Method, device and equipment for processing test data of fuel cell and storage medium

Abstract

The application discloses a kind of processing method, device, equipment and storage medium of the test data of fuel cell, specifically, establish data stack and sequentially store test data into data stack;Load test standard operating condition data, test standard operating condition data is used to indicate the parameter characteristics of effective data;The correlation index of the data in the data stack in the sliding window and test standard operating condition data is calculated;The data that meets the threshold range requirement of correlation index in data stack is output;The threshold range of correlation index is used to indicate that the data in data stack is effective data.The application realizes the continuous processing of test data by the way of sequentially storing test data into data stack, no longer needs manual splicing test data, improves the processing efficiency of test data, and the process of processing test data is based on the effective data obtained by test standard operating condition and strict threshold range of correlation index, improves the credibility of the effective data obtained.

Description

Methods, devices, equipment, and storage media for processing test data of fuel cells Technical Field

[0001] This application relates to the field of fuel cell testing technology, and in particular to a method, apparatus, equipment and storage medium for processing test data of fuel cells. Background Technology

[0002] Currently, with the increasing maturity of fuel cell technology, its applications have gradually penetrated various industries. Correspondingly, the workload of fuel cell testing and the amount of data generated from these tests are rapidly increasing. Each fuel cell product undergoes various types of testing throughout its testing cycle, and each test generates test data.

[0003] However, due to the limited computing power of the desktop computers used for testing fuel cells, when the testing cycle for a certain type of fuel cell test is long, the test data obtained is split into multiple sub-data files. When analysis of the test data is required, it is necessary to manually piece together the test data stored in different data files and then extract the effective data related to fuel cell performance. This process of processing test data is not only time-consuming and labor-intensive, but also very inefficient, and the reliability of the extracted effective data may decrease due to manual extraction. Summary of the Invention

[0004] In view of the above problems, this application provides a method, apparatus, device, and storage medium for processing test data of fuel cells, so as to achieve efficient processing of test data and improve the reliability of the valid data obtained from the processed test data. The specific solution is as follows:

[0005] A method for processing test data of a fuel cell, comprising:

[0006] Create a data stack and store the test data into the data stack sequentially;

[0007] Load the test standard operating condition data, which is used to indicate the parameter characteristics of valid data;

[0008] Calculate the correlation index between the data in the data stack within the sliding window and the test standard operating condition data;

[0009] Output the data in the data stack that meets the threshold range requirements of the correlation index; the threshold range of the correlation index is used to indicate that the data in the data stack is valid data.

[0010] Optionally, a data stack is established, including:

[0011] Create an empty data stack and define a data variable to represent the length of the data stack.

[0012] Optionally, before calculating the correlation index between the data in the data stack within the sliding window and the test standard condition data, the following steps are also included:

[0013] Determine whether the length of the data stack is greater than or equal to the length of the test standard operating condition data;

[0014] If the length of the data stack is determined to be greater than or equal to the length of the test standard operating condition data, then the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is calculated.

[0015] Optionally, after determining that the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, the method further includes:

[0016] Enclosed data stack.

[0017] Optionally, after determining whether the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, the method further includes:

[0018] If the length of the data stack is determined to be less than the length of the test standard operating condition data, the test data will be returned and stored into the data stack in sequence.

[0019] Optionally, the correlation index between the data in the data stack within the sliding window and the test standard condition data is calculated, including:

[0020] Calculate the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard operating condition data.

[0021] Optionally, the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard condition data are calculated, including:

[0022] Calculate the Pearson correlation coefficient and Euclidean distance between the data in the data stack within the sliding window and the test standard operating condition data.

[0023] Optionally, after calculating the correlation index between the data in the data stack within the sliding window and the test standard condition data, the following steps are also included:

[0024] If the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is determined to be inconsistent with the threshold range requirement of the correlation index, the relative position of the sliding window and the data stack is updated, and the updated sliding window is used to return to calculate the correlation index between the data in the data stack within the sliding window and the test standard operating condition data.

[0025] Optionally, if the data in the updated sliding window's data stack is the bottom data of the data stack, and the correlation coefficient between the data in the updated sliding window's data stack and the test standard operating condition data does not meet the threshold range requirement of the correlation index, then all test data in the data stack will be output.

