Fuel cell excess oxygen ratio control method, system, device and storage medium

Abstract

This invention relates to the field of fuel cell technology, and discloses a method, system, device, and storage medium for controlling the excess oxygen ratio in a fuel cell. The method includes: acquiring the air supply pipe pressure of the air compressor and the stack current of the fuel cell; establishing a fuel cell air supply model; estimating the partial pressures of oxygen and nitrogen at the cathode of the fuel cell using sliding mode control to obtain assessed values ​​for these pressures; calculating the excess oxygen ratio to obtain the actual value; performing model predictive control on the fuel cell air supply model based on a reference sequence of the excess oxygen ratio; and performing fuzzy adaptive PID control on the air compressor voltage based on the air compressor speed output from the model predictive control and the air compressor speed output from the fuel cell air supply model to obtain the air compressor voltage control quantity. This embodiment improves the accuracy of excess oxygen ratio regulation by evaluating the difficult-to-measure partial pressures of oxygen and nitrogen within the fuel cell air supply system using sliding mode control.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and in particular to a method, system, device and storage medium for controlling an excess oxygen ratio of a fuel cell. Background Art

[0002] The air supply system of the proton exchange membrane fuel cell is an important subsystem to ensure the normal operation of the entire fuel cell system. The oxygen excess ratio of the air supply system has an important impact on the performance of the entire system. In the air supply system, affected by the dynamic characteristics of the air compressor and the supply pipeline, there is a time lag in the air supply, and the air supply will lag behind the demand of the stack. This means that when the load current suddenly changes, if the oxygen supply is insufficient, the cathode will be "oxygen hungry", the battery output voltage will drop, the stack will be flooded, and even the life of the fuel cell will be shortened. If the oxygen supply is too large, the parasitic power of the system will increase, reducing the net power output of the stack, resulting in reduced system efficiency, and even excessive internal pressure in the stack, causing unnecessary safety accidents.

[0003] The existing control methods for the excess oxygen ratio of the air supply system include PID control, fuzzy control, neural network control, model predictive control and sliding mode control, etc. PID control has poor control effect on nonlinear systems, fuzzy control design lacks systematicity, neural network control requires a large amount of data for training, model predictive control has a slow response speed, sliding mode control has chattering, and most control strategies do not take into account the actual system state parameters, especially the internal parameters of the fuel cell system (such as cathode oxygen partial pressure and nitrogen partial pressure). Summary of the invention

[0004] The purpose of the present invention is to provide a method, system, device and storage medium for controlling the excess oxygen ratio of a fuel cell to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] In a first aspect, a method for controlling an excess oxygen ratio of a fuel cell is provided, comprising:

[0006] Obtain the air supply pipe pressure of the air compressor and the stack current of the fuel cell;

[0007] The fuel cell air supply model is established according to the electrochemical reaction state variables of the fuel cell;

[0008] The cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell are estimated by a sliding mode control process to obtain an estimated oxygen partial pressure value and an estimated nitrogen partial pressure value;

[0009] The excess oxygen ratio is calculated according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor, and the stack current of the fuel cell to obtain the actual value of the excess oxygen ratio;

[0010] According to the reference sequence of the overoxygen ratio, the fuel cell air supply model is subjected to model predictive control to constrain the speed of the air compressor. According to the air compressor speed output by the model predictive control and the air compressor speed output by the fuel cell air supply model, the air compressor voltage is subjected to fuzzy adaptive PID control to obtain the air compressor voltage control variable.

[0011] Furthermore, the fuel cell air supply model is specifically described as follows:

[0012]

[0013]

[0014]

[0015]

[0016] The representation model of W(x1,x2) is:

[0017]

[0018] The measurable output matrix of the fuel cell air supply model output is:

[0019] y=[y1,y2,y3] T =[y1(x1,x2),x4,y3(x3,x4)] T ;

[0020] The expression model of the excess oxygen ratio of the fuel cell is:

[0021]

[0022] The expression model of PEMFC performance index is:

[0023]

[0024] Wherein, x1 is the cathode oxygen partial pressure, x2 is the cathode nitrogen partial pressure, x3 is the air compressor speed, x4 is the air supply pipe pressure, u is the air compressor voltage, d is the stack current, y3(x3, x4) and W(x1, x2) represent the gas flow rate of the compressor and the gas flow rate of the fuel cell cathode respectively, W O2，in The amount of oxygen supplied to the cathode, W O2，react is the amount of oxygen consumed by the reaction, g is the PEMFC performance index, g1 is the net power of the system, and g2 = λ O2 ,λ O2 is the oxygen excess ratio, y1 is the voltage output of the battery stack, y2 is the gas supply pipe pressure output, y3 is the air compressor flow output, and the parameter c i, i∈{1,…24} are all constants.

[0025] Further, the estimating the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell by the sliding mode control process includes:

[0026] The cathode gas pressure variable is defined according to the cathode oxygen partial pressure and the cathode nitrogen partial pressure, and the expression model of the cathode gas pressure variable is determined according to the mapping relationship among the cathode oxygen partial pressure, the cathode nitrogen partial pressure, the supply pipeline pressure and the air compressor flow in the fuel cell air supply model;

[0027] The supply pipeline pressure and air compressor flow are processed by second-order synovial differential and first-order synovial differential respectively to obtain the pipeline pressure evaluation value and flow evaluation value;

[0028] According to the pipe pressure evaluation value and the flow evaluation value, the expression model of the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value is constructed, and the error of the pipe pressure evaluation value and the error of the flow evaluation value are converged within a limited time, so that the oxygen partial pressure evaluation value converges to the cathode oxygen partial pressure, and the nitrogen partial pressure evaluation value converges to the cathode nitrogen partial pressure.

