Modeling simulation method for methanol reforming hydrogen production fuel cell

Abstract

The invention provides a methanol reforming hydrogen production fuel cell modeling simulation method, which comprises the following steps: acquiring current, voltage, temperature, gas flow and methanol concentration data in real time, inputting the data into a trained performance prediction model to obtain a performance prediction value, and calculating an efficiency prediction value by combining a voltage value. Meanwhile, current, temperature, gas flow and methanol concentration data are input into the efficiency compensation model to obtain an efficiency error prediction value, the efficiency prediction value is compensated, and finally an accurate efficiency detection result is obtained. The operation stability and efficiency of the fuel cell can be improved, the energy consumption is reduced, and technical support is provided for optimization control and performance improvement of the methanol reforming hydrogen production fuel cell.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and more specifically, to a modeling and simulation method for a methanol reforming hydrogen production fuel cell. Background Art

[0002] As a highly efficient energy conversion device, methanol reforming hydrogen fuel cells have attracted extensive attention in the energy field due to their high energy density, environmental friendliness, and utilization of renewable energy. Traditional methanol reforming hydrogen fuel cell systems usually rely on complex hardware equipment and sensors to monitor battery performance and efficiency. However, these systems often have problems such as high cost, slow response speed, and difficult maintenance. In addition, since the operating environment of methanol reforming hydrogen fuel cells is changeable, factors such as temperature, pressure, and methanol concentration will affect their performance, so a more accurate and real-time monitoring method is needed to ensure the efficient operation of the battery.

[0003] Existing technologies often use static models or simple linear models to predict the performance of methanol reforming hydrogen fuel cells. These models have insufficient prediction accuracy when facing complex nonlinear relationships and are difficult to meet the needs of practical applications. At the same time, due to the lack of an effective efficiency compensation mechanism, existing technologies often ignore the impact of real-time data when processing efficiency predictions, resulting in a large deviation between the prediction results and the actual values.

[0004] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: the existing methanol reforming hydrogen production fuel cell modeling and simulation method cannot achieve real-time and accurate prediction of battery performance and efficiency; the existing method lacks effective real-time data support when processing efficiency compensation, resulting in insufficient accuracy and reliability of the prediction results; the prior art lacks a dynamic update mechanism for real-time data and measured values ​​during model training and correction, which limits the adaptability and generalization ability of the model. Summary of the invention

[0005] The present invention provides a modeling and simulation method for a methanol reforming hydrogen production fuel cell, comprising:

[0006] Real-time data collection, including: current value I, voltage value V, temperature value T, gas flow value F and methanol concentration value C of methanol reforming hydrogen fuel cell;

[0007] The current value I of the methanol reforming hydrogen production fuel cell collected in real time is input into the trained methanol reforming hydrogen production fuel cell performance prediction model, and after processing, the methanol reforming hydrogen production fuel cell performance prediction value P is obtained;

[0008] Based on the predicted value P of the performance of the methanol reforming hydrogen production fuel cell and the voltage value V collected in real time, a predicted value η of the efficiency of the methanol reforming hydrogen production fuel cell is obtained;

[0009] The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell collected in real time are input into the trained methanol reforming hydrogen production fuel cell efficiency compensation model, and after processing, the methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is obtained;

[0010] The methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is used to compensate the methanol reforming hydrogen production fuel cell efficiency prediction value η to obtain the final methanol reforming hydrogen production fuel cell efficiency error prediction value Δη.

[0011] Further, the performance prediction model of the methanol reforming hydrogen production fuel cell is trained in the following manner: a first sample set is obtained, wherein each group of first sample data in the first sample set includes: a current value I of the methanol reforming hydrogen production fuel cell, a voltage value V of the methanol reforming hydrogen production fuel cell, and a measured value η of the efficiency of the methanol reforming hydrogen production fuel cell measured ;

[0012] Based on the measured value η of the methanol reforming hydrogen production fuel cell efficiency in each group of first sample data measured and voltage value V, and obtain the performance standard value P of methanol reforming hydrogen fuel cell standard ;

[0013] The current value I of the methanol reforming hydrogen production fuel cell in each group of the first sample data is used as the input, and the performance standard value P of the methanol reforming hydrogen production fuel cell is used as the input. standard as labels, training the performance prediction model of the methanol reforming hydrogen production fuel cell, determining the structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell, and obtaining a trained performance prediction model of the methanol reforming hydrogen production fuel cell.

[0014] Furthermore, in the performance prediction model of the methanol reforming hydrogen production fuel cell, the structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell are determined based on the LS least squares method.

