T-S fuzzy modeling method and system of solid oxide fuel cell

Abstract

The invention discloses a T-S fuzzy modeling method and system of a solid oxide fuel cell. The method comprises the following steps: analyzing a model structure of a solid oxide fuel cell system; based on a model structure analysis result of the solid oxide fuel cell system, decomposing the solid oxide fuel cell system into five linear sub-models by utilizing an included angle-based gridding and equilibrium decomposition algorithm; converting the five linear sub-models into five segmented radiation models; converting the five segmented radiation models into five fuzzy rules according to a modeling principle of a T-S fuzzy model by taking the hydrogen flow as a prerequisite variable; constructing a corresponding fuzzy membership function according to the five segmented radiation models, and obtaining a T-S fuzzy model of the solid oxide fuel cell through weighted summation in combination with five fuzzy rules; according to the method, the T-S (Takagi-Sugeno) fuzzy model of the solid oxide fuel cell system can be established, so that the SOFC system can be subsequently analyzed and optimized by using a linear analysis method.

Description

Technical Field

[0001] The present invention relates to the technical field of modeling of solid oxide fuel cells for humans, and particularly to a T-S fuzzy modeling method and system for solid oxide fuel cells. Background Art

[0002] Fuel cell technology is the fourth generation of power generation technology after hydraulic power, thermal power, and nuclear power. It has a series of advantages such as high power generation efficiency, fast response speed, low pollution, low noise, and high reliability, bringing revolutionary changes to the energy industry. Among them, in addition to the above advantages, solid oxide fuel cells (SOFCs) also have the advantages of a wide range of fuel applicability, recoverable high-temperature waste heat, a fully solid-state structure, and no use of precious metals. Therefore, it has broad application prospects in the fields of large-scale power generation, distributed power generation, combined heat and power, transportation, and peak shaving energy storage, and is regarded as the new energy power generation technology with the most promising power generation in the 21st century. Vigorously developing solid oxide fuel cell technology will help promote the structural reform of China's energy supply side and drive the energy technology revolution. It lays a technical foundation for achieving the goals of carbon peak and carbon neutrality.

[0003] However, the solid oxide fuel cell system is a very complex non-linear system. It is difficult to accurately establish its model, and it is also difficult to perform subsequent analysis and control on the complex non-linear model. Therefore, it is very important to study a modeling method that is convenient for subsequent analysis and control.

[0004] The information disclosed in this background art section is only intended to increase the understanding of the overall background of the present invention, and should not be regarded as an admission or any form of suggestion that this information constitutes prior art already known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a T-S fuzzy modeling method and system for solid oxide fuel cells, which can accurately establish the T-S (Takagi-Sugeno) fuzzy model of the solid oxide fuel cell system, facilitating subsequent analysis and optimization of the SOFC system using linear analysis methods.

[0006] To achieve the above purpose, the present invention is implemented by the following technical solutions:

[0007] In a first aspect, the present invention provides a T-S fuzzy modeling method for solid oxide fuel cells, including:

[0008] Analyze the model structure of the solid oxide fuel cell system;

[0009] Based on the analysis results of the model structure of the solid oxide fuel cell system, decompose the solid oxide fuel cell system into five linear sub-models using the grid-based and balanced decomposition algorithm based on the included angle;

[0010] Convert five linear sub-models into five piecewise radiation models;

[0011] Taking the hydrogen flow rate as the premise variable, and converting the five piecewise radiation models into five fuzzy rules according to the modeling principle of the T-S fuzzy model;

[0012] Construct the corresponding fuzzy membership function according to the five piecewise radiation models, and combine the five fuzzy rules to obtain the T-S fuzzy model of the solid oxide fuel cell through weighted summation.

[0013] Optionally, taking the output voltage as the scheduling variable of the solid oxide fuel cell system, analyze the model structure of the solid oxide fuel cell system, and the formula is expressed as follows:

[0014]

[0015] Among them, represents the hydrogen input flow rate; are the hydrogen partial pressure, oxygen partial pressure and water vapor partial pressure respectively; represent the derivatives of the hydrogen partial pressure, oxygen partial pressure and water vapor partial pressure respectively; I fc is the current of the fuel cell system; V fc is the output voltage of the fuel cell system; represents the time constant of the hydrogen flow; represents the time constant of the water flow; represents the time constant of the oxygen flow; represents the hydrogen molar constant; K r represents the set constant; represents the water molar constant; represents the oxygen molar constant; r H-O represents the hydrogen-oxygen ratio; represents the number of cells in the stack; E 0 represents the standard cell electromotive force; R represents the universal gas constant; T represents the absolute temperature; F represents the Faraday constant; r represents the ohmic loss.

