A hydrogen fuel cell evaluation method based on entropy-weighted stack stability index

Abstract

The present invention discloses a hydrogen fuel cell evaluation method based on an entropy-weighted stack stability index, comprising the following steps: S1, inputting a voltage matrix of each single cell, calculating the average value of each single cell voltage, and constructing an average value matrix of the single cell voltage; S2, calculating the mean deviation of the single cell voltage, and constructing a mean value matrix of the single cell voltage; S3, dividing the mean deviation of the single cell voltage into intervals, and constructing a mean deviation interval matrix of the single cell voltage; S4, calculating the frequency of each mean deviation interval area, and constructing a frequency matrix of each interval data; S5, calculating the Shannon entropy of each single cell, and constructing a Shannon entropy value matrix; S6, calculating the deviation value of the mean deviation interval relative to the target interval, and constructing a weighted deviation matrix; S7, calculating the entropy-weighted stack stability index, and constructing an entropy-weighted stack stability index matrix; S8, using the entropy-weighted stack stability index to evaluate the consistency and stability between multiple single cells in a hydrogen fuel cell system.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a hydrogen fuel cell evaluation method based on an entropy-weighted stack stability index. Background Art

[0002] Currently, hydrogen fuel cell stacks, a key component of hydrogen fuel cell engine systems, consist of multiple cells connected in series. Inconsistencies in cell voltage directly impact the performance stability and consistency of the entire stack. In actual operation, the stack exhibits a "barrel effect," where its lifespan is determined by the performance of the worst-performing cell. Therefore, evaluating fuel cell stack voltage consistency is essential for improving performance and extending lifespan.

[0003] Traditional battery stack consistency assessment methods typically use graphical methods, single-cell voltage fluctuation amplitude, and single-cell voltage root mean square (RMS) methods. Existing methods mostly rely on intuitive test data, such as changes in parameters such as voltage, current, and temperature. However, these methods fail to fully consider the relative differences between batteries and ignore the comprehensive consideration of multi-dimensional data. Specifically, the graphical method can intuitively reflect the fluctuation of single-cell voltage, but every time an additional factor affecting single-cell performance is added, the number of graphs increases significantly, or an additional dimension is added to the coordinates. Therefore, the graphical method is not suitable for the analysis of voltage consistency under multiple factors. At the same time, without the help of other evaluation indicators, it is difficult to quantitatively analyze voltage consistency using the graphical method. The single-cell voltage fluctuation amplitude and single-cell voltage root mean square (RMS) are not suitable for direct use in situations where the data measurement range is too large or the data dimensions are different. When the voltage fluctuation range is too large, the fluctuation amplitude and the RMS value will be too dependent on the extreme values. The extreme maximum or minimum values ​​will distort the fluctuation amplitude or RMS value, making these indicators no longer able to truly reflect the uniformity of battery performance. When the data dimensions are different, since these two methods do not normalize or standardize the voltage values ​​of different dimensions, simply using the fluctuation amplitude or RMS value cannot provide a fair assessment.

[0004] With the gradual development of fuel cell technology, objectively and accurately evaluating the consistency of fuel cell stacks has become a pressing technical challenge. Traditional evaluation methods struggle to comprehensively consider multiple factors affecting a battery, especially considering its dynamic behavior and complex operating environments. The lack of a scientific evaluation method that can integrate these multiple factors hinders the management, monitoring, and prediction of fuel cell performance, making it difficult to meet actual usage requirements. Summary of the Invention

[0005] To solve the above problems, the present invention proposes a hydrogen fuel cell evaluation method based on entropy-weighted stack stability index.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] A hydrogen fuel cell evaluation method based on an entropy-weighted stack stability index comprises the following steps:

[0008] S1. Input the voltage matrix of each single cell, calculate the average value of each cell voltage, and construct the average value matrix of the cell voltage; wherein the voltage matrix of each single cell is: , where is the voltage matrix of each single battery; is an element in the voltage matrix, i=1,2,…,m, i represents the different moments or different steady states of the battery, j=1,2,…,n, j represents the number of the single battery;

