Method and device for evaluating performance consistency of fuel cell

Abstract

The invention provides a method and a device for evaluating the performance consistency of a fuel cell, relates to the technical field of fuel cells, and solves the technical problem that the prior art is difficult to meet the requirement of the industry for comprehensively and accurately evaluating the performance of the fuel cell. The method comprises the following steps: acquiring measurement parameters of each fuel cell in an operation process through a sensor; the measurement parameters comprise battery performance measurement parameters and working condition environment parameters; analyzing the measurement parameters by adopting multiple linear regression analysis, and establishing a quantitative relation model corresponding to each fuel cell; the quantitative relation model is used for representing the incidence relation between the battery performance measurement parameters and the working condition environment parameters; and for each fuel cell, carrying out performance consistency evaluation on the cell performance prediction parameters obtained by calculation under the working condition environment parameters of the same working condition based on the corresponding quantitative relation model to obtain a performance consistency evaluation result. The method is used in the fuel cell evaluation process.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fuel cells, and particularly relates to a performance consistency evaluation method and device for fuel cells. BACKGROUND

[0002] As a high-efficiency clean energy conversion device, fuel cells have shown great application potential in the fields of automobiles and distributed power generation. However, the performance consistency problem has become a key bottleneck restricting the industrial scale development, directly affecting the system stability and reliability, and leading to uneven product quality and high cost.

[0003] At present, the performance consistency evaluation technology of fuel cells still faces many challenges. Limited by the technical principles and test conditions, the existing evaluation methods have deficiencies in systematization, working condition adaptability and measurement accuracy, and it is difficult to meet the needs of the industry for comprehensive and accurate evaluation of the performance of fuel cells, resulting in that the performance consistency evaluation effect in actual application is difficult to achieve the expected effect. SUMMARY

[0004] The present application provides a performance consistency evaluation method and device for fuel cells, which solves the technical problem that the prior art cannot meet the needs of the industry for comprehensive and accurate evaluation of the performance of fuel cells.

[0005] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, a performance consistency evaluation method for fuel cells is provided, comprising: collecting measurement parameters of each fuel cell in the running process through a sensor; the measurement parameters include battery performance measurement parameters and working condition environment parameters; the battery performance measurement parameters include voltage, current, battery internal temperature and battery internal pressure; the working condition environment parameters include gas flow, environmental temperature, environmental humidity and altitude; using multivariate linear regression analysis to analyze the measurement parameters, and establishing a quantitative relationship model corresponding to each fuel cell; the quantitative relationship model is used to represent the correlation between the battery performance measurement parameters and the working condition environment parameters; for each fuel cell, the battery performance prediction parameters calculated under the same working condition environment parameters based on the corresponding quantitative relationship model are used for performance consistency evaluation, and the performance consistency evaluation result is obtained.

[0007] Based on the technical solution, the application can collect measurement parameters of each fuel cell in the running process through a sensor, wherein the measurement parameters include battery performance measurement parameters and working condition environment parameters, so that various parameters affecting the performance of the fuel cell can be more comprehensively obtained, thereby avoiding the limitation of relying on a single parameter in the traditional method. Then, the application can analyze the measurement parameters by using multiple linear regression analysis, establish a corresponding quantitative relationship model for each fuel cell, and perform performance consistency evaluation on the battery performance prediction parameters calculated based on the corresponding quantitative relationship model under the same working condition environment parameters for each fuel cell, thereby ensuring the uniformity of the evaluation standard. In this way, the application can more comprehensively and accurately reflect the performance consistency of the fuel cell, and compared with the traditional method, the application considers more comprehensive factors and the evaluation result is closer to the actual situation, thereby providing more reliable basis for quality detection of fuel cell production enterprises and research and development test of research institutions.

[0008] In combination with the first aspect, in a possible implementation manner, the quantitative relationship model includes a dynamic weight adjustment function constructed based on the running time or the cumulative use times, and the dynamic weight adjustment function is used to adjust the weight of the battery performance measurement parameters and / or the working condition environment parameters in the quantitative relationship model.

[0009] In combination with the first aspect, in a possible implementation manner, the dynamic weight adjustment function is represented by the following formula:

[0010] w i (t)=w i0 ×e kt ;

[0011] wherein w i (t) is the weight of the i-th parameter in the measurement parameters at t, t is the running time or the cumulative use times, w i0 is the initial weight of the i-th parameter, and k is a fitting coefficient.

[0012] In combination with the first aspect, in a possible implementation manner, the quantitative relationship model is composed of the following formula:

[0013] Y=k1X1+k2X2+...+k n X n +b;

[0014] wherein Y is any one of the battery performance measurement parameters, X1, X2…X n are multiple items of the working condition environment parameters, k1, k2…k n are coefficients of the various working condition environment parameters, and b is a constant term, and the coefficients and the constant term are obtained by training the preprocessed measurement parameters through multiple linear regression analysis.

[0015] With the first aspect above, in a possible implementation, the working condition environment parameters of the same working condition correspond to at least two simulated working condition scenarios; the method comprises: for each simulated working condition scenario, inputting the corresponding working condition environment parameters into the quantitative relationship model to calculate the cell performance prediction parameters of each fuel cell under the simulated working condition scenario; and performing performance consistency evaluation on the cell performance prediction parameters of each fuel cell under each simulated working condition scenario to obtain the performance consistency evaluation result.

[0016] With the first aspect above, in a possible implementation, the method comprises: inputting the cell performance prediction parameters of each fuel cell under each simulated working condition scenario and the working condition environment parameters into the trained evaluation model as input parameters; the evaluation model comprises a feature extraction module and a performance consistency evaluation module; the feature extraction module is used to perform feature extraction on the input parameters to generate feature data; and the performance consistency evaluation module is used to perform performance consistency evaluation based on the extracted feature data to obtain the performance consistency evaluation result.

[0017] With the first aspect above, in a possible implementation, the input parameters further comprise raw material batch information of the fuel cell, the raw material batch information comprising electrode material batch number and electrolyte material batch number; wherein the raw material batch information is converted into a vector of the same dimension as the cell performance prediction parameters after encoding processing, and is input into the evaluation model after being spliced with the cell performance prediction parameters.

