CN113422088B - Hydrogen fuel cell air supply system and decoupling control method thereof - Google Patents
Hydrogen fuel cell air supply system and decoupling control method thereof Download PDFInfo
- Publication number
- CN113422088B CN113422088B CN202110718075.3A CN202110718075A CN113422088B CN 113422088 B CN113422088 B CN 113422088B CN 202110718075 A CN202110718075 A CN 202110718075A CN 113422088 B CN113422088 B CN 113422088B
- Authority
- CN
- China
- Prior art keywords
- fuel cell
- air
- cell stack
- supply system
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04082—Arrangements for control of reactant parameters, e.g. pressure or concentration
- H01M8/04089—Arrangements for control of reactant parameters, e.g. pressure or concentration of gaseous reactants
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04746—Pressure; Flow
- H01M8/04753—Pressure; Flow of fuel cell reactants
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04746—Pressure; Flow
- H01M8/04776—Pressure; Flow at auxiliary devices, e.g. reformer, compressor, burner
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04992—Processes for controlling fuel cells or fuel cell systems characterised by the implementation of mathematical or computational algorithms, e.g. feedback control loops, fuzzy logic, neural networks or artificial intelligence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Abstract
The application discloses a hydrogen fuel cell air supply system and a decoupling control method thereof, wherein the system comprises an air compressor module, a supply pipeline module, a cathode flow field module and an exhaust module which are connected in sequence; the air compressor module is used for obtaining air compressor outlet flow according to air compressor rotating speed and air inlet pressure ratio, and the supply pipeline module is used for obtaining electric pile inlet pressure according to the air compressor outlet flow, the electric pile inlet flow and the pile temperature; the decoupling control method is used for decoupling and controlling the system by establishing and training a fuzzy neural network model, so that the coordinated control of the air inlet flow and the air inlet pressure is realized, the stability of the pressure in the fuel cell stack is ensured, and the rapid response of the stack inlet pressure and the flow can be met when the load changes.
Description
Technical Field
The present application relates to a hydrogen fuel cell air supply system, and more particularly, to a hydrogen fuel cell air supply system and a decoupling control method thereof
Background
In recent years, fossil energy is gradually reduced in the world, hydrogen energy is an important exploration direction for energy transformation, the industrial development momentum is strong, the hydrogen energy becomes a focus of accumulated power in various countries, and the hydrogen energy becomes an important development object in energy revolution due to the advantages of environmental protection and ubiquitous energy. The development of hydrogen energy will advance fuel cell vehicles, and the air supply system is one of the important subsystems, and the quality of the control performance of the air supply system will affect the output quality of the fuel cell stack.
Most current air supply system control strategies focus primarily on flow control based on the excess oxygen ratio by which the stack is brought to a given output power. However, the hydrogen fuel cell engine system is a multi-input multi-output coupled system, the air compressor and the back pressure valve in the air supply system both affect the stack inlet pressure and flow rate, and the air compressor itself also has a coupling relationship between flow rate and pressure, so that under the condition that the two affect each other, how to effectively coordinate and control the stack inlet flow rate and pressure will affect the stack output performance. Meanwhile, when the PEMFC is operated, if the required power is changed, the stack inlet flow and pressure are also changed to meet different power requirements, so that for the air supply system, the realization of the flow and pressure coordinated control not only ensures the stability of the pressure in the stack, but also meets the requirement of the rapid response of the stack inlet pressure and flow when the load changes.
The rotating speed of the air compressor and the opening degree of the back pressure valve have strong influence on the air inlet pressure and the air inlet flow, the air inlet pressure and the air inlet flow have a coupling effect, and how to perform decoupling control directly influences an air supply system.
