Control method of back pressure valve, fuel cell controller and fuel cell system

Abstract

The invention provides a control method of a back pressure valve, a fuel cell controller and a fuel cell system. The control method of the back pressure valve comprises the following steps: acquiring the current actual position of the back pressure valve, and calculating the set position to which the back pressure valve needs to be adjusted according to the load demand condition of a fuel cell system; and calculating a deviation value between the actual position and the set position, calculating a first driving amount and a second driving amount through a fuzzy control algorithm and a PID control algorithm based on the deviation value, and superposing the first driving amount and the second driving amount to obtain a driving signal for controlling the back pressure valve. According to the control method of the back pressure valve, the first driving amount is calculated based on the fuzzy control algorithm according to the deviation value condition between the set position and the actual position of the back pressure valve so as to cope with the condition that the static friction force and the back pressure of the valve need to be overcome when the back pressure valve is started from a static state; therefore, the problem that dead zones exist in the action process of the back pressure valve is solved, and the control effect of the back pressure valve is improved.

Description

Technical Field

[0001] The present invention relates to the field of fuel cell technology, and in particular to a control method for a back pressure valve. In addition, the present invention also relates to a fuel cell controller and a fuel cell system. Background Art

[0002] In the fuel cell system, an air unit is required to supply gas to the stack; a back pressure valve is installed on the exhaust pipe of the air unit. The main function of the back pressure valve is to adjust the back pressure inside the stack during the operation of the fuel cell system. The precise control of the back pressure valve plays an important role in the performance of the fuel cell system. If the back pressure is too low, the performance of the stack may decline, affecting the power generation efficiency; if the back pressure is too high, the power consumption of the air compressor in the air unit may increase, and even cause the air compressor to surge; if the back pressure control is unstable, the pressure difference between the positive and negative electrodes of the stack may be too large, damaging the life of the stack membrane electrode. It is for the above reasons that the precise control of the valve position of the back pressure valve and the rapid response play a very important role in the control of the fuel cell system.

[0003] At present, the position control of the back pressure valve usually adopts an ordinary PID control scheme, that is, the deviation between the set position and the actual position of the back pressure valve is used as the input of the PID controller, and the PID controller outputs a PWM duty cycle to adjust the valve opening.

[0004] In the existing technical solutions, the PWM duty cycle and position of the valve need to have a relatively strict linear relationship, that is, the valve position strictly follows the duty cycle. However, most back pressure valves currently have a very large dead zone, and the valve position may not necessarily change with the duty cycle.

[0005] For valves with dead zones, using ordinary PID controller solutions will cause the valve to respond slowly and lag in action, which will lead to lag and instability in back pressure control.

[0006] The dead zone of the back pressure valve is usually caused by the need to overcome the static friction of the back pressure valve and the actual back pressure currently applied to the valve plate when the back pressure valve is in motion. After the valve starts to move, only a small driving force (only dynamic friction) needs to be provided to control the valve movement. According to the characteristics of the back pressure valve, the control of the back pressure valve needs to consider the following two working conditions:

[0007] Working condition 1: The valve moves from static to moving: This process needs to overcome the valve's own static friction + back pressure;

[0008] Working condition 2: The valve starts to move to the set position: This process requires overcoming the dynamic friction of the valve + back pressure.

[0009] Obviously, under the first working condition, the duty cycle of the valve drive is nonlinearly related to the valve position. If it is adjusted only by an ordinary PID controller, it is easy to cause a lag in the valve response. Summary of the invention

[0010] In view of this, the present invention aims to provide a control method of a back-pressure valve to improve the control effect of the back-pressure valve.

[0011] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0012] A control method for a back-pressure valve comprises: obtaining the current actual position of the back-pressure valve, and calculating the set position to which the back-pressure valve needs to be adjusted according to the load demand of a fuel cell system; calculating the deviation value between the actual position and the set position, and calculating a first driving quantity and a second driving quantity based on the deviation value by using a fuzzy control algorithm and a PID control algorithm respectively, and superimposing the first driving quantity and the second driving quantity to obtain a driving signal for controlling the back-pressure valve.

[0013] Furthermore, the fuzzy control algorithm includes: searching for the first driving quantity corresponding to the deviation value in a preset fuzzy set based on fuzzy control theory.

