Apparatus and method for life prediction of fuel cell

The fuel cell life prediction device models cell degradation patterns considering interdependencies to enhance reliability and optimize maintenance by accurately predicting failure, addressing the challenges of complex interactions in fuel cell stacks.

KR103047408B1Active Publication Date: 2026-11-11INDUSTRY UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
KR1020230188924
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-12-21
Publication Date
2026-11-11
Estimated Expiration
2043-12-21

AI Technical Summary

Technical Problem

Fuel cells face challenges in predicting their lifespan reliably due to complex component interactions and susceptibility to internal and external influences, leading to unpredictable degradation patterns that affect the entire stack's performance.

Method used

A fuel cell life prediction device and method that models the degradation pattern of each unit cell, considering the dependency between individual cells, to improve reliability and optimize repair cycles by diagnosing failures in unit cells.

Benefits of technology

Enhances the reliability of life prediction for both individual cells and the fuel cell stack by accurately correcting degradation patterns, reducing excessive replacements and lowering costs through precise failure determination.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112023144147741-PAT00032_ABST
    Figure 112023144147741-PAT00032_ABST
Patent Text Reader

Abstract

A fuel cell life prediction device according to one embodiment may be provided by including: an information collection unit that measures the voltage of each of a plurality of unit cells provided in a fuel cell stack; a cell prediction model unit that generates a cell degradation prediction model to define a degradation pattern of each unit cell based on the voltage measured in the unit cell; a cell prediction correction unit that generates a cell degradation correction model to correct the degradation pattern so as to reflect the degree of dependence of the degradation pattern of one unit cell among the degradation patterns of the plurality of unit cells on the degradation pattern of another unit cell; and a life prediction unit that predicts the life of each unit cell based on the cell degradation correction model and outputs the time required for the predicted life to reach a failure judgment condition.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to a fuel cell life prediction device and method for predicting the life of a fuel cell. Background Technology

[0002] Fuel cells face a situation where reliability is lacking compared to traditional products due to their complex component relationships and the short period since they were commercialized. In particular, fuel cells have the disadvantage of weak durability because they are relatively more susceptible to internal and external influences than other energy acquisition devices; therefore, understanding the interactions and dependencies between internal and external factors is crucial for ensuring precise reliability. As such, securing precise reliability for fuel cells is challenging, and various methods of analyzing fuel cell degradation patterns are being conducted to enhance the reliability of lifespan predictions.

[0003] A fuel cell stack is a device that generates electricity through the chemical reaction of hydrogen and oxygen. It takes the form of a stack assembly in which multiple cells are arranged in series to secure the electrical energy required to operate a specific system. Due to this configuration, the overall performance of the fuel cell stack depends heavily on the performance of the individual cells; if even one of the individual cells degrades, performance deteriorates irreversibly. In this case, it affects the entire lifespan of the stack, making it difficult to achieve the stable performance originally expected. Therefore, reliability in predicting the lifespan of each individual cell, as well as the lifespan of the fuel cell stack, is required.

[0004] Due to the series structure of fuel cell stacks, the degradation of a single cell can affect adjacent cells. Accordingly, when predicting fuel cell stack degradation, it is necessary to consider not only the data characteristics of individual cells but also the influence of adjacent cells or other external factors. The problem to be solved

[0005] The disclosed embodiment provides a fuel cell life prediction device and a control method thereof that improves the reliability of life prediction for each unit cell by modeling the degradation pattern of each unit cell of a fuel cell stack.

[0006] A fuel cell life prediction device and a control method are provided that improve the reliability of life prediction for each unit cell by precisely correcting the degradation pattern of each unit cell by considering the dependency between the degradation pattern of the unit cell and the degradation pattern of an adjacent unit cell.

[0007] The present invention provides a fuel cell life prediction device and a control method thereof that improve the reliability of life prediction for a fuel cell stack integrating multiple unit cells through the analysis of the degradation pattern of a unit cell.

