Method for controlling humidifying equipment, humidifier, system and device

Abstract

The embodiment of the invention provides a method for controlling humidification equipment, a humidifier, a system and a device.The method comprises the steps that first control information output by a fuzzy controller is obtained, the first control information is information obtained through calculation based on first system parameters of a fuel cell system, and the first system parameters of the fuel cell system are calculated according to the first control information; the first control information is used for representing the rationality of the amount of liquid released by the humidifying equipment, and the humidifying equipment is used for humidifying a fuel cell in the fuel cell system; inputting the first control information into a target network model to obtain a first target control parameter output by the target network model; and controlling the liquid release of the humidifying equipment according to the first target control parameter so as to control the electric energy generated by the fuel cell. According to the method and the device, the problems of relatively low accuracy and efficiency of adjusting the humidifier in the fuel cell in related technologies are solved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of equipment control, and specifically, to a method for controlling a humidification device and a humidifier, system, and device. Background Art

[0002] As a clean energy, hydrogen energy is of great significance in renewable energy and energy storage. Fuel cells, as an important way to utilize hydrogen energy, have the advantages of high energy conversion efficiency and environmental friendliness, and have attracted widespread attention.

[0003] Hydrogen fuel cells have high energy conversion efficiency, but they have high requirements for the working environment, usually requiring purer air, higher humidity, lower temperature and stable voltage, etc. For the temperature and humidity control during the operation of hydrogen fuel cells, the traditional control method is usually to set the humidification parameters of the humidifier and then stop adjusting them.

[0004] At present, the adjustment of humidification parameters during system operation is usually done manually, that is, according to the problems found during system operation, which results in low efficiency and accuracy. Summary of the invention

[0005] The embodiments of the present application provide a method for controlling a humidification device and a humidifier, a system, and a device to at least solve the problem of low accuracy and efficiency in adjusting a humidifier in a fuel cell in the related art.

[0006] According to one embodiment of the present application, a method for controlling a humidification device is provided, comprising: obtaining first control information output by a fuzzy controller, wherein the first control information is information calculated based on a first system parameter of a fuel cell system, the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, and the humidification device is used to humidify fuel cells in the fuel cell system; inputting the first control information into a target network model to obtain a first target control parameter output by the target network model; and controlling the release of liquid by the humidification device according to the first target control parameter to control the electrical energy generated by the fuel cell.

[0007] In an exemplary embodiment, obtaining the first control information output by the fuzzy controller includes: obtaining the first system parameters of the fuel cell system through a plurality of sensing devices, wherein the first system parameters include: the actual humidity of the proton exchange membrane in the fuel cell, the target humidity of the proton exchange membrane, the humidity change rate of the actual humidity of the proton exchange membrane, and the performance index of the fuel cell; inputting the first system parameters into the fuzzy controller to obtain the first control information output by the fuzzy controller, wherein the fuzzy controller outputs the first control information in the following manner: converting the input actual humidity, the target humidity, the humidity change rate, and the performance index into fuzzy values ​​respectively to obtain a plurality of input variables; converting the plurality of input variables into a plurality of fuzzy sets, wherein the fuzzy sets include fuzzy linguistic variables; matching the plurality of fuzzy sets with a fuzzy rule base, and calculating the weight of each fuzzy set based on the matching result, wherein the fuzzy rule base defines the relationship between the plurality of fuzzy sets; and outputting the first control information according to the weight of each fuzzy set.

[0008] In an exemplary embodiment, before inputting the first control information into the target network model to obtain the first target control parameter output by the target network model, the method includes: acquiring multiple groups of training data, wherein each group of the training data includes: sample control information and sample control parameters, the sample control information is information calculated by the fuzzy controller based on the sample system parameters of the fuel cell system and used to indicate the rationality of the amount of liquid released by the humidification device, and the sample control parameter is information generated based on the sample control information and used to adjust the amount of liquid released by the humidification device; using the multiple groups of training data to train the initial network model to obtain the target network model, wherein for each group of training data, the initial network model is used to determine the weights of multiple sub-control parameters included in the sample control parameters based on the sample control information, and adjust the values ​​of the control parameters according to the weights of the multiple sub-control parameters.

[0009] In an exemplary embodiment, the initial network model is trained using the above-mentioned multiple sets of training data to obtain the above-mentioned target network model, including: iteratively training the initial network model using the multiple sets of training data until the number of times the initial network model is trained reaches a first target number, and then the training is terminated to obtain the target network model; or, when the number of times the performance of the fuel cell outputting electrical energy meets a preset performance reaches a second target number, the training is terminated to obtain the target network model, wherein the performance of the fuel cell outputting electrical energy is the performance obtained by controlling the control parameters output by the initial network model during the training of the initial network model.

[0010] In an exemplary embodiment, the release of liquid by the humidification device is controlled according to the first target control parameter to control the electric energy generated by the fuel cell, including: obtaining a proportional control parameter, an integral control parameter and a differential control parameter included in the first target control parameter, wherein the proportional control parameter is used to adjust the response speed of the fuel cell system, the integral control parameter is used to adjust the steady-state error of the fuel cell system, and the differential control parameter is used to adjust the oscillation of the fuel cell system; generating a control instruction using a first humidity deviation value, the proportional control parameter, the integral control parameter and the differential control parameter, wherein the first humidity deviation value is the difference between the target humidity and the actual humidity of the fuel cell; adjusting the opening of the humidifier valve according to the valve opening value included in the control instruction to control the amount of liquid released by the humidification device, wherein the humidifier valve is arranged in the humidifier.