[0014] Further, the fuzzy set includes a first fuzzy set about the deviation value, a second fuzzy set about the rate of change of the deviation value, and a third fuzzy set about the first driving quantity; the fuzzy control algorithm also includes:

[0015] Based on a set discrete rule, a first discrete value is obtained through the first fuzzy set, and a second discrete value is obtained through the second fuzzy set;

[0016] Under the preset fuzzy control rules, the element values ​​of the third fuzzy set on the physical domain are determined by the first discrete value and the second discrete value, and fuzzy reasoning and inverse fuzzification are performed on the discrete results of the third fuzzy set to obtain the first driving quantity.

[0017] Furthermore, the discrete rule is calculated based on the following formula:

[0018]

[0019]

[0020] Where a is an element of the set; b is the discretized value of element a. When b is a non-integer, it is rounded to the nearest integer. X H represents the upper limit of the physical domain of the set, X LRepresents the lower limit of the physical domain of the set; k in formula 1 is the quantization factor, which is calculated by formula 2.

[0021] Furthermore, the fuzzy reasoning is performed using the Mamdani method, and / or the defuzzification is performed using the maximum membership method.

[0022] Further, the establishment of the first fuzzy set includes: establishing fuzzy sets of negative large-NB, negative small-NS, zero-ZE, positive small-PS, and positive large-PB on the physical domain of the deviation value range;

[0023] The establishment of the second fuzzy set includes: establishing a fuzzy set of negative-N, zero-ZE, and positive-P on the physical domain of the range of the change rate;

[0024] The establishment of the third fuzzy set includes: establishing a fuzzy set of negative large-NB, negative medium-NM, negative small-NS, zero-ZE, positive small-PS, positive medium-PM, and positive large-PB on the physical domain of the range of the first driving amount;

[0025] The fuzzy control rules are determined by querying the following table:

[0026]

[0027] Furthermore, the back pressure valve is an electric valve, and the first driving amount, the second driving amount, and the driving signal are all PWM duty cycle signals.

[0028] Compared with the prior art, the present invention has the following advantages:

[0029] The control method of the back-pressure valve of the present invention, while adopting the PID control algorithm to obtain the second driving quantity for controlling the back-pressure valve, calculates the first driving quantity based on the fuzzy control algorithm according to the deviation value between the set position and the actual position of the back-pressure valve, so as to cope with the situation that the back-pressure valve needs to overcome the static friction force and the back-pressure pressure of the valve itself when starting from a stationary state, thereby improving the problem of dead zone in the operation process of the back-pressure valve, which is beneficial to improving the control effect of the back-pressure valve.

[0030] In addition, based on the test data, reasonable elements are set for each fuzzy set, and a database table suitable for actual control is established. The first driving quantity corresponding to the deviation value can be quickly determined by table lookup, thereby improving the technical calculation efficiency of the control method.

[0031] Another object of the present invention is to provide a fuel cell controller, the fuel cell controller comprising a processor and a memory, the memory storing at least one computer program, the computer program being loaded and executed by the processor to implement the back pressure valve control method of the present invention. The fuel cell controller of the present invention has the technical advantages of the back pressure valve control method described above.

[0032] The present invention further provides a fuel cell system, wherein a back pressure valve is provided in the fuel cell system, and the fuel cell system includes the fuel cell controller described in the present invention.

[0033] Furthermore, the back pressure valve is an electric valve, and the fuel cell controller controls the action of the back pressure valve through a PWM duty cycle signal.

[0034] The fuel cell system of the present invention has the technical advantages possessed by the above-mentioned back pressure valve control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which constitute part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention. The directional terms such as front and back, up and down, etc. involved therein are only used to indicate relative positional relationships and do not constitute improper limitations on the present invention. In the accompanying drawings:

[0036] Figure 1 This is a control flow diagram of a method for controlling a back pressure valve according to Embodiment 1 of the present invention;

[0037] Figure 2 This is a curve comparison diagram of the valve set position and the actual position of the back pressure valve described in Example 1 of the present invention when only PID control is adopted;

[0038] Figure 3 This is a curve comparison diagram of the valve set position and the actual position of the back pressure valve described in Example 1 of the present invention when PID control + fuzzy control is adopted;

[0039] Figure 4 This is a schematic diagram of the system structure of the air unit of the fuel cell system according to the second embodiment of the present invention.