[0015] Further, the structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell are determined in the following manner: the performance prediction value P of the methanol reforming hydrogen production fuel cell and the current value I of the methanol reforming hydrogen production fuel cell satisfy:

[0016] P=aI 2 +bI+c (1)

[0017] The performance standard values ​​and performance prediction values ​​of methanol reforming hydrogen production fuel cells meet the following requirements:

[0018]

[0019] Where n represents the number of groups of the first sample data in the first sample set; P standard (i) represents the standard value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group, and P(i) represents the predicted value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group;

[0020] Based on the LS least squares method, the parameters a, b and c are estimated with the minimum value of J(a, b, c) as the goal, and the estimated values ​​of the parameters a, b and c are obtained;

[0021] The trained methanol reforming hydrogen fuel cell performance prediction model is:

[0022] P=a′I+b′ (3)

[0023] Furthermore, the performance standard value of the methanol reforming hydrogen production fuel cell is obtained according to the following method:

[0024]

[0025] Among them, η measured (i) represents the measured value of the methanol reforming hydrogen production fuel cell efficiency in the first sample data of the i-th group, P c (i) represents the voltage value of the methanol reforming hydrogen production fuel cell in the i-th group of first sample data, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

[0026] Further, the methanol reforming hydrogen production fuel cell efficiency compensation model is trained in the following manner: a second sample set is obtained, and each group of second sample data in the second sample set includes: a measured value η of the methanol reforming hydrogen production fuel cell efficiency measured , the voltage value V of the methanol reforming hydrogen production fuel cell, the current value I of the methanol reforming hydrogen production fuel cell, the temperature value T of the methanol reforming hydrogen production fuel cell, the gas flow value F and the methanol concentration value C;

[0027] Input the current value I of the methanol reforming hydrogen production fuel cell in each group of second sample data into the trained methanol reforming hydrogen production fuel cell performance prediction model, and obtain the corresponding methanol reforming hydrogen production fuel cell performance prediction value P after processing;

[0028] Based on the methanol reforming hydrogen production fuel cell performance prediction value P and voltage value V corresponding to each set of second sample data, the corresponding methanol reforming hydrogen production fuel cell efficiency prediction value η is obtained;

[0029] The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell in each group of second sample data are used as input, the predicted value η of the methanol reforming hydrogen production fuel cell efficiency and the measured value η of the methanol reforming hydrogen production fuel cell efficiency measured The difference between is used as a label to train the methanol reforming hydrogen production fuel cell efficiency compensation model to obtain a trained methanol reforming hydrogen production fuel cell efficiency compensation model.

[0030] Furthermore, the predicted value η of the efficiency of the methanol reforming hydrogen production fuel cell is calculated according to the following formula, including:

[0031]

[0032] Wherein, P represents the performance prediction value of the methanol reforming hydrogen production fuel cell, V represents the voltage value of the methanol reforming hydrogen production fuel cell, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

[0033] Furthermore, the efficiency compensation model of methanol reforming hydrogen production fuel cell is realized based on radial basis function neural network.

[0034] Furthermore, the method further comprises: during the real-time data collection process, regularly collecting the actual measured value of the efficiency of the methanol reforming hydrogen production fuel cell;

[0035] If the error between the regularly collected actual measured value of the methanol reforming hydrogen fuel cell efficiency and the final methanol reforming hydrogen fuel cell efficiency detection result obtained based on the actual collected data at that moment is lower than the set error, the actual collected data at that moment and the actual measured value of the methanol reforming hydrogen fuel cell efficiency are used as a set of correction data, and multiple sets of correction data form a correction data set, and the methanol reforming hydrogen fuel cell efficiency compensation model is corrected online based on the correction data set.

[0036] Furthermore, the temperature value of the methanol reforming hydrogen production fuel cell is detected based on a thermocouple arranged in the methanol reforming hydrogen production fuel cell.

[0037] According to the above-mentioned embodiment of the present invention, at least the following beneficial effects are achieved: the modeling and simulation method of the methanol reforming hydrogen production fuel cell of the present invention can accurately predict the performance and efficiency of the methanol reforming hydrogen production fuel cell by real-time acquisition of the current value, voltage value, temperature value, gas flow value and methanol concentration value of the methanol reforming hydrogen production fuel cell, and inputting these data into the trained performance prediction model and efficiency compensation model. The method calculates the efficiency prediction value using the performance prediction value and the voltage value acquired in real time, and then compensates the efficiency prediction value by the efficiency error prediction value, and finally obtains a more accurate efficiency detection result. This method can improve the prediction accuracy of the efficiency of the methanol reforming hydrogen production fuel cell, reduce the energy waste caused by the prediction error, and thus improve the energy utilization efficiency of the entire system.

