Method for predicting service life of hybrid-driven SOFC (Solid Oxide Fuel Cell) combined heat and power system

Abstract

The invention belongs to the technical field of solid fuel cells, and particularly relates to a hybrid-driven SOFC (Solid Oxide Fuel Cell) combined heat and power system service life prediction method, which comprises establishment of an SOFC system dynamic attenuation model and establishment of a hybrid-driven SOFC system service life prediction model. The service life of the system is predicted by simulating the dynamic attenuation of the SOFC combined heat and power system and performing machine learning, so that the performance of the whole SOFC combined heat and power system is predicted, and the influence of the interaction of each component on the service life of the system under the long-time operation of the system is analyzed. The method is short in test time and high in accuracy, the cost is saved, and the research and development progress is accelerated; an important reference basis is provided for long-life operation of the system, the influence of BOP parts on the whole life of the system can be clearly analyzed, and a direction is pointed out for the long-life operation of the system; and a machine learning method is utilized to avoid accidental results possibly existing in single simulation, so that the results have universality.

Description

Technical Field

[0001] The invention belongs to the technical field of solid fuel cells, and in particular relates to a life prediction method for a hybrid-driven SOFC cogeneration system. Background Art

[0002] As a renewable secondary energy carrier, hydrogen energy is regarded as the cleanest energy with the greatest development potential in the 21st century. As a zero-carbon emission energy carrier, it is gaining more and more attention. Solid oxide fuel cell (SOFC) is a new generation of disruptive power generation technology, a key way to build a new energy security system, and an important tool to achieve the dual carbon goals. Its fuel is hydrogen and oxygen generated directly or indirectly, which react electrochemically inside the battery to generate electricity and a large amount of heat. In order to improve the overall fuel utilization rate, it is necessary to use BOP (Banlance of Plants, BOP) components such as heat exchangers to realize the recovery and utilization of heat. Therefore, in practice, the work of SOFC is often realized in the form of SOFC cogeneration system.

[0003] At present, the prediction research on SOFC life is often focused on the electrochemical decay of the stack itself, without considering that the performance decay of BOP components will change the working environment of the stack and then affect the life of the stack. Therefore, based on the analysis of stack decay, the decay mechanism of typical BOP components is considered to form a dynamic decay model of SOFC cogeneration system. In addition, since the mechanism of SOFC is still unclear, it is impossible to accurately predict the remaining life of the system by relying solely on mathematical models. Therefore, data-driven + model-driven data processing methods are used for machine learning. Based on this, the life prediction of SOFC system can provide important reference for the optimization design of SOFC system and point out the direction for the long-life operation of the system. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a hybrid-driven SOFC cogeneration system life prediction method, which predicts the system life by simulating the dynamic attenuation of the SOFC cogeneration system and performing machine learning, and then predicts the performance of the entire SOFC cogeneration system, and analyzes the impact of the interaction between various components on the system life under long-term operation of the system.

[0005] To achieve the above object, the technical solution adopted by the present invention is: A hybrid-driven SOFC cogeneration system life prediction method includes establishing a SOFC system dynamic decay model and establishing a hybrid-driven SOFC system life prediction model; wherein the establishment of the SOFC system dynamic decay model includes the following steps: S0: Determine the specific process of the SOFC thermoelectric system and the typical BOP components used; S1: Analyze the performance attenuation principle of the battery stack and establish the attenuation model of the battery stack; S2: Analyze the performance attenuation principle of typical BOP components and establish an attenuation model of typical BOP components; S3: Based on the attenuation model, the dynamic attenuation model of the system was built and verified using MATLAB software; S4: Lifespan prediction based on the constructed neural network.

[0006] The life prediction model of the hybrid-driven SOFC system is mainly based on the data results of a large number of different working conditions simulated by the SOFC dynamic attenuation model. The multi-dimensional time series prediction method is combined with the established neural network model for machine learning. After training and verification, the life prediction model of the SOFC system is obtained. The specific steps include: 1) Set different boundary condition parameters to obtain the SOFC system operation data set under different working conditions; 2) Correlation analysis to select parameters that have a greater impact on system life; 3) Build a suitable life prediction neural network model based on the characteristics of SOFC system operation data; 4) Use the collected data set to train and verify the neural network. If the error is within 10%, the model training is defined as successful, and the system life prediction model is obtained.