[0009] S2. Calculate the deviation of the cell voltage from the mean and construct a cell voltage deviation matrix; wherein the cell voltage deviation matrix is: , where is the mean value matrix of the monomer voltage; is the element in the mean value matrix of the monomer voltage, and the calculation formula is: , where is the element in the matrix of the average value of the cell voltage;

[0010] S3. Divide the mean difference of the cell voltage into intervals and construct a mean difference interval matrix of the cell voltage; wherein the mean difference interval matrix of the cell voltage is: , where is the mean difference interval matrix of the monomer voltage; is the element in the mean difference interval matrix of the single cell voltage, and the calculation formula is: ;

[0011] S4. Calculate the frequency of each deviation interval and construct a frequency matrix for each interval data. The frequency matrix of the interval data is: , where is the frequency matrix of interval data; is an element in the frequency matrix of interval data, and the calculation process is: ,

[0012] Where, is the indicator function, defined as follows: , where S is a set; x is an element;

[0013] S5. Calculate the Shannon entropy of each single battery and construct a Shannon entropy matrix; wherein the Shannon entropy matrix is: , where is the Shannon entropy matrix; is the Shannon entropy matrix for calculating the inconsistency between individual cells; is the Shannon entropy matrix when calculating the stability of the j-th single cell; is an element in the Shannon entropy matrix, and the calculation process is: ;

[0014] S6. Calculate the deviation of the mean difference interval relative to the target interval and construct a weighted deviation matrix; wherein the weighted deviation matrix is: , where is the weighted deviation matrix; is the weighted deviation matrix used to calculate the inconsistency between individual cells; is the weighted deviation matrix when calculating the stability of the j-th single cell; is the element in the weighted deviation matrix, and the calculation process is: ;

[0015] S7. Calculate the entropy-weighted fuel cell stability index and construct an entropy-weighted fuel cell stability index matrix; wherein the entropy-weighted fuel cell stability index matrix is: , where is the entropy-weighted stack stability index matrix; is the entropy-weighted stability index matrix used to calculate the inconsistency between individual cells; The entropy-weighted stability index matrix is ​​used to calculate the stability of each battery during operation; is an element in the entropy-weighted stack stability index matrix, and the calculation process is: , where the exponential term is a weighted term, which is used to amplify the impact of data deviation from the target interval, so that data points far away from the target interval have a greater impact on the results; β is an adjustment parameter used to control the influence of weighted deviation on the entropy-weighted stack stability index. β Balancing dispersion and deviation;

[0016] S8. Use the entropy-weighted stack stability index to evaluate the consistency and stability between multiple cells in a hydrogen fuel cell system.

[0017] Preferably, the average value matrix of the cell voltage in step S1 is: , where The calculation formula is: .

[0018] Preferably, the specific process of dividing the deviation of the cell voltage from the mean into intervals in step S3 is: dividing the deviation voltage value from the mean into multiple intervals with a length of 5 mV, and the starting value of the interval is 0 mV.

[0019] After adopting the above technical solution, the present invention has the following beneficial effects: the entropy-weighted stack stability index calculated by the present invention can objectively and comprehensively evaluate the consistency and difference between multiple single cells in the hydrogen fuel cell system and the stability of each single cell over time and working conditions. Through multi-dimensional consistency and stability analysis, the present invention can not only see the differences in hydrogen fuel cells in certain dimensions (such as time, current, voltage, temperature, humidity), but also quantify their similarities and consistency in multi-dimensional data space, thereby providing a valuable basis for optimizing the performance of hydrogen fuel cell systems. The present invention is suitable for scenarios that require comprehensive consideration of multi-dimensional factors and quantification of uncertainties. It can be widely used in the consistency and stability evaluation of hydrogen fuel cell stacks, which is conducive to the management, supervision and prediction of fuel cell performance. It has important application value in the following fields: (1) Battery manufacturing industry: used for monitoring and controlling the consistency of stacks during the production process; (2) Electric vehicle industry: used for consistency testing and monitoring of electric vehicle battery systems to ensure the overall performance and stability of battery packs; (3) Energy storage system: used for consistency management of batteries in large-scale energy storage systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of the process of the present invention;