Disclosure of Invention
The application provides a hydrogen fuel cell air supply system and a decoupling control method thereof, the fuel cell stack air supply system is established, the coupling effect between the fuel cell stack air inlet pressure and the air inlet flow is obtained through the variation characteristics of the fuel cell stack air inlet pressure and the air inlet flow, a fuzzy neural network model is established for decoupling control, the control values of the air compressor rotating speed and the back pressure valve opening degree in the air supply system are obtained, the coordination control of the air inlet flow and the air inlet pressure is realized, the stability of the pressure in the fuel cell stack is ensured, and the quick response of the stack inlet pressure and the flow can be met when the load changes.
In order to achieve the above purpose, the present application provides the following solutions: a hydrogen fuel cell air supply system is used for adjusting the pressure in a cathode cavity of a fuel cell stack and comprises an air compressor module, a supply pipeline module, a cathode flow field module and an exhaust module;
the air compressor module, the supply pipeline module, the cathode flow field module and the exhaust module are connected in sequence;
the air compressor module is used for obtaining the air outlet flow of the air compressor according to the rotating speed of the air compressor and the air inlet pressure ratio, wherein the air inlet pressure ratio is the ratio of the air inlet pressure of the air compressor to the atmospheric pressure;
the supply pipeline module is used for obtaining the inlet pressure of the fuel cell stack according to the outlet flow of the air compressor, the inlet flow of the fuel cell stack and the temperature of the fuel cell stack;
the cathode flow field module is used for obtaining the inlet flow and the outlet flow of the fuel cell stack according to the inlet pressure of the fuel cell stack, the outlet pressure of the fuel cell stack, the coefficient of the fuel cell stack and the oxygen consumption of the fuel cell stack;
and the exhaust module is used for obtaining the outlet pressure of the fuel cell stack according to the outlet flow of the fuel cell stack, the temperature of the fuel cell stack, the flow of the backpressure valve and the inlet pressure ratio.
Preferably, the fuel cell stack coefficient adopts a barard fuel cell stack coefficient.
The exhaust module comprises a backpressure valve unit and an exhaust pipeline unit;
the back pressure valve unit is used for obtaining the flow of the back pressure valve according to the opening degree of the back pressure valve;
and the exhaust pipeline unit is used for obtaining the outlet pressure of the fuel cell stack according to the outlet flow of the fuel cell stack, the temperature of the fuel cell stack, the flow of the backpressure valve and the inlet pressure ratio.
The application also discloses a decoupling control method of the hydrogen fuel cell air supply system, which is used for decoupling control of the hydrogen fuel cell air supply system and comprises the following steps:
establishing and training a fuzzy neural network model, and performing decoupling control on the air supply system through the fuzzy neural network model; the input data of the fuzzy neural network model is the actual physical value of the controlled quantity of the air supply system, and the output data of the fuzzy neural network model is the control value of the controlled quantity of the air supply system; the controlled quantity comprises the rotating speed of the air compressor and the opening degree of the back pressure valve.
Preferably, the fuzzy neural network model comprises an input layer, a membership function layer, a fuzzy inference layer and an output layer;
the input layer is used for receiving the actual physical value;
the membership function layer is used for converting the actual physical value into a fuzzy variable;
the fuzzy inference layer is used for obtaining a fuzzy inference value according to a fuzzy inference rule between the fuzzy variable and the fuzzy inference layer;
and the output layer is used for obtaining the control value according to the fuzzy inference value.
Preferably, the input layer comprises a first input and a second input;
the actual physical values include a clear value of error and a clear value of rate of change; the error clear value enters the fuzzy neural network model through the first input end, and the change rate clear value enters the fuzzy neural network model through the second input end.
Preferably, before the actual physical value enters the fuzzy neural network model, the actual physical value is quantized to obtain a fuzzy physical value.
Preferably, the membership function layer uses a gaussian function to fuzzify and solve the actual physical value to obtain the fuzzy variable.
Preferably, the method for training the fuzzy neural network model comprises: and training the fuzzy neural network model by using an error back propagation algorithm.