[0007] Preferably, in step S0, the modeling of the SOFC thermoelectric system mainly considers components such as the SOFC stack, reformer, mixer, water evaporator, heat exchanger, and exhaust gas combustion chamber; the specific SOFC workflow is that the anode side fuel gas passes through a desulfurizer for desulfurization (the sulfur content is not considered in the modeling, and it is assumed that the fuel sulfur content is 0), and after heat exchange in the heat exchanger, enters the mixer to mix with water vapor (assuming that the gas is evenly mixed), and then enters the reformer for reforming, and the reformed gas enters the stack anode.

[0008] Preferably, in step S0, cathode air enters the cathode of the fuel cell stack after heat exchange in a heat exchanger.

[0009] Preferably, in step S0, the tail gas at the anode outlet first enters the tail gas combustion chamber for combustion, and the high-temperature flue gas from the combustion first provides a suitable reaction temperature for the reforming reactor, and then preheats the fuel gas before entering the mixer.

[0010] Preferably, in step S0, the cathode outlet exhaust gas preheats the inlet air.

[0011] Preferably, in step S1, the attenuation of the SOFC stack is mainly considered under continuous operation conditions, and the specific electrochemical attenuation model is: ; ; ; ; ; ; ; ; ; ; c i = k i 72 X [ D P − ( D P + D s ) n ] n D s 2 D P 2 ( 1 − 1 − X 2 ) , i = a , c ; in, is the actual voltage of the SOFC stack, is the number of cells in the battery stack, is the starting voltage of a single cell, is the voltage decay rate, is the fitting coefficient, which is obtained by fitting according to the actual battery performance. is the fuel utilization rate, is the damage variable, is the temperature inside the battery stack, is the ideal operating temperature of the battery stack. is the natural constant 2.718, i is the current density, E N is the Nernst voltage, or ohm is the ohmic loss, or act is the activation loss, or con is the concentration loss, E 0 is the standard potential, F is the Faraday constant (96485C mol -1 ), R is the other universal constant (8.314 J mol -1 K -1 ), p is the gas pressure, R cell is the resistance, i L is the exchange current density, i oais the anodic exchange current density, i oc is the cathode exchange current density, c is the pre-exponential factor corresponding to the exchange current density of the anode and cathode (where the subscript a Indicates anode, subscript with c represents the cathode), P ref is atmospheric pressure, E act,a is the anode activation energy, E act,c is the cathode activation energy, k i is the exchange current density coefficient, X is the ratio of the grain contact neck length to the grain size, D p is the aperture, D s is the grain size, n is the electrode porosity.

[0012] Preferably, in step S1, the temperature, pressure, and composition changes are calculated according to the following equations: ; ; ; ; ; ; in, N out is the outlet molar flow rate, N in is the inlet molar flow rate, R i is the molar reaction rate, N is the molar content in the component, X is the mole fraction, C V is the specific heat at constant volume, R is the universal gas constant, h is the enthalpy, For components i The enthalpy value, is the standard enthalpy of component i at 298.15K.

[0013] Preferably, in step S2, the equations for the temperature, pressure, and composition of typical BOP components are based on the equations in S1.

[0014] Preferably, in step S2, the performance degradation of the heat exchanger is mainly the following equation: ; ; in, Q in To exchange heat, S area is the heat exchange area, h gs is the convective heat transfer coefficient, T _ban is the heat exchange partition temperature, T _hotgas is the heat transfer fluid, F is the heat transfer attenuation coefficient, h ex is the initial convective heat transfer coefficient.

[0015] Preferably, in step S2, multi-level modeling is performed for the chemical reactions occurring inside the reformer, wherein the reactions occurring inside the reformer include: Reforming reaction: ; Water gas shift reaction: ; The reforming reaction is assumed to be completely reformed initially, that is: ; in, r SR is the reforming reaction rate, N fuel,in is the fuel inlet molar flow rate, is the methane concentration at the fuel inlet.

[0016] Then, considering the effect of carbon deposition, the reforming rate is set to decrease gradually over time, where MD (Methane Decomposition reaction) is the methane cracking reaction, and BR (Boundouard reaction) is the reverse Boundouard reaction. The details are as follows: ; ; ; ; ; in, is the reforming reaction activity, is the reformer inlet molar flow rate, is the inlet methane content, is the thermal conductivity, K BR、K MD is the adsorption coefficient, is the carbon deposit concentration (mol / m 3 ), r is the reaction rate (mol / m 3 / s), are the reaction rates of the reverse Boudouard reaction and methane cracking reaction, respectively. p is the gas pressure, M C is the molar mass (kg / mol).