[0016] Optionally, based on the analysis result of the model structure of the solid oxide fuel cell system, decompose the solid oxide fuel cell system into five linear sub-models by using the grid-based and balanced decomposition algorithm based on the included angle, including:

[0017] Based on the analysis result of the model structure of the solid oxide fuel cell system, that is, on the basis of equations (1) and (2), let y = V fc ;

[0018] Use the grid-based and balanced decomposition algorithm based on the included angle to perform multi-model decomposition on equations (1) and (2) and discretize them to obtain the following five linear sub-models in state-space form:

[0019]

[0020] Among them, k represents time, that is, the k-th moment; A i , B i , C i , D i are the relevant matrices of the linear sub-model, that is, the state-space matrices of the discretized linear sub-model of the solid oxide fuel cell system at the equilibrium point (x 0i , u 0i , y 0i ). x 0i , u 0i , y 0i respectively represent the values of the state variable, input, and output at the i-th equilibrium point, and i represents the sequence number.

[0021] Optionally, convert the five linear sub-models into five piecewise radiation models, where the i-th piecewise radiation model is expressed as follows:

[0022]

[0023] Among them, b i =-A i x 0i -B i u 0i , d i =-C i x 0i -D i u 0i .

[0024] Optionally, use the hydrogen flow rate as the premise variable and convert the five piecewise radiation models into five fuzzy rules according to the modeling principle of the T-S fuzzy model, where the i-th fuzzy rule R i is expressed as follows:

[0025]

[0026] Among them, is the premise variable, also known as the antecedent variable; F i is 's fuzzy universe of discourse, that is, the i-th sub-region corresponding to the i-th piecewise radiation model.

[0027] Optionally, construct the corresponding fuzzy membership functions according to the five piecewise radiation models, including:

[0028] Calculate the slope angle θ of the static input-output curve corresponding to the solid oxide fuel cell system at time k k = actan(K k ); where K k is the slope value of the curve

[0029] Based on the slope angle θ k , calculate the normalized angle between the solid oxide fuel cell system at time k and the i-th piecewise radiation model which is expressed as follows

[0030]

[0031] where, θ max is the maximum angle, that is, the maximum value of the absolute value of the difference between the slope angles of any two points on the static input-output curve

[0032] According to the normalized angle calculate the membership function φ i (k) of the i-th piecewise radiation model at time k, which is expressed as follows

[0033]

[0034] where, k e > 0, is a tuning parameter; and φ i (k) satisfies j represents the sequence number

[0035] Optionally, by combining five fuzzy rules and obtaining the T-S fuzzy model of the solid oxide fuel cell through weighted summation, which is expressed as follows

[0036]

[0037] Second, the present invention provides a T-S fuzzy modeling system for a solid oxide fuel cell, including

[0038] The first processing module analyzes the model structure of the solid oxide fuel cell system

[0039] The second processing module is used to decompose the solid oxide fuel cell system into five linear sub-models by using the angle-based grid and equalization decomposition algorithm based on the analysis result of the model structure of the solid oxide fuel cell system

[0040] The third processing module is used to convert the five linear sub-models into five piecewise radiation models

[0041] The fourth processing module is used to take the hydrogen flow rate as a premise variable and convert five piecewise radiation models into five fuzzy rules according to the modeling principle of the T-S fuzzy model;

[0042] The fifth processing module is used to construct corresponding fuzzy membership functions according to the five piecewise radiation models, and combine the five fuzzy rules to obtain the T-S fuzzy model of the solid oxide fuel cell through weighted summation.