The beneficial effect of this application does:
the application discloses a hydrogen fuel cell air supply system and a decoupling control method thereof, wherein the fuel cell air supply system is established through an air compressor module, a supply pipeline module, a cathode flow field module and an exhaust module, the air outlet flow of the air compressor is obtained according to the rotating speed of the air compressor, the inlet pressure of a fuel cell stack is obtained through the supply pipeline module, the inlet and outlet flow of the stack is obtained according to the inlet and outlet pressure, the stack coefficient and the oxygen consumption of the cathode flow field module, the rotating speed of the air compressor and the opening degree of a back pressure valve in the exhaust module are further obtained to have strong influence on the inlet pressure and flow of the fuel cell stack, and the coupling effect between the inlet pressure and the inlet flow of the fuel cell stack is obtained through the variation characteristics of the inlet pressure and the inlet flow of the air supply system; furthermore, a fuzzy neural network model is established and trained aiming at the coupling effect between the intake pressure and the intake flow, the trained fuzzy neural network model is used for decoupling control, the control values of the rotating speed of the air compressor and the opening degree of the back pressure valve in the air supply system are obtained, the coordination control of the intake flow and the intake pressure of the fuel cell stack is realized, the stability of the pressure in the fuel cell stack is ensured, when the load power is changed, the intake flow and the intake pressure can realize quick response, and the efficiency of the hydrogen fuel cell is improved.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a schematic diagram of the composition of a prior art fuel cell air supply apparatus in an embodiment of the present application;
FIG. 2 is a schematic view of a fuel cell air supply system constructed in an embodiment of the present application;
FIG. 3 is a characteristic curve corresponding to the air pressure of the air supply system under the given simulation calculation conditions in the embodiment of the present application;
FIG. 4 is a characteristic curve corresponding to the air flow rate of the air supply system under the given simulation calculation conditions in the embodiment of the present application;
FIG. 5 is a schematic diagram of a fuzzy neural network model decoupling control of an air supply system in an embodiment of the present application;
FIG. 6 is a schematic structural diagram of a fuzzy neural network model in an embodiment of the present application;
fig. 7 is a graph showing the variation of the objective function in the example of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
As shown in fig. 1, the fuel cell air supply apparatus mainly includes a two-stage air filter, an air compressor, a muffler, a cooling device, a humidifier, and a back pressure valve.
The air filter is composed of physical filtration and chemical adsorption, wherein the physical filtration mainly removes particles such as dust, and the chemical adsorption mainly strips harmful gases which are not removed by the physical adsorption. After air cleaner's twofold purification, during clean air was sent into the compressor, the air compressor machine was carried out the pressure boost to the air and is handled in order to reach into heap target pressure, because the air compressor machine adopts the centrifugal pump body, the high-speed rotation of blade can produce huge noise, influences whole car travelling comfort, consequently can connect the muffler in order to eliminate the noise at the rear end of air compressor machine. The air compressor machine also can make the corresponding rise of temperature of air after pressurizeing the air, and too high temperature can reduce the wetness degree of membrane, leads to the membrane to dry and split the damage, influences battery life, and the air after the pressurization needs cooling treatment for the temperature falls to the suitable operating temperature within range of galvanic pile. The air compressor machine not only makes the gas temperature rise, also makes the moisture in the gas evaporate completely simultaneously almost, so need make dry air reach suitable humidity through the humidifier, and suitable humidity can make fuel cell performance promote. And finally, the residual air of the reaction is discharged through a back pressure valve at the outlet of the cathode side, and the gas flow resistance can be adjusted by changing the opening degree of the valve, so that the pressure inside the cathode cavity of the pile is adjusted.
Therefore, the air compressor and the back pressure valve can affect the pressure and flow rate of the fuel cell stack, so that the air compressor and the back pressure valve need to be controlled in a coordinated mode to obtain the proper air inlet flow rate and air inlet pressure of the fuel cell stack.
Based on the above analysis, in the present embodiment, a fuel cell air supply system is established using Simulink for adjusting the pressure inside the cathode chamber of the fuel cell stack, as shown in fig. 2, including an air compressor module, a supply pipe module, a cathode flow field module, and an exhaust module, which are connected in sequence.