[0017] In step S2, the attenuation modeling of other components is not considered for the time being, and only the changes in internal components, temperature, and pressure are considered, and modeling is performed according to S1.

[0018] Preferably, in step S3, SIMULINK models of the battery stack and various components are combined to connect the variables that affect each other to form a dynamic attenuation model of the system.

[0019] Preferably, in step S3, the model is adjusted and verified in combination with actual operation data to ensure that the error between the model result and the actual result is within 10%.

[0020] The life prediction model of the hybrid-driven SOFC system is mainly based on the data results of a large number of different working conditions simulated by the SOFC dynamic attenuation model. The multi-dimensional time series prediction method is combined with the established neural network model for machine learning. After training and verification, the life prediction model of the SOFC system is obtained. In step S3, the SIMULINK model of the battery stack and each component is combined to connect the variables that affect each other to form a dynamic attenuation model of the system; the model is adjusted and verified in combination with the actual operation data to ensure that the error between the model result and the actual result is within 10%.

[0021] Preferably, in the process of establishing the SOFC system life prediction model, a large amount of operating data under different operating conditions is calculated using the SOFC dynamic attenuation model as a data set for machine learning; correlation analysis is performed on system variables, and typical variables are selected to study the SOFC system and establish a life prediction model.

[0022] Preferably, for SOFC stack data, the first 90% of the data are selected as the training set and the validation set, and the last 10% of the data are selected as the test set; according to the divided intervals, each model for comparison within the interval and between intervals is randomly initialized before the start of training.

[0023] Preferably, the fuel cell life prediction is divided into two stages: a learning-training stage and a prediction-inference stage. The specific process is as follows: ① Model building: build various neural network models and set relevant structural parameters; ② Input the training set for model learning: Use the training set to train the model; ③Evaluate the model on the validation set: The trained model is inferred on the validation set, and the mean square error, root mean square error, mean absolute error, mean absolute percentage error and determination coefficient are calculated for comprehensive evaluation; ④ Parameter adjustment: optimize the model structure parameters and training parameters according to the results of model evaluation; ⑤The model predicts the final result on the test set: The tuned model performs a final evaluation on the test set.

[0024] The neural network models were trained, verified and tested in different intervals. The evaluation indicators of each model used the commonly used mean absolute error MAE, mean square error MSE, root mean square error RMSE, mean absolute percentage error MAPE and determination coefficient R2 to comprehensively evaluate the prediction performance of the model from multiple angles. The calculation method of each error is as follows: ; ; ; ; ; in, a is the sample size, j is the specific value number in each sample, Y j Sample serial number j The true value, Sample serial number j When the predicted value, is the mean of the true values ​​of the samples.

[0025] After obtaining the life prediction model, it is necessary to compare the output of the life prediction model with the data of the actual SOFC system. If the error requirements are met, the accuracy of the life prediction model can be determined. If the accuracy requirements are not met, the composition of the life prediction model needs to be adjusted, and retraining, verification and testing are performed to obtain the system life prediction model after meeting the error requirements. Model training is defined as successful if the error is within 10%.

[0026] Compared with the prior art, the present invention has the following beneficial effects: The test time is short and the cost is saved. Compared with the long-term operation experiment of the actual system, the system life prediction can obtain the expected design life of the system through simulation, which saves the experimental cost and speeds up the research and development progress; It provides an important reference for the long-life operation of the system. The dynamic attenuation simulation and life prediction of the system can clearly analyze the impact of BOP components on the entire life of the system, and point out the direction for the long-life operation of the system. The accuracy is high. The machine learning method is used to avoid the accidental results of a single simulation, making the results universal and highly accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Establish a flow chart for the SOFC system life prediction model.

[0028] Figure 2 This is a flow chart of the SOFC cogeneration system of the present invention.

[0029] Figure 3 Flowchart for debugging and validating the life prediction model.

[0030] Figure 4 The results are verified for the SOFC system life prediction model. DETAILED DESCRIPTION

[0031] The drawings are for illustrative purposes only. To better illustrate the present embodiment, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, some well-known structures and their descriptions in the drawings may be omitted, and therefore, they should not be understood as limitations on the present invention.