[0011] In an exemplary embodiment, after adjusting the opening of the humidifier valve according to the control instruction, the method further includes: detecting the humidity of the fuel cell; when a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, superimposing the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter to obtain superimposed information, and sending the superimposed information to the fuzzy controller; obtaining second control information output by the fuzzy controller, wherein the second control information is information calculated by the fuzzy controller based on the superimposed information and the second system parameter of the fuel cell system, and is used to indicate the rationality of the amount of liquid released by the humidifier; inputting the second control information into the target network model to obtain the second target control parameter output by the target network model, wherein the second control parameter is used to control the release of liquid by the humidifier.

[0012] In an exemplary embodiment, when a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter are superimposed to obtain superimposed information, including: respectively determining the weights of the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter in the target network model, wherein the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter are all weights determined by the target network model based on the first control information; superimposing the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter according to the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter to obtain the superimposed information.

[0013] According to another embodiment of the present application, a humidification controller is provided. The humidification controller is connected to a humidification device in a fuel cell system, and the humidification controller is used to execute the above method steps.

[0014] According to another embodiment of the present application, a fuel cell system is provided, comprising: a sensor group, a fuzzy controller, and a humidification controller such as the above-mentioned, wherein the sensor group is used to obtain a first system parameter of the fuel cell system; and the fuzzy controller is used to output first control information based on the first system parameter.

[0015] According to another embodiment of the present application, a device for controlling a humidification device is provided, including: a first acquisition module, used to acquire first control information output by a fuzzy controller, wherein the first control information is information calculated based on a first system parameter of a fuel cell system, and the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, and the humidification device is used to humidify fuel cells in the fuel cell system; a first input module, used to input the first control information into a target network model to obtain a first target control parameter output by the target network model; and a first control module, used to control the release of liquid by the humidification device according to the first target control parameter to control the electric energy generated by the fuel cell.

[0016] According to another embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0017] According to another embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when run.

[0018] According to another embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0019] Through the present application, by combining the fuzzy controller and the target network model, the first control information output by the fuzzy controller is input into the target network model to obtain the first target control parameter output by the target network model; the release of the liquid by the humidification device can be controlled according to the first target control parameter to control the electric energy generated by the fuel cell. Thereby, the efficiency of the fuel cell system can be significantly improved, the self-optimization of parameters can be achieved, and the accuracy of parameter adjustment can be improved. Therefore, the problem of low accuracy and efficiency of adjusting the humidifier in the fuel cell in the related art can be solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a hardware structure block diagram of a server device of a method for controlling a humidification device in an embodiment of the present application;

[0021] Figure 2 is a flow chart of a method for controlling a humidification device according to an embodiment of the present application;

[0022] Figure 3 is a schematic structural diagram of a proton exchange membrane fuel cell system according to an embodiment of the present application;

[0023] Figure 4 is a working principle diagram of a proton exchange membrane fuel cell system according to an embodiment of the present application;

[0024] Figure 5 is a schematic diagram of the relationship between the voltage and the load weight of the battery according to an embodiment of the present application;

[0025] Figure 6 is a structural schematic diagram of adjusting the first target control parameter according to an embodiment of the present application;

[0026] Figure 7 It is a structural block diagram of an apparatus for controlling a humidification device according to an embodiment of the present application.

[0027] Description of reference numerals:

[0028] Hydrogen device 31; oxygen device 32; humidification device 33; fuel cell 34; fuzzy controller 35; humidification controller 36; value fuzzification component 61; fuzzy rule pool 62; defuzzification component 63; inter-process communication device 64; instruction controller 65. DETAILED DESCRIPTION

[0029] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0031] The method embodiments provided in the embodiments of the present application can be executed in a server device or a similar computing device. Taking running on a server device as an example, Figure 1 1 is a hardware structure block diagram of a server device of a method for controlling a humidification device in an embodiment of the present application. Figure 1 As shown, the server device may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the server device may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above server device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0032] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for controlling the humidification device in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the server device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0033] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the server device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] In this embodiment, a method for controlling a humidification device is provided. Figure 2 is a flow chart of a method for controlling a humidification device according to an embodiment of the present application, such as Figure 2 As shown, the process includes the following steps:

[0035] Step S202, obtaining first control information output by the fuzzy controller, wherein the first control information is information calculated based on a first system parameter of the fuel cell system, and the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, and the humidification device is used to humidify the fuel cell in the fuel cell system;

[0036] Optionally, the fuel cell included in the fuel cell system includes but is not limited to a proton exchange membrane fuel cell (PEMFC), which is a device that generates electrical energy through an electrochemical reaction of hydrogen and oxygen. In order to maintain the performance and stability of the PEMFC, the PEMFC requires an appropriate humidity level to ensure the conductivity of the proton exchange membrane (PEM) and the activity of the catalytic layer.

[0037] Optionally, a fuzzy controller is provided in the fuel cell system, which is a control system based on fuzzy logic, capable of handling uncertainty and ambiguity, and which maps input to output through fuzzy rules. For example, the fuzzy controller simplifies the first system parameter into several levels, such as good, relatively good, and not good, for quick judgment. In addition, the fuzzy controller is based on a rule system, and guides decision-making through rules summarized from experience, such as parameter evaluation in a fuel cell system.

[0038] Optionally, a humidifying device is arranged in the fuel cell system and connected to the fuel cell to humidify the fuel cell in the fuel cell system. It includes a liquid tank filled with liquid, and the liquid is sprayed during the operation of the fuel cell to ensure the conductivity of the proton exchange membrane and the activity of the catalytic layer. The core component of the humidifying device is a device that can activate the hydrogen and oxygen mixed gas and provide appropriate humidity. The device is monitored by a controller and can control the humidity level of the final gas by adjusting the flow, pressure and temperature of the water. At the same time, considering the optimal operating temperature range of the fuel cell, the humidifying device also needs to monitor and adjust the water temperature in time to maintain the stability and efficiency of the fuel cell operation.