[0008] A fuel cell life prediction device and a control method thereof are provided, which predict the optimal repair cycle and reduce costs by preventing excessive replacement of the entire fuel cell stack by determining failures in unit cells and diagnosing replacements. means of solving the problem

[0009] A fuel cell life prediction device according to one embodiment includes: an information collection unit that measures the voltage of a plurality of unit cells provided in a fuel cell stack; a cell prediction model unit that generates a cell degradation prediction model to define a degradation pattern of each unit cell based on the voltage measured in the unit cells; a cell prediction correction unit that generates a cell degradation correction model to correct the degradation pattern so as to reflect the degree of dependence of the degradation pattern of one unit cell among the degradation patterns of the plurality of unit cells on the degradation pattern of another unit cell; and a life prediction unit that predicts the life of each unit cell based on the cell degradation correction model and outputs the time required for the predicted life to reach a failure judgment condition.

[0010] It includes a stack prediction model unit that generates an integrated degradation prediction model to define the degradation pattern of the fuel cell stack based on the degradation patterns of the plurality of unit cells corrected by the cell prediction correction unit.

[0011] The above-mentioned life prediction unit predicts the life of the fuel cell stack based on the above-mentioned integrated degradation prediction model and outputs the time required for the predicted life to reach the degradation judgment condition.

[0012] The above cell prediction model unit is characterized by defining a cell degradation prediction model as shown in [Equation 1] below.

[0013] The above cell prediction correction unit is characterized by correcting the degradation pattern as shown in [Equation 2] below.

[0014] It further includes a storage unit that stores information regarding the voltage measured by the information collection unit, the cell degradation prediction model generated by the cell prediction model unit, and the cell degradation correction model generated by the cell prediction correction unit.

[0015] The system includes: an information collection unit that measures the voltage of a plurality of unit cells provided in a fuel cell stack; a cell prediction model unit that predicts the degradation pattern of each unit cell based on the voltage measured in the unit cells; a cell prediction correction unit that corrects the degradation pattern to reflect the interdependence of the plurality of unit cell degradation patterns; a stack prediction model unit that predicts the degradation pattern of the fuel cell stack based on the corrected degradation pattern; and a life prediction unit that predicts the lifespan of the unit cells and the fuel cell stack, respectively, based on the corrected degradation pattern of the unit cells and the degradation pattern of the fuel cell stack.

[0016] A fuel cell life prediction method according to another embodiment comprises: an information collection step of measuring the voltage of each of a plurality of unit cells provided in a fuel cell stack; a cell prediction step of generating a cell degradation prediction model to define a degradation pattern of each unit cell based on the voltage measured in the unit cells; a cell prediction correction step of generating a cell degradation correction model to correct the degradation pattern of one unit cell among the degradation patterns of the plurality of unit cells to reflect the degree of dependence of the degradation pattern of one unit cell to the degradation pattern of another unit cell; and a life prediction step of predicting the life of each unit cell based on the cell degradation correction model and outputting the time required for the predicted life to reach a failure judgment condition.

[0017] It further includes a stack prediction step of generating an integrated degradation prediction model to define the degradation pattern of the fuel cell stack based on the cell degradation correction model above.

[0018] The above-mentioned life prediction step further includes the feature of predicting the life of the fuel cell stack based on the above-mentioned integrated degradation prediction model and outputting the time required for the predicted life to reach the failure judgment condition. Effects of the invention

[0019] According to a fuel cell life prediction device and a control method thereof, the reliability of life prediction for each unit cell is improved by modeling the degradation pattern of each unit cell of a fuel cell stack.

[0020] According to a fuel cell life prediction device and a control method thereof, the reliability of life prediction for each unit cell is improved by precisely correcting the degradation pattern of each unit cell by considering the dependency between the degradation pattern of a unit cell and the degradation pattern of an adjacent unit cell.