[0040] Description of reference numerals:

[0041] 1. Air filter; 2. Air flow meter; 3. Air compressor; 4. Intercooler;

[0042] 5. Back pressure valve; 50. Bypass valve; 51. Stack entry stop valve;

[0043] 6. Humidifier; 7. Battery stack; T0, first temperature sensor;

[0044] T1, second temperature sensor; T2, stack temperature sensor;

[0045] P1, air inlet pressure sensor; P2, air supply pressure sensor; P3, cathode inlet pressure sensor; P4, cathode outlet pressure sensor. DETAILED DESCRIPTION

[0046] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0047] In the description of the present invention, unless otherwise clearly defined, the terms "installed", "connected", "connection" and "connector" should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, an indirect connection through an intermediate medium, or a connection between the two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in combination with specific circumstances. The limiting terms such as "first, second, A, B, C, D" that appear in the description of the present invention are only for distinguishing similar features of different positions, attributes or uses, so as to achieve the purpose of avoiding ambiguity and confusion in the description, and cannot be understood as indicating or implying relative importance.

[0048] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0049] Embodiment 1

[0050] This embodiment relates to a control method for a back pressure valve, which can improve the control effect of the back pressure valve 5; an exemplary control process is as follows: Figure 1 At the same time, this embodiment also relates to a fuel cell controller.

[0051] In general, the control method of the back pressure valve includes:

[0052] Obtaining the current actual position of the back pressure valve 5, and calculating the set position to which the back pressure valve 5 needs to be adjusted according to the load demand of the fuel cell system;

[0053] The deviation value s between the actual position and the set position is calculated, and based on the deviation value s, the first drive quantity and the second drive quantity are calculated by the fuzzy control algorithm and the PID control algorithm respectively, and the first drive quantity and the second drive quantity are superimposed to obtain a drive signal for controlling the back pressure valve 5.

[0054] The fuel cell controller of this embodiment includes a processor and a memory; wherein at least one computer program is stored in the memory, and the computer program is compiled based on the control method of this embodiment, loaded by the processor, and can be executed to implement the control method of the back pressure valve of this embodiment. Accordingly, the above-mentioned fuzzy control algorithm can be integrated into a fuzzy controller in a processor or a computer program; the above-mentioned PID control algorithm can be integrated into a PID controller in a processor or a computer program; the valve opening of the back pressure valve 5 in the air unit of the fuel cell system is jointly controlled by the fuzzy controller and the PID controller to adjust the back pressure inside the stack during the operation of the fuel cell system.

[0055] Of course, the back pressure valve 5 can be a valve driven by pneumatic, oil pressure or other means. Correspondingly, the driving signal can be a control signal suitable for the driving mechanism. In this embodiment, the back pressure valve 5 is an electric valve, and the first driving amount, the second driving amount and the driving signal are all PWM duty cycle signals. Figure 1 As shown in , the first driving amount is defined as PWM duty cycle_1, the second driving amount is defined as PWM duty cycle_2, and the driving signal is duty.

[0056] Specifically, the fuzzy control algorithm of this embodiment includes: searching for the first driving quantity corresponding to the deviation value s in a preset fuzzy set based on fuzzy control theory. Among them, the fuzzy controller mainly calculates the PWM duty cycle _1 of the valve drive according to different working conditions, while the PID controller calculates the PWM duty cycle _2 of the valve drive according to the position error. The main purpose of the fuzzy controller design is to consider the duty cycle size that needs to be applied to the valve to overcome the static friction, dynamic friction, and back pressure of the valve under different working conditions, while the PID control only calculates the duty cycle size that needs to be applied to the valve according to the position deviation. Through the coordinated control of the two controllers, the accuracy and rapidity of the position control of the back pressure valve under different working conditions can be guaranteed.

[0057] It should be noted that the set position of the back pressure valve 5 is usually calculated based on the load current of the fuel cell system; the actual position of the back pressure valve 5 can be obtained through the position sensor on the back pressure valve 5. The drive signal (duty) is output as the final PWM duty cycle signal through the fuel cell controller (FCU) to drive the valve action. The above-mentioned deviation value s is obtained by calculating the deviation between the set position and the actual position of the back pressure valve 5, and the above-mentioned change rate v is the change rate value of the deviation value s of the back pressure valve 5 based on time.

[0058] After the two input quantities of the deviation value s and the change rate v, and the duty output quantity are determined, fuzzy sets can be established and discretized on their corresponding physical domains. Specifically, the fuzzy sets include a first fuzzy set about the deviation value s, a second fuzzy set about the change rate v of the deviation value s, and a third fuzzy set about the first driving quantity.