[0038] In addition, the present invention also provides an online correction mechanism, which regularly collects the measured value of the efficiency of the methanol reforming hydrogen production fuel cell and compares it with the efficiency detection result obtained by real-time data. If the error is lower than the set value, these data are used as correction data to update and optimize the efficiency compensation model. This online correction mechanism can ensure that the model maintains a high prediction accuracy and adaptability during long-term operation, while reducing the system's dependence on manual intervention and reducing maintenance costs. In this way, the present invention can continuously improve the performance and efficiency of methanol reforming hydrogen production fuel cells and enhance the reliability and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0040] Figure 1 A schematic flow chart of a method for modeling and simulating a methanol reforming hydrogen production fuel cell according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0042] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0043] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0044] Reference below Figure 1 , Figure 1 A schematic diagram of a flow chart of a modeling and simulation method for a methanol reforming hydrogen production fuel cell provided in one embodiment of the present invention. Figure 1 As shown, a methanol reforming hydrogen production fuel cell modeling simulation method 100 includes:

[0045] Real-time data collection, including: current value I, voltage value V, temperature value T, gas flow value F and methanol concentration value C of methanol reforming hydrogen fuel cell;

[0046] The current value I of the methanol reforming hydrogen production fuel cell collected in real time is input into the trained methanol reforming hydrogen production fuel cell performance prediction model, and after processing, the methanol reforming hydrogen production fuel cell performance prediction value P is obtained;

[0047] Based on the predicted value P of the performance of the methanol reforming hydrogen production fuel cell and the voltage value V collected in real time, a predicted value η of the efficiency of the methanol reforming hydrogen production fuel cell is obtained;

[0048] The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell collected in real time are input into the trained methanol reforming hydrogen production fuel cell efficiency compensation model, and after processing, the methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is obtained;

[0049] The methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is used to compensate the methanol reforming hydrogen production fuel cell efficiency prediction value η to obtain the final methanol reforming hydrogen production fuel cell efficiency detection result η final .

[0050] It should be noted that the method first involves real-time collection of key operating parameters of methanol reforming hydrogen fuel cells, including current, voltage, temperature, gas flow and methanol concentration. These parameters are the basis for evaluating battery performance and efficiency, and are monitored in real time through high-precision sensors to ensure the accuracy and real-time nature of the data.

[0051] Specifically, the current value refers to the amount of charge flowing through the fuel cell, the voltage value is the potential difference between the two ends of the battery, the temperature value reflects the operating temperature of the battery, the gas flow value is the amount of gas entering the battery, and the methanol concentration value refers to the concentration of methanol before entering the battery. The collection of these parameters can be achieved through corresponding sensors and data acquisition systems, such as using high-precision current sensors, voltage sensors, thermocouples, mass flow meters and methanol concentration sensors.

[0052] Preferably, the collected data can be transmitted in real time to a central processing unit via a wireless communication module, which has a built-in trained performance prediction model. The input parameters of the model can be adjusted according to the specific design and operating conditions of the battery to achieve the best prediction effect. In addition, the model can be trained using machine learning algorithms, such as neural networks, to handle complex nonlinear relationships and ensure the accuracy of the prediction.

[0053] In some embodiments, the methanol reforming hydrogen production fuel cell performance prediction model is trained by: obtaining a first sample set, each set of first sample data in the first sample set includes: a current value I of the methanol reforming hydrogen production fuel cell, a voltage value V of the methanol reforming hydrogen production fuel cell, and a measured value η of the efficiency of the methanol reforming hydrogen production fuel cell measured ;

[0054] Based on the measured value η of the methanol reforming hydrogen production fuel cell efficiency in each group of first sample data measured and voltage value V, and obtain the performance standard value P of methanol reforming hydrogen fuel cell standard ;

[0055] The current value I of the methanol reforming hydrogen production fuel cell in each group of the first sample data is used as the input, and the performance standard value P of the methanol reforming hydrogen production fuel cell is used as the input. standard as labels, training the performance prediction model of the methanol reforming hydrogen production fuel cell, determining the structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell, and obtaining a trained performance prediction model of the methanol reforming hydrogen production fuel cell.