[0021] According to a fuel cell life prediction device and a control method thereof in one aspect, the reliability of life prediction for a fuel cell stack in which multiple unit cells are integrated is improved through the analysis of the degradation pattern of a unit cell.

[0022] According to a fuel cell life prediction device and a control method thereof, by determining the failure of a unit cell and diagnosing replacement, the entire fuel cell stack is prevented from being replaced excessively, thereby reducing costs and predicting the optimal repair cycle. Brief explanation of the drawing

[0023] FIG. 1 is a drawing illustrating a fuel cell stack and a fuel cell life prediction device according to one embodiment of the present invention. FIG. 2 is a diagram illustrating the configuration of a fuel cell life prediction device according to one embodiment of the present invention. Figure 3 shows a graph of predicting a degradation pattern using a cell degradation prediction model (M1) of a plurality of unit cells in the cell prediction model section of the fuel cell life prediction device of the present invention. Figure 4 shows a graph corrected by a cell degradation correction model (M2) by reflecting the inter-unit cell dependency in the degradation pattern of Figure 3. Figure 5 shows an evaluation graph of the fuel cell life prediction device of the present invention, which predicts without considering the dependency of the degradation pattern of the unit cell. Figure 6 shows an evaluation graph that predicts the lifespan of a unit cell by considering the dependency of the degradation pattern of the fuel cell of the present invention. Figure 7 shows a graph comparing the predicted mean lifespan (MTTF) of the fuel cell of the present invention with and without considering the dependency of the degradation pattern of the unit cell with the most severe degradation. FIG. 8 is a diagram illustrating the operation flow of a fuel cell life prediction method according to one embodiment of the present invention. Specific details for implementing the invention

[0024] Throughout the specification, the same reference numerals refer to the same components. This specification does not describe all elements of the embodiments, and general content in the art to which the invention pertains or content that overlaps between embodiments is omitted.

[0025] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0026] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0027] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0028] In addition, terms such as "~part," "~unit," "~block," "~part," and "~module" may refer to a unit that processes at least one function or operation. For example, the above terms may refer to at least one piece of hardware such as an FPGA (field-programmable gate array) or ASIC (application specific integrated circuit), at least one piece of software stored in memory, or at least one process processed by a processor.

[0029] The symbols attached to each step are used to identify each step and do not indicate the order of the steps relative to one another; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0030] Hereinafter, an embodiment relating to a fuel cell life prediction device and a control method according to one aspect will be described in detail with reference to the attached drawings.

[0031] FIG. 1 is a drawing illustrating a fuel cell stack and a fuel cell life prediction device according to one embodiment of the present invention.

[0032] As illustrated in FIG. 1, a fuel cell stack (10) according to one embodiment of the present invention includes a plurality of unit cells (11), and a fuel cell life prediction device (100) is connected to each unit cell (11) to predict the life of the fuel cell.

[0033] The fuel cell stack (10) can be used to provide power for driving an electric vehicle. The application range of the fuel cell stack (10) is not limited to vehicle systems, but can also be used to provide electrical energy to electronic equipment and household electrical systems.

[0034] A fuel cell stack (10) may be composed of a plurality of unit cells (11). Specifically, the fuel cell stack (10) may refer to a stack formed by repeatedly stacking and connecting a plurality of unit cells (11).

[0035] As the fuel cell stack (10) undergoes repeated charging and discharging, degradation and deterioration occur, resulting in a decrease in available capacity. At this time, as the fuel cell stack (10) consists of a plurality of unit cells (11) connected in series, the degradation of a unit cell (11) can have electrochemical and physical effects on the degradation of adjacent unit cells (11) within the stack. Therefore, to predict the lifespan of the fuel cell stack (10), not only the degradation pattern of each unit cell (11) but also the interdependence between unit cells (11) within the fuel cell stack (10) must be considered.

[0036] The fuel cell life prediction device (100) can collect and store information about the unit cell (11), for example, the current (I) and voltage (V) of the unit cell (11) in real time or at a predetermined time interval.