The fuel cell air supply system gives two controlled amounts, which are the air compressor rotation speed and the back pressure valve opening, from which the intake air flow and the intake air pressure entering the cell stack are calculated.
The air compressor module is used for obtaining the air outlet flow of the air compressor according to the rotating speed of the air compressor and an air inlet pressure ratio, wherein the air inlet pressure ratio is the ratio of the air inlet pressure of the air compressor to the atmospheric pressure.
The input quantity of the supply pipeline module comprises the air compressor outlet flow, the fuel cell stack inlet flow and the fuel cell stack temperature, and the fuel cell stack inlet pressure is calculated through a state equation.
The cathode flow field module obtains the inlet flow of the fuel cell stack and the outlet flow of the fuel cell stack by calculating the Barrad fuel cell stack coefficient, the inlet pressure of the fuel cell stack, the outlet pressure of the fuel cell stack and the consumed oxygen amount under the current.
The exhaust module comprises a backpressure valve unit and an exhaust pipeline unit; the back pressure valve unit calculates the flow of the back pressure valve through a given back pressure valve opening; the exhaust pipeline unit is similar to the attack pipeline module, and the exhaust pressure of the fuel cell stack is obtained through a state equation.
In the above fuel cell air supply system, the controlled amounts directly related to the operating state of the fuel cell stack include the rotation speed of the air compressor and the opening degree of the back pressure valve, and by changing the settings of both, the variation characteristics of the intake pressure and the intake flow rate of the air supply system can be obtained. As shown in table 1, for the set simulation calculation conditions:
TABLE 1
The results of the response characteristics of the air supply system obtained at this time are shown in fig. 3 and 4, and the flow rate and pressure of the fuel cell stack air supply system entering the stack gradually tend to be stable with the operation of the air compressor and the back pressure valve. When the rotating speed of the air compressor is changed independently at 20s and 40s, the pressure and the flow entering the electric pile are correspondingly improved along with the increase of the rotating speed, and are reduced along with the decrease of the rotating speed. This is because the rotational torque of the air compressor is increased to increase the rotational speed, thereby driving the flow velocity of the air to increase and increasing the outlet flow of the air compressor. When the opening degree of the back pressure valve is changed independently at 60s and 80s, the inflow air flow changes correspondingly with the increase and decrease of the opening degree, but the change of the inflow air pressure is opposite to the change of the inflow air flow, because the resistance of the gas flowing out of the cathode of the stack becomes smaller along with the increase of the opening degree of the back pressure valve, the speed of the flowing gas is increased, and meanwhile, the flow rate of the flowing gas becomes larger due to the reduction of the flow resistance. Furthermore, the influence of the rotating speed of the air compressor and the opening degree of the back pressure valve on the air inlet pressure and the air inlet flow can be obtained, and the coupling effect between the air inlet pressure and the air inlet flow is reflected.
Aiming at the characteristics, the decoupling control method of the fuel cell air supply system is established, the fuzzy neural network model is established and trained, and the decoupling control is carried out on the air supply system through the fuzzy neural network model; the input data of the fuzzy neural network model is the actual physical value of the controlled quantity of the air supply system, and the output data of the fuzzy neural network model is the control value of the controlled quantity of the air supply system; the controlled quantity comprises the rotating speed of the air compressor and the opening degree of the back pressure valve.
As shown in fig. 5, it is a schematic diagram of a decoupling structure of the fuzzy neural network used in the method.
Two fuzzy neural network model decoupling control loops are adopted to respectively control the rotating speed of an air compressor and the opening degree of a back pressure valve of the air supply system, so that the adjustment of air pressure and flow is realized. In this embodiment, MATLAB is used to build a fuzzy neural network decoupling model of the air supply system, where the Simulink model of the system above needs to be converted into a difference equation, as follows:
where k is the current number of samples, y 1 As a flow output value, y 2 As the pressure output value, u 1 For the speed of rotation of the air compressor u 2 Is the opening degree of the back pressure valve.