[0056] It should be noted that this embodiment focuses on the process of training the performance prediction model of methanol reforming hydrogen fuel cell. This involves obtaining a first sample set, where each set of sample data includes current values, voltage values ​​and efficiency measured values. These data will be used to train the model to predict the performance of the battery.

[0057] Specifically, the first sample set is obtained by collecting experimental or historical operation data. The current value and voltage value in the sample set are the measured values ​​of the battery under specific conditions, and the efficiency measured value is the efficiency actually measured under these conditions. The performance standard value is calculated based on the measured value and voltage value and is used as a reference value for training the model. The model training process may include steps such as data preprocessing, feature selection, model selection, and parameter optimization.

[0058] Preferably, the model training can adopt the least square method, which is a common mathematical optimization technique for finding the best function match for the data by minimizing the sum of squares of errors. In the model, multiple parameters may need to be determined, such as the slope and intercept in a linear regression model.

[0059] Further, techniques such as cross-validation can be used to evaluate the performance of the model and select the best model structure and parameters. Alternatives may include adopting nonlinear models or machine learning methods such as support vector machines or deep learning models to handle more complex data relationships.

[0060] In some embodiments, in the methanol reforming hydrogen production fuel cell performance prediction model, the structure and parameters of the methanol reforming hydrogen production fuel cell performance prediction model are determined based on the LS least squares method.

[0061] It should be noted that this embodiment describes in detail how to use the least squares method LS to determine the structure and parameters of the methanol reforming hydrogen fuel cell performance prediction model. The least squares method is a mathematical optimization technique that finds the best function matching of data by minimizing the sum of squares of errors.

[0062] Specifically, the least square method mentioned in the embodiment is applied to the estimation of model parameters. The structure of the model may be a linear regression model, whose parameters include slope and intercept. These parameters are determined by minimizing the sum of squares of errors between predicted values ​​and actual values. In actual operation, this involves setting an objective function that calculates the prediction error of all sample data and finding the parameter value that minimizes this objective function.

[0063] Preferably, to improve the predictive accuracy of the model, regularization techniques such as ridge regression or Lasso can be used to avoid overfitting. In addition, stepwise regression or other feature selection methods can be used to determine which input variables contribute most to the predictive ability of the model.

[0064] Further alternatives include using nonlinear models such as polynomial regression or tree-based models that are able to capture more complex data patterns. In terms of parameter optimization, in addition to the traditional least squares method, you can also consider using gradient descent or other optimization algorithms to find the optimal parameters.

[0065] In some embodiments, the structure and parameters of the methanol reforming hydrogen production fuel cell performance prediction model are determined in the following manner: the methanol reforming hydrogen production fuel cell performance prediction value P and the methanol reforming hydrogen production fuel cell current value I satisfy:

[0066] P=aI 2 +bI+c (1)

[0067] The performance standard values ​​and performance prediction values ​​of methanol reforming hydrogen production fuel cells meet the following requirements:

[0068]

[0069] Where n represents the number of groups of the first sample data in the first sample set; P standard(i) represents the standard value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group, and P(i) represents the predicted value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group;

[0070] Based on the LS least squares method, the parameters a, b and c are estimated with the minimum value of J(a, b, c) as the goal, and the estimated values ​​of the parameters a, b and c are obtained;

[0071] The trained methanol reforming hydrogen fuel cell performance prediction model is:

[0072] P=a′I+b′ (3)

[0073] Specifically, the performance standard value mentioned in the embodiment is calculated by measuring the efficiency value and the voltage value. This involves dividing the measured efficiency value by the voltage value and then adding the height difference between the measurement positions of the voltage value. The height difference between the measurement positions of the voltage value here is an important correction factor, which takes into account the voltage drop that may exist inside the battery.

[0074] Preferably, during the model training process, automated feature engineering tools can be used to identify and select the parameters that have the greatest impact on performance prediction. In addition, automated model selection and hyperparameter optimization techniques, such as grid search or random search, can be used to determine the optimal model structure and parameters.

[0075] Further alternatives include employing ensemble learning methods such as random forests or gradient boosting machines, which can improve the generalization ability and prediction accuracy of the model.

[0076] In some embodiments, the performance standard value of the methanol reforming hydrogen production fuel cell is obtained according to the following method:

[0077]

[0078] Among them, η measured (i) represents the measured value of the methanol reforming hydrogen production fuel cell efficiency in the first sample data of the i-th group, P c (i) represents the voltage value of the methanol reforming hydrogen production fuel cell in the i-th group of first sample data, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

[0079] It should be noted that this embodiment describes a method for obtaining a performance standard value of a methanol reforming hydrogen production fuel cell. The performance standard value is a key reference in model training, which is obtained through a specific calculation formula based on the measured value of the battery efficiency and voltage value.