[0043] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0044] The present invention provides a T-S fuzzy modeling method and system for a solid oxide fuel cell. For the nonlinear solid oxide fuel cell (SOFC) system, this method first decomposes it into five linear sub-models by using the angle-based equalization decomposition method, and then converts these five linear sub-models into five piecewise radiation models (PWA) models; secondly, selects the hydrogen flow rate as a premise variable to establish five fuzzy rules for the five PWA models; then constructs fuzzy membership functions for each PWA model by using the angle, and obtains the T-S fuzzy model of the SOFC system through weighted summation. The modeling method provided by the present invention for the SOFC system not only has a high-precision T-S fuzzy model finally established, but also is convenient for subsequent analysis and optimal control. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 The figure shows a schematic flow diagram of the T-S fuzzy modeling method in an embodiment of the present invention;

[0046] Figure 2 The figure shows a schematic diagram of five angle-based fuzzy membership curves in an embodiment of the present invention;

[0047] Figure 3 The figure shows the open-loop model verification of the SOFC system in an embodiment of the present invention, that is, a schematic diagram of the comparison between the system output and the T-S model output;

[0048] Figure 4 The figure shows a schematic diagram of the residual of the open-loop model verification of the SOFC system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be used to limit the protection scope of the present invention.

[0050] Embodiment 1

[0051] As Figure 1 shown, the embodiment of the present invention introduces a T-S fuzzy modeling method for a solid oxide fuel cell, including the following steps:

[0052] S1: Analyze the model structure of the solid oxide fuel cell system;

[0053] S2: Based on the analysis results of the model structure of the solid oxide fuel cell system, decompose the solid oxide fuel cell system into five linear sub-models by using the grid-based and balanced decomposition algorithm based on the included angle;

[0054] S3: Convert the five linear sub-models into five piecewise-radiating models;

[0055] S4: Take the hydrogen flow rate as the premise variable, and convert the five piecewise-radiating models into five fuzzy rules according to the modeling principle of the T-S fuzzy model;

[0056] S5: Construct the corresponding fuzzy membership functions according to the five piecewise-radiating models, and combine the five fuzzy rules to obtain the T-S fuzzy model of the solid oxide fuel cell through weighted summation.

[0057] This embodiment provides a T-S fuzzy modeling method for a solid oxide fuel cell. This method aims at the non-linear solid oxide fuel cell (SOFC) system. First, it decomposes the system into five linear sub-models by using the balanced decomposition method based on the included angle, and then converts these five linear sub-models into five piecewise-radiating (PWA) models. Secondly, it selects the hydrogen flow rate as the premise variable and establishes five fuzzy rules for the five PWA models. Then, it constructs fuzzy membership functions for each PWA model by using the included angle, and obtains the T-S fuzzy model of the SOFC system through weighted summation. The modeling method provided by the present invention not only has a high-precision T-S fuzzy model finally established, but also is convenient for subsequent analysis and optimal control.

[0058] In this embodiment, in step S1, the output voltage is used as the scheduling variable of the solid oxide fuel cell system to analyze the model structure of the solid oxide fuel cell system, and the formula is expressed as follows:

[0059]

[0060] Among them, represents the hydrogen input flow rate; are the hydrogen partial pressure, oxygen partial pressure, and water vapor partial pressure respectively; represent the derivatives of the hydrogen partial pressure, oxygen partial pressure, and water vapor partial pressure respectively; I fc (A) is the current of the fuel cell system; V fc (V) is the output voltage of the fuel cell system; represents the time constant of the hydrogen flow; represents the time constant of the water flow; represents the time constant of the oxygen flow; Denoted as the hydrogen molar constant; K r Denoted as the set constant; Denoted as the water molar constant; Denoted as the oxygen molar constant; r H-O Denoted as the hydrogen-oxygen ratio; Denoted as the number of cells in the stack; E 0 Denoted as the standard cell electromotive force; R is denoted as the universal gas constant; T is denoted as the absolute temperature; F is denoted as the Faraday constant; r is denoted as the ohmic loss.

[0061] In this embodiment, step S2 is based on the model structure analysis result of the solid oxide fuel cell system, and the solid oxide fuel cell system is decomposed into five linear sub-models by using the grid-based and balanced decomposition algorithm based on the included angle, including:

[0062] Based on the model structure analysis result of the solid oxide fuel cell system, that is, equations (1) and (2), let y = V fc ;

[0063] The grid-based and balanced decomposition algorithm based on the included angle is used to perform multi-model decomposition and discretization on equations (1) and (2) to obtain the following five linear sub-models in state-space form:

[0064]

[0065] Among them, k represents time, that is, the kth moment; A i , B i , C i , D i Are the relevant matrices of the linear sub-model, that is, the state-space matrices of the discretized linear sub-model of the solid oxide fuel cell system at the equilibrium point (x 0i , u 0i , y 0i ). x 0i , u 0i , y 0i Respectively represent the values of the state variable, input, and output at the ith equilibrium point, and i represents the sequence number.