[0026] A device for processing test data of a fuel cell, comprising:

[0027] The data acquisition module is used to sequentially store test data into the data stack and load test standard operating condition data;

[0028] The data processing module is used to build a data stack and calculate the correlation index between the data in the data stack within the sliding window and the test standard operating condition data.

[0029] The data input and output module is used to output data from the data stack that meets the threshold range requirements of the correlation index.

[0030] A device for processing test data of a fuel cell includes at least one processor and a memory connected to the processor, wherein:

[0031] Memory is used to store computer programs or instructions;

[0032] The processor is used to execute computer programs or instructions to enable the fuel cell test data processing device to implement the fuel cell test data processing method as described in any of the above.

[0033] A storage medium is used in a fuel cell test data processing device. The storage medium carries one or more computer programs. When the one or more computer programs are executed by the fuel cell test data processing device, the fuel cell test data processing device is able to implement the fuel cell test data processing method as described in any of the above claims.

[0034] By utilizing the above technical solution, the fuel cell test data processing method provided in this application achieves continuous processing of test data by sequentially storing the test data into a data stack, eliminating the need for manual splicing of test data and greatly improving the processing efficiency of test data. Furthermore, the process of processing test data is based on valid data derived from test standard operating conditions and threshold ranges of strict correlation indicators, which greatly improves the reliability of the processed valid data. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 is a flowchart of a method for processing test data of a fuel cell provided in an embodiment of this application;

[0037] Figure 2 is a schematic diagram of a fuel cell test data processing device provided in an embodiment of this application;

[0038] Figure 3 is a block diagram of a fuel cell test data processing device provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] Currently, with the increasing maturity of fuel cell technology, its application has gradually penetrated various industries. Correspondingly, the workload of fuel cell testing and the amount of data generated by these tests are rapidly increasing. Each fuel cell product undergoes various types of testing throughout its testing cycle, and each test generates a large amount of raw test data.

[0041] However, due to the limited computing power of the desktop computers used for testing fuel cells, when a certain type of test has a long cycle, the test data is split into multiple sub-data files. When analysis of the test data is required, it is necessary to manually piece together the test data stored in different data files and then extract the effective data related to fuel cell performance. This process of processing test data is not only time-consuming and labor-intensive, but also very inefficient, and the reliability of the effective data obtained is also very low.

[0042] To improve the processing efficiency and reliability of valid data obtained from fuel cell test data, this application provides a method, apparatus, device, and storage medium for processing fuel cell test data. This method uses electronic equipment as the physical carrier, automatically and continuously reads and combines test data by sequentially storing it into a data stack, and uses a sliding window to identify and extract a complete cycle of test data. The processing is based on standard test conditions and strict threshold ranges for correlation indicators to obtain valid data from the test data, thereby significantly improving the processing speed, efficiency, and reliability of the valid data obtained from the processed test data.

[0043] The present application will be described in detail below with reference to specific embodiments.

[0044] Example 1

[0045] Figure 1 shows a flowchart of the method for processing test data of fuel cells provided in an embodiment of this application.

[0046] S100. Define the test type and determine the standard test conditions.

[0047] Generally, each type of fuel cell undergoes various types of testing throughout its testing cycle. Depending on the testing conditions and requirements, some test data is generated from long-term testing, while other test data is generated from short-term or ad-hoc testing. Based on the different objects generating the test data, these various test data include complete operational, status, and fault information for different levels and levels of integration of fuel cell components, stacks, and systems.

[0048] Test types are typically categorized into long-cycle tests and short-cycle tests based on the length of the test period and the number of test data files generated. Long-cycle tests generally have a longer test period and generate a larger number of test data files, while short-cycle tests generally have a shorter test period and generate a smaller number of test data files. For long-cycle tests, such as those testing the durability performance of fuel cells, a single standard test condition is usually used, and the standard test condition needs to be repeatedly tested cyclically throughout the entire fuel cell durability performance testing process. This results in the number of test data files generated starting in the thousands. Therefore, the test type can be clearly defined as a long-cycle test based on the length of the durability performance test period and the large number of test data files generated.

[0049] For short-cycle testing, the number of cycles of the standard operating condition is usually small. Some short-cycle tests do not even repeat the standard operating condition test. The test process can be completed by performing the standard operating condition test only once. This results in a relatively small number of test data files generated by the short-cycle testing process. Therefore, the test type can be clearly identified as short-cycle testing based on the short test cycle and the relatively small number of test files generated.