As shown in fig. 6, the dotted line frame is the fuzzy neural network model adopted in this embodiment, which is a four-layer network with two inputs and one output, and the error e between the set value and the actual output value and the error change rate e thereof -1 By a quantization factor k 1 、k 2 Convert both to input variable x on the fuzzy domain 1 、x 2 (ii) a Mu and alpha are respectively a second layer and a third layer of the fuzzy neural network, a ij Is the central value of the Gaussian function, b ij Scale factors that are gaussian functions; w is the connection weight between the third layer and the fourth layer.
The first layer is an input layer, and the input layer inputs the actual physical value of the controlled quantity of the system and is divided into a first input end and a second input end.
The second layer is a membership function layer set according to reality, each node converts an input variable into a fuzzy linguistic variable in a fuzzy rule through a membership function, such as NB, PO, and the like, that is, the membership function of each linguistic variable is calculated to obtain the membership degree of the linguistic variable belonging to the fuzzy set, so that the input language which can be identified by a fuzzy control algorithm is realized, and the embodiment adopts a gaussian function to perform fuzzification solution:
wherein i =1,2, ·, n; j =1,2 i 。
The third layer is a fuzzy inference layer, and each neuron represents a fuzzy inference rule with practical significance. Each node of the layer is connected with only one of m nodes and one of n nodes in the second layer, and m multiplied by n rules are provided, and the output of each rule is the algebraic product of the upper layer Gaussian function connected with each node:
in the formula i 1 ∈{1,2,...,m 1 }；i 2 ∈{1,2,...,m 2 }；i n ∈{1,2,...,m n }；j＝1,2,..,m；m≤m i ，i＝1,2,…,n。
The fourth layer is an output layer, and the fuzzy variables are converted into required physical accurate values by setting connection weights between the three layers and the four layers, so that the clearness calculation is realized:
in the formula, r is the number of output variables y.
In the operation process of the fuzzy neural network, the whole network is continuously adjusted and trained by using an error back propagation algorithm. The quality of the network training result is evaluated by the following objective function formula:
where Y is the desired output, Y is the actual output, and E is the squared error function.
If the value of the objective function is closer to zero, the error of the network is smaller, and if the function value does not reach the predetermined precision, the central value a of the gaussian function needs to be further matched ij Scale factor b of Gaussian function ij And weight w of output layer ij The adjustment is made by the following formula:
where v is the learning rate and λ is the momentum factor.
Therefore, on the basis of determining the decoupling structure of the fuzzy neural network, the initial values of all parameters of the system and the network are set, wherein k is 1 、k 2 、k 3 The input fuzzification and the output fuzzification of the fuzzy neural network are used for adjusting the size of an input value and an output value, namely, the error clearness values of the pressure and the flow and the clearness values of the change rate of the error clearness values are converted into a range in which fuzzy control can be calculated from an actual universe of speaking, and vice versa. In this embodiment, the quantization factor k of the input error signal e in the two decoupled control loops of pressure and flow 1 0.02 and 0.05, respectively, and error change rate e -1 Quantization factor k of 2 Respectively 0.02 and 0.05, and respectively enter the fuzzy neural network model through the first input end and the second input end; the scale factor k corresponding to the output variables of the two 3 The values of (a) and (b) are 0.4 and 1.5 respectively, the learning rates v of the two decoupling controllers are both 0.65, the momentum factor lambda is 0.5, and the training times are 20 times. And comparing the actual pressure and flow output with the set reference input in the training process, continuously adjusting the central value, the scale factor, the output weight and the like of the Gaussian function in the decoupling controller through an error back propagation correction formula (7) by continuous training, and finally enabling the value of the target function formula (6) to reach a preset precision value or the number of times that the system reaches the training to finish the decoupling training.