[0059] The fuzzy control algorithm specifically includes:

[0060] Based on the set discrete rule, a first discrete value is obtained through a first fuzzy set, and a second discrete value is obtained through a second fuzzy set;

[0061] Under the preset fuzzy control rule, the element value of the third fuzzy set on the physical domain is determined by the first discrete value and the second discrete value, and the discrete result of the third fuzzy set is subjected to fuzzy reasoning and inverse fuzzification to obtain the first driving quantity.

[0062] Specifically, we can first set the range of the deviation value s to [-50 50], and establish the fuzzy sets (first fuzzy sets) of negative large-NB, negative small-NS, zero-ZE, positive small-PS, and positive large-PB on the physical domain. Discretize the domain, set the discrete domain Nx = [-2 -1 0 12], and calculate the set discrete rule based on the following formula (assuming that the discretized value of element a is b):

[0063]

[0064]

[0065] Where a is an element of the set; b is the discretized value of element a. When b is a non-integer, it is rounded to the nearest integer. X H represents the upper limit of the physical domain of the set, X L Represents the lower limit of the physical domain of the set; k in formula 1 is the quantization factor, which is calculated by formula 2.

[0066] Use the tabular representation to make the names of fuzzy sets and domain elements as shown in the following table:

[0067] Nx -2 -1 0 1 2 NB 1 0.5 0 0 0 NS 0.5 1 0.5 0 0 ZE 0 0.5 1 0.5 0 PS 0 0 0.5 1 0.5 PB 0 0 0 0.5 1

[0068] Similarly, set the range of the rate of change v, and establish a fuzzy set (second fuzzy set) of negative-N, zero-ZE, and positive-P on the physical domain. Discretize the domain and set the discrete domain Ny = [-1 0 1]. Set the discrete rule as follows (assuming that the value of element a after discretization is b):

[0069] When a>0, b=-1; when a=0, b=0; when a<0, b=1.

[0070] Use tabular notation to make the names of common sets and domain elements as shown in the following table:

[0071] Ny -1 0 1 N 1 0 0 ZE 0 1 0 P 0 0 1

[0072] Assume that the range of PWM duty cycle output duty is [-9090], and establish the fuzzy set (third fuzzy set) of negative large-NB, negative medium-NM, negative small-NS, zero-ZE, positive small-PS, positive medium-PM, and positive large-PB on this physical domain. Discretize the domain and set the discrete domain Nz = [-3 -2 -1 0 1 2 3]. The discrete rules are the same as those of the deviation value s and the change rate v, and will not be repeated here.

[0073] Use the tabular representation to make the names of fuzzy sets and domain elements as shown in the following table:

[0074] Nz -3 -2 -1 0 1 2 3 NB 1 0.5 0 0 0 0 0 NM 0.5 1 0.5 0 0 0 0 NS 0 0.5 1 0.5 0 0 0 ZE 0 0 0.5 1 0.5 0 0 PS 0 0 0 0.5 1 0.5 0 PM 0 0 0 0 0.5 1 0.5 PB 0 0 0 0 0 0.5 1

[0075] For the deviation value s of the input position and the output PWM duty cycle duty, the membership of different elements to the set can be determined based on actual experience; and for the deviation value s change rate v, since it is a common set, the membership of each element to the set can be uniquely determined. The membership function in the above table can be determined based on experimental data and experience. Based on the test data, reasonable elements are set for each fuzzy set, and a database table suitable for actual control is established. The first driving quantity corresponding to the deviation value s can be quickly determined by table lookup, thereby improving the technical calculation efficiency of the control method.

[0076] Based on the above configuration, the fuzzy control rules can adopt the following principles:

[0077] For the deviation value s, the following rule can be determined: when the deviation is large, a larger driving force is required for the valve of the back pressure valve 5; when the deviation is small, a smaller driving force is required for the valve of the back pressure valve 5.

[0078] For the change rate v, the following rule can be determined: when the change rate v is 0, the static friction and back pressure of the valve need to be overcome; when the change rate v is greater than or less than 0, the dynamic friction and back pressure of the valve need to be overcome.