[0050] It should be noted that there is no direct correlation between test standard conditions and test types. Instead, test standard conditions are matched according to the needs of the test type. Specifically, the same test standard condition can be used for both long-cycle and short-cycle testing. For the same test type, a single test standard condition or a combination of different test standard conditions can be used.

[0051] It should also be noted that the data processing method for fuel cells provided in the embodiments of this application applies to both long-cycle and short-cycle testing. The difference between short-cycle and long-cycle testing is that different test standard conditions need to be matched.

[0052] S101, Establish data stack D s And define the data stack D s length

[0053] Define a memory address in the electronic device's memory to create an empty data stack, denoted as D. s (Data Stack). Specifically, the data stack D s Essentially, it's a variable-length address space defined in the electronic device's memory, used to store test data, and the data stack D... s The length is determined by the data length of the test standard operating condition.

[0054] Additionally, a separate memory address needs to be defined in the electronic device's memory to create data variables. These data variables represent the length of the data stack Ds, denoted as... Used to control the data stack D s The timing of opening and closing. Specifically, the data stack D. s Enabling refers to storing the test data into the data stack D after reading the test data. s In, and the data stack D s Output of some or all of the data; data stack D s The enclosed nature refers to the data stack D. s No data input or output is performed.

[0055] By controlling the data stack Ds Opening and closing, thereby controlling the data stack D s Memory usage can indirectly reduce data stack size (D). s It reduces the use of computer memory resources and improves the computer's processing efficiency.

[0056] S102, Read the test standard operating condition D sc The length of the standard test condition is defined as Len. sc .

[0057] Generally, after step S100 above clarifies the test type and standard test conditions of the fuel cell, it is necessary to read the test standard test condition D corresponding to the test type. sc And define the length of the standard test condition as Len. sc Generally speaking, standard test conditions exist in the form of power spectrum or current spectrum. For the fuel cell test data processing method provided in the embodiments of this application, the spectrum type of the standard test conditions is not specifically limited, and can exist in the form of power spectrum or current spectrum.

[0058] It should be noted that in the fuel cell test data processing method provided in this application embodiment, the data recorded in the test data only needs to include the parameter information corresponding to the test standard operating condition data. For example, if the test standard operating condition exists in the form of a power spectrum, then the power information of the test data needs to be recorded during the test. Only when the parameter information of the test data recorded during the test includes the parameter information corresponding to the test standard operating condition will the obtained correlation coefficient and distance metric between the test data and the test standard operating condition data have reference value, and thus the valid data in the test data can be derived based on the correlation coefficient and distance metric.

[0059] S103. Read the original test data and update D. s and

[0060] During fuel cell testing, due to the limited memory capacity of electronic devices, the generated raw test data is numbered sequentially (data_01, data_02, ..., data_n) and stored in a large-capacity external memory. When processing the raw test data, it is necessary to read the raw test data from the large-capacity external memory sequentially and store it into the data stack D. s In this process, the raw test data from the large-capacity external memory is sequentially stored into the data stack D. s After that, D needs to be updated. s and

[0061] S104, Judgment Whether it is valid or not.

[0062] In data stack D s During the continuous storage of raw test data, it is necessary to determine whether the data stack D needs to be closed. s This then initiates the entire data analysis process. Specifically, when determining... When it is established, i.e., data stack D s If the data length in the data stack is greater than or equal to the data length in the standard test condition, it means that the data stack D can be closed. s The original test data in the data stack D is used to begin processing. s The original test data.

[0063] It should be noted that during the testing process, it is necessary to process the data of a complete working condition as much as possible. Therefore, the original test data needs to be stored sequentially into the data stack D. s Next, determine the data stack D. s Checking whether the data length is greater than or equal to the data length of the standard test condition ensures that the test data used for processing in the data stack is a complete test condition data, thus improving the accuracy of data processing.

[0064] S105, Closed Data Stack D s Initialize the sliding window and set its width Len. sw =Len sc .