[0018] With the first aspect above, in a possible implementation, the method further comprises: performing a preprocessing operation on the collected measurement parameters; the preprocessing operation comprises smoothing processing and outlier removal; the smoothing processing is implemented based on a sliding average filtering algorithm; and the outliers in the outlier removal are measurement values that differ from the average value by more than 3 standard deviations.

[0019] In a second aspect, a performance consistency evaluation device for fuel cells is provided, comprising: a communication unit and a processing unit; the communication unit is configured to collect measurement parameters of each fuel cell during operation through a sensor; the measurement parameters comprise cell performance measurement parameters and working condition environment parameters; the cell performance measurement parameters comprise voltage, current, cell internal temperature and cell internal pressure; the working condition environment parameters comprise gas flow, environmental temperature, environmental humidity and altitude; the processing unit is configured to analyze the measurement parameters by using multivariate linear regression analysis to establish a corresponding quantitative relationship model for each fuel cell; the quantitative relationship model is used to represent the correlation between the cell performance measurement parameters and the working condition environment parameters; and the processing unit is configured to perform performance consistency evaluation on the cell performance prediction parameters of each fuel cell under the same working condition environment parameters calculated based on the corresponding quantitative relationship model to obtain a performance consistency evaluation result.

[0020] In a possible implementation manner of the second aspect, the quantitative relationship model comprises a dynamic weight adjustment function constructed based on the running time or the cumulative use times, and the dynamic weight adjustment function is used to adjust the weight of the battery performance measurement parameter and / or the working condition environment parameter in the quantitative relationship model.

[0021] In a possible implementation manner of the second aspect, the dynamic weight adjustment function is represented by the following formula:

[0022] w i (t)=w i0 ×e kt ;

[0023] wherein w i (t) is the weight of the i th parameter in the measurement parameter at t, t is the running time or the cumulative use times, w i0 is the initial weight of the i th parameter, and k is a fitting coefficient.

[0024] In a possible implementation manner of the second aspect, the quantitative relationship model is composed of the following formula:

[0025] Y=k1X1+k2X2+...+k n X n +b;

[0026] wherein Y is any one of the battery performance measurement parameters, X1, X2…X n are multiple ones of the working condition environment parameters, k1, k2…k n are coefficients of the working condition environment parameters, and b is a constant term, and the coefficients and the constant term are obtained by training the preprocessed measurement parameters through multiple linear regression analysis.

[0027] In a possible implementation manner of the second aspect, the working condition environment parameters of the same working condition correspond to at least two simulation working condition scenarios, and the processing unit is configured to: input the corresponding working condition environment parameters into the quantitative relationship model to obtain the battery performance prediction parameters of each fuel cell under the simulation working condition scenario for each simulation working condition scenario; and perform performance consistency evaluation through the battery performance prediction parameters of each fuel cell under each simulation working condition scenario to obtain the performance consistency evaluation result.

[0028] In a possible implementation manner of the second aspect, the processing unit is configured to: input the cell performance prediction parameters and the working condition environment parameters of each fuel cell under each simulated working condition scenario as input parameters into the trained evaluation model; the evaluation model comprises a feature extraction module and a performance consistency evaluation module; the feature extraction module is configured to perform feature extraction on the input parameters to generate feature data; and the performance consistency evaluation module is configured to perform performance consistency evaluation based on the extracted feature data to obtain a performance consistency evaluation result.

[0029] In a possible implementation manner of the second aspect, the input parameters further comprise raw material batch information of the fuel cell, the raw material batch information comprising an electrode material batch number and an electrolyte material batch number; and after being encoded, the raw material batch information is converted into a vector of the same dimension as the cell performance prediction parameters, and the vector is input into the evaluation model after being spliced with the cell performance prediction parameters.

[0030] In a possible implementation manner of the second aspect, the processing unit is configured to: perform a preprocessing operation on the collected measurement parameters; the preprocessing operation comprises smoothing processing and outlier removal; the smoothing processing is implemented based on a sliding average filtering algorithm; and the outliers in the outlier removal are measurement values that differ from the average value by more than 3 standard deviations.

[0031] In a third aspect, the present application provides a fuel cell performance consistency evaluation device, comprising: a processor and a storage medium; the storage medium comprises instructions, and the processor is configured to execute the instructions to implement the method described in any of the above embodiments. The fuel cell performance consistency evaluation device can be an electronic device or a chip in an electronic device.

[0032] In a fourth aspect, the present application provides a computer readable storage medium, which stores instructions, and when the instructions are executed on the fuel cell performance consistency evaluation device, the fuel cell performance consistency evaluation device executes the method described in any of the above embodiments.

[0033] In a fifth aspect, the present application provides a computer program product comprising instructions, and when the computer program product is executed on the fuel cell performance consistency evaluation device, the fuel cell performance consistency evaluation device executes the method described in any of the above embodiments.

[0034] It should be understood that the description of technical features, technical solutions, advantages or similar language in this application does not imply that all features and advantages can be realized in any single embodiment. On the contrary, it can be understood that the description of a feature or advantage means that the specific technical feature, technical solution or advantage is included in at least one embodiment. Therefore, the description of technical features, technical solutions or advantages in this specification does not necessarily refer to the same embodiment. Further, the technical features, technical solutions and advantages described in this embodiment can be combined in any appropriate manner. Those skilled in the art will understand that the embodiments can be implemented without one or more specific technical features, technical solutions or advantages of a specific embodiment. In other embodiments, additional technical features and advantages can be identified in specific embodiments that do not embody all embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A system architecture diagram of a fuel cell performance consistency evaluation system provided by an embodiment of the application is provided.

[0036] Figure 2 A flowchart of a fuel cell performance consistency evaluation method provided by an embodiment of the application is provided.

[0037] Figure 3 A flowchart of another fuel cell performance consistency evaluation method provided by an embodiment of the application is provided.