The change of the objective function in the decoupling process of the fuzzy neural network is shown in fig. 7, after the set value is changed, the value is monotonically decreased and rapidly reduced to be close to a zero value, which indicates the correctness of the selection of each initial value of the fuzzy neural network, so that the system starts to work stably. The fuzzy neural network model decoupling control can continuously adjust the network parameters and the weight value through training, has better adaptability, and realizes the generalized decoupling of pressure and flow.
The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the spirit of the present application should fall within the protection scope defined by the claims of the present application.
Claims (6)
1. The air supply system of the hydrogen fuel cell is characterized by comprising an air compressor module, a supply pipeline module, a cathode flow field module and an exhaust module;
the air compressor module, the supply pipeline module, the cathode flow field module and the exhaust module are connected in sequence;
the air compressor module is used for obtaining the air outlet flow of the air compressor according to the rotating speed of the air compressor and an air inlet pressure ratio, wherein the air inlet pressure ratio is the ratio of the air inlet pressure of the air compressor to the atmospheric pressure;
the supply pipeline module is used for obtaining the inlet pressure of the fuel cell stack according to the outlet flow of the air compressor, the inlet flow of the fuel cell stack and the temperature of the fuel cell stack;
the cathode flow field module is used for obtaining the inlet flow and the outlet flow of the fuel cell stack according to the inlet pressure of the fuel cell stack, the outlet pressure of the fuel cell stack, the coefficient of the fuel cell stack and the oxygen consumption of the fuel cell stack;
the exhaust module is used for obtaining the outlet pressure of the fuel cell stack according to the outlet flow of the fuel cell stack, the temperature of the fuel cell stack, the flow of a back pressure valve and the inlet pressure ratio;
the fuel cell stack coefficient adopts a Brad fuel cell stack coefficient;
the exhaust module comprises a backpressure valve unit and an exhaust pipeline unit;
the back pressure valve unit is used for obtaining the flow of the back pressure valve according to the opening of the back pressure valve;
the exhaust pipeline unit is used for obtaining the outlet pressure of the fuel cell stack according to the outlet flow of the fuel cell stack, the temperature of the fuel cell stack, the flow of the backpressure valve and the inlet pressure ratio;
the hydrogen fuel cell air supply system decoupling method comprises the following steps: establishing and training a fuzzy neural network model, and performing decoupling control on the air supply system through the fuzzy neural network model; the input data of the fuzzy neural network model is the actual physical value of the controlled quantity of the air supply system, and the output data of the fuzzy neural network model is the control value of the controlled quantity of the air supply system; the controlled quantity comprises the rotating speed of the air compressor and the opening degree of the back pressure valve;
the hydrogen fuel cell air supply system mainly comprises a two-stage air filter, an air compressor, a silencer, a cooling device, a humidifier and a back pressure valve;
the air filter consists of physical filtration and chemical adsorption, wherein the physical filtration is used for removing dust particles, and the chemical adsorption is used for stripping harmful gases which are not removed by the physical adsorption;
the silencer is used for eliminating noise generated by the air compressor.
2. The hydrogen fuel cell air supply system according to claim 1, wherein the fuzzy neural network model includes an input layer, a membership function layer, a fuzzy inference layer, and an output layer;
the input layer is used for receiving the actual physical value;
the membership function layer is used for converting the actual physical value into a fuzzy variable;
the fuzzy inference layer is used for obtaining a fuzzy inference value according to a fuzzy inference rule between the fuzzy variable and the fuzzy inference layer;
and the output layer is used for obtaining the control value according to the fuzzy inference value.
3. The hydrogen fuel cell air supply system according to claim 2, wherein the input layer includes a first input and a second input;
the actual physical values include a clear value of error and a clear value of rate of change;
the error clear value enters the fuzzy neural network model through the first input end, and the change rate clear value enters the fuzzy neural network model through the second input end.
4. The hydrogen fuel cell air supply system according to claim 3,
and before the actual physical value enters the fuzzy neural network model, quantizing the actual physical value to obtain a fuzzy physical value.