[0065] When the above step S104 is determined When established, step S105 needs to be executed to close the data stack D. s Initialize the sliding window and set its width Len. sw Equal to the data length Len of the standard test condition sc Initializing the sliding window refers to setting the width Len of the sliding window. sw (Length of Slidin g The value of Window is set to Len. sc And set the initial top edge position of the sliding window to Index_SW Upper With data stack D s Align the top edge with the sliding window, and set the initial bottom edge position to Index_SW. Lower Set to Index_SW Lower =Index_SW Upper +Len sw That is, the initial bottom edge position of the sliding window is set to the initial top edge position of the sliding window plus the width of the sliding window.

[0066] It should be noted that the above steps use a data stack to process data, making data processing more flexible. By varying the length of the data stack, at least one complete working condition data can be stored in the data stack, which better meets the requirement of processing data according to a complete working condition during the processing.

[0067] S106. Select data D within the sliding window. sw And calculate the correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw ).

[0068] Slide the window along the data stack D s Slide the top edge to the data stack D s During the lower edge process, the data stack D within the sliding window s The original test data in the window is also constantly changing. Let D be the data stack within the current sliding window. s The original test data in D is sw Then it is necessary to calculate the data D of the test standard operating condition. sc With the data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc， D sw ).

[0069] Among them, the correlation coefficient Person(D) sc D sw The formula for calculating ) is:

[0070]

[0071] In the formula, Cov(D) sc D sw ) is D sc With D sw The covariance of the two; D sc Standard deviation; D sw The standard deviation.

[0072] Specifically, the test standard operating condition data D provided in this application sc Data stack D within the sliding window s The original test data D in swThe correlation coefficient Person(D) sc D sw The Pearson correlation coefficient (PRC) is used to characterize the degree of linear correlation between variables. It is a dimensionless quantity, typically ranging from 0 to 1. A PRC of 0 indicates no correlation between the two variables, while a PRC of 1 indicates a linear correlation. For example, for two variables x and y, their relationship can be expressed as: y = kx, where k is a constant. The closer the correlation coefficient is to 1 (i.e., the closer k is to 1), the stronger the linear correlation between the two variables; conversely, the closer the correlation coefficient is to 0 (i.e., the closer k is to 0), the weaker the linear correlation between the two variables.

[0073] Distance metric Euclid(D) sc D sw The formula for calculating ) is:

[0074]

[0075] Specifically, the test standard operating condition data D provided in this application sc With the data stack D within the sliding window s The original test data D in sw Euclid (D) distance metric sc D sw () refers to Euclidean distance, which is used to characterize the distance between two points in Euclidean space. The smaller the Euclidean distance value, the closer the distance between the two variables being measured.

[0076] It should be noted that the data D in the calculation of the standard test condition... sc With the data stack D within the sliding window s The original test data D in sw When considering the correlation index, the data D of the test standard operating condition calculated in the embodiments of this application is... sc With the data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw This is merely an illustrative example and is not intended to be specific. It only requires the calculated test standard condition data D. sc With the data stack D within the sliding window s The original test data D in swIf the correlation index meets the threshold range of the correlation index, then the valid data in the test data can be obtained.

[0077] S107. Determine the correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw Do all requirements meet the criteria?

[0078] When the above step S106 calculates the test standard operating condition data D sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw After that, it is necessary to determine the data D of the test standard operating condition. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw Do all requirements meet the criteria?

[0079] Specifically, only the data D from the standard operating conditions was tested. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If all requirements are met, then proceed to step S109 and output the data stack D. s The data in the middle; only the data of the standard operating condition test D. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If any one of the requirements is not met, proceed to step S108 to update the sliding window.

[0080] It should be noted that the specific requirements for the threshold range of the correlation index to be met vary depending on the different test objects and test methods. Regarding the correlation coefficient Person(D) provided in the embodiments of this application... sc D sw For the distance metric Euclid(D) provided in this application, the correlation coefficient is generally required to be within the range of [0.9, 1]. The specific value requirement is determined by the specific test conditions and is not specifically limited here. sc D sw Generally, the distance metric is required to be within the range of [100, 35000]. The specific value requirement depends on the specific test conditions and is not specified here.

[0081] S108, Update the sliding window.