[0029] Furthermore, the convergence of the error of the pipe pressure evaluation value and the error of the flow evaluation value within a limited time includes:

[0030] The error evaluation model is constructed according to the differential process of synovial differential treatment;

[0031] The error between each pipe pressure evaluation value and the actual pipe pressure differential parameter and the error between each flow evaluation value and the actual flow differential parameter are evaluated through the error evaluation model to obtain the pipe pressure error value and the flow error value;

[0032] In a limited time, each pipe pressure error value and each flow error value converge to the origin;

[0033] The pipe pressure evaluation value includes a pipe pressure estimation value, a first-order differential pipe pressure estimation value and a second-order differential pipe pressure estimation value, and the flow evaluation value includes a flow estimation value and a first-order differential flow estimation value.

[0034] Further, the method of performing model predictive control on the fuel cell air supply model according to the reference sequence of the excess oxygen ratio to constrain the speed of the air compressor includes:

[0035] Converting the fuel cell air supply model into a state space model; wherein the state space model includes control variables, measurable disturbance variables, state variables and output variables;

[0036] Set the change logic of the control variable and the change logic of the measurable interference quantity, and predict the state variable and output variable at the future moment according to the change logic of the control variable and the measurable interference quantity;

[0037] Track the peroxygen ratio reference sequence, solve the optimal control sequence according to the peroxygen ratio reference sequence, and obtain the optimized control objective function;

[0038] The speed of the air compressor is constrained according to the optimization control objective function.

[0039] Furthermore, the change logic of the control variable is: the control variable outside the control time domain remains unchanged and is equal to the value of the last control variable of the control sequence;

[0040] The change logic of the measurable interference amount is: the value of the measurable interference amount at a future moment is equal to the value of the measurable interference amount at a current moment.

[0041] Further, the fuzzy adaptive PID control of the voltage of the air compressor is performed according to the actual value of the air compressor speed and the preset air compressor speed reference value, including:

[0042] The calculation model predicts the difference between the air compressor speed output by the control and the air compressor speed output by the fuel cell air supply model to obtain the speed difference;

[0043] Perform fuzzy processing on the speed difference and the rate of change of the speed difference to obtain fuzzy subsets;

[0044] According to the fuzzy subset and fuzzy control model, the fuzzy matrix table of proportional coefficient, integral coefficient and differential coefficient is designed through fuzzy synthesis reasoning;

[0045] The proportional coefficient, integral coefficient and differential coefficient are corrected online according to the fuzzy matrix table, and the corrected proportional coefficient, integral coefficient and differential coefficient are used to perform PID control operation to obtain the air compressor voltage control quantity used to regulate the air compressor voltage.

[0046] In a second aspect, a fuel cell excess oxygen ratio control system is provided, comprising:

[0047] An acquisition module is used to obtain the air supply pipe pressure of the air compressor and the stack current of the fuel cell;

[0048] A model building module, used for building a fuel cell air supply model according to the electrochemical reaction state variables of the fuel cell;

[0049] An evaluation module, used for estimating the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell through sliding mode control processing to obtain an oxygen partial pressure evaluation value and a nitrogen partial pressure evaluation value;

[0050] The overoxygen ratio calculation module is used to calculate the overoxygen ratio according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor and the stack current of the fuel cell to obtain the actual value of the overoxygen ratio;

[0051] The control module is used to perform model predictive control on the fuel cell air supply model according to a reference sequence of the overoxygen ratio to constrain the speed of the air compressor, and to perform fuzzy adaptive PID control on the voltage of the air compressor according to the air compressor speed output by the model predictive control and the air compressor speed output by the fuel cell air supply model to obtain the air compressor voltage control value.

[0052] According to a third aspect, a computer device is provided, comprising:

[0053] at least one memory;

[0054] at least one processor;

[0055] The memory stores a computer program, and the processor executes the computer program to implement the excess oxygen ratio control method of the fuel cell according to the first aspect.

[0056] In a fourth aspect, a computer storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the method for controlling the excess oxygen ratio of a fuel cell according to the first aspect is implemented.

[0057] The beneficial effects of the present invention are as follows: by establishing a control-oriented fuel cell air supply model and evaluating the oxygen partial pressure and nitrogen partial pressure that are difficult to measure inside the fuel cell air supply system through sliding film control, the accuracy of the system is improved. The controller combines the advantages of model predictive control and fuzzy adaptive PID control, and can quickly and accurately adjust the peroxygen ratio to improve the output power of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a flow chart of the excess oxygen ratio control method of the fuel cell provided by the embodiment of the present disclosure.

[0059] Figure 2 yes Figure 1 Flowchart of step S300 in FIG.

[0060] Figure 3 yes Figure 1 Flowchart of step S330 in .

[0061] Figure 4 yes Figure 1 One of the flowcharts of step S300 in .

[0062] Figure 5 yes Figure 1 Flowchart 2 of step S500 in FIG.

[0063] Figure 6 It is a structural diagram of the excess oxygen ratio control system of the fuel cell provided in the embodiment of the present disclosure.

[0064] Figure 7It is a schematic diagram of the hardware structure of the computer device provided in the embodiment of the present disclosure. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the present invention will be further described below in conjunction with the embodiments and drawings.