[0039] For example, Figure 3 FIG. 1 is a schematic diagram of the structure of the proton exchange membrane fuel cell system in this embodiment. The proton exchange membrane fuel cell system includes:

[0040] Proton exchange membrane (PEM): This is the core part of the fuel cell 34, usually made of polymer materials such as fluorosulfonic acid resin (Nafion). Its function is to allow protons (H+) to pass through, but block the passage of electrons and gas molecules, thereby forming a potential difference between the anode and the cathode.

[0041] Catalyst layer: Usually made of platinum (Pt) or its alloy, covering both sides of the membrane. The role of the catalyst is to accelerate the redox reaction of hydrogen and oxygen.

[0042] Gas diffusion layer (GDL): Located on both sides of the catalyst layer, it is usually made of porous carbon material. Its function is to provide gas channels, allowing hydrogen and oxygen to reach the catalyst layer and help remove the water generated by the reaction.

[0043] Bipolar Plate: Bipolar plates connect the anodes and cathodes of adjacent battery cells to form a circuit. Bipolar plates are usually made of graphite composites or metals and have good conductivity and corrosion resistance.

[0044] Anode: accepts hydrogen input, where it is oxidized, releasing electrons and protons. The electrons flow through the external circuit, while the protons pass through the proton exchange membrane to the cathode.

[0045] Cathode: Receives oxygen input, where oxygen combines with protons and electrons transferred through the membrane to form water molecules.

[0046] Cooling system: Since fuel cells generate heat during operation, a cooling system is required to maintain a suitable operating temperature.

[0047] Gas supply system: includes hydrogen equipment 31 and oxygen equipment 32, as well as a delivery system to ensure a stable gas supply to the fuel cell.

[0048] Control system: responsible for monitoring and adjusting the operating status of the fuel cell system, including gas flow, pressure, temperature, etc. The control system includes a humidification device 33, a fuzzy controller 35 and a humidification controller 36.

[0049] Electrical output system: Converts the direct current generated by the fuel cell into a form suitable for use, such as alternating current.

[0050] Together, these components form a complete proton exchange membrane fuel cell system, enabling it to efficiently convert chemical energy into electrical energy.

[0051] Optionally, the first system parameter in this embodiment includes but is not limited to temperature, pressure, humidity, battery voltage, current density, etc. generated by the fuel system during operation.

[0052] In the operation of fuel cells, the ideal humidity state is crucial to improving their power efficiency. Since the load (such as vehicle driving conditions, weather conditions and number of passengers) will change continuously, the humidification amount needs to be adjusted in real time to ensure that the battery can continue to operate efficiently. If the humidification is not properly controlled, the fuel in the hydrogen tank may not be enough to support long-term endurance. In addition, in order to achieve maximum benefits, the system needs to have self-regulating functions, such as recycling and storing excess water or oxygen to form a cycle. The two major innovations of the fuel cell system are the small-scale humidifier design and the large-scale hydrogen and oxygen material control system. Among them, the humidifier is responsible for accurately controlling the humidity to the optimal state to adapt to environmental changes and maximize the performance of the fuel cell. In addition, in the material supply link, the system needs to effectively control the supply of hydrogen and oxygen to ensure that they participate in the chemical reaction with the highest efficiency.

[0053] like Figure 4As shown, it is a working principle diagram of the proton exchange membrane fuel cell system in this embodiment, specifically including: hydrogen is supplied to the anode of the fuel cell from the hydrogen storage tank in the system. At the anode (positive electrode), hydrogen molecules (H2) are oxidized to generate protons (H+) and electrons (e-). The chemical reaction is: H2→2H++2e-. The generated electrons cannot pass through the proton exchange membrane, so they must flow through an external circuit to generate current. The proton exchange membrane (PEM) allows protons to pass, but not electrons. This forces electrons to flow through an external circuit, thereby generating electricity. Oxygen is supplied to the cathode (negative electrode) of the fuel cell from the oxygen storage tank in the system. At the cathode, oxygen, protons and electrons combine to generate water. The chemical reaction is: O2+4H++4e-→2H2O. The water generated by the reaction can be discharged, and the heat generated can be used to heat the system or for other purposes. Electrons flow from the anode to the cathode through an external circuit to provide power to the device. The entire system is monitored by a control system to ensure the supply of hydrogen and oxygen, as well as the control of temperature and pressure to optimize performance. The generated water and unreacted gas (if any) are exhausted from the system. Advantages of proton exchange membrane fuel cells include high efficiency, low emissions and fast response.

[0054] Step S204, inputting the first control information into the target network model to obtain a first target control parameter output by the target network model;

[0055] Optionally, the target network model includes but is not limited to a model based on deep learning, which is a type of algorithm that uses a multi-layer neural network for training and prediction, such as a convolutional neural network (CNN) and a recurrent neural network (RNN). In this embodiment, the deep learning model can be used to optimize the performance of the fuzzy controller, mainly including the following aspects:

[0056] S1, training process: Data collection: First, historical data related to the fuel cell system needs to be collected. These data may include the input (e.g., sensor data) and output (e.g., control signal) of the fuel cell system, as well as the status information of the fuel cell system. Data preprocessing: Clean and standardize the collected data to ensure the quality and consistency of the data. Model selection: Select a suitable deep learning model (e.g., neural network, convolutional neural network, etc.) and adjust it according to the specific application scenario and data characteristics. Training: Use the collected training data to train the deep learning model. Adjust the model parameters through the back propagation algorithm and optimizer (e.g., Adam, SGD, etc.) to minimize the prediction error. Among them, the training data can come from the operation record of the actual system, the data generated by the simulation model, or the samples obtained by experiment. It usually includes input features (e.g., sensor readings, environmental variables, etc.) and target outputs (e.g., desired control signals).