[0082] In step S107 above, the data D of the test standard working condition is determined. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If any one of the requirements is not met, step S108 needs to be executed to update the sliding window. The formula for updating the sliding window is:

[0083] Index_SWU pper ′=Index_SW Upper +1

[0084] Index_SW Lower ′=Index_SW Lower +1

[0085] In the formula, Index_SW Upper Index_SW represents the initial top edge position of the sliding window. Lower Index_SW is the initial bottom edge position of the sliding window. Upper ' represents the initial top edge position of the updated sliding window, Index_SW Lower ' represents the initial lower edge position of the updated sliding window. Specifically, updating the sliding window refers to updating the relationship between the sliding window and the data stack D. s The relative position is determined by updating the sliding window and the data stack D. s The relative positions are used to obtain the updated data stack D within the sliding window. s Original test data D sw .

[0086] It should be noted that after updating the sliding window, step S106 needs to be executed again to reselect the data stack D within the updated sliding window. s Original test data D sw And calculate the test standard operating condition data D sc With the updated sliding window's data stack D s Original test data D sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw ).

[0087] If the test data D is under standard operating conditions sc With the updated sliding window's data stack D s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If any one of the requirements is still not met, continue with step S108 until the data D of the standard operating condition is tested. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If all requirements are met, then proceed to step S109.

[0088] It should also be noted that if the sliding window moves along the data stack D s Slide the top edge to the data stack D s During the downward movement, the sliding window continues until it reaches the data stack D. s The data stack D at the bottom of the stack and within the sliding window. s The original test data D sw The test standard operating condition data D still does not meet the requirements. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If required, then output the data stack D. sUse all the original test data to re-execute steps S103 to S107.

[0089] If the sliding window moves along the data stack D s Slide the top edge to the data stack D s During the process of lowering the edge, it appears The situation, namely data stack D s The data length is greater than three times the width of the sliding window, and the data stack D within the sliding window... s The original test data D in sw Data D still does not meet the test standard operating conditions. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw To avoid repeatedly judging invalid data and reduce the consumption of computing resources, it is necessary to output the data stack D. s Top edge to sliding window width Len sw Length of the data.

[0090] S109, Output Data Stack D s The data in the middle.

[0091] In step S107, the data D of the test standard working condition is determined. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If all requirements are met, then data stack D is enabled. s Output the current data stack D s All test data from the top edge to the bottom edge of the sliding window. Specifically, since step S106 calculates the data D for the standard test condition. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw Therefore, when testing standard operating condition data D sc Data stack D within the sliding window sThe original test data D in sw The correlation coefficient Person(D) sc D sw ) and distance metric Euclid (D sc D sw If all requirements are met, then define the data stack D within the sliding window. s The original test data D in sw For valid data, data stack D s The original test data from the top edge to the top edge of the sliding window is invalid data.

[0092] S110, Judgment Whether it is valid or not.

[0093] In step S109, the data stack is enabled, and the current data stack D is output. s After collecting all test data from the top edge to the bottom edge of the sliding window, the data stack D needs to be re-evaluated. s Data length Data length Len with sliding window width sw The relationship between the two. If the data stack D is determined... s Data length Data length Len less than the width of the sliding window sw ,Right now If the condition is met, then steps S103 to S109 are executed again; if the data stack D is determined... s Data length Data length Len that is greater than or equal to the width of the sliding window sw ,Right now If the condition is met, then repeat steps S105 to S109.

[0094] Due to data stack D s It processes the test data in a loop, when the data stack D s Data length Data length Len less than the width of the sliding window sw At this point, it is necessary to continue storing the test data into the data stack D. s In the middle, steps S103 to S109 are executed until all test data is stored in the data stack D. s Only after completing the above steps can all test data processing be considered complete.

[0095] S111, Process data as needed and then output the data.

[0096] After completing the above steps, different data processing methods can be used depending on the test type. For long-cycle testing processes, since the test process involves cyclical repetition of standard operating conditions, multiple sets of test data will be generated for the same parameter. When processing the data, the data can be processed according to a specified parameter sequence, and the specified statistical value of each parameter point can be calculated and output. For example, for multiple sets of test data generated for the same parameter, the average value of each parameter point can be calculated and output. For short-cycle testing processes, the original test data D can be directly output. sw .

[0097] It should be noted that data output can take two forms: centralized output and cyclic output. Centralized output means that all data generated during the entire data extraction and processing process is temporarily stored in the electronic device's memory until all the original test data has been processed, at which point all data generated during the entire processing is output to a large-capacity external storage device at once. Cyclic output means that during the above-mentioned test data processing, after each execution of step S109, the data stack D is output. s After processing the data, you can execute an output of the data results.