[0080] Specifically, the calculation of the performance standard value involves two main parameters: the measured efficiency value and the voltage value. The measured efficiency value refers to the actual efficiency of the battery under specific operating conditions, while the voltage value is the potential difference between the two ends of the battery. The height difference value refers to the difference between the measurement positions of the battery voltage value. This parameter plays a corrective role in the calculation to ensure the accuracy of the performance standard value. The calculation formula is the measured efficiency value divided by the voltage value, and then added to the height difference between the measurement positions of the voltage value.

[0081] Preferably, in order to improve the accuracy of the performance standard value calculation, high-precision measuring equipment can be used to obtain the measured efficiency value and voltage value. In addition, advanced data processing techniques such as signal filtering and data smoothing can be used to reduce the impact of measurement noise.

[0082] Further alternatives include using different correction factors, such as temperature or pressure differences, to accommodate different operating conditions or battery types. During model training, cross-validation can also be considered to evaluate the prediction effect of the performance standard value and adjust the calculation formula accordingly.

[0083] In some embodiments, the methanol reforming hydrogen production fuel cell efficiency compensation model is trained by: obtaining a second sample set, each set of second sample data in the second sample set includes: a measured value of the methanol reforming hydrogen production fuel cell efficiency η measured , the voltage value V of the methanol reforming hydrogen production fuel cell, the current value I of the methanol reforming hydrogen production fuel cell, the temperature value T of the methanol reforming hydrogen production fuel cell, the gas flow value F and the methanol concentration value C;

[0084] Input the current value I of the methanol reforming hydrogen production fuel cell in each group of second sample data into the trained methanol reforming hydrogen production fuel cell performance prediction model, and obtain the corresponding methanol reforming hydrogen production fuel cell performance prediction value P after processing;

[0085] Based on the methanol reforming hydrogen production fuel cell performance prediction value P and voltage value V corresponding to each set of second sample data, the corresponding methanol reforming hydrogen production fuel cell efficiency prediction value η is obtained;

[0086] The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell in each group of second sample data are used as input, the predicted value η of the methanol reforming hydrogen production fuel cell efficiency and the measured value η of the methanol reforming hydrogen production fuel cell efficiency measured The difference between is used as a label to train the methanol reforming hydrogen production fuel cell efficiency compensation model to obtain a trained methanol reforming hydrogen production fuel cell efficiency compensation model.

[0087] It should be noted that this embodiment describes in detail the training process of the methanol reforming hydrogen production fuel cell efficiency compensation model. The model is trained by using the data of the second sample set, including the efficiency measured value, voltage value, current value, temperature value, gas flow value and methanol concentration value, so as to more accurately predict the battery efficiency.

[0088] Specifically, the second sample set contains multiple sets of data, each of which covers the key parameters of battery operation. These parameters include the measured efficiency of the battery, which is the efficiency actually measured under specific conditions; the voltage value, which is the potential difference between the two ends of the battery; the current value, which is the amount of charge flowing through the battery; the temperature value, which reflects the operating temperature of the battery; the gas flow value, which is the amount of gas entering the battery; and the methanol concentration value, which is the concentration of methanol before entering the battery. These data will be used as input to the model, and the difference between the efficiency prediction value and the measured value will be used as the label for model training.

[0089] Preferably, when training the efficiency compensation model, a radial basis function neural network RBFNN can be used. RBFNN is a commonly used neural network suitable for processing nonlinear problems. It uses radial basis function as an activation function to achieve efficient nonlinear fitting. During the model training process, the parameters of the network, such as the number of neurons in the hidden layer, the learning rate and the regularization parameter, can be adjusted to optimize the performance of the model.

[0090] Furthermore, different performance evaluation indicators, such as mean square error (MSE) or mean absolute error (MAE), can be used to monitor the model's training progress and adjust the training strategy accordingly. Alternatives may include using other types of neural networks, such as convolutional neural networks (CNN) or recurrent neural networks (RNN), which may be more suitable for processing data with specific structures or time series data.

[0091] In some embodiments, the predicted value η of the efficiency of the methanol reforming hydrogen production fuel cell is calculated according to the following formula, including:

[0092]

[0093] Wherein, P represents the performance prediction value of the methanol reforming hydrogen production fuel cell, V represents the voltage value of the methanol reforming hydrogen production fuel cell, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

[0094] It should be noted that this embodiment describes a method for calculating the efficiency prediction value of a methanol reforming hydrogen production fuel cell. The method uses the performance prediction value and voltage value of the methanol reforming hydrogen production fuel cell to calculate the efficiency prediction value through a specific formula.