[0066] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0067] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0068] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0069] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0070] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0071] First, some nouns involved in this application are analyzed:

[0072] A fuel cell is a power generation device that converts the chemical energy in fuel and oxidant directly into electrical energy through an electrocatalytic reaction on the electrodes. A fuel cell is mainly composed of a proton exchange membrane and a bipolar plate. The proton exchange membrane is the core of the fuel cell. It is a dense functional membrane that selectively transmits protons. Therefore, it is one of the key components of a proton exchange membrane fuel cell (PEMFC). It separates the fuel and oxidant and prevents them from reacting directly. It also acts as a conductive proton to insulate electrons. During the operation of the fuel cell system, the compressor provides air (oxygen) to the fuel cell and is an important part of the fuel cell system.

[0073] The excess oxygen ratio is the ratio of the oxygen supplied by the cathode of the fuel cell stack to the oxygen consumed by the electrochemical reaction.

[0074] Sliding mode control is a special nonlinear control system. The fundamental difference between it and conventional control lies in the discontinuity of control, that is, a switching characteristic that makes the system "structure" change at any time. The key to sliding mode control lies in the selection of sliding surface function and sliding gain. The sliding surface function determines the accuracy of the observation function, and the sliding gain determines the convergence speed of the estimate.

[0075] Model Predictive Control, Model Predictive Control (MPC) is a special type of control. Its current control action is obtained by solving a finite time domain open-loop optimal control problem at each sampling moment. The current state of the process is used as the initial state of the optimal control problem. The optimal control sequence obtained only implements the first control action. This is the biggest difference between it and those algorithms that use pre-calculated control laws. In essence, model predictive control solves an open-loop optimal control problem. Its idea has nothing to do with the specific model, but its implementation is related to the model.

[0076] Fuzzy adaptive PID control is based on the PID algorithm, with error e and error change rate e c As input, fuzzy rules are used for fuzzy reasoning, and the fuzzy matrix table is queried to adjust the parameters to meet the requirements of e and e at different times. c Requirements for self-tuning of PID parameters.

[0077] In the prior art, the control method of the excess oxygen ratio of the fuel cell air supply system is single, such as PID control, fuzzy control, neural network control, model predictive control or sliding mode control. Among them, PID control has poor control effect on nonlinear systems, fuzzy control design lacks systematicity, neural network control requires a large amount of data for training, model predictive control has a slow response speed, sliding mode control has a chattering phenomenon, and most control strategies do not take into account the actual system state parameters, especially the internal parameters of the fuel cell system (such as cathode oxygen partial pressure and nitrogen partial pressure).

[0078] Based on this, the embodiments of the present disclosure propose a method, system, device and storage medium for controlling the excess oxygen ratio of a fuel cell, establish a control-oriented fuel cell air supply model, and evaluate the oxygen partial pressure and nitrogen partial pressure that are difficult to measure inside the fuel cell air supply system through sliding film control, thereby improving the accuracy of the system. The controller combines the advantages of model predictive control and fuzzy adaptive PID control, and can quickly and accurately adjust the excess oxygen ratio to improve the output power of the system.

[0079] Reference Figure 1 According to the first aspect of the embodiments of the present disclosure, the method for controlling the excess oxygen ratio of a fuel cell includes but is not limited to steps S100 to S500.

[0080] Step S100, obtaining the air supply pipe pressure of the air compressor and the stack current of the fuel cell;

[0081] Step S200, establishing a fuel cell air supply model according to the electrochemical reaction state variables of the fuel cell;

[0082] Step S300, estimating the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell through sliding mode control processing to obtain an estimated oxygen partial pressure value and an estimated nitrogen partial pressure value;

[0083] Step S400, calculating the overoxygen ratio according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor, and the stack current of the fuel cell to obtain an actual overoxygen ratio value;

[0084] Step S500, based on the reference sequence of the overoxygen ratio, the fuel cell air supply model is subjected to model predictive control to constrain the speed of the air compressor, and the actual value of the air compressor speed is obtained; based on the actual value of the air compressor speed and a preset air compressor speed reference value, the voltage of the air compressor is subjected to fuzzy adaptive PID control to obtain the air compressor voltage control value.

[0085] In step S100 of some embodiments, the air supply pipe pressure of the air compressor and the stack current of the fuel cell are obtained by collecting signals through sensors.

[0086] In step S200 of some embodiments, the fuel cell air supply model is specifically expressed as:

[0087]

[0088]

[0089]

[0090]

[0091] The expression model of W(x1, x2) is:

[0092]

[0093] The measurable output matrix of the fuel cell air supply model output is:

[0094] y=[y1,y2,y3] T =[y1(x1,x2),x4,y3(x3,x4)] T ;

[0095] The expression model of the excess oxygen ratio of the fuel cell is:

[0096]

[0097] The expression model of PEMFC performance index is:

[0098]

[0099] Where x1 is the cathode oxygen partial pressure, x2 is the cathode nitrogen partial pressure, x3 is the air compressor speed, x4 is the air supply pipe pressure, u is the air compressor voltage, d is the stack current, y3(x3,x4) and W(x1,x2) represent the gas flow rate of the compressor and the gas flow rate of the fuel cell cathode respectively, W O2,in The amount of oxygen supplied to the cathode, W O2,react is the amount of oxygen consumed by the reaction, g is the PEMFC performance index, g1 is the net power of the system, and g2 = λ O2 ,λ O2 is the oxygen excess ratio, y1 is the voltage output of the battery stack, y2 is the gas supply pipe pressure output, y3 is the air compressor flow output, and the parameter c i ,i∈{1,…24} are all constants.