[0098] The fuel cell test data processing method provided in this application embodiment adopts a data stack D. s The raw test data is processed in a manner that involves storing the raw test data into a data stack D. s In the middle, and using the sliding window algorithm, the sliding window moves along the data stack D s During the sliding process, the data D of the standard test condition is calculated. sc Data stack D within the sliding window s The original test data D in sw The correlation coefficient between the two is Person(D) sc D sw ) and distance metric Euclid (D sc D sw Only the correlation coefficient between the two, Person(D), is considered. sc D sw ) and distance metric Euclid (D sc D sw Only when all requirements are met will the data be processed as valid data, enabling rapid extraction of valid data. This eliminates the need for dedicated personnel to analyze and extract data, greatly improving data processing efficiency and the reliability of valid data obtained from processing test data.

[0099] Meanwhile, for long-cycle testing processes, the number of test data files generated starts at several thousand. The fuel cell test data processing method provided in this application can achieve rapid analysis and processing of large amounts of data. It can promptly view the changes in the performance and state of the tested object during long-cycle testing, monitor the problems generated by the tested object during testing, reduce the possibility of damage to the tested object during testing, and thus save testing costs. Moreover, the entire fuel cell test data processing process is based on standard test conditions and rigorous analysis algorithms to analyze and process data, which greatly improves the reliability of fuel cell test data extraction and processing results.

[0100] Example 2

[0101] Figure 2 shows a schematic diagram of the fuel cell test data processing device provided in an embodiment of this application.

[0102] The data processing device for the fuel cell test includes: a data acquisition module, a data input and output module, and a data processing module. Among them:

[0103] The data acquisition module collects raw test data generated by the test bench computer. The module stores the collected raw test data sequentially into a data stack for subsequent data analysis. During testing, the test type and standard operating conditions must first be clearly defined, specifying whether it is a long-cycle or short-cycle test. Based on the test type, the appropriate standard operating conditions are selected. Some tests use a single standard operating condition, while others use a combination of different standard operating conditions. After identifying the required standard operating conditions, the data acquisition module loads the test standard operating condition data into the fuel cell test data extraction and processing device for subsequent data analysis.

[0104] The data acquisition module communicates with the test machine via Ethernet. The test machine transmits the test data generated during the test to the data acquisition module via Ethernet. After receiving the test data, the data acquisition module performs transcoding and filtering on the test data, transforming the raw test data into raw test data that the data processing module can recognize.

[0105] It should be noted that the test data generated during the testing process will have various different data parameters due to different test types. Therefore, the test data collected by the data acquisition module should at least include all data parameters used for subsequent data analysis.

[0106] The data input and output module consists of Random Access Memory (RAM) and a large-capacity external memory. It is used to transfer test data between various modules involved in the testing process and to store data generated during fuel cell testing. Specifically, the data input and output module has two main functions. The first is to relay test data between modules of the fuel cell test data extraction and processing device. For example, relay data generated by the data processing module during data extraction and processing can be stored in the RAM of the data input and output module, enabling immediate retrieval during high-speed extraction and processing. The second major function is to achieve long-term storage of test data. For example, large amounts of raw test data and effective data processed by the data processing module can be stored in the large-capacity external memory of the data input and output module. Simultaneously, the large-capacity external memory can also output data through external access devices.

[0107] Specifically, during the fuel cell testing process, the data input and output modules are used to input the test data collected by the data acquisition module. At the same time, the test data will be processed by the data processing module and finally used to output the data in the processed data stack. Among them, the data that meets the threshold range requirements of the correlation index is valid data, and the rest of the data is invalid data.

[0108] The data processing module, composed of hardware such as a central processing unit (CPU), is used to extract and process raw test data and output the processing results to the data input and output modules. The data processing module is the computing center of the fuel cell test data extraction and processing device. It is responsible for processing the raw test data collected by the data acquisition module, and simultaneously, during the data processing, outputting the processing results and relay data generated during the process to the data input and output modules for storage.

[0109] Specifically, the data processing module establishes a data stack during the data processing process. Test data is stored sequentially into the data stack. As a sliding window slides along the top and bottom edges of the data stack, the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is calculated. Data that meets the threshold range of the correlation index is determined to be valid data, while the rest is invalid data. Finally, the valid data is output through the data input and output modules.