[0038] Figure 4 A flowchart of another fuel cell performance consistency evaluation method provided by an embodiment of the application is provided.

[0039] Figure 5 A flowchart of another fuel cell performance consistency evaluation method provided by an embodiment of the application is provided.

[0040] Figure 6 A structural diagram of a fuel cell performance consistency evaluation device provided by an embodiment of the application is provided.

[0041] Figure 7 A hardware structure diagram of a fuel cell performance consistency evaluation device provided by an embodiment of the application is provided. DETAILED DESCRIPTION

[0042] In the description of the application, unless otherwise specified, " / " means "or", for example, A / B can mean A or B. "And / or" herein is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean: A exists alone, A and B exist together, and B exists alone. In addition, "at least one" means one or more, and "multiple" means two or more. "First", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. do not necessarily mean different.

[0043] It should be noted that in this application, "exemplary" or "for example" means to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in this application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner.

[0044] Fuel cells, as a kind of efficient and clean energy conversion device, have received extensive attention and research in the context of today's energy transformation. It has many advantages such as high energy conversion efficiency, environmental friendliness, etc., and has shown great application potential in the fields of automobiles, distributed power generation, portable power sources, etc. However, in the practical application of fuel cells, the performance consistency problem has become one of the key factors restricting its large-scale promotion.

[0045] Currently, for the evaluation of fuel cell performance consistency, the methods and devices used in the industry have many shortcomings. In terms of evaluation methods, some traditional methods mainly rely on simple performance parameter measurement, such as only focusing on the output voltage or current of the fuel cell, while ignoring the influence of other key parameters on performance consistency. For example, during the operation of the fuel cell, changes in temperature and pressure will significantly affect its electrochemical reaction process, and thus affect performance. However, the existing simple measurement method cannot comprehensively and comprehensively consider these factors, resulting in inaccurate and comprehensive evaluation results of performance consistency.

[0046] In addition, some evaluation methods lack simulation of the actual operating conditions of fuel cells. Fuel cells have large differences in working conditions in different application scenarios, such as the start-stop, acceleration, deceleration process of a car, and the load change of a distributed power generation system. The existing evaluation methods are often tested under ideal steady-state conditions, which is far from the actual use. Therefore, the performance consistency evaluation results obtained based on this test method that deviates from the actual working conditions cannot truly reflect the performance of fuel cells in actual applications, making it difficult for enterprises to make accurate decisions when selecting products and designing applications.

[0047] In addition, the existing evaluation method and device are difficult to realize the rapid evaluation of a large number of fuel cell samples. With the development of the fuel cell industry, the production scale is continuously expanding, and the performance consistency of a large number of products needs to be evaluated. However, the existing means is inefficient and cannot meet the detection needs of large-scale production, which affects the production progress and product quality control to some extent. In summary, the existing fuel cell performance consistency evaluation method and device cannot meet the needs of the rapid development of the industry, and an evaluation method and device that is more efficient, accurate, simple and can simulate actual working conditions are needed to solve these problems.

[0048] Therefore, the embodiment of the present application provides a fuel cell performance consistency evaluation method, which collects measurement parameters of each fuel cell in the running process through a sensor, wherein the measurement parameters include battery performance measurement parameters and working condition environment parameters, so that various parameters affecting the performance of the fuel cell can be more comprehensively obtained, thereby avoiding the limitation of relying on a single parameter in the traditional method. Then, the present application can analyze the measurement parameters by using multivariate linear regression analysis, establish a corresponding quantitative relationship model for each fuel cell, and perform performance consistency evaluation on each fuel cell based on the battery performance prediction parameters calculated under the same working condition environment parameters of the corresponding quantitative relationship model, thereby ensuring the uniformity of the evaluation standard. In this way, the present application can more comprehensively and accurately reflect the performance consistency of the fuel cell, and compared with the traditional method, it considers more comprehensive factors and the evaluation result is closer to the actual situation, which can provide more reliable basis for quality detection of fuel cell production enterprises and research and development test of research institutions.

[0049] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0050] The fuel cell performance consistency evaluation method provided by the embodiment of the present application can be applied to a fuel cell performance consistency evaluation system as shown in Figure 1 , which comprises a fuel cell test module 101, a data acquisition and transmission module 102, a data analysis and processing module 103, and a man-machine interaction module 104. Figure 1

[0051] The fuel cell test module 101 is used to place the fuel cell to be tested and is equipped with various devices simulating actual working conditions to simulate different actual working conditions. For example, a load adjusting device simulates different power demands, and a gas supply device provides reaction gas with different flow rates and pressures.

[0052] ​The data acquisition and transmission module 102 is configured to acquire the measurement parameters (including the battery performance measurement parameters and the working condition environment parameters) in the operation process of the fuel cell through the sensors, and transmit the data to the data analysis and processing module 103 in real time. The sensors can be arranged at various positions of the fuel cell test module 101 and inside the fuel cell.

[0053] The data analysis and processing module 103 is internally provided with a processing logic based on the multiple linear regression analysis and the artificial intelligence algorithm, and is configured to establish a quantitative relationship model and perform the performance consistency evaluation.

[0054] The man-machine interaction module 104 is configured to provide an operation interface, and support the user to set the test parameters, view the evaluation results and the analysis report.

[0055] It should be noted that the embodiments of the present application can be mutually referenced or borrowed, for example, the same or similar steps, method embodiments, system embodiments and device embodiments can be mutually referenced, without limitation.

[0056] Figure 2 A flowchart of a performance consistency evaluation method of a fuel cell provided by an embodiment of the present application is shown in FIG. 1. Figure 2 As shown in the figure, the method comprises the following steps:

[0057] In step 201, the measurement parameters in the operation process of each fuel cell are acquired through the sensors.

[0058] The measurement parameters include the battery performance measurement parameters and the working condition environment parameters, the battery performance measurement parameters include the voltage, the current, the internal temperature of the battery and the internal pressure of the battery, and the working condition environment parameters include the gas flow, the environmental temperature, the environmental humidity and the altitude.

