reducing the liquid cooling valve opening is within the preset temperature range. If yes, the reduced liquid cooling valve opening is determined as the target opening of the liquid cooling valve. If not, the reduced liquid cooling valve opening is reduced again by a preset amount, and the reduced liquid cooling valve opening is taken as the opening of the liquid cooling valve, until the measured temperature is within the preset temperature range or the liquid cooling valve opening is at its minimum opening.

[0079] When the coolant flow feedback signal j is greater than or equal to the maximum flow safety threshold, and the measured temperature continues to rise for several consecutive preset cycles (e.g., two consecutive cycles of 5 seconds) while the valve opening remains unchanged, the flow reduction mode is entered, which means the opening of the liquid cooling valve is gradually reduced by a preset amplitude and preset cycle. With a 5-second cycle, the maximum opening of the liquid cooling valve is increased by 5% each time, until the measured temperature drops back to the preset temperature range or the liquid cooling valve opening is reduced to the minimum opening of 0.

[0080] The temperature control method for fuel cell stacks in this application can be applied to vehicle fuel cell systems, stationary fuel cell power generation systems, or portable fuel cell power supply systems.

[0081] Based on the same inventive concept, this application also provides a method for implementing the above-mentioned issues. The solution provided by this device is similar to the solution described in the above-described method; therefore, the specific limitations in one or more temperature control device embodiments of fuel cell stacks provided below can be found in the limitations of the temperature control method for fuel cell stacks described above, and will not be repeated here.

[0082] In one exemplary embodiment, such as Figure 6 As shown, an apparatus for providing a temperature control method for a fuel cell stack includes: Temperature acquisition module 51 is used to acquire the measured temperature of the fuel cell stack in real time.

[0083] The first data acquisition module 52 is used to acquire the current load condition sequence of the fuel cell stack when the measured temperature is less than or equal to the temperature safety threshold.

[0084] The cooling capacity prediction module 53 is used to input the current load condition sequence into the trained prediction model to predict the cooling capacity demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences.

[0085] The first target opening determination module 54 is used to obtain a cooling difference based on the predicted cooling capacity demand, and to determine the target opening of the liquid-cooled valve based on the cooling difference.

[0086] The second data acquisition module 55 is used to issue an alarm signal and acquire the actual opening feedback signal of the liquid cooling valve and the flow feedback signal of the coolant when the measured temperature is greater than the temperature safety threshold.

[0087] The second target opening determination module 56 is used to determine the target opening of the liquid-cooled valve based on the actual opening feedback signal of the liquid-cooled valve, the opening threshold, the flow feedback signal of the coolant, and the flow safety range.

[0088] The control module 57 is used to control the liquid-cooled valve based on the target opening degree to achieve temperature control of the fuel cell stack.

[0089] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database is used to acquire the measured temperature of the fuel cell stack in real time. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a temperature control method for the fuel cell stack.

[0090] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0091] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0092] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0093] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0094] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0095] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0096] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0097] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A temperature control method of a fuel cell stack, characterized by, A cooling device for a fuel cell stack is provided, comprising a flat-plate heat pipe and a liquid-cooled housing. The flat-plate heat pipe is disposed on the side of the fuel cell stack and inside the liquid-cooled housing. The flat-plate heat pipe absorbs heat generated by the fuel cell stack during operation and releases the absorbed heat into the liquid-cooled housing. A liquid-cooled valve is provided at the inlet of the liquid-cooled housing to control the flow rate of coolant into the liquid-cooled housing. The temperature control method for the fuel cell stack includes: Real-time acquisition of the measured temperature of the fuel cell stack; When the measured temperature is less than or equal to the temperature safety threshold, the current load condition sequence of the fuel cell stack is obtained; The current load condition sequence is input into the trained prediction model to predict the cooling demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences; The target opening degree of the liquid-cooled valve is determined based on the predicted cooling capacity requirement; When the measured temperature exceeds the temperature safety threshold, an alarm signal is issued and the actual opening degree feedback signal of the liquid cooling valve and the flow rate feedback signal of the coolant are obtained. The target opening degree of the liquid-cooled valve is determined based on the actual opening degree feedback signal, the opening degree threshold, the flow rate feedback signal of the coolant, and the flow rate safety range. The liquid-cooled valve is controlled based on the target opening degree to achieve temperature control of the fuel cell stack.

2. The temperature control method of a fuel cell stack according to claim 1, characterized by, Determining the target opening degree of the liquid-cooled valve based on the predicted cooling capacity demand specifically includes: The cooling difference is obtained based on the predicted cooling demand. The refrigerant mass flow rate is obtained based on the refrigeration difference; The target opening of the liquid-cooled valve is obtained based on the relationship between the opening degree of the liquid-cooled valve and the mass flow rate, and the mass flow rate of the coolant.

3. The temperature control method of a fuel cell stack according to claim 2, characterized by, The expression for the relationship between the opening degree of the liquid-cooled valve and the mass flow rate is: ； wherein, is the liquid cooling valve opening is the corresponding coolant mass flow, is the coolant density, is the equivalent maximum flow area of the liquid cooling valve at maximum opening, k is a non-linear exponent coefficient between the opening and the flow area of the liquid cooling valve, is the pressure difference across the liquid cooling circuit.