[0100] For parameter c i ,i∈{1,…24}, as shown in Table 1:

[0101]

[0102] Table 1

[0103] The relevant parameter definitions and values ​​in Table 1 are shown in Table 2:

[0104]

[0105] Table 2

[0106] In step S300 of some embodiments, the cathode oxygen partial pressure and cathode nitrogen partial pressure of the fuel cell are estimated by sliding mode control processing. Since the cathode oxygen partial pressure and cathode nitrogen partial pressure of the fuel cell system are difficult to measure using sensors, they need to be estimated by sliding mode control processing. Specifically, the cathode oxygen partial pressure and cathode nitrogen partial pressure can be estimated by a pre-designed sliding mode differentiator and state observer and a representation model of the excess oxygen ratio of the fuel cell. After obtaining the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value, the errors of the partial pressure evaluation value and the nitrogen partial pressure evaluation value are converged to the minimum value, so that relatively accurate cathode oxygen partial pressure and cathode nitrogen partial pressure can be obtained.

[0107] In step S400 of some embodiments, the overoxygen ratio is calculated according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor, and the stack current of the fuel cell to obtain the actual value of the overoxygen ratio. Specifically, the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value obtained by the sliding mode control process, as well as the parameters such as the air supply pipe pressure and the stack current collected by the sensor are substituted into the representation model of the overoxygen ratio of the fuel cell for calculation, and then the actual value of the overoxygen ratio is calculated.

[0108] In step S500 of some embodiments, the fuel cell air supply model is subjected to model predictive control according to a reference sequence of the overoxygen ratio to constrain the numerical range of the air compressor voltage and the overoxygen ratio. Specifically, the fuel cell air supply model is subjected to model predictive control so that the control quantity for controlling the air compressor voltage at future moments can quickly and accurately track the reference sequence of the overoxygen ratio. At the same time, the numerical range of the air compressor voltage and the overoxygen ratio is constrained to avoid outputting unreasonable control quantities that may exceed the system load. Fuzzy adaptive PID control is performed on the air compressor voltage according to the actual value of the overoxygen ratio and a preset reference value of the overoxygen ratio. Specifically, the control quantity for adjusting the air compressor voltage is determined and then subjected to fuzzy adaptive PID control, and the fuzzy control quantity is output to control the air compressor flow rate, thereby achieving the effect of adjusting the overoxygen ratio.

[0109] In some embodiments, Figure 2 As shown, step S300 specifically includes but is not limited to steps S310 to S330.

[0110] Step S310, defining a cathode gas pressure variable according to the cathode oxygen partial pressure and the cathode nitrogen partial pressure, and determining a representation model of the cathode gas pressure variable according to a mapping relationship among the cathode oxygen partial pressure, the cathode nitrogen partial pressure, the supply pipeline pressure, and the air compressor flow in the fuel cell air supply model;

[0111] Step S320, performing second-order synovial differential processing and first-order synovial differential processing on the supply pipeline pressure and the air compressor flow, respectively, to obtain a pipeline pressure evaluation value and a flow evaluation value;

[0112] Step S330, constructing a representation model of the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value according to the tube pressure evaluation value and the flow evaluation value, converging the error of the tube pressure evaluation value and the error of the flow evaluation value within a limited time, so that the oxygen partial pressure evaluation value converges to the cathode oxygen partial pressure, and the nitrogen partial pressure evaluation value converges to the cathode nitrogen partial pressure.

[0113] In step S310 of some embodiments, the process of defining the cathode gas pressure variable according to the cathode oxygen partial pressure and the cathode nitrogen partial pressure and determining the expression model of the cathode gas pressure variable is specifically:

[0114] Define a new variable χ, let χ = ​​x1 + x2 + c2, and deduce from the specific expression of x4 in the above fuel cell air supply model:

[0115]

[0116]

[0117] Further deduction, based on the expression model of cathode gas pressure variable, the expression model of cathode oxygen partial pressure and cathode nitrogen partial pressure is updated as follows:

[0118]

[0119]

[0120] Where, χ is the cathode pressure, is the first-order differential of x1, is the first-order differential of x2, is the first-order differential of x3, is the first-order differential of x4, is the first-order differential of y2, is the second-order differential of y2, is the first-order differential of y3, For y2, The function of y3, For y2, The function of y3, For y2, y3, The first function of For y2, y3, The second function of , the same below.

[0121] In step S320 of some embodiments, the process of performing second-order synovial differential processing on the supply pipeline pressure is specifically:

[0122] Design a second-order sliding mode differentiator. Considering that y2 is a smooth function, the second-order sliding mode differentiator used is as follows:

[0123]

[0124]

[0125]

[0126] Among them, z0, z1, and z2 are y2, , λ0, λ1, λ2 are all positive design parameters, l1 and l2 are attractor design parameters, and satisfy l1>0, l2>0, l1<l2, v0 and v1 represent the internal states of the second-order sliding mode differentiator respectively, the same below.

[0127] Similarly, the process of first-order synovial differential processing of air compressor flow is as follows:

[0128] Design a first-order sliding mode differentiator, considering that y3 is a smooth function, and the first-order sliding mode differentiator used is as follows:

[0129]

[0130]

[0131] Among them, q0 and q1 are y3, , k0 and k1 are both positive design parameters, n1 and n2 are attractor design parameters, and satisfy n1>0, n2>0, n1<n2, w0 and w1 represent the internal states of the first-order sliding mode differentiator respectively, the same below.