[0032] In order to make the technical means, creative features, purpose and efficacy of the present invention easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0033] Example 1

[0034] like Figure 1 As shown, a hybrid-driven SOFC cogeneration system life prediction method includes the establishment of a SOFC system dynamic decay model and a hybrid-driven SOFC system life prediction model; wherein the establishment of the SOFC system dynamic decay model includes the following steps.

[0035] S0: Determine the specific process of the SOFC thermoelectric system and the typical BOP components used.

[0036] like Figure 2As shown, in step S0, the modeling of the SOFC thermoelectric system mainly considers the components such as the SOFC stack, reformer, mixer, water evaporator, heat exchanger, and tail gas combustion chamber; the specific SOFC workflow is that the anode side fuel gas passes through the desulfurizer for desulfurization (the sulfur content is not considered in the modeling, assuming that the fuel sulfur content is 0), and after heat exchange in the heat exchanger, enters the mixer to mix with water vapor (assuming that the gas is evenly mixed), and then enters the reformer for reforming. The reformed gas enters the anode of the stack. The cathode air enters the cathode of the stack after heat exchange in the heat exchanger.

[0037] The tail gas at the anode outlet first enters the tail gas combustion chamber for combustion. The high-temperature flue gas first provides a suitable reaction temperature for the reforming reactor, and then preheats the fuel gas before entering the mixer.

[0038] The cathode outlet exhaust gas preheats the inlet air.

[0039] S1: Analyze the performance degradation principle of the battery stack and establish a degradation model for the battery stack.

[0040] In step S1, the attenuation of the SOFC stack is mainly considered under continuous operation conditions. The specific electrochemical attenuation model is: , ; ; ; ; ; ; ; ; ; c i = k i 72 X [ D P − ( D P + D s ) n ] n D s 2 D P 2 ( 1 − 1 − X 2 ) , i = a , c ; in, is the actual voltage of the SOFC stack, is the number of cells in the battery stack, is the starting voltage of a single cell, is the voltage decay rate, is the fitting coefficient, which is obtained by fitting according to the actual battery performance. is the fuel utilization rate, is the damage variable, is the temperature inside the battery stack, is the ideal operating temperature of the battery stack. is the natural constant 2.718,i is the current density, E N is the Nernst voltage, or ohm is the ohmic loss, or act is the activation loss, or con is the concentration loss, E 0 is the standard potential, F is the Faraday constant (96485C mol -1 ), R is the other universal constant (8.314 J mol -1 K -1 ), p is the gas pressure, R cell is the resistance, i L is the exchange current density, i oa is the anodic exchange current density, i oc is the cathode exchange current density, c is the pre-exponential factor corresponding to the exchange current density of the anode and cathode (where the subscript a Indicates anode, subscript with c represents the cathode), P ref is atmospheric pressure, E act,a is the anode activation energy, E act,c is the cathode activation energy, k i is the exchange current density coefficient, X is the ratio of the grain contact neck length to the grain size, D p is the aperture, D s is the grain size, n is the electrode porosity.

[0041] In step S1, the temperature, pressure, and composition changes are calculated according to the following equations: ; ; ; ; ; ; in,N out is the outlet molar flow rate, N in is the inlet molar flow rate, R i is the molar reaction rate, N is the molar content in the component, X is the mole fraction, C V is the specific heat at constant volume, R is the universal gas constant, h is enthalpy.

[0042] S2: Analyze the performance attenuation principle of typical BOP components and establish an attenuation model of typical BOP components.

[0043] The temperature, pressure, and composition of typical BOP components are based on equations such as S1.

[0044] The performance degradation of the heat exchanger is mainly based on the following equation: ; ; in, Q in To exchange heat, S area is the heat exchange area, h gs is the convective heat transfer coefficient, T _ban is the heat exchange partition temperature, T _hotgas is the heat transfer fluid, F is the heat transfer attenuation coefficient, h ex is the initial heat transfer coefficient.

[0045] In step S2, multi-level modeling is performed for the chemical reactions occurring inside the reformer, wherein the reactions occurring inside the reformer are: Reforming reaction: .

[0046] Water gas shift reaction: .