[0037] The fuel cell life prediction device (100) can generate a cell degradation prediction model (M1) that predicts the degradation pattern of the unit cell (11) by analyzing voltage variability based on the voltage (V) of the stored unit cell (11). A more detailed description of the cell degradation prediction model (M1) will be provided later.

[0038] The fuel cell life prediction device (100) can generate a cell degradation correction model (M2) that corrects the degradation pattern of each unit cell (11) to accurately predict the degradation pattern by considering the degree of interdependence (dependence) of each cell degradation prediction model (M1). A more detailed description of the cell degradation correction model (M2) will be provided later.

[0039] The fuel cell life prediction device (100) can obtain each corrected degradation pattern through the cell degradation correction model (M2) and can generate an integrated degradation prediction model (M3) that predicts the degradation pattern of the fuel cell stack (10) based on this.

[0040] The fuel cell life prediction device (100) can quantitatively predict the degradation of the unit cell (11) and / or fuel cell stack (10) after a predetermined time based on the cell degradation prediction model (M1) and the cell degradation correction model (M2), and can quantitatively derive the time required until the point of failure determination. At this time, the failure determination condition is set to a predetermined value, for example, it can be defined as the point in time when the measured voltage of the unit cell (11) and / or fuel cell stack (10) is determined to have degraded by 10% compared to the initial voltage.

[0041] The fuel cell life prediction device (100) according to the present invention may be implemented inside a vehicle. At this time, the fuel cell life prediction device (100) may be formed integrally with the internal control units of the vehicle, or it may be implemented as a separate device and connected to the control units of the vehicle by a separate connection means. Here, the device (100) may operate in conjunction with the engine and motor of the vehicle, and may also operate in conjunction with a control unit that controls the operation of the engine or motor.

[0042] FIG. 2 is a diagram illustrating the configuration of a fuel cell life prediction device according to one embodiment of the present invention.

[0043] Referring to FIG. 2, the fuel cell life prediction device (100) may include a control unit (110), an interface unit (120), a communication unit (130), a storage unit (140), an information collection unit (150), a cell prediction model unit (160), a cell prediction correction unit (170), a stack prediction model unit (180), and a life prediction unit (190). Here, the control unit (110) can process signals transmitted between each component of the device (100).

[0044] The interface unit (120) may include an input means for receiving control commands from a user and an output means for outputting the operating status and results of the device (100).

[0045] Here, the input means may include key buttons, and may also include a mouse, joystick, jog shuttle, stylus pen, etc. Additionally, the input means may include soft keys implemented on a display.

[0046] The output means may include a display and may also include a voice output means such as a speaker. In this case, if a touch sensor such as a touch film, touch sheet, or touch pad is provided on the display, the display operates as a touch screen and may be implemented in a form where the input means and the output means are integrated. In this case, the display may include at least one of a Liquid Crystal Display (LCD), a Thin Film Transistor-Liquid Crystal Display (TFT LCD), an Organic Light-Emitting Diode (OLED), a Flexible Display, a Field Emission Display (FED), and a 3D Display.

[0047] The communication unit (130) may include a communication module that supports a communication interface with electrical components and / or control units equipped in the vehicle. As an example, the communication module may be connected to the fuel cell stack (10) of the vehicle (or a system managing information of the fuel cell stack) to receive information regarding the stack current and stack voltage of the fuel cell stack (10).

[0048] Here, the communication module may include a module that supports vehicle network communication such as CAN (Controller Area Network) communication, LIN (Local Interconnect Network) communication, and Flex-Ray communication.

[0049] Additionally, the communication unit (130) may include a communication module that supports a communication interface with an external device. As an example, the communication module may transmit the lifespan prediction result of the vehicle's fuel cell stack (10) to a vehicle management system that manages the vehicle's status.