[0021] Figure 2 This is a graph showing how the entropy-weighted stack stability index of the present invention changes over time. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0023] like Figures 1 to 2 As shown, a hydrogen fuel cell evaluation method based on entropy-weighted stack stability index includes the following steps:

[0024] S1. Input the voltage matrix of each single cell, calculate the average value of each cell voltage, and construct the average value matrix of the cell voltage; wherein the voltage matrix of each single cell is: , where is the voltage matrix of each single battery; is an element in the voltage matrix, i=1,2,…,m, i represents the different moments or different steady states of the battery, j=1,2,…,n, j represents the number of the single battery;

[0025] The average value matrix of the cell voltage in step S1 is: , where The calculation formula is: ;

[0026] S2. Calculate the deviation of the cell voltage from the mean and construct a cell voltage deviation matrix; wherein the cell voltage deviation matrix is: , where is the mean value matrix of the monomer voltage; is the element in the mean value matrix of the monomer voltage, and the calculation formula is: , where is the element in the matrix of the average value of the cell voltage;

[0027] S3. Divide the mean difference of the cell voltage into intervals and construct a mean difference interval matrix of the cell voltage; wherein the mean difference interval matrix of the cell voltage is: , where is the mean difference interval matrix of the monomer voltage; is the element in the mean difference interval matrix of the single cell voltage, and the calculation formula is: ;

[0028] The specific process of dividing the deviation of the cell voltage from the mean into intervals in step S3 is as follows: dividing the deviation voltage value from the mean into multiple intervals of 5 mV, with the starting value of the interval being 0 mV;

[0029] S4. Calculate the frequency of each deviation interval and construct a frequency matrix for each interval data. The frequency matrix of the interval data is: , where is the frequency matrix of interval data; is an element in the frequency matrix of interval data, and the calculation process is: ,

[0030] Where, is the indicator function, defined as follows: , where S is a set; x is an element;

[0031] S5. Calculate the Shannon entropy of each single battery and construct a Shannon entropy matrix; wherein the Shannon entropy matrix is: , where is the Shannon entropy matrix; is the Shannon entropy matrix for calculating the inconsistency between individual cells; is the Shannon entropy matrix when calculating the stability of the j-th single cell; is an element in the Shannon entropy matrix, and the calculation process is: ;

[0032] S6. Calculate the deviation of the mean difference interval relative to the target interval and construct a weighted deviation matrix; wherein the weighted deviation matrix is: , where is the weighted deviation matrix; is the weighted deviation matrix used to calculate the inconsistency between individual cells; is the weighted deviation matrix when calculating the stability of the j-th single cell; is the element in the weighted deviation matrix, and the calculation process is: ;

[0033] S7. Calculate the entropy-weighted fuel cell stability index and construct an entropy-weighted fuel cell stability index matrix; wherein the entropy-weighted fuel cell stability index matrix is: , where is the entropy-weighted stack stability index matrix; is the entropy-weighted stability index matrix used to calculate the inconsistency between individual cells; The entropy-weighted stability index matrix is ​​used to calculate the stability of each battery during operation; is an element in the entropy-weighted stack stability index matrix, and the calculation process is: , where the exponential term is a weighted term, which is used to amplify the impact of data deviation from the target interval, so that data points far away from the target interval have a greater impact on the results; β is an adjustment parameter used to control the influence of weighted deviation on the entropy-weighted stack stability index. β Balancing dispersion and deviation;

[0034] S8. Use the entropy-weighted stack stability index to evaluate the consistency and stability between multiple cells in a hydrogen fuel cell system.