[0110] It should be noted that the data processing module also has reserved software function interfaces, which can be matched with extended data processing function modules to achieve richer data processing functions.

[0111] In some embodiments, during the process of the fuel cell test data processing device executing the fuel cell test data processing method provided in Embodiment 1 above, the data processing module establishes the data stack by: establishing an empty data stack and defining a data variable, which is used to characterize the data length of the data stack.

[0112] In some embodiments, before calculating the correlation index between the data in the data stack within the sliding window and the test standard operating condition data, the data processing module also needs to determine whether the data length of the data stack is greater than or equal to the data length of the test standard operating condition data. Specifically, if it is determined that the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, then the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is calculated.

[0113] In some embodiments, the data processing module closes the data stack if it determines that the data length of the data stack is greater than or equal to the data length of the test standard operating condition data.

[0114] In some embodiments, if the data processing module determines that the data length of the data stack is less than the data length of the test standard operating condition data, it will return to execute the test data and store it into the data stack sequentially.

[0115] In some embodiments, the data processing module calculates the correlation index between the data in the data stack within the sliding window and the test standard operating condition data. Specifically, the data processing module calculates the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard operating condition data.

[0116] In some embodiments, the data processing module calculates the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard operating condition data. Specifically, the data processing module calculates the Pearson correlation coefficient and Euclidean distance between the data in the data stack within the sliding window and the test standard operating condition data.

[0117] In some embodiments, after the data processing module calculates the correlation index between the data in the data stack within the sliding window and the test standard operating condition data, it determines that the correlation index between the data in the data stack within the sliding window and the test standard operating condition data does not meet the threshold range requirement of the correlation index. The data processing module then updates the sliding window and returns to calculate the correlation index between the data in the data stack within the sliding window and the test standard operating condition data with the updated sliding window.

[0118] In some embodiments, when the data in the updated sliding window's data stack is the bottom data of the data stack, and the data processing module calculates that the correlation coefficient between the data in the updated sliding window's data stack and the test standard operating condition data still does not meet the threshold range requirement of the correlation index, then the data input and output module outputs all the test data in the data stack.

[0119] Example 3

[0120] Figure 3 is a block diagram of a fuel cell test data processing device according to an embodiment of this application.

[0121] Referring to Figure 3, a schematic diagram of a structure suitable for processing test data of a fuel cell according to embodiments of this disclosure is shown. The processing device for test data of a fuel cell according to embodiments of this disclosure may include, but is not limited to, fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. The fuel cell test data processing device shown in Figure 3 is merely an example and should not impose any limitation on the functionality and scope of use of embodiments of this disclosure.

[0122] As shown in Figure 3, the fuel cell test data processing device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage device 308 into the random access memory (RAM) 303. When the fuel cell test data processing device is powered on, the RAM 303 also stores various programs and data required for the operation of the fuel cell test data processing device. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0123] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, memory cards, hard drives, etc.; and communication devices 309. Communication device 309 allows the fuel cell test data processing equipment to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 shows a fuel cell test data processing equipment with various devices, it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices can be implemented or possessed alternatively.

[0124] Example 4

[0125] This embodiment provides a computer-readable storage medium applied to a fuel cell test data processing device. The computer-readable medium carries one or more programs, which, when executed by the fuel cell test data processing device, enable the device to implement the fuel cell test data processing method described in Embodiment 1.

[0126] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0127] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0128] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for processing test data of a fuel cell, characterized in that, include: Establish a data stack and store the test data into the data stack sequentially; Load the test standard operating condition data, which is used to indicate the parameter characteristics of valid data; Determine whether the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, wherein the data length of the data stack is determined by the data length of the test standard operating condition data; If so, during the process of sliding the sliding window from the upper edge of the data stack to the lower edge of the data stack, the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is calculated, and the width of the sliding window is equal to the data length of the test standard operating condition data. Output the data in the data stack that meets the threshold range requirement of the correlation index; the threshold range of the correlation index is used to indicate that the data in the data stack is valid data; if, during the process of sliding the sliding window from the upper edge to the lower edge of the data stack, the sliding window slides to the bottom of the data stack, and there is still no data in the data stack within the sliding window that meets the threshold range requirement of the correlation index, then output all the test data in the data stack and return to the step of storing the test data into the data stack in sequence; If, during the process of sliding from the top edge of the data stack to the bottom edge of the data stack along the sliding window, the data length of the data stack is greater than three times the data length of the sliding window width, and the data in the data stack within the sliding window does not meet the threshold range requirement of the correlation index, then the data length from the top edge of the data stack to the width of the sliding window will be output. If it is determined that the data length of the data stack is less than the data length of the test standard operating condition data, then return to the step of storing the test data into the data stack sequentially, until all the test data has been stored into the data stack and all the test data has been processed, then the processing ends.