[0050] At this time, the communication module may include a module for wireless internet access or a module for short-range communication. Here, wireless internet technologies may include Wireless LAN (WLAN), Wireless Broadband (Wibro), Wi-Fi, World Interoperability for Microwave Access (WiMAX), etc., and short-range communication technologies may include Bluetooth, ZigBee, Ultra Wideband (UWB), Radio Frequency Identification (RFID), Infrared Data Association (IrDA), etc.

[0051] The storage unit (140) can store data and / or algorithms, etc., necessary for the fuel cell life prediction device (100) to operate.

[0052] For example, the storage unit (140) may store information on the current and voltage of the unit cell (11) and the fuel cell stack (10) received through the communication unit (130). Additionally, the storage unit (140) may store commands and / or algorithms for generating a lifespan prediction model, and may also store a cell degradation prediction model (M1), a cell degradation correction model (M2), and an integrated degradation prediction model (M3).

[0053] Additionally, the storage unit (140) may store commands and / or algorithms for predicting the lifespan of the fuel cell stack (10), and may also store the lifespan prediction results of the fuel cell stack (10) using a lifespan prediction model.

[0054] Here, the storage unit (140) may include a storage medium such as RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), PROM (Programmable Read-Only Memory), and EEPROM (Electrically Erasable Programmable Read-Only Memory).

[0055] The information collection unit (150) collects the voltage (V) of the unit cell and the fuel cell stack (10) and stores it in the storage unit (140). The information collection unit (150) can collect current and voltage from the unit cell and the fuel cell stack (10) in real time, at a predetermined time interval, and irregularly at a predetermined time.

[0056] The cell prediction model unit (160) extracts voltage information stored in the storage unit (140) and generates a cell degradation prediction model (M1) that defines a degradation pattern between the voltage and time of the unit cell (11). The cell prediction model unit (160) models independent degradation patterns by individually predicting the degradation patterns of the unit cell (11).

[0057] The cell degradation prediction model (M1) can be modeled as a nonlinear stochastic process based on the relationship between accumulated voltage and time. The cell degradation prediction model (M1) can be prepared as a nonlinear Wiener process that identifies the relationship between voltage and time, and can be defined as shown in [Equation 1] below.

[0058]

[0059] In [Mathematical Formula 1], i is an index for a unit cell, an integer between 1 and n; j is an arbitrary point in time, an integer between 1 and n; is time Voltage at; The parameter is Transformation function for time; σ is the diffusion parameter; means Brownian motion.

[0060] For example, the cell prediction model unit (160) can define a cell degradation prediction model (M1) using the accumulated voltage of the unit cell (11) at each time point (1st to jth time point) that meets a predetermined condition, and store the model equation in the storage unit (140). Accordingly, the storage unit (140) stores the cell degradation prediction model (M1) for each of the i unit cells (11), and the cell degradation prediction model (M1) for each unit cell (11) can store the model generated at j time points.

[0061] The cell prediction correction unit (170) generates a cell degradation correction model (M2) that corrects the cell degradation prediction model (M1) to reflect the degree to which the degradation patterns of a plurality of unit cells (11) are mutually dependent. Specifically, the cell prediction correction unit (170) corrects the degradation patterns of a plurality of unit cells (11) to reflect the degree of dependence in which the degradation pattern of one unit cell is dependent on the degradation pattern of another unit cell, thereby improving the reliability of the lifespan prediction of each unit cell (11).

[0062] The cell degradation correction model (M2) can correct the model to consider the dependency of the unit cells (11) within a single fuel cell stack (10) through the correlation between the first difference values ​​of the actual cell degradation values ​​of the multiple unit cells (11). The cell degradation correction model (M2) can be provided as a Copula model that considers the correlation between models and can be defined as [Equation 2] below.

[0063]

[0064] In [Mathematical Formula 2] represents the joint cumulative distribution between the first difference values ​​of the actual cell degradation values ​​modeled through the Copula function C, and is the transformation function of the first difference value of the actual cell degradation value at time j of the i-th unit cell, represents a parameter that controls the correlation between the first difference values ​​of the actual cell degradation values.