[0066] Specifically, the relevant matrices A i , B i , C i , D i Are respectively represented as follows:

[0067] For the first linear sub-model, that is, when i = 1 in the above linear sub-model formula:

[0068] C 1 = [148.9, -8.5, 72.82], D 1 = 0;

[0069] For the second linear sub-model, i.e., when i = 2 in the above linear sub-model formula:

[0070] C 2 = [121.1 -8.5 68.3], D 2 = 0;

[0071] For the third linear sub-model, i.e., when i = 3 in the above linear sub-model formula:

[0072] C 3 = [99.9 -8.5 63.9], D 3 = 0;

[0073] For the fourth linear sub-model, i.e., when i = 4 in the above linear sub-model formula:

[0074] C 4 = [81.9 -8.5 59.0], D 4 = 0;

[0075] For the fifth linear sub-model, i.e., when i = 5 in the above linear sub-model formula:

[0076] C 5 = [65.4 -8.5 53.3], D 5 = 0;

[0077] Specifically, the values of the state variables, inputs, and outputs at the i-th equilibrium point are respectively expressed as:

[0078] The first equilibrium point: x 01 = [0.1414, 2.4811, 0.1446]', u 01 = 0.816, y 01 = 328.3

[0079] The second equilibrium point: x 02 = [0.1738, 2.4811, 0.1541]', u 02 = 0.844, y 02 = 333.3

[0080] The third equilibrium point: x 03 = [0.2109, 2.4811, 0.1649]', u 03= 0.875, y 03 = 338.1

[0081] The fourth equilibrium point: x 04 = [0.2573, 2.4811, 0.1785]', u 04 = 0.914, y 04 = 343.1

[0082] The fifth equilibrium point: x 05 = [0.3221, 2.4811, 0.1974]', u 05 = 0.969, y 05 = 348.9

[0083] In this embodiment, step S3 converts five linear sub-models into five piecewise radiation models, where the i-th piecewise radiation model is expressed as follows:

[0084]

[0085] Where, b i = -A i x 0i -B i u 0i , d i = -C i x 0i -D i u 0i .

[0086] In this embodiment, step S4 takes the hydrogen flow rate as the premise variable and converts the five piecewise radiation models into five fuzzy rules according to the modeling principle of the T-S fuzzy model. The i-th fuzzy rule R i is expressed as follows:

[0087]

[0088] Where, is the premise variable, also known as the antecedent variable; F i is the fuzzy universe of discourse of

[0089] Specifically, the first sub-region corresponding to the first piecewise radiation model: 0.75 ≤ u < 0.828;

[0090] The second sub-region corresponding to the second piecewise radiation model: 0.828 ≤ u < 0.856;

[0091] The third sub-region corresponding to the third piecewise radiation model: 0.856 ≤ u < 0.891;

[0092] The fourth sub-region corresponding to the fourth piecewise radiation model: 0.891 ≤ u < 0.938;

[0093] The fifth sub-region corresponding to the fifth piecewise radiation model: 0.938 ≤ u < 1.

[0094] In this embodiment, step S5 constructs the corresponding fuzzy membership function according to five piecewise radiation models, including:

[0095] Considering that the SOFC system described by equations (1) and (2) has a Hammerstein-Wiener model structure, and its non-linear characteristics can be measured by the included angle, so n grid points are distributed on its static input-output curve. In this embodiment, n = 70 is set.

[0096] Thus, the slope angle θ at any grid point on the static input-output curve of the solid oxide fuel cell (SOFC) system is calculated z = actan(K z ), where That is, the slope at the z-th grid point on the static input-output curve of the SOFC system.