[0059] The sensors can be arranged at corresponding positions to ensure the data accuracy. For example, the pressure sensors are installed at the gas inlet and outlet of the battery stack, to monitor the pressure changes when the gas enters and exits the battery stack in real time, to determine the transmission resistance of the gas in the battery stack through the pressure difference, and to analyze the influence of the internal structure of the battery stack on the gas distribution consistency. The temperature sensors are pasted at different positions of the surface of the battery plate, for example, the thermistor type temperature sensors are used to accurately measure the temperature of each part during the operation of the battery, because the uniformity of the internal temperature distribution of the fuel cell has a great influence on the performance consistency. Meanwhile, the high-precision voltage and current sensors are connected to the positive and negative electrodes of the battery, to obtain the output voltage and current data in real time. In addition, the gas flow sensor is installed in the gas inlet pipeline, to monitor the flow of the hydrogen and oxygen (or air) entering the battery stack in real time. Each sensor acquires the data at a set sampling frequency of 100 Hz, and converts the analog signals into digital signals through the data acquisition module, and transmits the signals to the subsequent processing module.

[0060] In addition to collecting the fuel cell performance measurement parameters, external environmental data (such as ambient temperature, humidity, altitude) and fuel cell raw material batch information and other working condition environmental parameters can be fused. By combining these data with the fuel cell performance parameters, more comprehensive performance influencing factors can be mined. For example, during the data collection stage, environmental sensors such as temperature and humidity sensors, altitude sensors are added to collect real-time environmental data. At the same time, the raw material batch information of each fuel cell is recorded, including the batch number of the electrode material and the electrolyte material.

[0061] It should be noted that the collected multi-source parameters need to cover the performance of the battery itself and external environmental factors to ensure the comprehensiveness of subsequent analysis.

[0062] Step 202, using multiple linear regression analysis to analyze the measurement parameters, and establishing a quantitative relationship model corresponding to each fuel cell.

[0063] The quantitative relationship model is used to represent the correlation between the battery performance measurement parameters and the working condition environmental parameters.

[0064] In some embodiments, the quantitative relationship model is composed of the following formula:

[0065] Y = k1X1 + k2X2 +... + k n X n + b;

[0066] Where Y is any one of the battery performance measurement parameters, X1, X2... X n is a plurality of working condition environmental parameters, k1, k2... k n is the coefficient of each working condition environmental parameter, and b is a constant term. The coefficients and constant terms are obtained by training the preprocessed measurement parameters through multiple linear regression analysis.

[0067] For example, if the voltage in the battery performance measurement parameters is Y, the gas flow in the working condition environmental parameters is X1, and the ambient temperature is X2, the quantitative relationship model can be represented as Y = k1X1 + k2X2 + b, where k1 and k2 are coefficients, and b is a constant term. Through a large number of experimental data training, the least squares method is used to solve the coefficients, so that the sum of squared errors between the predicted value and the actual value of the model is minimized. For example, 1000 groups of environmental temperature, gas flow and voltage data under different working conditions are collected, and the data is divided into a training set (800 groups) and a test set (200 groups). Multiple iterations are performed on the training set to obtain the optimal values of the coefficients and the constant term, thereby determining the quantitative relationship model. The mean square error of the predicted value and the actual value is calculated by substituting the test set data into the model, and the accuracy of the model is evaluated.

[0068] It should be noted that the quantitative relationship model needs to be established for each fuel cell separately to reflect individual differences.

[0069] In step 203, for each fuel cell, the performance consistency evaluation is performed based on the cell performance prediction parameters calculated under the same working condition environmental parameters of the corresponding quantitative relationship model, and the performance consistency evaluation result is obtained.

[0070] In the same working condition, the working condition environmental parameters need to be consistent, for example, for 10 fuel cells of the same batch, the working condition parameters of the simulated uniform speed driving of the automobile (such as current 20A, gas flow 40L / min, and environmental temperature 25℃) are input.

[0071] In some implementations, the performance consistency evaluation can use cluster analysis, and the cell performance prediction parameters are used as feature vectors to calculate the Euclidean distance to determine the similarity. For example, if the Euclidean distance of the voltage prediction values of two fuel cells is less than a threshold value 5, it is considered that the performance consistency is good.

[0072] In some embodiments, the technical solutions provided by the embodiments of the present application can also be applied to the performance consistency evaluation of a fuel cell stack composed of multiple fuel cells. At this time, the performance consistency evaluation of the fuel cell stack is the performance consistency evaluation of the multiple fuel cells in the fuel cell stack. In addition, the fuel cell stack can also be evaluated as a whole, for example, the consistency evaluation of the cell performance of a single fuel cell under multiple working conditions.

[0073] It should be noted that the evaluation result needs to be judged in combination with the specific application scene, for example, the vehicle fuel cell has higher consistency requirements under the acceleration condition.

[0074] Based on the above technical solutions, the present application can collect the measurement parameters of each fuel cell in the running process through the sensor, wherein the measurement parameters include the cell performance measurement parameters and the working condition environmental parameters. In this way, various parameters affecting the performance of the fuel cell can be more comprehensively obtained, thereby avoiding the limitation of relying on a single parameter in the traditional method. Then, the present application can analyze the measurement parameters by using the multiple linear regression analysis, establish the corresponding quantitative relationship model of each fuel cell, and perform the performance consistency evaluation based on the cell performance prediction parameters calculated under the same working condition environmental parameters of the corresponding quantitative relationship model for each fuel cell, thereby ensuring the uniformity of the evaluation standard. In this way, the present application can more comprehensively and accurately reflect the performance consistency of the fuel cell. Compared with the traditional method, the present application considers more comprehensive factors, and the evaluation result is closer to the actual situation, which can provide more reliable basis for the quality detection of the fuel cell production enterprise and the research and development test of the research institution.

[0075] In addition, the quantitative relationship model can be dynamically adjusted in weight in the embodiments of the present application, so as to improve the accuracy of the evaluation.