[0095] Specifically, the calculation of the efficiency prediction value involves two key parameters: performance prediction value and voltage value. The performance prediction value is the battery performance indicator obtained by model prediction, while the voltage value is the potential difference between the two ends of the battery. The height difference value in the formula refers to the difference between the measurement positions of the battery voltage value. This parameter plays a corrective role in the calculation to ensure the accuracy of the efficiency prediction value. The calculation formula is the performance prediction value minus the product of the voltage value and the height difference value.

[0096] Preferably, in order to improve the calculation accuracy of the efficiency prediction value, a high-precision measuring device can be used to obtain the performance prediction value and the voltage value. In addition, advanced data processing techniques, such as signal filtering and data smoothing, can be used to reduce the impact of measurement noise.

[0097] Furthermore, other influencing factors such as temperature and pressure can be introduced during the calculation process to further improve the accuracy of the prediction. Alternative solutions include using different correction factors, such as considering the effects of battery aging or environmental changes, to adapt to different operating conditions or battery states.

[0098] In some embodiments, the methanol reforming hydrogen production fuel cell efficiency compensation model is implemented based on a radial basis function neural network.

[0099] Specifically, the RBFNN model includes an input layer, a hidden layer, and an output layer. The input layer receives parameters such as the battery current value, temperature value, gas flow value, and methanol concentration value. The hidden layer is composed of multiple radial basis function neurons, each neuron corresponds to a radial basis function, which is used to process the nonlinear mapping of the input data. The output layer generates an efficiency error prediction value, which is used to compensate for the efficiency prediction value. During the model training process, it is necessary to set and adjust the parameters of the network, including the number of neurons, learning rate, regularization parameters, etc.

[0100] Preferably, when training the RBFNN model, a variety of radial basis functions, such as Gaussian functions, polynomial functions, etc., can be used to adapt to different data distributions and nonlinear characteristics. In addition, advanced optimization techniques such as genetic algorithms and particle swarm optimization can be used to determine the optimal network parameters and weights. In the model verification and testing stage, methods such as cross-validation can be used to evaluate the generalization ability of the model.

[0101] Further alternatives may include adopting other types of neural networks, such as deep belief networks (DBNs) or long short-term memory networks (LSTMs), which may be better suited for processing complex sequence data or data with deep structures.

[0102] 9 In some embodiments, the method further comprises: during the real-time data collection process, regularly collecting the actual measured value of the efficiency of the methanol reforming hydrogen production fuel cell;

[0103] If the error between the regularly collected actual measured value of the methanol reforming hydrogen fuel cell efficiency and the final methanol reforming hydrogen fuel cell efficiency detection result obtained based on the actual collected data at that moment is lower than the set error, the actual collected data at that moment and the actual measured value of the methanol reforming hydrogen fuel cell efficiency are used as a set of correction data, and multiple sets of correction data form a correction data set, and the methanol reforming hydrogen fuel cell efficiency compensation model is corrected online based on the correction data set.

[0104] It should be noted that this embodiment describes the online correction process of the methanol reforming hydrogen production fuel cell efficiency compensation model. This process involves real-time data collection and regular collection of measured values, as well as online updating and optimization of the model based on these data.

[0105] Specifically, the online correction process includes real-time collection of operating data of the methanol reforming hydrogen fuel cell, such as current, voltage, temperature, gas flow rate and methanol concentration. At the same time, the actual efficiency values ​​are collected regularly, which are direct measurements of the actual operating efficiency of the battery. If the error between the actual measured value and the efficiency value predicted by the model is lower than the preset error threshold, then these data will be regarded as correction data.

[0106] Preferably, when implementing online corrections, incremental learning or online learning techniques in machine learning can be used. These techniques allow the model to be updated in real time when new data is received without having to retrain from scratch.

[0107] Furthermore, a dynamic update mechanism can be set up to adjust the frequency and amplitude of model updates according to the size and frequency of errors.

[0108] Going a step further, alternatives include using adaptive filtering algorithms, such as Kalman filters, which can fine-tune model parameters while maintaining model stability. In addition, it is also possible to consider introducing expert systems to allow domain experts to manually intervene and correct when the model performs poorly.

[0109] In some embodiments, the temperature value of the methanol reforming hydrogen production fuel cell is detected based on a thermocouple disposed in the methanol reforming hydrogen production fuel cell.