[0079] Based on the above, the following fuzzy control rule base is established:

[0080] When the position deviation is positive and the deviation change rate is positive, the drive duty cycle is medium;

[0081] When the position deviation is positive and large and the deviation change rate is zero, the drive duty cycle is positive and large;

[0082] When the position deviation is positive and large and the rate of change of the deviation is negative, the drive duty cycle is positive and medium;

[0083] When the position deviation is positive and small and the deviation change rate is positive, the drive duty cycle is positive and small;

[0084] When the position deviation is positive and small and the deviation change rate is zero, the drive duty cycle is positive and large;

[0085] When the position deviation is small and positive and the rate of change of the deviation is negative, the drive duty cycle is positive and medium;

[0086] When the position deviation is zero, the drive duty cycle is zero;

[0087] When the position deviation is large negative and the deviation change rate is negative, the drive duty cycle is medium negative;

[0088] When the position deviation is large negative and the deviation change rate is zero, the drive duty cycle is large negative;

[0089] When the position deviation is large negative and the deviation change rate is positive, the drive duty cycle is medium negative;

[0090] When the position deviation is small negative and the deviation change rate is negative, the drive duty cycle is small negative;

[0091] When the position deviation is small negative and the deviation change rate is zero, the drive duty cycle is large negative;

[0092] When the position deviation is small negative and the deviation change rate is positive, the drive duty cycle is medium negative;

[0093] The above fuzzy rules are expressed in a table as follows:

[0094]

[0095] For the actual fuzzy controller input, the CRI table lookup method (Compositional Rule of Inference, abbreviated as CRI) or the Mamdani method (Mamdani fuzzy reasoning method) is usually used to obtain the fuzzy set of the output quantity. Then the output set is defuzzified to obtain a unique output. The defuzzification method usually uses the maximum membership method, the left-take-largest and right-take-largest methods, and the center of gravity method. In this embodiment, the fuzzy controller preferably uses the Mamdani method for fuzzy reasoning and the maximum membership method for defuzzification. The above two algorithms can be implemented with reference to the prior art and will not be repeated in this embodiment.

[0096] Figure 2 A curve comparison diagram of the valve set position and the actual position of the back pressure valve 5 when only PID control is adopted is shown; Figure 3 The figure shows the curve comparison of the valve setting position and the actual position of the back pressure valve 5 under the condition of PID control + fuzzy control. Figure 2 and 3 In the figure, A represents the actual position of the back pressure valve 5, and B represents the set position of the back pressure valve 5. By comparing the two figures, it can be seen that when only the PID controller is used, when the set position of the back pressure valve 5 changes, due to the valve dead zone characteristics, the PID controller needs to gradually accumulate to overcome the static friction, which causes the valve response to lag significantly. After adding the fuzzy controller, the fuzzy controller directly outputs the duty cycle of the static friction, dynamic friction and back pressure that need to be overcome according to the position deviation and the position deviation change rate, and the valve responds quickly without obvious lag.

[0097] To sum up, the control method of the back-pressure valve in this embodiment, while adopting the PID control algorithm to obtain the second driving quantity for controlling the back-pressure valve 5, calculates the first driving quantity based on the fuzzy control algorithm according to the deviation value s between the set position and the actual position of the back-pressure valve 5, so as to cope with the situation that the back-pressure valve 5 needs to overcome the static friction force and back pressure of the valve itself when starting from a stationary state, thereby improving the problem of dead zone in the operation process of the back-pressure valve 5, which is beneficial to improving the control effect of the back-pressure valve 5.

[0098] Embodiment 2

[0099] This embodiment relates to a fuel cell system, an exemplary system structure of an air unit thereof is as follows: Figure 4 The fuel cell system adopts the fuel cell controller provided in the first embodiment, and adopts the back pressure valve control method of the first embodiment to control the action of the back pressure valve 5 .

[0100] Furthermore, the back pressure valve 5 of the present embodiment is an electric valve, and accordingly, the fuel cell controller drives the back pressure valve 5 to operate through a PWM duty cycle signal.

[0101] like Figure 4 As shown in FIG, the outside air passes through the air filter 1 and the air flow meter 2 to reach the air compressor 3, and after being pressurized by the air compressor 3, passes through the intercooler 4 to reach the humidifier 6, and then enters the fuel cell stack 7 through the stack entry stop valve 51. The gas of the fuel cell stack 7 is discharged through the exhaust pipeline, and the exhaust pipeline is provided with a back pressure valve 5. A bypass pipeline can also be provided between the outlet of the intercooler 4 and the exhaust pipeline, and a bypass valve 50 is provided on the bypass pipeline. Among them, the air filter 1 is mainly used to filter gases in the air that are harmful to the fuel cell stack; the air flow meter 2 is used to measure the air flow rate entering the fuel cell stack at the front end of the air compressor; the air compressor 3 is the core component of the air unit of the fuel cell system, and mainly controls the air flow rate entering the fuel cell stack; the intercooler 4 is used to reduce the air temperature after the compressor; the humidifier 6 humidifies the air to prevent the air entering the fuel cell stack from being too dry; the stack entry shut-off valve 51 is used to control whether the air should enter the fuel cell stack, and the back pressure valve 5 controls the back pressure of the cathode of the fuel cell stack 7 by adjusting the valve opening.