[0097] Furthermore, the included angle between any two points can be obtained according to the following formula:

[0098] θ zj = |θ z - θ j |, 1 ≤ z, j ≤ n

[0099] And the maximum included angle among them is obtained:

[0100]

[0101] Based on the above theory, the slope angle θ of the static input-output curve corresponding to the solid oxide fuel cell system at time k can be calculated first k = actan(K k ); where K k is the slope value of the curve,

[0102] Then, according to the slope angle θ k , the normalized included angle between the solid oxide fuel cell system at time k and the i-th piecewise radiation model is calculated It is expressed as follows:

[0103]

[0104] Among them, θ maxis the maximum included angle, that is, the maximum value of the absolute value of the difference between the slope angles of any two points on the static input-output curve;

[0105] Finally, according to the normalized included angle calculate the membership function φ i (k) of the i-th piecewise radiation model at time k, which is expressed as follows:

[0106]

[0107] where k e > 0, which is a tuning parameter and is equal to 5 here; and φ i (k) satisfies j represents the sequence number.

[0108] Specifically, as Figure 2 shown in the schematic diagram of the curves of the membership functions of the five piecewise radiation models, where MF 1 , MF 2 , MF 3 , MF 4 , MF 5 represent the membership curves of the first, second, third, fourth, and fifth piecewise radiation models respectively;

[0109] In this embodiment, by combining five fuzzy rules and obtaining the T-S fuzzy model of the solid oxide fuel cell through weighted summation, it is expressed as follows:

[0110]

[0111] Embodiment 2

[0112] On the basis of the T-S fuzzy modeling method of the solid oxide fuel cell provided in Embodiment 1, this embodiment provides an example, which is introduced as follows:

[0113] In this embodiment, a pseudo-random binary signal between [0.75, 1] is used to perform open-loop simulation on the T-S fuzzy model and the SOFC system. As Figure 3 shown, y represents the output voltage of the SOFC system under the action of the pseudo-random binary signal, and y m represents the output voltage of the T-S fuzzy model structure under the action of the pseudo-random binary signal; Figure 3 The abscissa of is t (s);

[0114] In Figure 3 On the basis of, the schematic diagram of the model verification residual of the SOFC system under the action of the pseudo-random binary signal as shown in Figure 4 can be obtained. error represents the difference between y and y mThe deviation between them; based on this, the overall root mean square error RMSE = 0.0012 is calculated. Therefore, it can be seen that the fitting degree is very high. So the T-S fuzzy model finally obtained based on the modeling method proposed by the present invention has high accuracy, can well approximate the dynamic characteristics of the SOFC, accurately express the SOFC system, and is convenient for subsequent analysis and optimal control.

[0115] Embodiment 3

[0116] This embodiment provides a T-S fuzzy modeling system for a solid oxide fuel cell, including:

[0117] The first processing module analyzes the model structure of the solid oxide fuel cell system;

[0118] The second processing module is used to decompose the solid oxide fuel cell system into five linear sub-models by using the grid-based and balanced decomposition algorithm based on the included angle according to the analysis result of the model structure of the solid oxide fuel cell system;

[0119] The third processing module is used to convert the five linear sub-models into five piecewise radiation models;

[0120] The fourth processing module takes the hydrogen flow rate as the premise variable and converts the five piecewise radiation models into five fuzzy rules according to the modeling principle of the T-S fuzzy model;

[0121] The fifth processing module is used to construct the corresponding fuzzy membership function according to the five piecewise radiation models, and combine the five fuzzy rules to obtain the T-S fuzzy model of the solid oxide fuel cell through weighted summation.

[0122] Embodiment 4

[0123] This embodiment provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed, it implements the T-S fuzzy modeling method for the solid oxide fuel cell described in Claim Embodiment 1.

[0124] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0126] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified functions in the Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0127] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the spirit of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A TS fuzzy modeling method for solid oxide fuel cells, characterized in that: include: Analyze the model structure of solid oxide fuel cell system; Based on the model structure analysis results of the solid oxide fuel cell system, the solid oxide fuel cell system is decomposed into five linear sub-models using angle-based gridding and balanced decomposition algorithms; The five linear sub-models were converted into five piecewise radial models; Taking hydrogen flow rate as the premise variable, the five segmented radiation models are transformed into five fuzzy rules according to the modeling principle of TS fuzzy model; The corresponding fuzzy membership functions are constructed according to the five segmented radiation models, and the TS fuzzy model of solid oxide fuel cell is obtained by weighted summation combined with five fuzzy rules.