[0057] S2, Dynamic update and adjustment of model parameters: In actual operation, the performance of the fuzzy controller can be improved by the dynamic update of the deep learning model: For example, online learning, real-time data acquisition: During the operation of the control system, new input and output data are collected in real time. Incremental learning: Incrementally train the deep learning model with new data to adapt to changes in the system. This can be achieved by regularly updating the model parameters. Adaptive adjustment, feedback mechanism: Adjust the rules or parameters of the fuzzy controller according to the actual performance of the control system (such as error, stability, etc.). The deep learning model can provide real-time feedback to help optimize the decision-making of the fuzzy controller. Generation of fuzzy rules: The deep learning model can analyze historical data and automatically generate or adjust fuzzy rules to improve control accuracy.

[0058] In this embodiment, the fuzzy controller can process complex input data more accurately through the powerful feature extraction ability of deep learning. The deep learning model can adapt to dynamically changing environments and improve the robustness of the fuzzy controller. Reduce manual intervention, automatically generate and adjust fuzzy rules, and improve the automation level of the system. In summary, the integration mechanism of fuzzy controller and deep learning can effectively improve the performance of the control system, and achieve more efficient and intelligent control strategies through the training and dynamic adjustment of deep learning models. This combination can not only handle complex nonlinear problems, but also provide better adaptability and flexibility in practical applications.

[0059] Step S206, controlling the release of the liquid by the humidification device according to the first target control parameter to control the electrical energy generated by the fuel cell.

[0060] Optionally, controlling the release of liquid by the humidifying device includes controlling the release amount of the humidifying device and the release speed.

[0061] The execution subject of the above steps may be a terminal, a server, a specific processor provided in the terminal or the server, or a processor or processing device provided relatively independently from the terminal or the server, or may be the pool robot itself, etc., but is not limited thereto. For example, the execution subject may be a humidification controller provided in the fuel cell system.

[0062] Through the above steps, due to the combination of the fuzzy controller and the target network model, the first control information output by the fuzzy controller is input into the target network model to obtain the first target control parameter output by the target network model; the release of the liquid by the humidification device can be controlled according to the first target control parameter to control the electric energy generated by the fuel cell. Thereby, the efficiency of the fuel cell system can be significantly improved, the self-optimization of parameters is achieved, and the accuracy of parameter adjustment is improved. Therefore, the problem of low accuracy and efficiency in adjusting the humidifier in the fuel cell in the related art can be solved.

[0063] In an exemplary embodiment, obtaining first control information output by a fuzzy controller includes: obtaining first system parameters of a fuel cell system through a plurality of sensing devices, wherein the first system parameters include: actual humidity of a proton exchange membrane in the fuel cell, target humidity of the proton exchange membrane, humidity change rate of the actual humidity of the proton exchange membrane, and performance indicators of the fuel cell; inputting the first system parameters into a fuzzy controller to obtain first control information output by the fuzzy controller, wherein the fuzzy controller outputs the first control information in the following manner: converting the input actual humidity, target humidity, humidity change rate, and performance indicators into fuzzy values ​​respectively to obtain a plurality of input variables; converting the plurality of input variables into a plurality of fuzzy sets, wherein the fuzzy sets include fuzzy linguistic variables; matching the plurality of fuzzy sets with a fuzzy rule base, and calculating the weight of each fuzzy set based on the matching result, wherein the fuzzy rule base defines the relationship between the plurality of fuzzy sets; and outputting the first control information according to the weight of each fuzzy set.

[0064] Optionally, a plurality of sensing devices including but not limited to sensors may be provided in the fuel cell system, for example, a voltage sensor and a current sensor provided in the fuel cell, a temperature sensor provided in the humidification device, etc.

[0065] For example, using a humidity sensor, such as a capacitive or resistive sensor, the humidity of the proton exchange membrane can be measured. The sensor should be installed near the proton exchange membrane or integrated directly into the membrane to ensure accurate measurement. The target humidity of the proton exchange membrane is determined according to the design and operating conditions of the fuel cell. It can be obtained through the fuel cell control software or pre-set parameters. The humidity change rate of the actual humidity of the proton exchange membrane is obtained by continuously monitoring the humidity of the proton exchange membrane and calculating the change between adjacent measured values. A data acquisition system can be set up to record the humidity values ​​regularly and calculate the rate of change using the difference.

[0066] Optionally, the performance indicators of the fuel cell include voltage, current, power output, efficiency, etc. For example, the voltage and current of the fuel cell can be measured using voltage and current sensors, and the power output can be calculated by multiplying the voltage and current.

[0067] Optionally, the fuzzy controller in this embodiment converts the actually measured humidity value into a fuzzy value, such as "low", "medium", or "high". The set target humidity value is also converted into a fuzzy value. The rate of change between the actual humidity and the target humidity is calculated and converted into a fuzzy value, such as "rapid increase", "slow increase", etc. The performance indicators (e.g., energy consumption, response time, etc.) are also converted into fuzzy values.

[0068] Convert the above fuzzy values ​​into fuzzy sets. Each fuzzy set represents the fuzzy state of an input variable, such as "low", "medium", and "high" humidity. The fuzzy rule base contains a series of predefined fuzzy rules that define the relationship between different fuzzy sets. For example, if the actual humidity is "high" and the target humidity is "low", the humidity may need to be reduced. According to the fuzzy rule base, each fuzzy set is matched and the weight of each fuzzy set is calculated. The weight reflects the importance of the fuzzy set in the current control decision. According to the calculated weight, the first control information is output. This control information may be a definition of the rationality of humidity, such as "the current humidity is not good", "the current humidity is poor", etc.