[0132] In step S330 of some embodiments, the specific process of constructing the expression model of the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value according to the pipe pressure evaluation value and the flow evaluation value is as follows:

[0133] The specific expressions of cathode oxygen partial pressure and nitrogen partial pressure under the state observer are:

[0134]

[0135]

[0136] in, are the observed values ​​of oxygen partial pressure and nitrogen partial pressure respectively, f3(y2,z1,z2,y3,q1) is the first function about y2,z1,z2,y3,q1, f4(y2,z1,z2,y3,q1) is the second function about y2,z1,z2,y3,q1, and the same below.

[0137] Within a limited time, the errors of each tube pressure evaluation value and the flow evaluation value in the specific expressions of the cathode oxygen partial pressure and nitrogen partial pressure are converged, so that the oxygen partial pressure evaluation value converges to the cathode oxygen partial pressure, the nitrogen partial pressure evaluation value converges to the cathode nitrogen partial pressure, and the oxygen partial pressure evaluation value gradually approaches the actual value of the oxygen partial pressure.

[0138] In some embodiments, Figure 3 As shown, step S330 specifically includes but is not limited to steps S331 to S333.

[0139] Step S331, constructing an error evaluation model according to the differential process of synovial differential processing;

[0140] Step S332, evaluating the error between each pipe pressure evaluation value and the actual pipe pressure differential parameter and the error between each flow evaluation value and the actual flow differential parameter through the error evaluation model to obtain a pipe pressure error value and a flow error value;

[0141] Step S333: Converging each pipe pressure error value and each flow error value to the origin within a limited time.

[0142] The pipe pressure evaluation value includes a pipe pressure estimation value, a first-order differential pipe pressure estimation value and a second-order differential pipe pressure estimation value, and the flow evaluation value includes a flow estimation value and a first-order differential flow estimation value.

[0143] Specifically, the process of constructing the error evaluation model according to the differential process of synovial differential processing is:

[0144] Define the error e0 = z0-y2, The first error system is obtained as:

[0145]

[0146]

[0147]

[0148] in, is the first-order differential of e0, is the first-order differential of e1, is the first-order differential of e2, 2 is the third-order differential of y2, the same below.

[0149] The first error system is stable in finite time, and the error will converge to the origin in finite time.

[0150] Define the error δ0 = q0-y3, The second error system is obtained as:

[0151]

[0152]

[0153] in, is the first-order differential of δ0, is the first-order differential of δ1, is the second-order differential of y3, the same below.

[0154] The first error system and the second error system are stable in finite time. When the error converges to the origin in finite time, the internal states z0, z1, and z2 of the sliding mode differentiator can accurately estimate y2, The error system is stable in finite time, and the internal states q0 and q1 of the sliding mode differentiator can accurately estimate y3 and The value of .

[0155] Furthermore, z1, z2 and q1 converge to and but Converge to x1 and x2 respectively in finite time.

[0156] In some embodiments, the specific process of calculating the oxygen ratio is based on the observer estimation and The calculation system outputs the oxygen peroxide ratio, and the oxygen peroxide ratio calculation formula is:

[0157]

[0158] In some embodiments, Figure 4 As shown, step S500 specifically includes but is not limited to steps S510 to S540.

[0159] Step S510, converting the fuel cell air supply model into a state space model; wherein the state space model includes control variables, measurable disturbance variables, state variables and output variables;

[0160] Step S520, setting the change logic of the control variable and the change logic of the measurable interference quantity, and predicting the state variable and output variable at a future moment according to the change logic of the control variable and the measurable interference quantity;

[0161] Step S530, tracking the peroxygen ratio reference sequence, solving the optimal control sequence according to the peroxygen ratio reference sequence, and obtaining the optimized control objective function;

[0162] Step S540: constraining the speed of the air compressor according to the optimization control objective function.

[0163] In step S510 of some embodiments, the fuel cell air supply model is converted into a state space model as follows:

[0164] The fuel cell air supply model is linearized at the equilibrium point using the Jacobian matrix, and the state space equation is obtained as follows:

[0165]

[0166] Discretize the above linearized system to get:

[0167]

[0168] Among them, x(k) is the state variable, u(k) is the control variable, d(k) is the measurable disturbance, y(k) is the output variable, A c , B cu , B cd , C c , A, B u , B d and C are parameters of multidimensional matrices, the same below.

[0169] In step S520 of some embodiments, specifically, the change logic of the control variable is: the control variable outside the control time domain remains unchanged and is equal to the value of the last control variable in the control sequence; the change logic of the measurable interference quantity is: the value of the measurable interference quantity at a future moment is equal to the value of the measurable interference quantity at a current moment.

[0170] Furthermore, the change logic of the control variable and the change logic of the measurable disturbance are set, and the state variables and output variables at the future moment are predicted according to the change logic of the control variable and the measurable disturbance. Specifically,

[0171] The following assumptions are made about the control variables and measurable disturbances:

[0172]

[0173] That is, control time domain N c The external control quantity remains unchanged and is equal to the last value of the control sequence; the value of the measurable interference quantity at time k+i remains unchanged and is equal to the value at time k.

[0174] Assume that the control domain N c The time domain control variable U in is:

[0175] U={u(k+1|k),u(k+2|k),...u(k+N c |k)};

[0176] Among them, u(k+N i |k) represents the k+Nthi The control quantity at the moment, i = 1, 2, ..., c, can predict the future k + N according to the current state and the U to be solved p The state quantity and output quantity at the moment are as follows:

[0177]

[0178] Among them, X is the state quantity, Y is the output quantity, and the same applies below.