[0065] Here, the cell prediction correction unit (170) generates a cell degradation correction model (M2) that derives a joint probability density function by characterizing the dependency between the surrounding density function and the surrounding distribution in the first difference value of a plurality of cell degradation values. Accordingly, the cell prediction correction unit (170) defines a cell degradation correction model (M2) that corrects the degradation pattern by reflecting the dependency between i unit cells and the remaining i-1 unit cells (11), and can store the model equation in the storage unit.

[0066] The stack prediction model unit (180) generates an integrated degradation prediction model (M3) to define the degradation pattern of the fuel cell stack (10) based on the degradation pattern of a plurality of unit cells (11) corrected by the cell prediction correction unit (170).

[0067] The stack prediction model unit (180) models the integrated degradation pattern of the fuel cell stack (10) based on the degradation pattern of each unit cell (11) whose reliability is improved by the cell degradation correction model (M2). That is, the integrated degradation prediction model (M3) can define the amount of change in voltage of the fuel cell stack (10) over time and store the model equation in the storage unit.

[0068] When a lifespan prediction unit (190) satisfies a predetermined condition or when a lifespan prediction event occurs due to a user's input signal, etc., it calls the cell degradation prediction model (M1), cell degradation correction model (M2), and integrated degradation prediction model (M3) stored in the storage unit (140).

[0069] The lifespan prediction unit (190) can predict the lifespan of each unit cell (11) through the called cell degradation prediction model (M1) and cell degradation correction model (M2) and output the time required for the predicted lifespan to reach a predetermined degradation judgment condition. Additionally, the lifespan prediction unit (190) can predict the lifespan of the fuel cell stack through the called integrated degradation prediction model (M3) and output the time required for the predicted lifespan to reach a predetermined degradation judgment condition.

[0070] The lifespan prediction unit (190) can store the lifespan prediction results of the unit cell (11) and the fuel cell stack (10) in the storage unit (140). Additionally, the lifespan prediction unit (190) can transmit the lifespan prediction results of the unit cell (11) and the fuel cell stack (10) to a vehicle management system inside or outside the vehicle via the communication unit (130).

[0071] Thus, the fuel cell life prediction device (100) of the present invention can predict not only the lifespan of the fuel cell stack (10) but also the lifespan of each individual unit cell (11) within the stack, and thereby determine the failure of the unit cell and predict the replacement cycle.

[0072] FIG. 3 shows a graph of a degradation pattern predicted by a cell degradation prediction model (M1) of 18 unit cells in the cell prediction model unit (160) of the fuel cell life prediction device of the present invention, and FIG. 4 shows a graph corrected by a cell degradation correction model (M2) by reflecting the dependency between unit cells in the degradation pattern of FIG. 3.

[0073] Referring to FIG. 3, in the case of an independent prediction model (M1) that does not consider the dependency between unit cells (11), the degradation patterns of all 18 unit cells (11) move in the same pattern. On the other hand, referring to FIG. 4, in the case of a corrected model (M2) that considers the dependency between unit cells, it can be seen that the degradation patterns of all 18 unit cells move in different patterns.

[0074] FIG. 5 shows an evaluation graph that predicts without considering the dependency of the degradation pattern of a unit cell using the fuel cell life prediction device of the present invention, and FIG. 6 shows an evaluation graph that predicts by considering the dependency of the degradation pattern of a unit cell using the fuel cell life prediction device of the present invention.

[0075] Referring to FIGS. 5 and 6, a cell degradation prediction model (M1) is generated based on voltage data of approximately 0 to 3000 cycles of a unit cell to predict a degradation pattern up to 8000 cycles or more. At this time, the criterion for determining failure of the unit cell can be defined as reaching 0.9, which is the point of 10% degradation relative to the initial voltage value of the unit cell.