2. The method for processing test data of a fuel cell according to claim 1, characterized in that, The process of establishing a data stack includes: establishing an empty data stack and defining a data variable, wherein the data variable is used to characterize the data length of the data stack.

3. The method for processing test data of a fuel cell according to claim 1, characterized in that, After determining that the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, the method further includes: closing the data stack.

4. The method for processing test data of a fuel cell according to claim 1, characterized in that, The correlation index between the data in the data stack within the sliding window and the test standard operating condition data includes: calculating the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard operating condition data.

5. The method for processing test data of a fuel cell according to claim 4, characterized in that, The step of calculating the correlation coefficient and distance metric between the data in the data stack within the sliding window and the test standard operating condition data includes: calculating the Pearson correlation coefficient and Euclidean distance between the data in the data stack within the sliding window and the test standard operating condition data.

6. The method for processing test data of a fuel cell according to claim 1, characterized in that, After calculating the correlation index between the data in the data stack within the sliding window and the test standard operating condition data, the method further includes: determining that the correlation index between the data in the data stack within the sliding window and the test standard operating condition data does not meet the threshold range requirement of the correlation index, updating the relative position of the sliding window and the data stack, and returning to execute the calculation of the correlation index between the data in the data stack within the sliding window and the test standard operating condition data with the updated sliding window.

7. The method for processing test data of a fuel cell according to claim 6, characterized in that, Also includes: If the data in the updated sliding window belongs to the bottom data of the data stack, and the correlation coefficient between the data in the updated sliding window and the test standard condition data does not meet the threshold range requirement of the correlation index, then all test data in the data stack will be output.

8. A device for processing test data of a fuel cell, characterized in that, include: The data acquisition module is used to sequentially store test data into the data stack and load test standard operating condition data; The data processing module is used to determine whether the data length of the data stack is greater than or equal to the data length of the test standard operating condition data, wherein the data length of the data stack is determined by the data length of the test standard operating condition data. If so, during the sliding window's movement from the upper edge to the lower edge of the data stack, a data stack is established, and the correlation index between the data in the data stack within the sliding window and the test standard operating condition data is calculated. The width of the sliding window is equal to the data length of the test standard operating condition data. If it is determined that the data length of the data stack is less than the data length of the test standard operating condition data, the process returns to the step of sequentially storing the test data into the data stack until all test data has been stored into the data stack and all test data has been processed, at which point the processing ends. The data input and output module is used to output the data in the data stack that meets the threshold range requirement of the correlation index. The fuel cell test data processing device is further used to: if, during the sliding window's movement from the upper edge to the lower edge of the data stack, the sliding window slides to the bottom of the data stack, and there is still no data in the data stack within the sliding window that meets the threshold range requirement of the correlation index, then all test data in the data stack is output, and the process returns to the step of sequentially storing the test data into the data stack. If, during the sliding window movement from the top edge to the bottom edge of the data stack, the data length of the data stack is greater than three times the width of the sliding window, and the data in the data stack within the sliding window does not meet the threshold range requirement of the correlation index, then the data length from the top edge of the data stack to the width of the sliding window will be output.

9. A device for processing test data of a fuel cell, characterized in that, The device includes at least one processor and a memory connected to the processor, wherein: the memory is used to store computer programs or instructions; and the processor is used to execute the computer programs or instructions to enable the fuel cell test data processing device to implement the fuel cell test data processing method as described in any one of claims 1 to 7.

10. A storage medium for processing test data of a fuel cell, characterized in that, The storage medium carries one or more computer programs that, when executed by the fuel cell test data processing device, enable the fuel cell test data processing device to implement the fuel cell test data processing method as described in any one of claims 1 to 7.

Images