[0179] In step S530 of some embodiments, the process of solving the optimal control sequence according to the peroxygen ratio reference sequence is specifically as follows:

[0180] Peroxygen ratio reference series R e for:

[0181] R e ={r(k+1), r(k+2),...r(k+N c ), ... r(k+N p )};

[0182] The final system output equation can be simplified to:

[0183] Y=S x x(k)+S u u(k)+S d d(k);

[0184] Among them, S x , S u and S d All are multidimensional matrices;

[0185]

[0186]

[0187]

[0188] Solving the optimal control sequence of the time domain control variable U enables the predicted output to quickly and accurately track the reference peroxygen ratio sequence R e , the objective function of the optimization control is:

[0189]

[0190] Among them, Q is the control output error weight coefficient matrix, R is the control sequence weight coefficient matrix, the same below.

[0191] In step S540 of some embodiments, the air compressor speed and the oxygen ratio are constrained according to the optimization control objective function, specifically:

[0192] The air compressor speed constraint is: 0≤ωcp ≤ω cp_r ;

[0193] The excess oxygen ratio output is constrained to: 1.5≤y(k)≤3;

[0194] Among them, ω cp_r is the rated speed of the air compressor, ω cp is the air compressor speed, ω cp Linearly related to u(k), y(k) is the excess oxygen output, the same below.

[0195] Furthermore, the constrained optimization control problem can be described as a quadratic programming problem, and the general form of quadratic programming is:

[0196] Constraints

[0197] Converting the original objective function into a quadratic programming form yields:

[0198]

[0199] in,

[0200]

[0201] H is the quadratic term matrix in the quadratic programming, A cons is the coefficient matrix of the inequality constraints, A eq is the coefficient matrix, f is the linear term vector in the quadratic programming, f T is the transposed representation of f, B cons and B eq are constraint vectors, l b and u b are the upper and lower bound constraints of U, respectively. T is the transposed representation of U, S u T For S u The transpose representation of Q T is the transposed representation of Q, E err The deviation defined for quadratic programming, the same below.

[0202] In some embodiments, Figure 5 As shown, step S500 specifically includes but is not limited to steps S550 to S580.

[0203] Step S550, calculating the difference between the air compressor speed output by the model prediction control and the air compressor speed output by the fuel cell air supply model to obtain the speed difference;

[0204] Step S560, fuzzifying the speed difference and the rate of change of the speed difference to obtain a fuzzy subset;

[0205] Step S570, designing a fuzzy matrix table of proportional coefficients, integral coefficients and differential coefficients through fuzzy synthesis reasoning according to the fuzzy subsets and the fuzzy control model;

[0206] Step S580, online calibrating the proportional coefficient, integral coefficient and differential coefficient according to the fuzzy matrix table, using the calibrated proportional coefficient, integral coefficient and differential coefficient to perform PID control operation, and obtaining the air compressor voltage control amount for regulating the air compressor voltage.

[0207] In step S550 of some embodiments, the formula for calculating the difference in peroxygen ratio is:

[0208] e(t)=ω cp1 -ω cp2 ;

[0209] Among them, e is the error between the actual value of the air compressor speed and the speed difference, e(t) is the error between the actual value of the air compressor speed and the speed difference at time t, ω cp1 is the air compressor speed output by the model predictive control, ω cp2 It is the air compressor speed output by the fuel cell air supply model, the same below.

[0210] In step S560 of some embodiments, the speed difference and the rate of change of the speed difference are fuzzy processed by converting the speed difference e and the error change rate e into c (error change rate, which can be obtained based on the error at each moment) is input to the fuzzy controller, and the error is calculated based on the different e and e at each moment. c , the fuzzy controller outputs several sets of proportional coefficients k p , integration coefficient k i and the differential coefficient k d , proportionality coefficient k p , integration coefficient k i and the differential coefficient k d After fuzzification processing, the fuzzy subsets are obtained.

[0211] In step S570 of some embodiments, the form of the fuzzy matrix table is as shown in Table 3:

[0212]

[0213] Table 3

[0214] In step S580 of some embodiments, the proportional coefficient, integral coefficient and differential coefficient are corrected online according to the fuzzy matrix table, and the PID control operation is performed using the corrected proportional coefficient, integral coefficient and differential coefficient. Specifically, by querying the fuzzy matrix table, the fuzzy controller outputs the proportional coefficient k p , integration coefficient k i and the differential coefficient k d To the PID controller, the PID controller is based on the input proportional coefficient k p , integration coefficient k i and the differential coefficient k d PID control is performed to output an air compressor voltage control amount for regulating the air compressor voltage, thereby controlling the air compressor voltage and the excess oxygen ratio of the fuel cell system.

[0215] An embodiment of the present invention proposes a method for controlling the excess oxygen ratio of a fuel cell. The accuracy of the system is improved by establishing a control-oriented fuel cell air supply model and evaluating the oxygen partial pressure and nitrogen partial pressure that are difficult to measure inside the fuel cell air supply system through sliding film control. The controller combines the advantages of model predictive control and fuzzy adaptive PID control, and can quickly and accurately adjust the excess oxygen ratio to improve the output power of the system.

[0216] like Figure 6 As shown, the embodiment of the present disclosure provides an excess oxygen ratio control system for a fuel cell, comprising:

[0217] An acquisition module 610 is used to acquire the air supply pipe pressure of the air compressor and the stack current of the fuel cell;

[0218] A model building module 620, for building a fuel cell air supply model according to the electrochemical reaction state variables of the fuel cell;

[0219] An evaluation module 630, configured to estimate the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell through a sliding mode control process to obtain an oxygen partial pressure evaluation value and a nitrogen partial pressure evaluation value;

[0220] The overoxygen ratio calculation module 640 is used to calculate the overoxygen ratio according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor and the fuel cell stack current to obtain the actual value of the overoxygen ratio;

[0221] The control module 650 is used to perform model predictive control on the fuel cell air supply model according to the reference sequence of the overoxygen ratio to constrain the speed of the air compressor, obtain the actual value of the air compressor speed, and perform fuzzy adaptive PID control on the voltage of the air compressor according to the actual value of the air compressor speed and a preset air compressor speed reference value to obtain the air compressor voltage control value.