[0069] This embodiment outputs the first control information through the fuzzy controller, so as to achieve the purpose of accurately understanding whether the current humidity is reasonable and adjusting and controlling the humidity in time.

[0070] In an exemplary embodiment, before inputting the first control information into the target network model to obtain the first target control parameter output by the target network model, the method further includes: acquiring multiple sets of training data, wherein each set of training data includes: sample control information and sample control parameters, the sample control information is information calculated by the fuzzy controller based on the sample system parameters of the fuel cell system and used to indicate the rationality of the amount of liquid released by the humidification device, and the sample control parameter is information generated based on the sample control information and used to adjust the amount of liquid released by the humidification device; using the multiple sets of training data to train the initial network model to obtain the target network model, wherein, for each set of training data, the initial network model is used to determine the weights of multiple sub-control parameters included in the sample control parameter based on the sample control information, and adjust the value of the control parameter according to the weights of the multiple sub-control parameters.

[0071] Optionally, the training process of the initial network model in this embodiment includes:

[0072] S1, during the kth training, determining the training data for the kth training, wherein the training data includes historical control parameters and historical control information;

[0073] S2, removing noise and outliers from the training data of the kth training, and performing data standardization or normalization, and converting the processed data into a coding variable matrix;

[0074] S3, select a machine learning model to build a model. The algorithm in the model includes a neural network algorithm;

[0075] S4, train the model using the training dataset and adjust the model parameters to find the best weight distribution;

[0076] S5, use the validation data set to test the performance of the model to ensure that the model has good generalization ability. According to the weight of the model output, adjust the value of the sub-control parameter. For example, if the model shows that a sub-control parameter has a greater impact on the result, then the weight of the parameter can be increased. Apply the adjusted control parameters to the actual system and monitor their effects. According to the results after implementation, iteratively optimize the model and control parameters to continuously improve the system performance.

[0077] In summary, the fuzzy controller in this embodiment first generates corresponding control decisions (for example, humidity level) according to the real-time operating conditions, and the initial network model receives these decision results as the data source for its own training, and automatically adjusts and optimizes the various parameters of the fuzzy controller through learning and simulation of a large amount of historical data, thereby achieving a more efficient closed-loop control process.

[0078] Through the above process, a network model can be systematically established and implemented to optimize control parameters and improve system performance.

[0079] In an exemplary embodiment, the initial network model is trained using multiple sets of training data to obtain a target network model, including: iteratively training the initial network model using the multiple sets of training data until the initial network model is trained a first target number of times, then terminating the training to obtain the target network model; or, when the performance of the fuel cell outputting electrical energy meets a preset performance a second target number of times, then terminating the training to obtain the target network model, wherein the performance of the fuel cell outputting electrical energy is the performance obtained by controlling the control parameters output by the initial network model during the training of the initial network model.

[0080] Optionally, the first target number in this embodiment is a pre-set target number of training iterations, that is, the number of rounds that the model needs to be trained. For example, training is stopped after 1,000 training times. The second target number is the number of times the set model output meets the preset performance indicators. For example, if the sample control parameters output 100 times in a row can make the electric energy output by the fuel cell reach the optimal state, the training can be ended. In addition, when training the model, some initial values ​​with good experience will be set in advance, and through iterative training, the value of the loss function will be monitored. When the loss function reaches a preset threshold, it is considered that the model has been trained and converged. The reference standard for the final model convergence is that the output power of the fuel cell reaches the maximum value and the fuel consumption is the least, that is, the price-performance ratio between fuel and output power reaches the optimal state.

[0081] This embodiment can achieve the purpose of quickly converging the initial network model by setting the first target number and the second target number.

[0082] In an exemplary embodiment, the release of liquid from a humidification device is controlled according to a first target control parameter to control the electrical energy generated by a fuel cell, including: obtaining a proportional control parameter, an integral control parameter and a differential control parameter included in the first target control parameter, wherein the proportional control parameter is used to adjust the response speed of the fuel cell system, the integral control parameter is used to adjust the steady-state error of the fuel cell system, and the differential control parameter is used to adjust the oscillation of the fuel cell system; generating a control instruction using a first humidity deviation value, a proportional control parameter, an integral control parameter and a differential control parameter, wherein the first humidity deviation value is the difference between the target humidity and the actual humidity of the fuel cell; adjusting the opening of a humidifier valve according to a valve opening value included in the control instruction to control the amount of liquid released by the humidification device, wherein the humidifier valve is arranged in the humidifier.

[0083] Optionally, the proportional control parameter, integral control parameter and differential control parameter included in the first target control parameter include but are not limited to Kp, Ki and Kd in the fuzzy controller, which respectively represent proportional, integral and derivative.

[0084] This embodiment needs to adjust the valve according to the quality of humidity, involving the adjustment of parameters of proportional, integral, differential and other regulators to achieve the optimal control state. By setting different proportional constants (K) and integral constants (A), rapid adjustment of system errors and long-term stable control can be achieved. For example, for the "neither good nor bad" result output by the fuzzy controller, the initial network model needs to be able to output the corresponding Kp value based on this result, and the processing process includes steps such as feature extraction and vector conversion, and finally inputs it to the next network layer for classification matching. That is, the initial network model will first perform feature extraction or vector conversion on the "neither good nor bad" result output by the fuzzy controller, and then input the processed data into the model. The model will first optimize the Kp value, keep the other two parameters Ki and Kd unchanged, and achieve optimization by continuously adjusting the Kp value. Until the optimal humidity parameter is reached, this parameter is used to control the opening of the valve.

