Fuel cell stack life prediction method and device and electronic equipment
Through the empirical modal decomposition of adaptive noise and the target autoregressive integral sliding average model, the problem of poor accuracy in fuel cell stack life prediction is solved, and the accurate capture and prediction of the stack life decay mechanism is achieved.
Patent Information
- Application Number
- CN202411619434.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-03-21
AI Technical Summary
The fuel cell stack lifetime prediction method based on the model in the prior art has poor prediction accuracy, and ignores the nonlinear characteristics of the complex mechanism of stack lifetime decline.
The life degradation data to be measured is processed using a complete set of empirical modal decomposition of adaptive noise, and the eigenmodal component data is predicted based on the preset target autoregressive integral sliding average model, and finally the predicted life degradation data is obtained through data fusion.
The nonlinear characteristics of the internal mechanism of the life decay of fuel cell stack are effectively considered, the accuracy of life prediction is improved, and the problem of simplifying the model based on hypothesis conditions in the prior art is overcome.
Smart Images
Figure CN119670031A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of fuel cell technology, and in particular to a method, device and electronic equipment for predicting the life of a fuel cell stack. Background Art
[0002] Solid oxide fuel cells are fuel cells that use solid oxides as electrolytes and operate at high temperatures, ranging from 800 to 1000°C. They have attracted widespread attention due to their all-solid structure, no corrosion and leakage problems, high operating temperature, high waste heat utilization value, wide fuel range, and no need for precious metal catalysts. Accurate prediction of the life of solid oxide fuel cell stacks is an important part of their commercialization and promotion.
[0003] In the prior art, the life prediction of solid oxide fuel cell stacks mainly includes model-based prediction, which predicts the evolution of performance degradation through mathematical formulas derived from failure physics.
[0004] However, model-based prediction methods usually use some assumptions to simplify the model, ignoring the nonlinear characteristics of the complex internal mechanism of fuel cell stack life degradation, and the prediction accuracy is poor. Summary of the invention
[0005] In view of this, it is necessary to provide a fuel cell stack life prediction method, device and electronic equipment to solve the problem of poor prediction accuracy of model-based prediction methods in the prior art.
[0006] In order to solve the above problems, the present application provides a fuel cell stack life prediction method, comprising: Obtaining the life decay data of the fuel cell stack to be tested; Performing complete set empirical mode decomposition of adaptive noise on the life decay data to be measured to obtain eigenmode component data to be measured; Based on a preset target autoregressive integrated moving average model, predicting the intrinsic mode component data to be measured, to obtain predicted intrinsic mode component data; The predicted intrinsic mode component data are fused to obtain predicted life decay data.
[0007] In some possible implementations, the lifetime decay data is in the form of voltage.
[0008] In some possible implementations, the target autoregressive integrated moving average model is obtained by the following steps: Obtain historical life decay data of fuel cell stacks; Performing complete set empirical mode decomposition of adaptive noise on the historical life decay data to obtain historical intrinsic mode component data; A preset initial autoregressive integrated moving average model is fitted based on the historical intrinsic mode component data to obtain a target autoregressive integrated moving average model.
[0009] In some possible implementations, obtaining historical life decay data of a fuel cell stack includes: Based on the degradation mechanism of nickel particle coarsening and oxidation in anode-supported single-unit solid oxide fuel cells, a fuel cell stack life decay model is constructed; Based on the fuel cell stack life decay model, historical life decay data of the fuel cell stack is obtained.
[0010] In some possible implementations, obtaining historical life decay data of a fuel cell stack includes: Obtain historical life decay data of the fuel cell stack when it works for a preset time under different working conditions.
[0011] In some possible implementations, the operating condition includes at least one of load, temperature, and flow.
[0012] In some possible implementations, fitting a preset initial autoregressive integrated moving average model based on the historical intrinsic mode component data to obtain a target autoregressive integrated moving average model includes: S601, predicting the historical intrinsic mode component data based on a preset initial autoregressive integrated moving average model to obtain a prediction result and its corresponding evaluation index; S602, determining whether the evaluation index reaches a preset range; S603: If the evaluation index does not reach the preset range, adjust the parameters of the initial autoregressive integrated moving average model and return to step S301; S604: If the evaluation index reaches a preset range, the initial autoregressive integrated moving average model is used as a target autoregressive integrated moving average model.
[0013] In some possible implementations, the evaluation index includes at least one of a root mean square error and an R-squared index.