[0035] In a specific application example, the hydrogen fuel cell stack is operated under the following conditions: temperature of 75°C, humidity of 60%, back pressure of 150kPa, cathode stoichiometric ratio of 1.4, and current of Figure 2 Under loading conditions, the entropy weighted stack stability index (hereinafter referred to as entropy weighted index) changes with time as shown in the following figure: Figure 2 shown.

[0036] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A hydrogen fuel cell evaluation method based on entropy-weighted stack stability index, characterized in that: The following steps are involved: S1. Input the voltage matrix of each single cell, calculate the average value of each cell voltage, and construct the average value matrix of the cell voltage; wherein the voltage matrix of each single cell is: , where is the voltage matrix of each single battery; is an element in the voltage matrix, i=1,2,…,m, i represents the different moments or different steady states of the battery, j=1,2,…,n, j represents the number of the single battery; S2. Calculate the deviation of the cell voltage from the mean and construct a cell voltage deviation matrix; wherein the cell voltage deviation matrix is: , where is the mean value matrix of the monomer voltage; is the element in the mean value matrix of the monomer voltage, and the calculation formula is: , where is the element in the matrix of the average value of the cell voltage; S3. Divide the mean difference of the cell voltage into intervals and construct a mean difference interval matrix of the cell voltage; wherein the mean difference interval matrix of the cell voltage is: , where is the mean difference interval matrix of the monomer voltage; is the element in the mean difference interval matrix of the single cell voltage, and the calculation formula is: ; S4. Calculate the frequency of each deviation interval and construct a frequency matrix for each interval data. The frequency matrix of the interval data is: , where is the frequency matrix of interval data; is an element in the frequency matrix of interval data, and the calculation process is: , Where, is the indicator function, defined as follows: , where S is a set; x is an element; S5. Calculate the Shannon entropy of each single battery and construct a Shannon entropy matrix; wherein the Shannon entropy matrix is: , where is the Shannon entropy matrix; is the Shannon entropy matrix for calculating the inconsistency between individual cells; is the Shannon entropy matrix when calculating the stability of the j-th single cell; is an element in the Shannon entropy matrix, and the calculation process is: ; S6. Calculate the deviation of the mean difference interval relative to the target interval and construct a weighted deviation matrix; wherein the weighted deviation matrix is: , where is the weighted deviation matrix; is the weighted deviation matrix used to calculate the inconsistency between individual cells; is the weighted deviation matrix when calculating the stability of the j-th single cell; is the element in the weighted deviation matrix, and the calculation process is: ; S7. Calculate the entropy-weighted fuel cell stability index and construct an entropy-weighted fuel cell stability index matrix; wherein the entropy-weighted fuel cell stability index matrix is: , where is the entropy-weighted stack stability index matrix; is the entropy-weighted stability index matrix used to calculate the inconsistency between individual cells; The entropy-weighted stability index matrix is ​​used to calculate the stability of each battery during operation; is an element in the entropy-weighted stack stability index matrix, and the calculation process is: , where the exponential term is a weighted term, which is used to amplify the impact of data deviation from the target interval, so that data points far away from the target interval have a greater impact on the results; β is an adjustment parameter used to control the influence of weighted deviation on the entropy-weighted stack stability index. β Balancing dispersion and deviation; S8. Use the entropy-weighted stack stability index to evaluate the consistency and stability between multiple cells in a hydrogen fuel cell system.

2. A hydrogen fuel cell evaluation method based on entropy-weighted stack stability index according to claim 1, characterized in that: The average value matrix of the cell voltage in step S1 is: , where The calculation formula is: .

3. The method for evaluating a hydrogen fuel cell based on an entropy-weighted stack stability index according to claim 1, wherein: The specific process of dividing the deviation of the cell voltage from the mean into intervals in step S3 is: dividing the deviation of the cell voltage from the mean into multiple intervals of 5 mV in length, with the starting value of the interval being 0 mV.

Images