[0222] The excess oxygen ratio control system of the fuel cell provided in the embodiment of the present disclosure executes the above-mentioned excess oxygen ratio control method of the fuel cell. The specific limitations of the model quantization training device can be found in the above limitations on the excess oxygen ratio control method of the fuel cell, which will not be repeated here.

[0223] Each module in the above-mentioned model quantization training device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0224] The present disclosure also provides an electronic device, including:

[0225] at least one memory;

[0226] at least one processor;

[0227] at least one program;

[0228] The program is stored in the memory, and the processor executes the at least one program to implement the above-mentioned fuel cell oxygen ratio control method implemented in the present disclosure. The electronic device can be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a car computer, etc.

[0229] like Figure 7 As shown, Figure 7 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0230] The processor 710 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present disclosure;

[0231] The memory 720 can be implemented in the form of ROM (Read Only Memory), static storage device, dynamic storage device or RAM (Random Access Memory). The memory 720 can store operating systems and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 720, and the processor 710 is used to call and execute the excess oxygen ratio control method of the fuel cell in the embodiment of the present disclosure;

[0232] Input / output interface 730, used to implement information input and output;

[0233] Communication interface 740, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0234] bus 750 , which transmits information between the various components of the device (e.g., processor 710 , memory 720 , input / output interface 730 , and communication interface 740 );

[0235] The processor 710 , the memory 720 , the input / output interface 730 , and the communication interface 740 are connected to each other in communication within the device via the bus 750 .

[0236] The embodiment of the present disclosure further provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned method for controlling the excess oxygen ratio of a fuel cell.

[0237] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0238] The embodiments described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0239] It can be understood by those skilled in the art that Figures 1 to 6 The technical solutions shown in the figure do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than those shown in the figure, or a combination of certain steps, or different steps.

[0240] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0241] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0242] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0243] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0244] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0245] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0246] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0247] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0248] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the present invention is not limited thereto. The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. In addition, although the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than that shown here.

[0249] A person skilled in the art may implement the present invention in a variety of variations without departing from the scope and essence of the present invention, such as using a feature of one embodiment to obtain another embodiment. The preferred embodiments of the embodiments of the present disclosure are described above with reference to the accompanying drawings, but the scope of rights of the embodiments of the present disclosure is not limited thereby. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the embodiments of the present disclosure shall be within the scope of rights of the embodiments of the present disclosure.

Claims

1. A method for controlling excess oxygen ratio of a fuel cell, characterized in that: include: Obtain the air supply pipe pressure of the air compressor and the stack current of the fuel cell; The fuel cell air supply model is established according to the electrochemical reaction state variables of the fuel cell; The cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell are estimated by sliding mode control processing to obtain an estimated oxygen partial pressure value and an estimated nitrogen partial pressure value; The excess oxygen ratio is calculated according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor, and the stack current of the fuel cell to obtain the actual value of the excess oxygen ratio; According to the reference sequence of the excess oxygen ratio, the fuel cell air supply model is subjected to model predictive control to constrain the speed of the air compressor, and according to the air compressor speed output by the model predictive control and the air compressor speed output by the fuel cell air supply model, the air compressor voltage is subjected to fuzzy adaptive PID control to obtain the air compressor voltage control value; The specific expression of the fuel cell air supply model is: ； ； ； ； The representation model of W(x1,x2) is: ； The measurable output matrix of the fuel cell air supply model output is: ； The expression model of the excess oxygen ratio of the fuel cell is: ； The expression model of PEMFC performance index is: ； Where x1 is the cathode oxygen partial pressure, x2 is the cathode nitrogen partial pressure, x3 is the air compressor speed, x4 is the air supply pipe pressure, u is the air compressor voltage, d is the stack current, y3(x3,x4) and W(x1,x2) represent the gas flow rate of the compressor and the gas flow rate of the fuel cell cathode respectively, W O2,in The amount of oxygen supplied to the cathode, W O2,react is the amount of oxygen consumed by the reaction, g is the PEMFC performance index, g1 is the net power of the system, and g2=λ O2 ,λ O2 is the oxygen excess ratio, y1 is the voltage output of the battery stack, y2 is the gas supply pipe pressure output, y3 is the air compressor flow output, and the parameter c i ,i∈{1 ,…24} are all constants.

2. The method for controlling excess oxygen ratio of a fuel cell according to claim 1, characterized in that: The method of estimating the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell by using the sliding mode control process comprises: The cathode gas pressure variable is defined according to the cathode oxygen partial pressure and the cathode nitrogen partial pressure, and the expression model of the cathode gas pressure variable is determined according to the mapping relationship among the cathode oxygen partial pressure, the cathode nitrogen partial pressure, the supply pipeline pressure and the air compressor flow in the fuel cell air supply model; The supply pipeline pressure and air compressor flow are processed by second-order synovial differential and first-order synovial differential respectively to obtain the pipeline pressure evaluation value and flow evaluation value; According to the pipe pressure evaluation value and the flow evaluation value, the expression model of the oxygen partial pressure evaluation value and the nitrogen partial pressure evaluation value is constructed, and the error of the pipe pressure evaluation value and the error of the flow evaluation value are converged within a limited time, so that the oxygen partial pressure evaluation value converges to the cathode oxygen partial pressure, and the nitrogen partial pressure evaluation value converges to the cathode nitrogen partial pressure.