[0076] As a possible embodiment of the present application, the quantitative relationship model comprises a dynamic weight adjustment function based on the running time or the cumulative use times, which is used to adjust the weight of the battery performance measurement parameters and / or the working condition environment parameters in the quantitative relationship model.

[0077] In some embodiments, the dynamic weight adjustment function is represented by the following formula:

[0078] w i (t)=w i0 ×e kt ;

[0079] wherein w i (t) is the weight of the i-th parameter in the measurement parameters at t, t is the running time or the cumulative use times, w i0 is the initial weight of the i-th parameter, and k is a fitting coefficient.

[0080] In some implementations, the value of k can be fitted by historical data. For example, the initial weight of the temperature parameter of a certain fuel cell is w i0 =0.3, and after the running time t=1000 hours, k=-0.0005, so the weight w i (1000) = 0.3×e -0.005×1000 ≈0.18.

[0081] It should be noted that the dynamic weight adjustment can make the model more suitable for the performance attenuation characteristics of the fuel cell with the use time. For example, the weight of the voltage parameter of a new battery is relatively high, and after 500 uses, the weight of the pressure parameter is increased due to the change of the sealing performance.

[0082] In some implementations, the weight adjustment can be performed in real time, for example, the weight value is updated every 1 hour. It should be noted that the model can dynamically reflect the change of the importance of the parameters, and improve the accuracy of the long-term evaluation.

[0083] Based on the above technical scheme, the dynamic weight adjustment function is constructed, so that the quantitative relationship model can adjust the weight of each parameter according to the running time or cumulative use frequency of the fuel cell, thus reflecting the characteristics of the change of the fuel cell performance with the use process, and the quantitative relationship model obtained can dynamically reflect the change of the importance of the parameters. This way solves the problem of the decrease in accuracy of the traditional fixed weight model in long-term evaluation, because the traditional model cannot adapt to the change of the importance of the parameters with time. For example, in the fuel cell life test, with the increase of the use time, the influence of some parameters (such as pressure) gradually increases, and the dynamic weight model can capture this change, thereby reducing the prediction error of voltage attenuation. Therefore, the scheme greatly improves the accuracy of long-term evaluation, and provides a more accurate reference for the life evaluation and maintenance of the fuel cell. In some embodiments, the performance consistency evaluation is performed based on the same working condition environment parameters corresponding to at least two simulation working condition scenes.

[0084] In some embodiments, the performance consistency evaluation is performed based on the same working condition environment parameters corresponding to at least two simulation working condition scenes. In some embodiments, the performance consistency evaluation is performed based on the same working condition environment parameters corresponding to at least two simulation working condition scenes.

[0085] In some embodiments, the performance consistency evaluation is performed based on the same working condition environment parameters corresponding to at least two simulation working condition scenes. Figure 2 In some embodiments, the performance consistency evaluation is performed based on the same working condition environment parameters corresponding to at least two simulation working condition scenes. Figure 3 As shown in the above step 203, the above step 203 can be implemented by the following steps. As shown in the above step 203, the above step 203 can be implemented by the following steps.

[0086] As shown in the above step 203, the above step 203 can be implemented by the following steps. As shown in the above step 203, the above step 203 can be implemented by the following steps.

[0087] As shown in the above step 203, the above step 203 can be implemented by the following steps. 2 As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s

[0088] As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s

[0089] As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s As an example, the vehicle fuel cell is taken as an example, and the simulation working condition scenes include vehicle starting, acceleration, uniform speed, deceleration, etc. For example, the acceleration working condition is set as: the current is linearly increased from 10A to 50A (acceleration 1m / s​​​​​​​​​

[0090] Exemplarily, for 5 fuel cells to be evaluated, the voltage prediction values are calculated respectively under the above-mentioned simulated working condition scenarios, and a range analysis method is adopted: if the range (maximum value-minimum value) of the voltage prediction values under a certain working condition is ≤0.5V, and the average value of the ranges of the four working conditions is ≤0.4V, it is determined that the performance consistency is good.

[0091] Based on the above technical solution, the embodiments of the present application break through the limitation of traditional single steady state working condition through multi-working condition simulation, so that the evaluation result can reflect the performance of the fuel cell in complex actual scenarios; through comprehensive evaluation of the multi-working condition results, the one-sidedness of single working condition evaluation is avoided. For example, the performance of a certain fuel cell is consistent under the uniform speed working condition, but the voltage fluctuation difference is significant under the starting working condition, which can be accurately identified by the embodiments, thereby further improving the evaluation accuracy.

[0092] In addition, the present application can also realize the performance consistency evaluation of the fuel cell based on artificial intelligence algorithm.

[0093] As a possible embodiment of the present application, in combination with Figure 3 As shown in Figure 4 The step 302 can be realized by the following steps.

[0094] Step 401, input the cell performance prediction parameters and working condition environment parameters of each fuel cell under each simulated working condition scenario as input parameters into the trained evaluation model.

[0095] The evaluation model includes a feature extraction module and a performance consistency evaluation module. The evaluation model adopts a two-level architecture of "feature extraction-classification", the feature extraction module can be composed of multiple layers of convolutional neural network, which converts the input parameters into feature vectors, and the performance consistency evaluation module is composed of fully connected layers, which outputs the consistency score (the higher the score, the better the consistency).

[0096] Step 402, feature extraction is performed on the input parameters by the feature extraction module to generate feature data.

[0097] Exemplarily, taking 12-dimensional parameters composed of voltage prediction values of 4 working conditions and 8 environment parameters as input parameters as an example, the 12-dimensional parameters can be converted into 32-dimensional feature vectors through feature extraction by the feature extraction module.

[0098] Step 403, based on the extracted feature data, the performance consistency evaluation module is used to perform performance consistency evaluation to obtain the performance consistency evaluation result.

[0099] Exemplarily, the application can also compare the evaluation results of the evaluation model with the actual measurement results, thereby ensuring the evaluation effect of the evaluation model. For example, after 10 fuel cells of a batch are evaluated by the evaluation model, 7 of them have scores of 85 or more (determined to be consistent and qualified), and 3 of them have scores of less than 70 (determined to be unqualified), and then the 10 fuel cells can be deployed in an actual operating environment for actual measurement, thereby analyzing the difference between the evaluation model and the actual measurement test.