[0085] like Figure 5 As shown in the figure, the battery voltage decreases as the load weight (i.e., load current) increases, for example, from 0.6 V to 0.4 V. When the load is large, the optimal battery voltage is usually lower and the corresponding current is the largest, forming a slope similar to the shape of a mountain top. By adjusting the input conditions, the battery can be ensured to be in the best condition and provide the highest power output.

[0086] like Figure 6As shown, it is the process of adjusting the first target control parameter in this embodiment. After receiving the system information transmitted by the sensor in the fuel cell system, the fuzzy controller inputs the system information into the fuzzification component 61, the fuzzy rule pool 62 and the defuzzification component 63, and finally obtains the first control information output by the fuzzification component. The first control information is transmitted to the target network model in the humidification controller 36. The target network model outputs the first target control parameter, and transmits the control parameter to the instruction controller 65 to generate a control instruction, and transmits the control instruction to the humidifier to adjust the valve opening of the humidifier. Among them, the sensor is the system information transmitted through the inter-process communication device 64. For example, for the result output by the fuzzy controller "neither good nor bad", the target network model needs to be able to output the corresponding Kp value based on this result, and the processing process includes steps such as feature extraction and vector conversion, and finally inputs it to the next network layer for classification matching. That is, the target network model will first perform feature extraction or vector conversion on the "neither good nor bad" result output by the fuzzy controller, and then input the processed data into the model. The model will first optimize the Kp value, keep the other two parameters Ki and Kd unchanged, and achieve optimization by continuously adjusting the Kp value until the optimal humidity parameter is reached, and then use this parameter to control the opening of the valve.

[0087] In an exemplary embodiment, after adjusting the opening of the humidifier valve according to the control instruction, the method further includes: detecting the humidity of the fuel cell; when a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, superimposing the gain of the proportional control parameter, the gain of the integral control parameter, and the gain of the differential control parameter to obtain superimposed information, and sending the superimposed information to the fuzzy controller;

[0088] Acquire second control information output by the fuzzy controller, wherein the second control information is information calculated by the fuzzy controller based on the superposition information and a second system parameter of the fuel cell system, and is used to indicate the rationality of the amount of liquid released by the humidification device; input the second control information into the target network model to obtain a second target control parameter output by the target network model, wherein the second control parameter is used to control the release of liquid by the humidification device.

[0089] Optionally, after adjusting the opening of the valve of the humidifier, this embodiment needs to determine in real time whether the amount of liquid released by the humidifier can achieve the optimal output of electrical energy of the fuel cell. The acquired second control information is input into the fuzzy controller again, and the target network model is iteratively optimized using the output second control information.

[0090] Optionally, when a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter are superimposed to obtain superimposed information, including: respectively determining the weights of the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter in the target network model, wherein the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter are all weights determined by the target network model based on the first control information; according to the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter, the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter are superimposed to obtain superimposed information.

[0091] Optionally, the gain of the deviation component is superimposed on the output of the fuzzy controller, mainly for fine-tuning the parameters of the fuzzy controller and improving system performance. Among them, the gain of the proportional control parameter is proportional to the second humidity deviation value, that is, the larger the second humidity deviation value, the stronger the control effect. The gain of the integral control parameter is proportional to the accumulated sum of the second humidity deviation values, which helps to eliminate steady-state errors. The gain of the differential control parameter is proportional to the rate of change of the second humidity deviation value, which helps to predict the future trend of the error, thereby reducing overshoot and oscillation.

[0092] Optionally, in the target network model, the weights of the gains of the proportional, integral and differential control parameters may be determined in the following manner: obtaining the first control information output by the fuzzy matrix. Based on the first control information, the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter are calculated to determine the importance of each control parameter in the overall control effect. According to their respective weights, the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter are weighted and summed. The calculated total gain is applied to the fuzzy controller to adjust the input of the target network model.

[0093] The method in this embodiment allows the fuzzy controller to maintain its ability to handle uncertainty and nonlinear problems while also taking advantage of the accuracy of PID control. By fine-tuning the Kp, Ki, and Kd parameters, the response of the controller can be adjusted more finely to achieve better control results.

[0094] In this embodiment, a humidification controller is also provided. Figure 3 As shown, the humidification controller is connected to the humidification device in the fuel cell system to perform the above method steps:

[0095] In this embodiment, a fuel cell system is also provided. Figure 3As shown, the fuel cell system includes: a sensor group, a fuzzy controller 35, and a humidification controller 36 as described above, wherein the sensor group is used to obtain a first system parameter of the fuel cell system; and the fuzzy controller 35 is used to output first control information based on the first system parameter.

[0096] The fuel cell 34 included in the fuel cell system includes but is not limited to a proton exchange membrane fuel cell (PEMFC), which is a device that generates electrical energy through an electrochemical reaction of hydrogen generated by a hydrogen device 31 and oxygen generated by an oxygen device 32. In order to maintain the performance and stability of the PEMFC, the PEMFC requires humidity provided by a humidifier 33 to ensure the conductivity of the proton exchange membrane (PEM) and the activity of the catalytic layer.

[0097] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0098] In this embodiment, a device for controlling a humidification device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0099] Figure 7 is a structural block diagram of an apparatus for controlling a humidification device according to an embodiment of the present application, such as Figure 7 As shown, the device comprises:

[0100] A first acquisition module 72, configured to acquire first control information output by the fuzzy controller, wherein the first control information is information calculated based on a first system parameter of the fuel cell system, and the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, wherein the humidification device is used to humidify the fuel cell in the fuel cell system;

[0101] A first input module 74, configured to input the first control information into a target network model to obtain a first target control parameter output by the target network model;

[0102] The first control module 76 is used to control the release of liquid by the humidification device according to the first target control parameter to control the electrical energy generated by the fuel cell.