[0076] Figure 7 shows a graph comparing the predicted mean lifespan (MTTF) of the fuel cell of the present invention with and without considering the dependency of the degradation pattern of the unit cell with the most severe degradation.

[0077] Referring to Figure 7, failure is predicted to occur within approximately 6,115 cycles when the dependency of the unit cell's degradation pattern is not taken into account. On the other hand, failure is predicted to occur within approximately 6,092 cycles when the dependency of the unit cell's degradation pattern is taken into account.

[0078] Here, when considering the dependency of the unit cell degradation pattern, the confidence interval (length) was estimated to be narrower compared to the case where the dependency of the unit cell degradation pattern is not considered; this implies that the reliability of the Mean Time to Fail (MTTF) prediction is improved when the dependency of the unit cell degradation pattern is considered.

[0079] A method for predicting fuel cell life according to one embodiment of the present invention will be described below.

[0080] FIG. 8 is a diagram illustrating the operation flow of a fuel cell life prediction method according to one embodiment of the present invention.

[0081] Referring to FIG. 8, a fuel cell lifespan prediction method (S100) comprises: an information collection step (S110) for measuring the voltage of each of a plurality of unit cells (11) provided in a fuel cell stack (10); a cell prediction step (S120) for generating a cell degradation prediction model (M1) to define the degradation pattern of each unit cell (11) based on the voltage measured in the unit cell (11); a cell prediction correction step (S130) for generating a cell degradation correction model (M2) to correct the degradation pattern of one unit cell (11) among the degradation patterns of the plurality of unit cells (11) to reflect the degree of dependence of the degradation pattern of one unit cell (11) on the degradation pattern of another unit cell; a stack prediction step (S140) for generating an integrated degradation prediction model to define the degradation pattern of the fuel cell stack (10) based on the cell degradation correction model (M2); and predicting the lifespan of each unit cell based on the cell degradation correction model (M2), wherein the predicted lifespan It may include a life prediction step (S150) that outputs the time required until a failure determination condition. Additionally, the life prediction step (S150) may further include the feature of predicting the life of the fuel cell stack (10) based on an integrated degradation prediction model (M3) and outputting the time required until the predicted life reaches a failure determination condition.

[0082] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present invention may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the invention. The disclosed embodiments are illustrative and should not be interpreted restrictively. Explanation of the symbols

[0083] 10: Fuel cell stack 11: Unit cell 100: Fuel cell life prediction device 110: Control unit 120: Interface section 130: Communications Department 140: Storage section 150: Information Gathering Department 160: Cell Prediction Model Section 170: Cell prediction correction unit 180: Stack Prediction Model Section 190: Life Prediction Unit