[0102] In order to monitor the temperature and pressure of each part of the gas in the air unit, a first temperature sensor T0 may be provided on the upstream pipeline of the air filter 1, a second temperature sensor T1 and an air inlet pressure sensor P1 may be provided on the pipeline between the air filter 1 and the air flow meter 2, a gas supply pressure sensor P2 may be provided on the outlet pipeline of the intercooler 4, and a stack temperature sensor T2 may be provided on the stack 7. At the same time, the stack 7 of this embodiment is also provided with a cathode inlet pressure sensor P3 and a cathode outlet pressure sensor P4.

[0103] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for controlling a back pressure valve, characterized in that: include: Acquiring the current actual position of the back pressure valve (5), and calculating the set position to which the back pressure valve (5) needs to be adjusted according to the load demand of the fuel cell system; The deviation value between the actual position and the set position is calculated, and based on the deviation value, a first driving quantity and a second driving quantity are calculated by a fuzzy control algorithm and a PID control algorithm respectively, and the first driving quantity and the second driving quantity are superimposed to obtain a driving signal for controlling the back pressure valve (5).

2. The back pressure valve control method according to claim 1, characterized in that: The fuzzy control algorithm includes: searching for the first driving quantity corresponding to the deviation value in a preset fuzzy set based on fuzzy control theory.

3. The back pressure valve control method according to claim 2, characterized in that: The fuzzy set includes a first fuzzy set about the deviation value, a second fuzzy set about the change rate of the deviation value, and a third fuzzy set about the first driving amount; the fuzzy control algorithm also includes: Based on a set discrete rule, a first discrete value is obtained through the first fuzzy set, and a second discrete value is obtained through the second fuzzy set; Under the preset fuzzy control rules, the element values ​​of the third fuzzy set on the physical domain are determined by the first discrete value and the second discrete value, and fuzzy reasoning and inverse fuzzification are performed on the discrete results of the third fuzzy set to obtain the first driving quantity.

4. The back pressure valve control method according to claim 3, characterized in that: The discrete rule is calculated based on the following formula: Where a is an element of the set; b is the discretized value of element a. When b is a non-integer, it is rounded to the nearest integer. X H represents the upper limit of the physical domain of the set, X L Represents the lower limit of the physical domain of the set; k in formula 1 is the quantization factor, which is calculated by formula 2.

5. The back pressure valve control method according to claim 3, characterized in that: The fuzzy reasoning is performed using the Mamdani method, and / or the defuzzification is performed using the maximum membership method.

6. The back pressure valve control method according to claim 3, characterized in that: The establishment of the first fuzzy set includes: establishing fuzzy sets of negative large-NB, negative small-NS, zero-ZE, positive small-PS, and positive large-PB on the physical domain of the deviation value range; The establishment of the second fuzzy set includes: establishing a fuzzy set of negative-N, zero-ZE, and positive-P on the physical domain of the range of the change rate; The establishment of the third fuzzy set includes: establishing a fuzzy set of negative large-NB, negative medium-NM, negative small-NS, zero-ZE, positive small-PS, positive medium-PM, and positive large-PB on the physical domain of the range of the first driving amount; The fuzzy control rules are determined by querying the following table:

7. The method for controlling a back pressure valve according to any one of claims 1 to 6, characterized in that: The back pressure valve (5) is an electric valve, and the first driving amount, the second driving amount, and the driving signal are all PWM duty cycle signals.

8. A fuel cell controller, characterized in that: The fuel cell controller includes a processor and a memory, wherein at least one computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the back pressure valve control method according to any one of claims 1 to 7.

9. A fuel cell system, wherein a back pressure valve (5) is provided in the fuel cell system, characterized in that: The fuel cell system comprises the fuel cell controller according to claim 8.

10. The fuel cell system according to claim 9, characterized in that: The back pressure valve (5) is an electric valve, and the fuel cell controller controls the action of the back pressure valve (5) through a PWM duty cycle signal.

Images