[0100] Based on the above technical solutions, the embodiments of the application realize automatic feature mining of multiple parameters by introducing an evaluation model, avoid the subjectivity of manual evaluation, and improve the standardization degree of evaluation through modular processing. Compared with the traditional analysis scheme, the application has stronger identification ability for subtle performance differences and higher evaluation accuracy.

[0101] In addition, the input parameters in the embodiments of the application can also include raw material batch information of the fuel cell, and the raw material batch information includes electrode material batch number and electrolyte material batch number.

[0102] The raw material batch information is converted into a vector of the same dimension as the battery performance prediction parameter after encoding processing, and is input into the evaluation model after being spliced with the battery performance prediction parameter.

[0103] Exemplarily, a group of fuel cells have performance differences due to the use of different batches of electrode materials, and at this time, the raw material batch information of different batches is also used as a dimension of performance consistency evaluation, which can further distinguish the performance differences caused by different batches of electrode materials, thereby improving the evaluation effect.

[0104] As a possible embodiment of the application, in combination with Figure 2 As shown in Figure 5 Before analyzing the measurement parameters, the method can further include the following steps.

[0105] Step 501, pre-processing the collected measurement parameters.

[0106] The pre-processing operation includes smoothing processing and outlier removal, and the smoothing processing is realized based on a sliding average filtering algorithm, and the outliers in the outlier removal are measurement values that differ from the average value by more than 3 standard deviations.

[0107] Exemplarily, the window size of the sliding average filtering can be set to 10, and the current data sampled at 100 Hz is smoothed to remove high-frequency noise; in the outlier removal, the mean μ and the standard deviation σ of the temperature parameter are calculated, and the data outside the range of μ±3σ (such as the 150℃ abnormal value in the temperature data of a certain battery, which is far beyond the normal range of 80±10℃) is removed. After pre-processing, the signal-to-noise ratio of the voltage parameter is significantly improved, and the stability of the model input data is significantly improved.

[0108] Based on the above technical solution, the pre-processing operation reduces the noise and abnormal interference in the original data, and provides high-quality input for subsequent modeling and evaluation. Experiments show that the prediction error of the quantitative relationship model constructed by the pre-processed parameters is significantly reduced, thereby ensuring the reliability of the final evaluation result.

[0109] The above describes the scheme of the embodiments of the present application mainly from the perspective of device implementation. It can be understood that, in order to implement the above functions, each device, for example, the fuel cell performance consistency evaluation device, comprises at least one of the corresponding hardware structure and software module for executing each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0110] The embodiments of the present application can divide the functional units of the fuel cell performance consistency evaluation device according to the above method examples, for example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be implemented in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical functional division. When actually implemented, there can be another division method.

[0111] In the case of using integrated units, Figure 6 A possible structure schematic diagram of the fuel cell performance consistency evaluation device (denoted as fuel cell performance consistency evaluation device 60) involved in the above embodiments is shown, which comprises a processing unit 601 and a communication unit 602, and can further comprise a storage unit 603. Figure 6 The structure schematic diagram shown can be used to illustrate the structure of the fuel cell performance consistency evaluation device involved in the above embodiments.

[0112] When Figure 6The illustrated structural diagram is used to illustrate the structure of the performance consistency evaluation device of the fuel cell involved in the above embodiment. The processing unit 601 is used to control and manage the operation of the performance consistency evaluation device of the fuel cell. The communication unit 602 is used for communication between the performance consistency evaluation device of the fuel cell and other devices. The storage unit 603 is used to store the program code and data of the performance consistency evaluation device of the fuel cell.

[0113] For example, the communication unit 602 is used to collect measurement parameters of each fuel cell during operation through sensors; the measurement parameters include battery performance measurement parameters and working condition environment parameters; the battery performance measurement parameters include voltage, current, battery internal temperature and battery internal pressure; the working condition environment parameters include gas flow, ambient temperature, ambient humidity and altitude.

[0114] The processing unit 601 is used to analyze the measurement parameters by using multiple linear regression analysis, and establish a corresponding quantitative relationship model for each fuel cell; the quantitative relationship model is used to represent the correlation between the battery performance measurement parameters and the working condition environment parameters.

[0115] The processing unit 601 is used to perform performance consistency evaluation on each fuel cell based on the battery performance prediction parameters calculated under the same working condition environment parameters according to the corresponding quantitative relationship model, and obtain the performance consistency evaluation result.

[0116] In a possible implementation, the quantitative relationship model includes a dynamic weight adjustment function constructed based on the running time or the cumulative use frequency, and the dynamic weight adjustment function is used to adjust the weight of the battery performance measurement parameters and / or the working condition environment parameters in the quantitative relationship model.

[0117] In a possible implementation, the dynamic weight adjustment function is represented by the following formula:

[0118] w i (t)=w i0 ×e kt ;

[0119] Wherein, w i (t) is the weight of the i-th parameter in the measurement parameters at t, t is the running time or the cumulative use frequency, w i0 is the initial weight of the i-th parameter, and k is the fitting coefficient.

[0120] In a possible implementation, the quantitative relationship model is composed of the following formula:

[0121] Y=k1X1+k2X2+...+k n X n +b;

[0122] Y is any one of the battery performance measurement parameters, X1, X2…X n are a plurality of working condition environment parameters, k1, k2…k n are coefficients of each working condition environment parameter, b is a constant term, and the coefficients and the constant term are obtained by training the preprocessed measurement parameters through multiple linear regression analysis.

[0123] In a possible implementation, the working condition environment parameters of the same working condition correspond to at least two simulation working condition scenarios; the processing unit 601 is configured to: for each simulation working condition scenario, input the corresponding working condition environment parameters into the quantitative relationship model, and calculate the battery performance prediction parameters of each fuel cell under the simulation working condition scenario; and perform performance consistency evaluation on the battery performance prediction parameters of each fuel cell under each simulation working condition scenario, to obtain a performance consistency evaluation result.