[0103] Through this device, by combining the fuzzy controller and the target network model, the first control information output by the fuzzy controller is input into the target network model to obtain the first target control parameter output by the target network model; the release of the liquid by the humidification device can be controlled according to the first target control parameter to control the electric energy generated by the fuel cell. This can significantly improve the efficiency of the fuel cell system, achieve parameter self-optimization, and improve the accuracy of parameter adjustment. Therefore, the problem of low accuracy and efficiency in adjusting the humidifier in the fuel cell in the related art can be solved.

[0104] In an exemplary embodiment, the first acquisition module 72 includes: a first acquisition unit, used to acquire a first system parameter of the fuel cell system through a plurality of sensing devices, wherein the first system parameter includes: the actual humidity of the proton exchange membrane in the fuel cell, the target humidity of the proton exchange membrane, the humidity change rate of the actual humidity of the proton exchange membrane, and the performance index of the fuel cell; a first input unit, used to input the first system parameter into the fuzzy controller to acquire the first control information output by the fuzzy controller, wherein the fuzzy controller outputs the first control information in the following manner: respectively converting the input actual humidity, the target humidity, the humidity change rate and the performance index into fuzzy values ​​to obtain a plurality of input variables; converting the plurality of input variables into a plurality of fuzzy sets, wherein the fuzzy sets include fuzzy linguistic variables; matching the plurality of fuzzy sets with a fuzzy rule base, and calculating the weight of each fuzzy set based on the matching result, wherein the fuzzy rule base defines the relationship between the plurality of fuzzy sets; and outputting the first control information according to the weight of each fuzzy set.

[0105] In an exemplary embodiment, the above-mentioned device also includes: a second acquisition module, which is used to input the first control information into the target network model to obtain multiple groups of training data before obtaining the first target control parameter output by the target network model, wherein each group of the training data includes: sample control information and sample control parameters, the sample control information is information calculated by the fuzzy controller based on the sample system parameters of the fuel cell system, and is used to indicate the rationality of the amount of liquid released by the humidification device, and the sample control parameter is information generated based on the sample control information for adjusting the amount of liquid released by the humidification device; a first training module, which is used to train the initial network model using the multiple groups of training data to obtain the target network model, wherein, for each group of the training data, the initial network model is used to determine the weights of multiple sub-control parameters included in the sample control parameter based on the sample control information, and adjust the value of the control parameter according to the weights of the multiple sub-control parameters.

[0106] In an exemplary embodiment, the above-mentioned first training module includes: a first training unit, which is used to iteratively train the initial network model using the multiple sets of training data until the number of times the initial network model is trained reaches a first target number, and the training is terminated to obtain the target network model; or, when the number of times the performance of the fuel cell outputting electrical energy meets the preset performance reaches a second target number, the training is terminated to obtain the target network model, wherein the performance of the fuel cell outputting electrical energy is the performance obtained by controlling the control parameters output by the initial network model during the training of the initial network model.

[0107] In an exemplary embodiment, the first control module 76 includes: a second acquisition unit, used to acquire the proportional control parameter, the integral control parameter and the differential control parameter included in the first target control parameter, wherein the proportional control parameter is used to adjust the response speed of the fuel cell system, the integral control parameter is used to adjust the steady-state error of the fuel cell system, and the differential control parameter is used to adjust the oscillation of the fuel cell system; a first generation unit, used to generate a control instruction using a first humidity deviation value, the proportional control parameter, the integral control parameter and the differential control parameter, wherein the first humidity deviation value is the difference between the target humidity and the actual humidity of the fuel cell; a first adjustment unit, used to adjust the opening of the humidifier valve according to the valve opening value included in the control instruction to control the release amount of liquid by the humidification device, wherein the humidifier valve is arranged in the humidifier.

[0108] In an exemplary embodiment, the above-mentioned device also includes: a first detection module, which is used to detect the humidity of the fuel cell after adjusting the opening of the humidifier valve according to the control instruction; a first superposition module, which is used to superimpose the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter when a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold value to obtain superposition information, and send the superposition information to the fuzzy controller; a third acquisition module, which is used to obtain second control information output by the fuzzy controller, wherein the second control information is information calculated by the fuzzy controller based on the superposition information and the second system parameter of the fuel cell system, and is used to indicate the rationality of the amount of liquid released by the humidification device; a second input module, which is used to input the second control information into the target network model to obtain the second target control parameter output by the target network model, wherein the second control parameter is used to control the release of liquid by the humidification device.

[0109] In an exemplary embodiment, the above-mentioned first superposition module includes: a first determination unit, used to respectively determine the weights of the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter in the target network model, wherein the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter are all weights determined by the target network model based on the first control information; a first superposition unit, used to superimpose the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter according to the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter to obtain the superposition information.

[0110] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0111] An embodiment of the present application further provides a computer-readable storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0112] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0113] An embodiment of the present application further provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0114] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0115] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0116] An embodiment of the present application further provides another computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0117] The embodiments of the present application also provide a computer program, which includes computer instructions, which are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any one of the above method embodiments.

[0118] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail herein.

[0119] Obviously, those skilled in the art should understand that the above modules or steps of the present application can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that herein, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0120] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling a humidification device, characterized in that: include: Acquire first control information output by the fuzzy controller, wherein the first control information is information calculated based on a first system parameter of the fuel cell system, and the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, and the humidification device is used to humidify the fuel cell in the fuel cell system; Inputting the first control information into a target network model to obtain a first target control parameter output by the target network model; The release of liquid by the humidification device is controlled according to the first target control parameter to control the electrical energy generated by the fuel cell.