Claims

Claim 1 A fuel cell life prediction device comprising: an information collection unit for measuring the voltage of a plurality of unit cells provided in a fuel cell stack; a cell prediction model unit for generating a cell degradation prediction model to define the degradation pattern of each unit cell based on the voltage measured in the unit cells; a cell prediction correction unit for generating a cell degradation correction model to correct the degradation pattern so as to reflect the degree of dependence of the degradation pattern of one unit cell among the degradation patterns of the plurality of unit cells on the degradation pattern of another unit cell; and a life prediction unit for predicting the life of each unit cell based on the cell degradation correction model and outputting the time required for the predicted life to reach a failure judgment condition. Claim 2 A fuel cell life prediction device further comprising: a stack prediction model unit that generates an integrated degradation prediction model to define the degradation pattern of the fuel cell stack based on the degradation patterns of the plurality of unit cells corrected by the cell prediction correction unit in claim 1. Claim 3 In paragraph 2, the life prediction unit predicts the life of the fuel cell stack based on the integrated degradation prediction model and outputs the time required for the predicted life to reach the degradation judgment condition, thereby forming a fuel cell life prediction device. Claim 4 A fuel cell life prediction device according to claim 1, wherein the cell prediction model unit defines a cell degradation prediction model as shown in [Equation 1] below. [Equation 1] (Here, i is an index for a unit cell, an integer between 1 and n; j is an arbitrary point in time, an integer between 1 and n; is time Voltage at; The parameter is Transformation function for time; σ is the diffusion parameter; ) Claim 5 A fuel cell life prediction device according to claim 4, wherein the cell prediction correction unit corrects the degradation pattern as shown in [Equation 2] below. [Equation 2] (Here, It is modeled through the Copula function C and represents the joint cumulative distribution between the first difference values ​​of cell degradation values, and is the transformation function of the first difference value of the cell degradation value at time j of the i-th unit cell, represents a parameter that controls the correlation between cell degradation prediction models.) Claim 6 A fuel cell life prediction device according to claim 1, further comprising: a storage unit that stores information regarding the voltage measured by the information collection unit, the cell degradation prediction model generated by the cell prediction model unit, and the cell degradation correction model generated by the cell prediction correction unit. Claim 7 A fuel cell life prediction device comprising: an information collection unit for measuring the voltage of a plurality of unit cells provided in a fuel cell stack; a cell prediction model unit for predicting the degradation pattern of each unit cell based on the voltage measured in the unit cell; a cell prediction correction unit for correcting the degradation pattern to reflect the interdependence of the plurality of unit cell degradation patterns; a stack prediction model unit for predicting the degradation pattern of the fuel cell stack based on the corrected degradation pattern; and a life prediction unit for predicting the lifespan of the unit cell and the fuel cell stack, respectively, based on the corrected degradation pattern of the unit cell and the degradation pattern of the fuel cell stack. Claim 8 A fuel cell life prediction method comprising: an information collection step of measuring the voltage of each of a plurality of unit cells provided in a fuel cell stack; a cell prediction step of generating a cell degradation prediction model to define the degradation pattern of each unit cell based on the voltage measured in the unit cell; a cell prediction correction step of generating a cell degradation correction model to correct the degradation pattern of one unit cell among the degradation patterns of the plurality of unit cells to reflect the degree of dependence of the degradation pattern of one unit cell to the degradation pattern of another unit cell; and a life prediction step of predicting the life of each unit cell based on the cell degradation correction model and outputting the time required for the predicted life to reach a failure judgment condition. Claim 9 A fuel cell life prediction method further comprising, in claim 8, a stack prediction step of generating an integrated degradation prediction model to define a degradation pattern of the fuel cell stack based on the cell degradation correction model. Claim 10 A fuel cell life prediction method according to claim 9, wherein the life prediction step further comprises the feature of predicting the life of the fuel cell stack based on the integrated degradation prediction model and outputting the time required for the predicted life to reach a failure determination condition. Claim 11 A fuel cell life prediction method according to claim 8, wherein the cell prediction step is characterized by defining a cell degradation prediction model as shown in [Equation 1] below. [Equation 1] (Here, i is an index for a unit cell, an integer between 1 and n; j is an arbitrary point in time, an integer between 1 and n; is time Voltage at; The parameter is Transformation function for time; σ is the diffusion parameter; ) Claim 12 A fuel cell life prediction method according to claim 11, wherein the cell prediction correction step corrects the degradation pattern as shown in [Equation 2] below. [Equation 2] (Here, It is modeled through the Copula function C and represents the joint cumulative distribution between the first difference values ​​of cell degradation values, and is the transformation function of the cell degradation prediction model at time point j of the i-th unit cell, represents a parameter that controls the correlation between cell degradation prediction models.)

Citation Information

Patent Citations

  • Life estimating device for fuel cell and fuel cell system

    JP2005174922A

  • Battery life diagnostic device and battery life diagnostic method

    JP2018179733A

  • Long-term deterioration detection device, life-time prediction device and life-time prediction method

    JP2020071035A

  • Method for predicting life cycle of membrane electrode assembly of fuel cel for power generation

    KR1020210008198A