4. The temperature control method of a fuel cell stack according to claim 1, characterized by Determining the target opening degree of the liquid-cooled valve based on the predicted cooling capacity demand specifically includes: The cooling difference is determined based on the predicted cooling demand. The target opening degree of the liquid-cooled valve is determined based on the aforementioned cooling difference, specifically as follows: When ΔQ≤0, the target opening degree of the liquid-cooled valve is determined to be 0; When 0 < ΔQ ≤ ΔQ1, the target opening degree of the liquid-cooled valve is determined to be 25% of the maximum opening degree of the liquid-cooled valve; When ΔQ1 < ΔQ ≤ ΔQ2, the target opening degree of the liquid-cooled valve is determined to be 75% of the maximum opening degree of the liquid-cooled valve; When ΔQ>ΔQ2, the target opening degree of the liquid-cooled valve is determined to be the maximum opening degree of the liquid-cooled valve; where ΔQ is the cooling difference, ΔQ1 is the first preset cooling difference, ΔQ2 is the second preset cooling difference, and the second preset cooling difference is greater than the first preset cooling difference.

5. The temperature control method for a fuel cell stack according to claim 1, characterized in that, The target opening degree of the liquid-cooled valve is determined based on the actual opening degree feedback signal, the opening degree threshold, the coolant flow rate feedback signal, and the flow rate safety range. Specifically, this includes: Determine whether the difference between the actual opening feedback signal of the liquid-cooled valve and the opening threshold is within a preset opening range. If the difference exceeds the preset opening range, then determine the target opening of the liquid-cooled valve as the opening threshold. When the difference does not exceed the preset opening range, it is determined whether the coolant flow feedback signal is within the safe flow range. When the flow feedback signal of the coolant does not exceed the safe flow range, the target opening of the liquid cooling valve is determined to be the current liquid cooling valve opening. When the flow feedback signal of the coolant exceeds the safe flow range, the opening of the liquid cooling valve is gradually adjusted with a preset amplitude and a preset period until the measured temperature is within the preset temperature range or the opening of the liquid cooling valve reaches the limit value, and the adjusted opening of the liquid cooling valve is determined as the target opening of the liquid cooling valve; wherein, the adjustment operation includes increasing operation and decreasing operation.

6. The temperature control method for a fuel cell stack according to claim 5, characterized in that, When the coolant flow feedback signal exceeds the safe flow range, the opening of the liquid cooling valve is gradually adjusted with a preset amplitude and a preset period until the measured temperature is within the preset temperature range or the liquid cooling valve opening reaches its limit value. The adjusted liquid cooling valve opening is then determined as the target opening of the liquid cooling valve, specifically including: When the coolant flow feedback signal is less than the minimum flow safety threshold, and the opening of the liquid cooling valve remains unchanged, and the measured temperature continues to decrease within a judgment step of M consecutive preset cycles, the opening of the liquid cooling valve is increased by a preset amount. The measured temperature of the fuel cell stack after increasing the opening of the liquid cooling valve is reacquired, and it is determined whether the measured temperature after increasing the opening of the liquid cooling valve is within the preset temperature range. If yes, the increased opening of the liquid cooling valve is determined as the target opening of the liquid cooling valve. If not, the increased opening of the liquid cooling valve is increased by a preset amount again, and the increased opening of the liquid cooling valve is taken as the opening of the liquid cooling valve, until the measured temperature is within the preset temperature range or the opening of the liquid cooling valve is at its maximum. When the coolant flow feedback signal is greater than or equal to the maximum flow safety threshold, and the opening of the liquid cooling valve remains unchanged, and the measured temperature continues to rise within a judgment step of M consecutive fixed cycles, the opening of the liquid cooling valve is reduced by a preset amount. The measured temperature of the fuel cell stack after reducing the liquid cooling valve opening is reacquired, and it is determined whether the measured temperature after reducing the liquid cooling valve opening is within the preset temperature range. If so, the reduced liquid cooling valve opening is determined as the target opening of the liquid cooling valve. If not, the reduced liquid cooling valve opening is reduced by a preset amount again, and the reduced liquid cooling valve opening is taken as the opening of the liquid cooling valve, until the measured temperature is within the preset temperature range or the liquid cooling valve opening is at its minimum opening.

7. A temperature control device for a fuel cell stack, characterized in that, The temperature control device of the fuel cell stack performs the temperature control method of the fuel cell stack according to any one of claims 1-6, and the temperature control device of the fuel cell stack includes: Temperature acquisition module, used to acquire the measured temperature of fuel cell stack in real time; The first data acquisition module is used to acquire the current load condition sequence of the fuel cell stack when the measured temperature is less than or equal to the temperature safety threshold. The cooling capacity prediction module is used to input the current load condition sequence into the trained prediction model to predict the cooling capacity demand; wherein, the prediction model includes a temporal convolutional network and an attention mechanism network, and the prediction model is trained using historical sample load condition sequences; The first target opening degree determination module is used to determine the target opening degree of the liquid-cooled valve based on the predicted cooling capacity. The second data acquisition module is used to issue an alarm signal and acquire the actual opening feedback signal of the liquid cooling valve and the flow feedback signal of the coolant when the measured temperature is greater than the temperature safety threshold. The second target opening determination module is used to determine the target opening of the liquid-cooled valve based on the actual opening feedback signal of the liquid-cooled valve, the opening threshold, the flow feedback signal of the coolant, and the flow safety range. The control module is used to control the liquid-cooled valve based on the target opening degree to achieve temperature control of the fuel cell stack.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the temperature control method for a fuel cell stack according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the temperature control method for the fuel cell stack as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the temperature control method for the fuel cell stack as described in any one of claims 1-6.

Images