3. The method for controlling excess oxygen ratio of a fuel cell according to claim 2, characterized in that: The error of the pipe pressure evaluation value and the error of the flow evaluation value that converge within a limited time include: The error evaluation model is constructed according to the differential process of synovial differential treatment; The error between each pipe pressure evaluation value and the actual pipe pressure differential parameter and the error between each flow evaluation value and the actual flow differential parameter are evaluated through the error evaluation model to obtain the pipe pressure error value and the flow error value; In a limited time, each pipe pressure error value and each flow error value converge to the origin; The pipe pressure evaluation value includes a pipe pressure estimation value, a first-order differential pipe pressure estimation value and a second-order differential pipe pressure estimation value, and the flow evaluation value includes a flow estimation value and a first-order differential flow estimation value.

4. The method for controlling excess oxygen ratio of a fuel cell according to claim 1, characterized in that: The method of performing model predictive control on the fuel cell air supply model according to the reference sequence of the excess oxygen ratio to constrain the speed of the air compressor includes: Converting the fuel cell air supply model into a state space model; wherein the state space model includes control variables, measurable disturbance variables, state variables and output variables; Set the change logic of the control variable and the change logic of the measurable interference quantity, and predict the state variable and output variable at the future moment according to the change logic of the control variable and the measurable interference quantity; Track the peroxygen ratio reference sequence, solve the optimal control sequence according to the peroxygen ratio reference sequence, and obtain the optimized control objective function; The speed of the air compressor is constrained according to the optimization control objective function.

5. The method for controlling excess oxygen ratio of a fuel cell according to claim 4, characterized in that: The change logic of the control variable is: the control variable outside the control time domain remains unchanged and equal to the value of the last control variable in the control sequence; The change logic of the measurable interference amount is: the value of the measurable interference amount at a future moment is equal to the value of the measurable interference amount at a current moment.

6. The method for controlling excess oxygen ratio of a fuel cell according to claim 1, characterized in that: The fuzzy adaptive PID control of the air compressor voltage is performed according to the air compressor speed output by the model prediction control and the air compressor speed output by the fuel cell air supply model, including: The calculation model predicts the difference between the air compressor speed output by the control and the air compressor speed output by the fuel cell air supply model to obtain the speed difference; The speed difference and the rate of change of the speed difference are fuzzy processed to obtain fuzzy subsets; According to the fuzzy subset and fuzzy control model, the fuzzy matrix table of proportional coefficient, integral coefficient and differential coefficient is designed through fuzzy synthesis reasoning; The proportional coefficient, integral coefficient and differential coefficient are corrected online according to the fuzzy matrix table, and the corrected proportional coefficient, integral coefficient and differential coefficient are used to perform PID control operation to obtain the air compressor voltage control quantity used to regulate the air compressor voltage.

7. A fuel cell excess oxygen ratio control system, characterized in that: include: An acquisition module is used to obtain the air supply pipe pressure of the air compressor and the stack current of the fuel cell; A model building module, used for building a fuel cell air supply model according to the electrochemical reaction state variables of the fuel cell; An evaluation module, used for estimating the cathode oxygen partial pressure and the cathode nitrogen partial pressure of the fuel cell through sliding mode control processing to obtain an oxygen partial pressure evaluation value and a nitrogen partial pressure evaluation value; The overoxygen ratio calculation module is used to calculate the overoxygen ratio according to the oxygen partial pressure evaluation value, the nitrogen partial pressure evaluation value, the air supply pipe pressure of the air compressor and the stack current of the fuel cell to obtain the actual value of the overoxygen ratio; A control module is used to perform model predictive control on the fuel cell air supply model according to a reference sequence of the excess oxygen ratio to constrain the speed of the air compressor, and to perform fuzzy adaptive PID control on the voltage of the air compressor according to the air compressor speed output by the model predictive control and the air compressor speed output by the fuel cell air supply model to obtain the air compressor voltage control amount; The specific expression of the fuel cell air supply model is: ； ； ； ； The representation model of W(x1,x2) is: ； The measurable output matrix of the fuel cell air supply model output is: ； The expression model of the excess oxygen ratio of the fuel cell is: ； The expression model of PEMFC performance index is: ； Where x1 is the cathode oxygen partial pressure, x2 is the cathode nitrogen partial pressure, x3 is the air compressor speed, x4 is the air supply pipe pressure, u is the air compressor voltage, d is the stack current, y3(x3,x4) and W(x1,x2) represent the gas flow rate of the compressor and the gas flow rate of the fuel cell cathode respectively, W O2,in The amount of oxygen supplied to the cathode, W O2,react is the amount of oxygen consumed by the reaction, g is the PEMFC performance index, g1 is the net power of the system, and g2=λ O2 ,λ O2 is the oxygen excess ratio, y1 is the voltage output of the battery stack, y2 is the gas supply pipe pressure output, y3 is the air compressor flow output, and the parameter c i ,i∈{1 ,…24} are all constants.

8. A computer device, characterized in that: include: at least one memory; at least one processor; The memory stores a computer program, and the processor executes the computer program to implement the method for controlling the excess oxygen ratio of a fuel cell according to any one of claims 1 to 6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the excess oxygen ratio control method of a fuel cell according to any one of claims 1 to 6 is implemented.

Images