[0124] In a possible implementation, the processing unit 601 is configured to: input the battery performance prediction parameters of each fuel cell under each simulation working condition scenario and the working condition environment parameters into the trained evaluation model as input parameters; the evaluation model includes a feature extraction module and a performance consistency evaluation module; the feature extraction module is configured to perform feature extraction on the input parameters to generate feature data; and the performance consistency evaluation module is configured to perform performance consistency evaluation based on the extracted feature data, to obtain a performance consistency evaluation result.

[0125] In a possible implementation, the input parameters further include raw material batch information of the fuel cell, and the raw material batch information includes electrode material batch number and electrolyte material batch number; the raw material batch information is converted into a vector of the same dimension as the battery performance prediction parameters after encoding processing, and the vector is input into the evaluation model after being spliced with the battery performance prediction parameters.

[0126] In a possible implementation, the processing unit 601 is configured to: perform a preprocessing operation on the collected measurement parameters; the preprocessing operation includes smoothing processing and abnormal value removal; the smoothing processing is implemented based on a sliding average filtering algorithm; and the abnormal value in the abnormal value removal is a measurement value that is greater than 3 standard deviations from the average value.

[0127] The processing unit 601 can be a processor or a controller, and the communication unit 602 can be a communication interface, a transceiver, a transceiver, a transceiver circuit, a transceiver device, etc. The communication interface is collectively referred to, and can include one or more interfaces. The storage unit 603 can be a memory. When the fuel cell performance consistency evaluation device 60 is a chip, the processing unit 601 can be a processor or a controller, and the communication unit 602 can be an input interface and / or an output interface, a pin or a circuit, etc. The storage unit 603 can be a storage unit (for example, a register, a cache, etc.) within the chip, or a storage unit (for example, a read-only memory (ROM), a random access memory (RAM), etc.) located outside the chip.

[0128] The communication unit can also be referred to as a transceiver unit. The antenna and control circuit with transceiver function in the fuel cell performance consistency evaluation device 60 can be regarded as the communication unit 602 of the fuel cell performance consistency evaluation device 60, and the processor with processing function can be regarded as the processing unit 601 of the fuel cell performance consistency evaluation device 60. Optionally, the device for realizing the receiving function in the communication unit 602 can be regarded as a communication unit, which is used to execute the receiving steps in the embodiments of the application, and the communication unit can be a receiver, a receiver, a receiving circuit, etc. The device for realizing the sending function in the communication unit 602 can be regarded as a sending unit, which is used to execute the sending steps in the embodiments of the application, and the sending unit can be a transmitter, a sender, a sending circuit, etc.

[0129] Figure 6 The integrated units in the above-mentioned embodiments can be stored in a computer readable storage medium if they are realized in the form of software function modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the application or the whole or part of the technical solutions that make essential contributions to the prior art can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiments of the application. The storage medium for storing computer software products includes a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and various media that can store program codes.

[0130] Figure 6 The units in the above-mentioned embodiments can also be referred to as modules, for example, the processing unit can be referred to as a processing module.

[0131] The embodiment of the present application further provides a hardware structure schematic diagram of the performance consistency evaluation device (denoted as a performance consistency evaluation device 70 of a fuel cell) of the fuel cell, referring to Figure 7 The performance consistency evaluation device 70 of the fuel cell comprises a processor 701, and optionally further comprises a memory 702 connected with the processor 701.

[0132] In the first possible implementation, referring to Figure 7 The performance consistency evaluation device 70 of the fuel cell further comprises a transceiver 703. The processor 701, the memory 702 and the transceiver 703 are connected through a bus. The transceiver 703 is used for communicating with other devices or communication networks. Optionally, the transceiver 703 can comprise a transmitter and a receiver. The device for realizing the receiving function in the transceiver 703 can be regarded as the receiver, and the receiver is used for executing the receiving steps in the embodiment of the present application. The device for realizing the sending function in the transceiver 703 can be regarded as the transmitter, and the transmitter is used for executing the sending steps in the embodiment of the present application.

[0133] Based on the first possible implementation, Figure 7 The structure schematic diagram shown can be used for indicating the structure of the performance consistency evaluation device of the fuel cell involved in the above embodiment.

[0134] Among them, Figure 7 The system chip in the performance consistency evaluation device of the fuel cell can also be indicated. In this case, the actions performed by the performance consistency evaluation device of the fuel cell can be realized by the system chip, and the specific actions performed can be referred to the above, and will not be described here.

[0135] In the implementation process, the steps in the method provided by the embodiment can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the software form. The steps of the method disclosed by the embodiment of the present application can be directly embodied as the execution completed by the hardware processor, or the execution completed by the combination of the hardware and the software module in the processor.

[0136] The processor in the present application can include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, and the like various computing devices running software, each of which can include one or more cores for executing software instructions to perform operations or processing. The processor can be a separate semiconductor chip, or can be integrated with other circuits as a semiconductor chip, for example, can be integrated with other circuits (such as coding and decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a SoC (system on chip), or can be integrated as a built-in processor in an ASIC. The ASIC integrated with the processor can be packaged separately or packaged together with other circuits. In addition to including cores for executing software instructions to perform operations or processing, the processor can further include necessary hardware accelerators, such as field programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits implementing special logic operations.

[0137] The memory in the embodiments of the present application can include at least one of the following types: read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, and can also be electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory can also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but not limited thereto.

[0138] The embodiments of the present application also provide a computer readable storage medium including instructions, which, when executed on a computer, cause the computer to perform any of the above methods.

[0139] The embodiments of the present application also provide a computer program product including instructions, which, when executed on a computer, cause the computer to perform any of the above methods.

[0140] The embodiment of the present application further provides a chip, which comprises a processor and an interface circuit, the interface circuit is coupled with the processor, the processor is used for running computer programs or instructions to realize the method described above, and the interface circuit is used for communicating with other modules outside the chip.