5. The hydrogen fuel cell air supply system according to claim 2,
and the membership function layer uses a Gaussian function to fuzzify and solve the actual physical value to obtain the fuzzy variable.
6. The hydrogen fuel cell air supply system according to claim 1,
the method for training the fuzzy neural network model comprises the following steps: and training the fuzzy neural network model by using an error back propagation algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110718075.3A CN113422088B (en) | 2021-06-28 | 2021-06-28 | Hydrogen fuel cell air supply system and decoupling control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110718075.3A CN113422088B (en) | 2021-06-28 | 2021-06-28 | Hydrogen fuel cell air supply system and decoupling control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113422088A CN113422088A (en) | 2021-09-21 |
| CN113422088B true CN113422088B (en) | 2023-02-17 |
Family
ID=77717036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110718075.3A Active CN113422088B (en) | 2021-06-28 | 2021-06-28 | Hydrogen fuel cell air supply system and decoupling control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113422088B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110190298A (en) * | 2019-06-03 | 2019-08-30 | 武汉众宇动力系统科技有限公司 | Air supply system and Supply Method for hydrogen fuel cell |
| CN114220999A (en) * | 2021-12-17 | 2022-03-22 | 山东国创燃料电池技术创新中心有限公司 | Air inlet control method, device and system storage medium of fuel cell system |
| CN114857061B (en) * | 2022-04-01 | 2023-06-02 | 西北工业大学 | Modeling and multi-target control method for aviation fuel cell air supply system |
| CN115050996B (en) * | 2022-05-17 | 2023-10-17 | 致瞻科技(上海)有限公司 | Air supply method and air supply system for fuel cell |
| CN114759233B (en) * | 2022-05-24 | 2024-01-26 | 苏州溯驭技术有限公司 | Nitrogen exhaust valve control method suitable for hydrogen fuel system and nitrogen exhaust valve system thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073015A (en) * | 2009-11-20 | 2011-05-25 | 上海济烨能源科技有限公司 | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell |
| CN106022482A (en) * | 2016-05-10 | 2016-10-12 | 东南大学 | Method for decoupling bed temperature and bed pressure of circulating fluidized bed by use of improved fuzzy neural network |
| CN110148768A (en) * | 2018-12-29 | 2019-08-20 | 安徽明天氢能科技股份有限公司 | A kind of air supply control method of fuel cell system |
| CN111948562A (en) * | 2020-08-24 | 2020-11-17 | 南京机电职业技术学院 | Full life cycle monitoring and evaluating system for fuel cell |
| CN112397749A (en) * | 2020-11-16 | 2021-02-23 | 合肥工业大学 | Method and device for controlling cathode and anode pressure balance of proton exchange membrane fuel cell |
| CN112455420A (en) * | 2020-10-23 | 2021-03-09 | 西安交通大学 | Hybrid power system energy control method based on fuzzy neural network |
| CN112736268A (en) * | 2020-12-17 | 2021-04-30 | 华中科技大学 | Control optimization method and system for prolonging service life of SOFC (solid oxide fuel cell) system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040034460A1 (en) * | 2002-08-13 | 2004-02-19 | Folkerts Charles Henry | Powertrain control system |
| US20040253489A1 (en) * | 2003-06-12 | 2004-12-16 | Horgan Thomas J. | Technique and apparatus to control a fuel cell system |
| CN110165248B (en) * | 2019-05-27 | 2020-10-02 | 湖北工业大学 | Fault-tolerant control method for air supply system of fuel cell engine |
-
2021
- 2021-06-28 CN CN202110718075.3A patent/CN113422088B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073015A (en) * | 2009-11-20 | 2011-05-25 | 上海济烨能源科技有限公司 | Spectrum analysis-based online fault diagnosis method of proton exchange membrane fuel cell |
| CN106022482A (en) * | 2016-05-10 | 2016-10-12 | 东南大学 | Method for decoupling bed temperature and bed pressure of circulating fluidized bed by use of improved fuzzy neural network |
| CN110148768A (en) * | 2018-12-29 | 2019-08-20 | 安徽明天氢能科技股份有限公司 | A kind of air supply control method of fuel cell system |