2. The method according to claim 1, characterized in that: Obtaining first control information output by the fuzzy controller, including: Acquiring a first system parameter of the fuel cell system through a plurality of sensing devices, wherein the first system parameter includes: an actual humidity of a proton exchange membrane in the fuel cell, a target humidity of the proton exchange membrane, a humidity change rate of the actual humidity of the proton exchange membrane, and a performance index of the fuel cell; The first system parameter is input into the fuzzy controller to obtain the first control information output by the fuzzy controller, wherein the fuzzy controller outputs the first control information in the following manner: the input actual humidity, the target humidity, the humidity change rate and the performance index are converted into fuzzy values ​​respectively to obtain multiple input variables; the multiple input variables are converted into multiple fuzzy sets, wherein the fuzzy sets include fuzzy linguistic variables; the multiple fuzzy sets are matched with a fuzzy rule base, and the weight of each fuzzy set is calculated based on the matching result, wherein the fuzzy rule base defines the relationship between the multiple fuzzy sets; and the first control information is output according to the weight of each fuzzy set.

3. The method according to claim 1, characterized in that Before inputting the first control information into a target network model to obtain a first target control parameter output by the target network model, the method includes: Acquire multiple sets of training data, wherein each set of the training data includes: sample control information and sample control parameters, wherein the sample control information is information calculated by the fuzzy controller based on the sample system parameters of the fuel cell system and is used to indicate the rationality of the amount of liquid released by the humidification device, and the sample control parameters are information generated based on the sample control information and used to adjust the amount of liquid released by the humidification device; The initial network model is trained using the multiple groups of training data to obtain the target network model, wherein, for each group of the training data, the initial network model is used to determine the weights of the multiple sub-control parameters included in the sample control parameters based on the sample control information, and adjust the values ​​of the control parameters according to the weights of the multiple sub-control parameters.

4. The method according to claim 3, characterized in that Using the multiple sets of training data to train the initial network model to obtain the target network model includes: Iteratively training the initial network model using the multiple sets of training data until the number of times the initial network model is trained reaches a first target number, and then terminating the training to obtain the target network model; or, When the performance of the fuel cell outputting electrical energy meets the preset performance for a second target number of times, the training is terminated to obtain the target network model, wherein the performance of the fuel cell outputting electrical energy is the performance obtained by controlling the control parameters output by the initial network model during the training of the initial network model.

5. The method according to claim 1, characterized in that Controlling the release of liquid by the humidification device according to the first target control parameter to control the electrical energy generated by the fuel cell includes: Acquire a proportional control parameter, an integral control parameter, and a differential control parameter included in the first target control parameter, wherein the proportional control parameter is used to adjust a response speed of the fuel cell system, the integral control parameter is used to adjust a steady-state error of the fuel cell system, and the differential control parameter is used to adjust an oscillation of the fuel cell system; generating a control instruction using a first humidity deviation value, the proportional control parameter, the integral control parameter, and the differential control parameter, wherein the first humidity deviation value is a difference between a target humidity and an actual humidity of the fuel cell; The opening of the humidifier valve is adjusted according to the valve opening value included in the control instruction to control the amount of liquid released by the humidifying device, wherein the humidifier valve is arranged in the humidifier.

6. The method according to claim 5, characterized in that After adjusting the opening of the humidifier valve according to the control instruction, the method further includes: detecting the humidity of the fuel cell; When a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, superimposing the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter to obtain superimposed information, and sending the superimposed information to the fuzzy controller; Acquire second control information output by the fuzzy controller, wherein the second control information is information calculated by the fuzzy controller based on the superposition information and a second system parameter of the fuel cell system, and is used to indicate the rationality of the amount of liquid released by the humidification device; The second control information is input into the target network model to obtain a second target control parameter output by the target network model, wherein the second control parameter is used to control the release of liquid by the humidification device.

7. The method according to claim 6, characterized in that When a second humidity deviation value between the humidity and the target humidity is greater than a preset threshold, the gain of the proportional control parameter, the gain of the integral control parameter, and the gain of the differential control parameter are superimposed to obtain superimposed information, including: Respectively determining the weights of the gain of the proportional control parameter, the gain of the integral control parameter, and the gain of the differential control parameter in the target network model, wherein the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter, and the weight of the gain of the differential control parameter are all weights determined by the target network model based on the first control information; According to the weight of the gain of the proportional control parameter, the weight of the gain of the integral control parameter and the weight of the gain of the differential control parameter, the gain of the proportional control parameter, the gain of the integral control parameter and the gain of the differential control parameter are superimposed to obtain the superimposed information.

8. A humidification controller, characterized in that: The humidification controller is connected to a humidification device in a fuel cell system, and the humidification controller is used to execute the method steps described in any one of claims 1-7.

9. A fuel cell system, characterized in that: include: A sensor group, a fuzzy controller, and a humidification controller according to claim 8, wherein the sensor group is used to obtain a first system parameter of the fuel cell system; The fuzzy controller is used to output first control information based on the first system parameter.

10. A device for controlling a humidifying device, characterized in that: include: a first acquisition module, configured to acquire first control information output by the fuzzy controller, wherein the first control information is information calculated based on a first system parameter of the fuel cell system, and the first control information is used to indicate the rationality of the amount of liquid released by the humidification device, wherein the humidification device is used to humidify the fuel cell in the fuel cell system; A first input module, used for inputting the first control information into a target network model to obtain a first target control parameter output by the target network model; The first control module is used to control the release of liquid by the humidification device according to the first target control parameter to control the electrical energy generated by the fuel cell.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 7 are implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program implements the steps of the method described in any one of claims 1 to 7 when executed by a processor.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

Images