[0141] In the above embodiments, the implementation can be achieved by software, hardware, firmware or any combination thereof, entirely or partially. When implemented by software, the implementation can be achieved in the form of a computer program product, entirely or partially. The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function described in the embodiments of the present application is generated, entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or data storage device including one or more servers, data centers, etc. integrated with the medium. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD), or semiconductor medium (such as solid state disk (SSD)) and the like.

[0142] Although the present application is described herein in conjunction with various embodiments, other variations of the disclosed embodiments can be understood and implemented by those skilled in the art with the benefit of the disclosure, the attached drawings, the disclosure content and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "one" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. Some measures described in mutually different dependent claims can be combined and produce good results.

[0143] Although the present application has been described in connection with the preferred embodiments thereof with reference to the specific content thereof, it will be apparent to those skilled in the art that various modifications and changes can be made thereto without departing from the spirit and scope of the application. Accordingly, it is intended that the present application cover all such modifications and changes as fall within the scope of the application. It should be understood that various holidays and alterations can be made to the application disclosed in this specification without departing from the spirit or ambit of the present application. It is intended that the present application embrace all such alternates, modifications and fall within the scope of the claims accompanying this specification.

Claims

1. A method for evaluating performance uniformity of a fuel cell, characterized by, The method comprises: collecting, by a sensor, a measurement parameter of each fuel cell during operation; the measurement parameter comprises a battery performance measurement parameter and a working condition environment parameter; the battery performance measurement parameter comprises voltage, current, internal temperature of the battery, and internal pressure of the battery; the working condition environment parameter comprises gas flow, ambient temperature, ambient humidity, and altitude; using multivariate linear regression analysis to analyze the measurement parameter, and establishing a quantitative relationship model corresponding to each fuel cell; the quantitative relationship model is used to represent the correlation between the battery performance measurement parameter and the working condition environment parameter; for each fuel cell, performing performance consistency evaluation on a battery performance prediction parameter calculated based on the corresponding quantitative relationship model under the same working condition environment parameter of the working condition, to obtain a performance consistency evaluation result.

2. The method of claim 1, wherein, The quantitative relationship model comprises a dynamic weight adjustment function constructed based on operation time or cumulative use frequency, and the dynamic weight adjustment function is used to adjust the weight of the battery performance measurement parameter and / or the working condition environment parameter in the quantitative relationship model.

3. The method of claim 2, wherein, The dynamic weight adjustment function is represented by the following formula: w i (t) = w i0 x e kt ; where w i (t) is the weight of the ith parameter in the measurement parameter at time t, t is the running time or cumulative use number, w i0 is the initial weight of the ith parameter, and k is a fitting coefficient.

4. The method of claim 1, wherein, The quantitative relationship model is composed of the following formula: Y = k1X1+ k2X2+... + k n X n +b; Wherein Y is any one of the battery performance measurement parameters, X1, X2…X n are a plurality of the working condition environment parameters, k1, k2…k n are coefficients of each working condition environment parameter, and b is a constant term, and the coefficients and the constant term are obtained by training the preprocessed measurement parameters through multiple linear regression analysis.

5. The method of claim 1, wherein, The same working condition environment parameter corresponds to at least two simulated working condition scenarios; the performance consistency evaluation result obtained by performing performance consistency evaluation on the battery performance prediction parameter calculated based on the corresponding quantitative relationship model under the same working condition environment parameter of the working condition for each fuel cell comprises: for each simulated working condition scenario, inputting the corresponding working condition environment parameter into the quantitative relationship model to calculate the battery performance prediction parameter of each fuel cell under the simulated working condition scenario; performing performance consistency evaluation on the battery performance prediction parameter of each fuel cell under each simulated working condition scenario to obtain a performance consistency evaluation result.

6. The method of claim 5, wherein, The performance consistency evaluation result obtained by performing performance consistency evaluation on the battery performance prediction parameter of each fuel cell under each simulated working condition scenario comprises: inputting the battery performance prediction parameter and the working condition environment parameter of each fuel cell under each simulated working condition scenario into a trained evaluation model as input parameters; the evaluation model comprises a feature extraction module and a performance consistency evaluation module; extracting features of the input parameters by the feature extraction module to generate feature data; performing performance consistency evaluation by the performance consistency evaluation module based on the extracted feature data to obtain a performance consistency evaluation result.

7. The method of claim 6, wherein, The input parameters further comprise raw material batch information of the fuel cell, and the raw material batch information comprises electrode material batch number and electrolyte material batch number; wherein, the raw material batch information is converted into a vector with the same dimension as the battery performance prediction parameter after encoding processing, and is input into the evaluation model after being spliced with the battery performance prediction parameter.

8. The method of claim 1, wherein, The method further comprises: The collected measurement parameters are preprocessed; the preprocessing operation includes smoothing processing and outlier removal; the smoothing processing is realized based on a sliding average filtering algorithm; the outliers in the outlier removal are measurement values that differ from the average value by more than 3 standard deviations.

9. A performance consistency evaluation device for fuel cells, characterized in that, The device comprises a communication unit and a processing unit. The communication unit is configured to collect measurement parameters of each fuel cell during operation by a sensor; the measurement parameters comprise cell performance measurement parameters and working condition environment parameters; the cell performance measurement parameters comprise voltage, current, cell internal temperature and cell internal pressure; the working condition environment parameters comprise gas flow, ambient temperature, ambient humidity and altitude; The processing unit is configured to analyze the measurement parameters by using multivariate linear regression analysis, and establish a corresponding quantitative relationship model for each fuel cell; the quantitative relationship model is used to represent the correlation between the cell performance measurement parameters and the working condition environment parameters; The processing unit is configured to perform performance consistency evaluation on the cell performance prediction parameters of each fuel cell under the same working condition environment parameters based on the corresponding quantitative relationship model, and obtain performance consistency evaluation results.

10. A performance consistency evaluation device for fuel cells, characterized in that, It comprises: A processor and a communication interface; the communication interface and the processor are coupled, and the processor is configured to run computer programs or instructions to realize the performance consistency evaluation method of the fuel cell as claimed in any one of claims 1-8.

Images