2. The TS fuzzy modeling method for solid oxide fuel cells according to claim 1, characterized in that: The model structure of the solid oxide fuel cell system is expressed as follows: in, Expressed as hydrogen input flow rate; are the partial pressures of hydrogen, oxygen and water vapor respectively; I represents the derivative of hydrogen partial pressure, oxygen partial pressure and water vapor partial pressure respectively; fc is the current of the fuel cell system; V fc is the output voltage of the fuel cell system; Expressed as the time constant of hydrogen flow; Expressed as the time constant of water flow; Expressed as the time constant of oxygen flow; Expressed as the hydrogen molar constant; K r Expressed as a set constant; Expressed as the water molar constant; Expressed as oxygen molar constant; r H-O Expressed as hydrogen-oxygen ratio; It is expressed as the number of batteries in the battery stack; E0 is the standard battery electromotive force; R is the universal gas constant; T is the absolute temperature; F is the Faraday constant; r is the ohmic loss.

3. The TS fuzzy modeling method for solid oxide fuel cells according to claim 2, characterized in that: Based on the model structure analysis results of the solid oxide fuel cell system, the solid oxide fuel cell system is decomposed into five linear sub-models using angle-based gridding and balanced decomposition algorithms, including: Based on the model structure analysis results of the solid oxide fuel cell system, namely, equations (1) and (2), let The angle-based gridding and balanced decomposition algorithm is used to perform multi-model decomposition and discretization on equations (1) and (2) to obtain the following five linear sub-models in the state space form: Among them, k represents time, that is, the kth moment; A i ,B i ,C i ,D i is the correlation matrix of the linear sub-model, that is, the solid oxide fuel cell system at the equilibrium point (x 0i ,u 0i ,y 0i ) is the state space matrix of the discretized linear sub-model, x 0i ,u 0i ,y 0i They represent the values ​​of the state variable, input, and output at the i-th equilibrium point respectively, and i represents the sequence number.

4. The TS fuzzy modeling method for solid oxide fuel cells according to claim 3, characterized in that: The five linear sub-models are converted into five segmented radiation models, wherein the i-th segmented radiation model is expressed as follows: Among them, b i =-A i x 0i -B i in 0i ,d i =-C i x 0i -D i in 0i 。 5. The TS fuzzy modeling method for solid oxide fuel cells according to claim 4, characterized in that: The hydrogen flow rate is taken as the premise variable, and the five segmented radiation models are transformed into five fuzzy rules according to the modeling principle of the TS fuzzy model, wherein the i-th fuzzy rule R i It is expressed as follows: in, is the premise variable, also called the antecedent variable; F i for The fuzzy domain of , that is, the i-th sub-region corresponding to the i-th piecewise radiation model.

6. The TS fuzzy modeling method for solid oxide fuel cells according to claim 5, characterized in that: The corresponding fuzzy membership functions are constructed according to the five segmented radiation models, including: Calculate the slope angle θ of the static input-output curve corresponding to the solid oxide fuel cell system at time k k =actan(K k );K k is the slope of the curve, Based on the slope angle θ k , calculate the normalized angle between the solid oxide fuel cell system at time k and the i-th segment radiation model It is expressed as follows: Among them, θ max is the maximum angle, that is, the maximum value of the absolute value of the difference in slope angle between any two points on the static input-output curve; According to the normalized angle Calculate the membership function φ of the i-th segmented radiation model at time k i (k), which is expressed as follows: Among them, k e >0, is the setting parameter; and φ i (k) Satisfaction j represents the sequence number.

7. The TS fuzzy modeling method for solid oxide fuel cells according to claim 6, characterized in that: The TS fuzzy model of solid oxide fuel cell is obtained by combining the five fuzzy rules through weighted summation, which is expressed as follows:

8. A TS fuzzy modeling system for a solid oxide fuel cell, characterized in that: include: A first processing module analyzes a model structure of a solid oxide fuel cell system; The second processing module is used to decompose the solid oxide fuel cell system into five linear sub-models based on the model structure analysis results of the solid oxide fuel cell system by using an angle-based gridding and balanced decomposition algorithm; a third processing module, for converting the five linear sub-models into five piecewise radial models; The fourth processing module is used to convert the five segmented radiation models into five fuzzy rules based on the modeling principle of the TS fuzzy model, taking the hydrogen flow rate as a premise variable; The fifth processing module is used to construct corresponding fuzzy membership functions according to the five segmented radiation models, and to obtain the TS fuzzy model of the solid oxide fuel cell by weighted summation in combination with the five fuzzy rules.

Images