[0047] Among them, the reforming reaction is assumed to be completely reformed at the beginning, that is: ; in, r SR is the reforming reaction rate, N fuel,in is the fuel inlet molar flow rate, is the methane concentration at the fuel inlet.

[0048] Then, considering the effect of carbon deposition, the reforming rate is set to gradually decrease over time, where MD (Methane Decomposition reaction) is a methane cracking reaction, and BR (Boundouard reaction) is a reverse Boundouard reaction. The details are as follows: ; ; ; ; .

[0049] in, is the reforming reaction activity, is the reformer inlet molar flow rate, is the inlet methane content, is the thermal conductivity, K BR、 K MD is the adsorption coefficient, is the carbon deposit concentration (mol / m 3 ), r is the reaction rate (mol / m 3 / s), p is the gas pressure, M C is the molar mass (kg / mol).

[0050] The attenuation modeling of other components is not considered for the time being. Only the changes in internal components, temperature, and pressure are considered and modeled according to the equation of S1.

[0051] S3: Based on the attenuation model, the dynamic attenuation model of the system is built and verified using MATLAB software.

[0052] The SIMULINK model of the battery stack and each component is combined to connect the variables that influence each other to form a dynamic attenuation model of the system.

[0053] In step S3, the model is adjusted and verified based on actual operation data to ensure that the error between the model result and the actual result is within 5%.

[0054] S4: Lifespan prediction based on the constructed neural network.

[0055] like Figure 3As shown in the figure, the life prediction model of the hybrid-driven SOFC system is mainly based on the data results of a large number of different working conditions simulated by the SOFC dynamic attenuation model. The multi-dimensional time series prediction method is combined with the established neural network model for machine learning. After training and verification, the life prediction model of the SOFC system is obtained. The specific steps include: 1) Set different boundary condition parameters to obtain the SOFC system operation data set under different working conditions; Since the training and debugging of neural networks require a large amount of data, but continuous operation in actual production takes a long time, the SOFC dynamic attenuation model is used to calculate a large amount of operating data under different operating conditions as the data set for machine learning.

[0056] 2) Correlation analysis to select parameters that have a greater impact on system life; The curves of the changes of various parameters over time during the operation of the SOFC system are obtained, but there are many variables in the entire system and it is impossible to consider and analyze them all. It is necessary to perform correlation analysis on these variables and analyze the correlation coefficients between the various parameters, so as to select several typical variables to study the SOFC system and establish a life prediction model.

[0057] The Pearson correlation coefficient is used to measure the degree of association between variables. The calculation of the correlation coefficient is as follows: ; Where: cov(X,Y) is the covariance of variables X and Y; DX is the variance of variable X, a is the sample size, j is the specific value number in each sample, Y j Sample serial number j The true value, Sample serial number j When the predicted value, is the mean of the true values ​​of the samples.

[0058] The value range of the Pearson correlation coefficient is [-1,1]. The closer its absolute value is to 1, the stronger the linear correlation between the two variables is. The coefficient value above 0.5 is selected as the parameter with a greater impact on the system life.

[0059] 3) Build a suitable life prediction neural network model based on the characteristics of SOFC system operation data; Based on the multi-dimensional and long-term characteristics of the SOFC system operation data, the main body uses LSTM (Long-short Time Memory) for machine learning. In order to ensure the health of the data used for machine learning, CNN (Convolutional Neural Network) is used to smooth and filter the data before entering LSTM. In order to reduce the amount of calculation, the original data is standardized through Max-Min normalization. In order to give greater play to the factors that have a greater impact on the system life, the Attention mechanism is added to enhance the influence of key parameters.

[0060] 4) Use the collected data set to train and verify the neural network. If the error is within 10%, the model training is defined as successful, and the system life prediction model is obtained; Since the operation of the SOFC stack is mainly divided into three stages, the activation stage, the stable operation stage, and the rapid failure stage, the data set is divided into activation + stable operation interval A, rapid failure interval B and total interval C accordingly.

[0061] To avoid data leakage, the logic of time series prediction is strictly followed. The first 90% of the data in the three intervals A, B, and C are selected as the training set (70%) and the validation set (20%), and the last 10% of the data is used as the test set. All models for intra-interval and inter-interval comparisons are randomly initialized before training.

[0062] Fuel cell life prediction is mainly divided into two stages: learning-training stage and prediction-inference stage. The specific process is explained as follows: ① Model building: build various neural network models and set relevant structural parameters; ② Input the training set for model learning: Use the training set to train the model; ③Evaluate the model on the validation set: The trained model is inferred on the validation set, and the mean square error, root mean square error, mean absolute error, mean absolute percentage error and determination coefficient are calculated for comprehensive evaluation; ④ Parameter adjustment: optimize the model structure parameters and training parameters according to the results of model evaluation; ⑤The model predicts the final result on the test set: The tuned model performs a final evaluation on the test set.

[0063] The neural network model was trained, verified and tested in three intervals respectively. The evaluation indicators of each model used the commonly used mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), mean absolute percentage error (MAPE) and determination coefficient (R-Square, R2). The prediction performance of the model was comprehensively evaluated from multiple angles. The calculation methods of each error are as follows: ; ; ; ; .

[0064] in, a is the sample size, j is the specific value number in each sample, Y j Sample serial number j The true value, Sample serial number j When the predicted value, is the mean of the true values ​​of the samples.

[0065] Each group of experiments adjusted the above parameters and selected the best performing model on the validation set to perform inference on the test set.

[0066] After obtaining the life prediction model, it is necessary to compare the output of the life prediction model with the data of the actual SOFC system. If the error requirements are met, the accuracy of the life prediction model can be determined. If the accuracy requirements are not met, it is necessary to adjust the composition of the life prediction model, retrain and re-verify. After the error requirements are met, the life prediction model of the system is obtained.

[0067] like Figure 4 As shown, the actual operating voltage decay over time of the SOFC system is compared with the results of the life prediction model when the operating temperature is 750°C, the operating current is 30A, the anode inlet gas is methane, and the cathode gas is air.

[0068] Of course, the above description is not a limitation of the present invention, and the present invention is not limited to the above examples. Changes, modifications, additions or substitutions made by technicians in this technical field within the essential scope of the present invention should also fall within the protection scope of the present invention.

Claims

1. A life prediction method for a hybrid-driven SOFC cogeneration system, characterized in that: The method includes establishing a dynamic attenuation model of a SOFC system and establishing a life prediction model of a hybrid-driven SOFC system; wherein the establishment of the dynamic attenuation model of a SOFC system includes the following steps: S0: Determine the specific process of the SOFC thermoelectric system and the typical BOP components used; S1: Analyze the performance attenuation principle of the battery stack and establish the attenuation model of the battery stack; S2: Analyze the performance attenuation principle of typical BOP components and establish an attenuation model of typical BOP components; S3: Based on the attenuation model, the dynamic attenuation model of the system was built and verified using MATLAB software; S4: Lifespan prediction based on the constructed neural network; The establishment of the SOFC system life prediction model includes the following steps: 1) Set different boundary condition parameters to obtain the SOFC system operation data set under different working conditions; 2) Correlation analysis to select parameters that have a greater impact on system life; 3) Build a suitable life prediction neural network model based on the characteristics of SOFC system operation data; 4) Use the collected data set to train and verify the neural network. If the error is within 10%, the model training is defined as successful, and the system life prediction model is obtained.

2. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In step S0, the specific SOFC working process is that the anode side fuel gas is desulfurized by the desulfurizer, enters the mixer to mix with water vapor after heat exchange in the heat exchanger, and then enters the reformer for reforming. The reformed gas enters the anode of the stack.

3. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 2, characterized in that: The cathode air enters the cathode of the fuel cell stack after heat exchange in the heat exchanger; the exhaust gas at the anode outlet first enters the exhaust gas combustion chamber for combustion. The high-temperature flue gas first provides a suitable reaction temperature for the reforming reactor, and then preheats the fuel gas before entering the mixer; the exhaust gas at the cathode outlet preheats the inlet air.

4. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In step S1, the attenuation of the SOFC stack is mainly considered under continuous operation conditions. The specific electrochemical attenuation model is: ， ； ； ； ； ； ； ； ； ； ； in, is the actual voltage of the SOFC stack, is the number of cells in the battery stack, is the starting voltage of a single cell, is the voltage decay rate, is the fitting coefficient, which is obtained by fitting according to the actual battery performance. is the fuel utilization rate, is the damage variable, is the temperature inside the battery stack, is the ideal operating temperature of the battery stack. is the natural constant 2.718, i is the current density, E N is the Nernst voltage, η ohm is the ohmic loss, η act is the activation loss, η con is the concentration loss, E 0 is the standard potential; F is the Faraday constant, which is 96485C mol -1 ; R is a general other constant, which is 8.314 J mol -1 K -1 ; p is the gas pressure, R cell is the resistance, i L is the exchange current density, i oa is the anodic exchange current density, i oc is the cathode exchange current density, γ is the pre-exponential factor corresponding to the exchange current density of the anode and cathode, where a represents the anode, c represents the cathode, P ref is atmospheric pressure, E act,a is the anode activation energy, E act,c is the cathode activation energy, k i is the exchange current density coefficient, X is the ratio of the grain contact neck length to the grain size, D p is the aperture, D s is the grain size, n is the electrode porosity.

5. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In step S2, the heat exchanger performance attenuation equation is: ； ； in, Q in To exchange heat, S area is the heat exchange area, h gs is the convective heat transfer coefficient, T _ban is the heat exchange partition temperature, T _hotgas is the heat transfer fluid, Φ is the heat transfer attenuation coefficient, h ex is the initial convective heat transfer coefficient.

6. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In step S2, the chemical reactions occurring inside the reformer are modeled, wherein the reactions occurring inside the reformer are: Reforming reaction: ； Water gas shift reaction: ； The reforming reaction is assumed to be completely reformed initially, that is: in, r SR is the reforming reaction rate, N fuel,in is the fuel inlet molar flow rate, is the fuel inlet methane concentration; Considering the effect of carbon deposition, the reforming rate is set to decrease gradually over time, where MD is the methane cracking reaction and BR is the reverse Boudouard reaction. The specific equation is as follows: ； ； ； ； ； in, is the reforming reaction activity, is the reformer inlet molar flow rate, is the inlet methane content, is the thermal conductivity, K BR is the adsorption coefficient; is the carbon deposit concentration, in mol / m 3 ; r is the reaction rate, are the reaction rates of the reverse Boudouard reaction and methane cracking reaction, respectively, in mol / m 3 / s; p is the gas pressure; M C is the molar mass in kg / mol.

7. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In step S3, the SIMULINK models of the battery stack and each component are combined to connect the variables that affect each other to form a dynamic attenuation model of the system; the model is adjusted and verified based on the actual operating data to ensure that the error between the model result and the actual result is within 10%.

8. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 1, characterized in that: In the process of establishing the SOFC system life prediction model, the SOFC dynamic attenuation model is used to calculate a large amount of operating data under different operating conditions as a data set for machine learning; correlation analysis is performed on system variables, and typical variables are selected to study the SOFC system and establish a life prediction model.

9. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 8, characterized in that: For SOFC stack data, the first 90% of the data were selected as training sets and validation sets, and the last 10% of the data were selected as test sets. According to the divided intervals, each model for comparison within the interval and between intervals was randomly initialized before training began.

10. The method for predicting the life of a hybrid-driven SOFC cogeneration system according to claim 9, characterized in that: Fuel cell life prediction is divided into two stages: learning-training stage and prediction-inference stage. The specific process is as follows: ① Model building: build various neural network models and set relevant structural parameters; ② Input the training set for model learning: Use the training set to train the model; ③Evaluate the model on the validation set: The trained model is inferred on the validation set, and the mean square error, root mean square error, mean absolute error, mean absolute percentage error and determination coefficient are calculated for comprehensive evaluation; ④ Parameter adjustment: optimize the model structure parameters and training parameters according to the results of model evaluation; ⑤ The model predicts the final result on the test set: the tuned model performs a final evaluation on the test set; The neural network models were trained, verified and tested in different intervals. The evaluation indicators of each model used the commonly used mean absolute error MAE, mean square error MSE, root mean square error RMSE, mean absolute percentage error MAPE and determination coefficient R2 to comprehensively evaluate the prediction performance of the model from multiple angles. The calculation method of each error is as follows: ； ； ； ； ； in, a is the sample size, j is the specific value number in each sample, Y j is the true value of sample number j, Sample serial number j When the predicted value, is the average value of the true value of the sample; After obtaining the life prediction model, the output of the life prediction model is compared with the data of the actual SOFC system. If the error requirements are met, the accuracy of the life prediction model can be determined. If the error requirements are not met, the composition of the life prediction model needs to be adjusted, and re-training, verification and testing are performed to obtain the life prediction model of the system after the error requirements are met.

Images