[0110] It should be noted that this embodiment describes a method for obtaining the temperature value of a methanol reforming hydrogen production fuel cell. The temperature value is an important parameter in battery performance evaluation. By accurately measuring the temperature of the battery, the operating state of the battery can be better monitored and controlled.

[0111] Specifically, the temperature value of the methanol reforming hydrogen fuel cell is detected by a thermocouple installed in the battery. Thermocouple is a commonly used temperature sensor that can convert temperature changes into electrical signals to achieve accurate temperature measurement. In practical applications, the type, installation location and number of thermocouples are determined according to the design and operating conditions of the battery.

[0112] Preferably, in order to improve the accuracy and reliability of temperature measurement, a high-precision thermocouple can be used and ensure good contact with the battery. In addition, temperature compensation technology can be used to correct the measurement error caused by the characteristics of the thermocouple itself. In terms of data processing, a filtering algorithm can be used to reduce noise interference and improve the quality of temperature data.

[0113] Further alternatives include using other types of temperature sensors, such as thermistors or infrared sensors, which may be better suited for specific application scenarios or provide additional functionality, such as non-contact measurement.

[0114] The above-mentioned embodiments of the present invention have the following beneficial effects: The methanol reforming hydrogen production fuel cell modeling and simulation method of the present invention can collect key operating parameters in real time, and accurately predict the battery performance and efficiency through advanced prediction models. This method can predict the performance and efficiency of the battery through real-time data input combined with a well-trained model, and then compensate the efficiency prediction value through the efficiency error prediction value, and finally obtain a more accurate efficiency detection result. This can not only improve the operating stability and efficiency of the methanol reforming hydrogen production fuel cell, but also reduce energy consumption and optimize the operating conditions of the battery.

[0115] In addition, the present invention also provides a method for continuously optimizing the model through an online correction mechanism. By regularly collecting measured values ​​and comparing them with the predicted results, if the error is lower than the set value, these data are used as correction data to update and optimize the efficiency compensation model. This mechanism can ensure that the model maintains high prediction accuracy and adaptability during long-term operation, while reducing the system's dependence on manual intervention and reducing maintenance costs. In this way, the performance and efficiency of methanol reforming hydrogen fuel cells can be continuously improved, and the reliability and stability of the system can be enhanced.

[0116] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0117] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention to form a technical solution.

Claims

1. A modeling and simulation method for a methanol reforming hydrogen production fuel cell, characterized in that: include: Real-time data collection, including: current value I, voltage value V, temperature value T, gas flow value F and methanol concentration value C of methanol reforming hydrogen fuel cell; The current value I of the methanol reforming hydrogen production fuel cell collected in real time is input into the trained methanol reforming hydrogen production fuel cell performance prediction model, and after processing, the methanol reforming hydrogen production fuel cell performance prediction value P is obtained; Based on the predicted value P of the performance of the methanol reforming hydrogen production fuel cell and the voltage value V collected in real time, a predicted value η of the efficiency of the methanol reforming hydrogen production fuel cell is obtained; The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell collected in real time are input into the trained methanol reforming hydrogen production fuel cell efficiency compensation model, and after processing, the methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is obtained; The methanol reforming hydrogen production fuel cell efficiency error prediction value Δη is used to compensate the methanol reforming hydrogen production fuel cell efficiency prediction value η to obtain the final methanol reforming hydrogen production fuel cell efficiency detection result η final .

2. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 1 is characterized in that: The performance prediction model of the methanol reforming hydrogen production fuel cell is trained by: obtaining a first sample set, wherein each group of first sample data in the first sample set includes: a current value I of the methanol reforming hydrogen production fuel cell, a voltage value V of the methanol reforming hydrogen production fuel cell, and a measured efficiency value η of the methanol reforming hydrogen production fuel cell measured ; Based on the measured value η of the methanol reforming hydrogen production fuel cell efficiency in each group of first sample data measured and voltage value V, and obtain the performance standard value P of methanol reforming hydrogen fuel cell standard ; The current value I of the methanol reforming hydrogen production fuel cell in each group of the first sample data is used as the input, and the performance standard value P of the methanol reforming hydrogen production fuel cell is used as the input. standard as labels, training the performance prediction model of the methanol reforming hydrogen production fuel cell, determining the structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell, and obtaining a trained performance prediction model of the methanol reforming hydrogen production fuel cell.

3. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 2 is characterized in that: In the methanol reforming hydrogen production fuel cell performance prediction model, the structure and parameters of the methanol reforming hydrogen production fuel cell performance prediction model are determined based on the LS least squares method.

4. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 3 is characterized in that: The structure and parameters of the performance prediction model of the methanol reforming hydrogen production fuel cell are determined in the following manner: the performance prediction value P of the methanol reforming hydrogen production fuel cell and the current value I of the methanol reforming hydrogen production fuel cell satisfy: P=aI 2 +bI+c (1) The performance standard values ​​and performance prediction values ​​of methanol reforming hydrogen production fuel cells meet the following requirements: Where n represents the number of groups of the first sample data in the first sample set; P standard (i) represents the standard value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group, and P(i) represents the predicted value of the performance of the methanol reforming hydrogen production fuel cell in the first sample data of the i-th group; Based on the LS least squares method, the parameters a, b and c are estimated with the minimum value of J(a, b, c) as the goal, and the estimated values ​​of the parameters a, b and c are obtained; The trained methanol reforming hydrogen fuel cell performance prediction model is: P=a′I+b′ (3) 5. The modeling and simulation method of a methanol reforming hydrogen production fuel cell according to claim 4, characterized in that: The performance standard value of methanol reforming hydrogen production fuel cell is obtained according to the following method: Among them, η measured (i) represents the measured value of the methanol reforming hydrogen production fuel cell efficiency in the first sample data of the i-th group, P c (i) represents the voltage value of the methanol reforming hydrogen production fuel cell in the i-th group of first sample data, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

6. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 1, characterized in that: The methanol reforming hydrogen production fuel cell efficiency compensation model is trained by: obtaining a second sample set, each set of second sample data in the second sample set includes: a measured value η of the methanol reforming hydrogen production fuel cell efficiency measured , the voltage value V of the methanol reforming hydrogen production fuel cell, the current value I of the methanol reforming hydrogen production fuel cell, the temperature value T of the methanol reforming hydrogen production fuel cell, the gas flow value F and the methanol concentration value C; Input the current value I of the methanol reforming hydrogen production fuel cell in each group of second sample data into the trained methanol reforming hydrogen production fuel cell performance prediction model, and obtain the corresponding methanol reforming hydrogen production fuel cell performance prediction value P after processing; Based on the methanol reforming hydrogen production fuel cell performance prediction value P and voltage value V corresponding to each set of second sample data, the corresponding methanol reforming hydrogen production fuel cell efficiency prediction value η is obtained; The current value I, temperature value T, gas flow value F and methanol concentration value C of the methanol reforming hydrogen production fuel cell in each group of second sample data are used as input, the predicted value η of the methanol reforming hydrogen production fuel cell efficiency and the measured value η of the methanol reforming hydrogen production fuel cell efficiency measured The difference between is used as a label to train the methanol reforming hydrogen production fuel cell efficiency compensation model to obtain a trained methanol reforming hydrogen production fuel cell efficiency compensation model.

7. The methanol reforming hydrogen production fuel cell modeling simulation method according to claim 1 or 6, characterized in that: The predicted value η of the methanol reforming hydrogen production fuel cell efficiency is calculated according to the following formula, including: Wherein, P represents the performance prediction value of the methanol reforming hydrogen production fuel cell, V represents the voltage value of the methanol reforming hydrogen production fuel cell, and ΔH represents the height difference between the measurement positions of the voltage value of the methanol reforming hydrogen production fuel cell.

8. The method for modeling and simulating a methanol reforming hydrogen production fuel cell according to claim 1 or 6, characterized in that: The efficiency compensation model of methanol reforming hydrogen production fuel cell is realized based on radial basis function neural network.

9. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 1, characterized in that: The method further comprises: during the real-time data collection process, regularly collecting the actual measured value of the efficiency of the methanol reforming hydrogen production fuel cell; If the error between the regularly collected actual measured value of the methanol reforming hydrogen fuel cell efficiency and the final methanol reforming hydrogen fuel cell efficiency detection result obtained based on the actual collected data at that moment is lower than the set error, the actual collected data at that moment and the actual measured value of the methanol reforming hydrogen fuel cell efficiency are used as a set of correction data, and multiple sets of correction data form a correction data set, and the methanol reforming hydrogen fuel cell efficiency compensation model is corrected online based on the correction data set.

10. The methanol reforming hydrogen production fuel cell modeling and simulation method according to claim 1, characterized in that: The temperature value of the methanol reforming hydrogen production fuel cell is detected based on a thermocouple arranged in the methanol reforming hydrogen production fuel cell.

Images