| CN111948562A (en) * | 2020-08-24 | 2020-11-17 | 南京机电职业技术学院 | Full life cycle monitoring and evaluating system for fuel cell |
| CN112455420A (en) * | 2020-10-23 | 2021-03-09 | 西安交通大学 | Hybrid power system energy control method based on fuzzy neural network |
| CN112397749A (en) * | 2020-11-16 | 2021-02-23 | 合肥工业大学 | Method and device for controlling cathode and anode pressure balance of proton exchange membrane fuel cell |
| CN112736268A (en) * | 2020-12-17 | 2021-04-30 | 华中科技大学 | Control optimization method and system for prolonging service life of SOFC (solid oxide fuel cell) system |
Non-Patent Citations (3)
| Title |
|---|
| Decoupling Control Strategy for Cathode System of Proton Exchange Membrane Fuel Cell Engine;Huize Liu等;《Proceedings of the 2020 4th CAA International Conference on Vehicular Control and Intelligence》;20210403;第567-572 * |
| 多变量系统模糊神经网络解耦的研究;平玉环;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20081115(第11期);I140-499 * |
| 燃料电池供给路系统建模与优化控制研究;雷宗坤;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》;20200815(第08期);C035-652 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113422088A (en) | 2021-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113422088B (en) | Hydrogen fuel cell air supply system and decoupling control method thereof | |
| CN111342086B (en) | Fuel cell air oxygen ratio and flow pressure cooperative control method and system | |
| CN109524693B (en) | Model predictive control method for fuel cell air supply system | |
| CN110335646B (en) | Vehicle fuel cell hydrogen peroxide ratio control method based on deep learning-prediction control | |
| JP6430209B2 (en) | Fuel cell stack state diagnosis method and fuel cell system control method | |
| CN113022384B (en) | Fuel cell automobile energy management method based on convex optimization | |
| CN107203137A (en) | The non-linear heuristic Adaptive PID Control method of pump-storage generator governing system gain | |
| Zheng et al. | A study of aero-engine control method based on deep reinforcement learning | |
| CN111860791A (en) | Aero-engine thrust estimation method and device based on similarity transformation | |
| CN113140765A (en) | Fuel cell air inlet flow and pressure decoupling control method and system | |
| CN114857061A (en) | Modeling and multi-target control method of aviation fuel cell air supply system | |
| CN212011145U (en) | Fuel cell with decoupling control | |
| CN112748665A (en) | Hydrogen fuel cell iteration control method and device based on fuzzy Kalman filtering | |
| CN110912185B (en) | Design method of PID controller of automatic power generation control system of power grid containing wind power generation | |
| CN113279997B (en) | Aero-engine surge active control system based on fuzzy switching of controller | |
| CN113326962B (en) | Subway train ATO speed curve prediction method based on BP neural network | |
| CN114970310A (en) | Separator condensation position prediction method based on hybrid simulated annealing algorithm | |
| CN111106371B (en) | Fuel cell air management system and method for acquiring related control signals thereof | |
| Binrui et al. | Temperature control of PEM fuel cell stack application on robot using fuzzy incremental PID | |
| Tong et al. | Real-time simplified variable domain fuzzy control of PEM fuel cell flow systems | |
| Ma et al. | Inverse control for the coordination system of supercritical power unit based on dynamic fuzzy neural network modeling | |
| CN114967423A (en) | Composite temperature control method of fuel cell test system | |
| CN117727977A (en) | Hydrogen fuel cell air flow and humidity MIMO dynamic cooperative control method | |
| CN114036628B (en) | Collaborative design method for variant aircraft wing span and control strategy | |
| CN113219833B (en) | Optimized control method of reverse osmosis membrane group based on optimized pressure self-adaptive compensation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |