An intelligent management method and system for fuel cells

Abstract

The present invention discloses an intelligent management method and system for a fuel cell. The method includes: constructing a fuel cell degradation experience model and a fuel cell life prediction model; after setting the model weights of the fuel cell degradation experience model and the fuel cell life prediction model by using a comparison set, superimposing the fuel cell degradation experience model and the fuel cell life prediction model according to the model weights to obtain a battery life prediction hybrid model; obtaining monitoring data of the fuel cell, and inputting the monitoring data into the battery life prediction hybrid model to obtain an estimated remaining life value of the fuel cell; generating a maintenance instruction for the fuel cell based on the estimated remaining life value; balancing the accuracy and uncertainty of predicting the remaining life of the fuel cell in the prior art, and realizing accurate prediction of the remaining service life of the fuel cell; based on the life prediction result, realizing intelligent task allocation and planned maintenance of the fuel cell device, and improving the reliability and life of the fuel cell system.

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cell health management, and particularly relates to an intelligent management method and an acceleration method for fuel cells. Background Art

[0002] As a clean energy technology, fuel cells show broad application prospects in fields such as construction machinery. In actual dynamic operation, factors such as fluctuations in stack current / voltage, changes in working temperature / pressure, and other unstable operating conditions will accelerate the degradation and failure rate of fuel cells, greatly reducing the remaining service life of fuel cells. Therefore, accurately predicting the remaining service life of fuel cells and performing timely maintenance on fuel cells according to the remaining service life of fuel cells are of great significance for improving power generation efficiency, extending the life cycle, and reducing operating costs.

[0003] Currently, the existing technologies for predicting the remaining service life of fuel cells include model-driven methods and data-driven methods. The model-driven methods predict the remaining life based on the theoretical mathematical equations of fuel cell degradation phenomena, including mechanism models, semi-empirical models, and empirical models. The data-driven methods train a machine learning framework through the monitoring data of fuel cells and predict the remaining life through the trained machine learning framework.

[0004] The model-driven methods have limitations in model accuracy and applicability and are difficult to cope with complex actual working conditions; the data-driven methods rely on the quality and quantity of data and usually lack interpretability, making it difficult to adapt to changing working conditions. In addition, the existing technologies do not involve intelligent task regulation and planned maintenance of fuel cell devices based on life prediction, and cannot fully utilize the application value of prediction results in actual operation. Summary of the Invention

[0005] The present invention provides an intelligent management method and system for fuel cells, which balance the accuracy and uncertainty of predicting the remaining life of fuel cells in the existing technologies, and achieve accurate prediction of the remaining service life of fuel cells; at the same time, based on the life prediction results, intelligent task allocation and planned maintenance of fuel cell devices are realized, improving the reliability and life of fuel cell systems.

[0006] To achieve the above object, the technical solution adopted by the present invention is:

[0007] In the first aspect of the present invention, an intelligent management method for fuel cells is provided, including

[0008] obtaining the monitoring data of the fuel cell, inputting the monitoring data into the battery life prediction hybrid model to obtain the remaining life evaluation value of the fuel cell; generating a maintenance instruction for the fuel cell based on the remaining life evaluation value;

[0009] The construction process of the battery life prediction hybrid model includes:

[0010] Obtain the historical operation data of the fuel cell; divide the historical operation data into a training set and a comparison set respectively;

[0011] Establish an initial fuel cell degradation model; input the historical operation data in the training set into the initial fuel cell degradation model, and use the particle filter algorithm to estimate the parameters of the initial fuel cell degradation model to obtain an empirical fuel cell degradation model;

[0012] Based on the long short-term memory neural network, establish a fuel cell life prediction model, use the historical operation data in the training set to train the fuel cell life prediction model, and repeat the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model;

[0013] After setting the model weights of the empirical fuel cell degradation model and the fuel cell life prediction model using the comparison set, superimpose the empirical fuel cell degradation model and the fuel cell life prediction model according to the model weights to obtain the battery life prediction hybrid model.

[0014] Furthermore, the process of establishing the initial fuel cell degradation model includes:

[0015] Use the actual output voltage of the fuel cell to represent the remaining service life state of the fuel cell, and construct an initial fuel cell degradation model; the expression formula is:

[0016] ;

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] In the formula, is the actual output voltage of the fuel cell; is the Nernst voltage of the fuel cell; is the activation loss of the fuel cell; is the ohmic loss of the fuel cell; is the concentration difference loss of the fuel cell; is the change in Gibbs free energy before and after the fuel cell reaction; is the Faraday constant; is the universal gas constant; is the entropy change before and after the fuel cell reaction; is the operating temperature of the fuel cell is the partial pressure of hydrogen; is the partial pressure of oxygen; is the pressure at the thermodynamic standard state; is the temperature at the thermodynamic standard state; and and and are fitting parameters; is the current density per unit electrode area; is the electrode area; is the charge transfer resistance per unit area; is the limiting current density.

[0022] Furthermore, input the historical operation data in the training set into the initial fuel cell degradation model, and use the particle filter algorithm to estimate the parameters of the initial fuel cell degradation model to obtain the fuel cell degradation empirical model. The process includes:

[0023] Obtain the initial measured value of the remaining service life of the fuel cell from the historical operation data in the training set, and set the measurement noise to conform to a normal distribution; obtain the initial state value of the remaining service life of the fuel cell based on the initial measured value and the measurement noise;

[0024] Generate a set number of particles according to the initial state value of the remaining service life of the fuel cell; set the initial weights of the particles, and the expression formula is: ; is the initial weight of the i-th particle;

[0025] Take the initial fuel cell degradation model as the state transition model; input the particles into the state transition model to obtain the predicted value of the fuel cell usage state at the next moment, obtain the measured value of the remaining service life of the fuel cell at the next moment from the historical operation data in the training set, update the particle weights according to the predicted value and the measured value of the remaining service life of the fuel cell, and normalize the weights of the particles;

[0026] Resample the particles according to the particle weights, and combine the resampled particle set to estimate the parameters of the initial fuel cell degradation model to obtain the fuel cell degradation empirical model.

[0027] Furthermore, updating the particle weights according to the predicted value and the measured value of the remaining service life of the fuel cell includes:

[0028] ;

[0029] In the formula, is the standard deviation of the measurement noise; is the updated weight of the particle; is the measured value of the remaining service life of the fuel cell; is the predicted value of the remaining service life of the fuel cell; is the pi; is the time step index.

[0030] Furthermore, normalizing the weights of the particles includes:

[0031] ;

[0032] In the formula, is the initial weight of the th particle; is the measured value of the remaining service life of the fuel cell; is the th particle's predicted value of the remaining service life of the fuel cell corresponding to; is the th particle's predicted value of the remaining service life of the fuel cell corresponding to; is the parameter vector of the state transition model.

[0033] Furthermore, using the historical operation data in the training set to train the fuel cell life prediction model, repeating the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model, the process includes:

[0034] The historical operation data in the training set is used as training samples, and the training samples include working time, fuel cell voltage, current, single cell voltage, intake pressure, exhaust pressure, intake metering ratio, inlet and outlet cooling water temperature, and the actual working life of the fuel cell; the actual working life of the fuel cell is used as the true label;

[0035] Input the historical operation data in the training set into the fuel cell life prediction model to obtain the battery life training value; calculate the training loss value based on the battery life training value and the true label; use the Adam optimizer to optimize the parameters of the fuel cell life prediction model according to the training loss value, and repeat the iteration of the training process of the fuel cell life prediction model until the number of iterations reaches the iteration threshold and output the trained fuel cell life prediction model.

[0036] Furthermore, using the comparison set to set the model weights of the fuel cell degradation empirical model and the fuel cell life prediction model, the process includes:

[0037] Input the comparison set into the fuel cell degradation empirical model to obtain the model-driven function of the probability distribution of the remaining service life of the fuel cell;

[0038] Input the comparison set into the fuel cell life prediction model to obtain the data-driven function of the probability distribution of the remaining service life of the fuel cell;

[0039] Establish the actual distribution function of the service life of a fuel cell based on the relatively concentrated actual working life of the fuel cell;

[0040] Calculate the model weights of the fuel cell degradation empirical model and the fuel cell life prediction model according to the model-driven function, the data-driven function, and the actual distribution function of the service life. The expression formula is:

[0041] ;

[0042] In the formula, is the actual distribution function of the service life; is the model-driven function of the probability distribution of the remaining service life of the fuel cell; is the data-driven function of the probability distribution of the remaining service life of the fuel cell; is the model weight of the fuel cell degradation empirical model; is the model weight of the fuel cell life prediction model; is the accuracy of the prediction result;

[0043] When the accuracy reaches 1, obtain the model weight of the fuel cell degradation empirical model and the model weight .

[0044] Furthermore, generate a maintenance instruction for the fuel cell based on the remaining life evaluation value. The process includes:

[0045] Calculate the life factor of the fuel cell according to the remaining life evaluation value. The expression formula is:

[0046] ;

[0047] The formula is, is the life factor; is the remaining life evaluation value of the fuel cell; is the service life of the fuel cell;

[0048] Generate a maintenance instruction for the fuel cell when the life factor is less than the life threshold.

[0049] The second aspect of the present invention provides an intelligent management system for a fuel cell, including:

[0050] A monitoring module for acquiring monitoring data of the fuel cell, inputting the monitoring data into the battery life prediction hybrid model to obtain the remaining life evaluation value of the fuel cell; generating a maintenance instruction for the fuel cell based on the remaining life evaluation value;

[0051] An acquisition module for acquiring historical operation data of the fuel cell; dividing the historical operation data into a training set and a comparison set respectively;

[0052] The first construction module establishes an initial fuel cell degradation model; inputs the historical operation data in the training set into the initial fuel cell degradation model, and uses the particle filter algorithm to estimate the parameters of the initial fuel cell degradation model to obtain an empirical fuel cell degradation model;

[0053] The second construction module establishes a fuel cell life prediction model based on a long short-term memory neural network, trains the fuel cell life prediction model using the historical operation data in the training set, and repeats the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model;

[0054] The fitting module sets the model weights of the empirical fuel cell degradation model and the fuel cell life prediction model using the comparison set, and then superimposes the empirical fuel cell degradation model and the fuel cell life prediction model according to the model weights to obtain a hybrid battery life prediction model.

[0055] The third aspect of the present invention provides an electronic device, including a storage medium and a processor; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the intelligent management method for fuel cells described in the first aspect.

[0056] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0057] The present invention obtains the monitoring data of the fuel cell, inputs the monitoring data into the hybrid battery life prediction model to obtain the remaining life evaluation value of the fuel cell; generates a maintenance instruction for the fuel cell based on the remaining life evaluation value; through planned maintenance and intelligent task allocation, it can extend the service life of the fuel cell, reduce the replacement frequency, and lower the long-term operation cost.

[0058] The present invention constructs an empirical fuel cell degradation model and a fuel cell life prediction model, sets the model weights of the empirical fuel cell degradation model and the fuel cell life prediction model using the comparison set, and then superimposes the empirical fuel cell degradation model and the fuel cell life prediction model according to the model weights to obtain a hybrid battery life prediction model. The hybrid battery life prediction model balances the accuracy and uncertainty of the two models and can more accurately predict the remaining service life of the fuel cell. Description of the Drawings

[0059] Figure 1 It is a flowchart of an intelligent management method for fuel cells provided in Embodiment 1 of the present invention;

[0060] Figure 2 It is a structural diagram of a fuel cell provided in Embodiment 1 of the present invention;

[0061] Figure 3Flowchart of the battery life prediction hybrid model provided in Embodiment 1 of the present invention. Detailed implementation manners

[0062] 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 cannot be used to limit the protection scope of the present invention.

[0063] Embodiment 1

[0064] As Figure 1 shown, the present embodiment provides an intelligent management method for a fuel cell, including:

[0065] As Figure 2 shown, the fuel cell includes a stack; a hydrogen supply circuit, an air supply circuit, and a cooling system are provided on the stack.

[0066] As Figure 3 shown, the process of constructing a battery life prediction hybrid model includes:

[0067] Obtain the historical operation data of the fuel cell; divide the historical operation data into a training set, a prediction set, and a comparison set respectively;

[0068] The process of establishing an initial fuel cell degradation model includes:

[0069] Use the actual output voltage of the fuel cell to represent the remaining service life state of the fuel cell, and construct an initial fuel cell degradation model; the expression formula is:

[0070] ;

[0071] ;

[0072] ;

[0073] ;

[0074] ;

[0075] In the formula, is the actual output voltage of the fuel cell; is the Nernst voltage of the fuel cell; is the activation loss of the fuel cell; is the ohmic loss of the fuel cell; is the concentration difference loss of the fuel cell; is the change in Gibbs free energy before and after the fuel cell reaction; is the Faraday constant; is the universal gas constant; is the entropy change before and after the fuel cell reaction; is the operating temperature of the fuel cell; is the partial pressure of hydrogen; is the partial pressure of oxygen; is the pressure at the thermodynamic standard state; is the temperature at the thermodynamic standard state; and and and are fitting parameters; is the current density per unit electrode area; is the electrode area; is the charge transfer resistance per unit area; is the limiting current density.

[0076] Input the historical operation data in the training set into the initial fuel cell degradation model, and use the particle filter algorithm to estimate the parameters of the initial fuel cell degradation model to obtain the fuel cell degradation empirical model. The process includes:

[0077] Obtain the initial measured value of the remaining service life of the fuel cell from the historical operation data in the training set, and set the measurement noise to conform to a normal distribution; obtain the initial state value of the remaining service life of the fuel cell based on the initial measured value and the measurement noise;

[0078] Generate a set number of particles according to the initial state value of the remaining service life of the fuel cell; set the initial particle weights, and the expression formula is: ; is the initial weight of the i-th particle;

[0079] Take the initial fuel cell degradation model as the state transition model; input the particles into the state transition model to obtain the predicted value of the fuel cell usage state at the next moment, and obtain the measured value of the remaining service life of the fuel cell at the next moment from the historical operation data in the training set.

[0080] Update the particle weights according to the predicted value and the measured value of the remaining service life of the fuel cell, including:

[0081] ;

[0082] In the formula, is the standard deviation of the measurement noise; is the updated weight of the particle; is the measured value of the remaining service life of the fuel cell; is the predicted value of the remaining service life of the fuel cell; is the pi; is the time step index.

[0083] Normalize the weights of the particles, including:

[0084] ;

[0085] In the formula, is the initial weight of the th particle; is the measured value of the remaining service life of the fuel cell; is the predicted value of the remaining service life of the fuel cell corresponding to the th particle; is the predicted value of the remaining service life of the fuel cell corresponding to the th particle; is the parameter vector of the state transition model.

[0086] Resample the particles according to the particle weights, and combine the resampled particle set to estimate the parameters of the initial fuel cell degradation model to obtain the fuel cell degradation empirical model.

[0087] Establish a fuel cell life prediction model based on the long short-term memory neural network, and use the historical operation data in the training set to train the fuel cell life prediction model. Repeat the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model. The process includes:

[0088] The historical operation data in the training set is used as the training sample. The training sample includes working time, fuel cell voltage, current, single cell voltage, intake pressure, exhaust pressure, intake metering ratio, inlet and outlet cooling water temperature, and the actual working life of the fuel cell; The actual working life of the fuel cell is used as the true label;

[0089] Input the historical operation data in the training set into the fuel cell life prediction model to obtain the battery life training value; Calculate the training loss value based on the battery life training value and the true label; Use the Adam optimizer to optimize the parameters of the fuel cell life prediction model according to the training loss value, and repeat the iteration of the training process of the fuel cell life prediction model until the number of iterations reaches the iteration threshold and output the trained fuel cell life prediction model.

[0090] Use the prediction set to test the fuel cell degradation empirical model and the fuel cell life prediction model. When the accuracy of the fuel cell degradation empirical model and the fuel cell life prediction model is less than the set accuracy threshold, re-obtain the historical operation data to optimize and train the fuel cell degradation empirical model and the fuel cell life prediction model.

[0091] When the accuracy of the fuel cell degradation empirical model and the fuel cell life prediction model reaches the set accuracy threshold, use the comparison set to set the model weights of the fuel cell degradation empirical model and the fuel cell life prediction model. The process includes:

[0092] Input the comparison set into the fuel cell degradation experience model to obtain the model-driven function of the probability distribution of the remaining service life of the fuel cell;

[0093] Input the comparison set into the fuel cell life prediction model to obtain the data-driven function of the probability distribution of the remaining service life of the fuel cell;

[0094] Based on the actual working life of the fuel cell in the comparison set, establish the actual distribution function of the service life of the fuel cell;

[0095] Calculate the model weights of the fuel cell degradation experience model and the fuel cell life prediction model according to the model-driven function, the data-driven function and the actual distribution function of the service life. The expression formula is:

[0096] ;

[0097] In the formula, is the actual distribution function of the service life; is the model-driven function of the probability distribution of the remaining service life of the fuel cell; is the data-driven function of the probability distribution of the remaining service life of the fuel cell; is the model weight of the fuel cell degradation experience model; is the model weight of the fuel cell life prediction model; is the accuracy of the prediction result;

[0098] When the accuracy reaches 1, obtain the model weight of the fuel cell degradation experience model and the model weight

[0099] of the fuel cell life prediction model. According to the model weights, superimpose the fuel cell degradation experience model and the fuel cell life prediction model to obtain the battery life prediction hybrid model; by balancing the accuracy and uncertainty of the fuel cell degradation experience model and the fuel cell life prediction model, the battery life prediction hybrid model can more accurately predict the remaining service life of the fuel cell.

[0100] Obtain the monitoring data of the fuel cell, input the monitoring data into the battery life prediction hybrid model to obtain the remaining life evaluation value of the fuel cell; generate the maintenance instruction of the fuel cell based on the remaining life evaluation value. The process includes:

[0101] Calculate the life factor of the fuel cell according to the remaining life evaluation value. The expression formula is:

[0102] ;

[0103] The formula is, is the life factor; is the remaining life assessment value of the fuel cell; is the service life of the fuel cell;

[0104] When the life factor is less than the life threshold, a maintenance instruction for the fuel cell is generated; it can issue a warning in a timely manner and carry out planned repair and maintenance, reduce the failure rate of the fuel cell system, and improve the reliability and stability of the system; through the intelligent management system, the need for manual monitoring is reduced, and an automated and intelligent maintenance plan is realized, thereby reducing the overall operation cost.

[0105] Embodiment 2

[0106] This embodiment provides an intelligent management system for a fuel cell. The intelligent management system is used to execute the intelligent management method described in Embodiment 1. The intelligent management system includes:

[0107] A monitoring module, which is used to obtain the monitoring data of the fuel cell, input the monitoring data into the battery life prediction hybrid model to obtain the remaining life assessment value of the fuel cell; and generate a maintenance instruction for the fuel cell based on the remaining life assessment value;

[0108] An acquisition module, which is used to obtain the historical operation data of the fuel cell; and divide the historical operation data into a training set and a comparison set respectively;

[0109] A first construction module, which establishes an initial fuel cell degradation model; inputs the historical operation data in the training set into the initial fuel cell degradation model, and uses the particle filter algorithm to estimate the parameters of the initial fuel cell degradation model to obtain an empirical fuel cell degradation model;

[0110] A second construction module, which establishes a fuel cell life prediction model based on the long short-term memory neural network, trains the fuel cell life prediction model using the historical operation data in the training set, and repeats the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model;

[0111] A fitting module, which sets the model weights of the empirical fuel cell degradation model and the fuel cell life prediction model using the comparison set, and then superimposes the empirical fuel cell degradation model and the fuel cell life prediction model according to the model weights to obtain a battery life prediction hybrid model.

[0112] The intelligent management system is configured with a monitoring screen; the monitoring screen provides multi-dimensional data statistical analysis results such as device macro data, single-device monitoring, and fault statistics, helping the operator better understand the device status and performance

[0113] The monitoring module is integrated into the data cloud platform, realizing the integrated management of device monitoring, data processing, data storage, and data forwarding, and improving the efficiency and accuracy of data processing.

[0114] Example 3

[0115] This embodiment provides an electronic device, including a storage medium and a processor; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the intelligent management method for fuel cells described in Embodiment 1.

[0116] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. 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 memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0117] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also 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, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0118] 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, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0120] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent management method for a fuel cell, characterized in that: include: Acquire monitoring data of the fuel cell, and input the monitoring data into a battery life prediction hybrid model to obtain a remaining life evaluation value of the fuel cell; generating a maintenance instruction for the fuel cell based on the remaining life estimate; The construction process of the battery life prediction hybrid model includes: Acquire historical operation data of the fuel cell; divide the historical operation data into a training set and a comparison set; The process of developing an initial fuel cell degradation model includes: The actual output voltage of the fuel cell is used to represent the remaining service life of the fuel cell, and the initial fuel cell degradation model is constructed; the expression formula is: V=EV act -V ohm -V conc In ohm =jAR ohm In the formula, V is the actual output voltage of the fuel cell; E is the Nernst voltage of the fuel cell; V act is the activation loss of the fuel cell; V ohm is the ohmic loss of the fuel cell; V conc is the concentration loss of the fuel cell; ΔG is the change in Gibbs free energy before and after the fuel cell reaction; F is the Faraday constant; R is the universal gas constant; ΔS is the entropy change before and after the fuel cell reaction; T is the operating temperature of the fuel cell; is the partial pressure of hydrogen; is the partial pressure of oxygen; P ref is the thermodynamic standard pressure; T ref is the thermodynamic standard state temperature; ζ1, ζ2, ζ3, ζ4 are fitting parameters; j is the current density per unit electrode area; A is the electrode area; R ohm is the charge transfer resistance per unit area; L is the limiting current density; The historical operation data in the training set is input into the initial model of fuel cell degradation, and the particle filter algorithm is used to estimate the parameters of the initial model of fuel cell degradation to obtain the empirical model of fuel cell degradation; A fuel cell life prediction model is established based on a long short-term memory neural network, and the fuel cell life prediction model is trained using historical operation data in the training set. The trained fuel cell life prediction model is obtained by repeated iterations until the training termination condition is reached. The model weights of the fuel cell degradation empirical model and the fuel cell life prediction model are set using the comparison set. The process includes: Inputting the comparison set into the fuel cell degradation empirical model to obtain the model driving function of the fuel cell remaining useful life probabilities distribution; The comparison set is input into a fuel cell life prediction model to obtain a data-driven function of the fuel cell remaining service life probabilities distribution; Establishing the actual distribution function of the service life of the fuel cell based on the actual working life of the fuel cell; The model weights of the fuel cell degradation empirical model and the fuel cell life prediction model are calculated based on the model driving function, data driving function and actual service life distribution function. The expression formula is: In the formula, is the actual distribution function of service life; A model-driven function for the distribution of the remaining useful life of a fuel cell; is the data-driven function for the distribution of the remaining useful life of the fuel cell; model is the model weight of the fuel cell degradation empirical model; data is the model weight of the fuel cell life prediction model; To ensure the accuracy of the prediction results; When accuracy When it reaches 1, the model weight λ of the fuel cell degradation empirical model is obtained. model and the model weight λ of the fuel cell life prediction model data ; The fuel cell degradation empirical model and the fuel cell life prediction model are superimposed according to the model weight to obtain a battery life prediction hybrid model.

2. The intelligent management method for fuel cells according to claim 1, characterized in that: The historical operation data in the training set is input into the initial model of fuel cell degradation, and the particle filter algorithm is used to estimate the parameters of the initial model of fuel cell degradation to obtain the empirical model of fuel cell degradation. The process includes: The initial measurement value of the remaining service life of the fuel cell is obtained from the historical operation data in the training set, and the measurement noise is set to conform to the normal distribution; the initial state value of the remaining service life of the fuel cell is obtained based on the initial measurement value and the measurement noise; Generate a set number n based on the initial state value of the remaining service life of the fuel cell s Particles; set the initial weight of the particles, the expression formula is: is the initial weight of the i-th particle; The initial fuel cell degradation model is used as a state transition model; the particles are input into the state transition model to obtain the predicted value of the fuel cell usage state at the next moment, and the measured value of the remaining service life of the fuel cell at the next moment is obtained from the historical operation data in the training set. The particle weight is updated according to the predicted value and measured value of the remaining service life of the fuel cell, and the particle weight is normalized; The particles are resampled according to the particle weights, and the parameters of the initial fuel cell degradation model are estimated by combining the resampled particle set to obtain the fuel cell degradation empirical model.

3. The intelligent management method for fuel cells according to claim 2, characterized in that: Update particle weights based on predicted and measured values ​​of the remaining useful life of the fuel cell, including: In the formula, σ is the standard deviation of the measurement noise; is the updated weight of the particle; is a measure of the remaining useful life of the fuel cell; is the predicted value of the remaining service life of the fuel cell; π is the pi; k is the time step index.

4. The intelligent management method for fuel cells according to claim 2, characterized in that: Normalize the particle weights, including: In the formula, is the initial weight of the i-th particle; is a measure of the remaining useful life of the fuel cell; is the predicted value of the remaining service life of the fuel cell corresponding to the i-th particle; is the predicted value of the remaining service life of the fuel cell corresponding to the vth particle; θ is the parameter vector of the state transition model.

5. The intelligent management method for fuel cells according to claim 1, characterized in that: The fuel cell life prediction model is trained using historical operating data in the training set, and repeated iterations are performed until the training termination condition is reached to obtain the trained fuel cell life prediction model. The process includes: The historical operation data in the training set is used as training samples, and the training samples include working time, fuel cell voltage, current, single chip voltage, intake pressure, exhaust pressure, intake metering ratio, inlet and outlet cooling water temperature, and actual working life of the fuel cell; the actual working life of the fuel cell is used as the true label; The historical operation data in the training set is input into the fuel cell life prediction model to obtain the battery life training value; the training loss value is calculated based on the battery life training value and the true label; the Adam optimizer is used to optimize the parameters of the fuel cell life prediction model according to the training loss value, and the training process of the fuel cell life prediction model is repeated until the number of iterations reaches the iteration threshold to output the trained fuel cell life prediction model.

6. The intelligent management method for fuel cells according to claim 1, characterized in that: Generate fuel cell maintenance instructions based on the remaining life assessment value, the process includes: The life factor of the fuel cell is calculated based on the remaining life evaluation value, and the expression formula is: The formula is, is the lifespan factor; T e is the estimated value of the remaining life of the fuel cell; T0 is the service life of the fuel cell; When the life factor is less than the life threshold, a maintenance instruction for the fuel cell is generated.

7. An intelligent management system for a fuel cell, characterized in that: include: A monitoring module is used to obtain monitoring data of the fuel cell and input the monitoring data into a battery life prediction hybrid model to obtain a remaining life evaluation value of the fuel cell; generating a maintenance instruction for the fuel cell based on the remaining life estimate; An acquisition module is used to acquire historical operation data of the fuel cell; and divide the historical operation data into a training set and a comparison set respectively; The first building module is to establish an initial model of fuel cell degradation; input the historical operation data in the training set into the initial model of fuel cell degradation, and use a particle filter algorithm to estimate the parameters of the initial model of fuel cell degradation to obtain an empirical model of fuel cell degradation; The second building block is to establish a fuel cell life prediction model based on a long short-term memory neural network, use the historical operation data in the training set to train the fuel cell life prediction model, and repeat the iteration until the training termination condition is reached to obtain the trained fuel cell life prediction model; A fitting module, after setting the model weights of the fuel cell degradation empirical model and the fuel cell life prediction model using the comparison set, superimposes the fuel cell degradation empirical model and the fuel cell life prediction model according to the model weights to obtain a battery life prediction hybrid model; The process of establishing the initial fuel cell degradation model by the first building module includes: The actual output voltage of the fuel cell is used to represent the remaining service life of the fuel cell, and the initial fuel cell degradation model is constructed; the expression formula is: V=EV act -V ohm -V conc In ohm =jAR ohm In the formula, V is the actual output voltage of the fuel cell; E is the Nernst voltage of the fuel cell; V act is the activation loss of the fuel cell; V ohm is the ohmic loss of the fuel cell; V conc is the concentration loss of the fuel cell; ΔG is the change in Gibbs free energy before and after the fuel cell reaction; F is the Faraday constant; R is the universal gas constant; ΔS is the entropy change before and after the fuel cell reaction; T is the operating temperature of the fuel cell; is the partial pressure of hydrogen; is the partial pressure of oxygen; P ref is the thermodynamic standard pressure; T ref is the thermodynamic standard state temperature; ζ1, ζ2, ζ3, ζ4 are fitting parameters; j is the current density per unit electrode area; A is the electrode area; R ohm is the charge transfer resistance per unit area; L is the limiting current density; The fitting module sets the model weights of the fuel cell degradation empirical model and the fuel cell life prediction model using the comparison set, and the process includes: Inputting the comparison set into the fuel cell degradation empirical model to obtain the model driving function of the fuel cell remaining useful life probabilities distribution; The comparison set is input into a fuel cell life prediction model to obtain a data-driven function of the fuel cell remaining service life probabilities distribution; Establishing the actual distribution function of the service life of the fuel cell based on the actual working life of the fuel cell; The model weights of the fuel cell degradation empirical model and the fuel cell life prediction model are calculated based on the model driving function, data driving function and actual service life distribution function. The expression formula is: In the formula, is the actual distribution function of service life; A model-driven function for the distribution of the remaining useful life of a fuel cell; is the data-driven function for the distribution of the remaining useful life of the fuel cell; model is the model weight of the fuel cell degradation empirical model; data is the model weight of the fuel cell life prediction model; To ensure the accuracy of the prediction results; When accuracy When it reaches 1, the model weight λ of the fuel cell degradation empirical model is obtained. model and the model weight λ of the fuel cell life prediction model data .

8. An electronic device, comprising a storage medium and a processor; the storage medium is used to store instructions; characterized in that: The processor is used to operate according to the instructions to execute the intelligent management method for a fuel cell according to any one of claims 1 to 6.

Images