[0014] The present application also provides a fuel cell stack life prediction device, comprising: A data acquisition unit, used to acquire the life decay data to be tested of the fuel cell stack; A modal decomposition unit, used for performing complete set empirical modal decomposition of adaptive noise on the life decay data to be measured, to obtain intrinsic modal component data to be measured; A model prediction unit, used for predicting the to-be-tested intrinsic mode component data based on a preset target autoregressive integrated moving average model to obtain predicted intrinsic mode component data; The modal fusion unit is used to fuse the predicted intrinsic modal component data to obtain predicted life decay data.
[0015] The present application also provides an electronic device, including a memory and a processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the above-mentioned fuel cell stack life prediction method.
[0016] The beneficial effect of the present application is that the fuel cell stack life prediction method provided by the present application effectively considers the nonlinear characteristics of the inherent mechanism of fuel cell stack life degradation through a data-based target autoregressive integral moving average model, overcomes the problem that the model-based prediction method in the prior art uses assumed conditions to simplify the model and ignores the nonlinear characteristics of the inherent complex mechanism, and realizes the accurate prediction of the fuel cell stack life.
[0017] Furthermore, the complete set empirical mode decomposition with adaptive noise is used to process the measured life decay data, which can effectively handle the linear trend and seasonality of the time series. At the same time, the intrinsic mode components of the white noise added in each decomposition are gradually reduced, and the inherent mode components have less residual noise, which effectively reduces the reconstruction error. There is a decomposition standard at each stage, and the decomposition efficiency is higher. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 A schematic flow chart of an embodiment of a method for predicting the life of a fuel cell stack provided in the present application; Figure 2 For this application Figure 1 A schematic flow chart of an embodiment of step S103; Figure 3 For this application Figure 2 A schematic flow chart of an embodiment of step S201; Figure 4 Schematic diagram of three different load fluctuations provided for this application; Figure 5 Schematic diagram of output voltage corresponding to three different load fluctuations provided in this application; Figure 6 For this application Figure 2 A schematic flow chart of an embodiment of step S203; Figure 7A schematic diagram of the structure of an embodiment of a fuel cell stack life prediction device provided in the present application; Figure 8 A schematic diagram of the structure of an embodiment of an electronic device provided in this application. DETAILED DESCRIPTION
[0019] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0020] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.
[0021] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.
[0022] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0023] The present application provides a method for predicting the life of a fuel cell stack, which is described below.
[0024] Figure 1 A schematic diagram of an embodiment of a fuel cell stack life prediction method provided in this application is shown in FIG. Figure 1 As shown, the fuel cell stack life prediction method includes: S101, obtaining life decay data to be measured of a fuel cell stack; It should be noted that the cost of measuring voltage is relatively low compared to other physical quantities, so voltage can be used as an important indicator for life prediction. In this application, voltage is used as the life decay data.
[0025] S102, performing complete set empirical mode decomposition of adaptive noise on the life decay data to be measured to obtain eigenmode component data to be measured; S103, predicting the eigenmode component data to be measured based on a preset target autoregressive integrated moving average model to obtain predicted eigenmode component data; S104, fusing the predicted intrinsic mode component data to obtain predicted life decay data.
[0026] Compared with the prior art, the present application effectively considers the nonlinear characteristics of the inherent mechanism of fuel cell stack life degradation through a data-based target autoregressive integrated moving average model, overcomes the problem that the model-based prediction method in the prior art simplifies the model by using assumptions and ignores the nonlinear characteristics of the inherent complex mechanism, and realizes accurate prediction of the fuel cell stack life.
[0027] Furthermore, the complete set empirical mode decomposition with adaptive noise is used to process the measured life decay data, which can effectively handle the linear trend and seasonality of the time series. At the same time, the intrinsic mode components of the white noise added in each decomposition are gradually reduced, and the inherent mode components have less residual noise, which effectively reduces the reconstruction error. There is a decomposition standard at each stage, and the decomposition efficiency is higher.
[0028] In order to obtain a better target autoregressive integrated moving average model, in some embodiments, such as Figure 2 As shown, the target autoregressive integrated moving average model in step S103 is obtained by the following steps: S201, obtaining historical life decay data of a fuel cell stack; S202, performing complete set empirical mode decomposition of adaptive noise on historical life decay data to obtain historical intrinsic mode component data; S203, fitting a preset initial autoregressive integrated moving average model based on historical intrinsic mode component data to obtain a target autoregressive integrated moving average model.
[0029] In order to obtain better historical life decay data, in some embodiments, a method combining data and models is used to build a main mechanism model of stack degradation to simulate voltage decay under different dynamic conditions. Specifically, Figure 3 As shown, step S201 includes: S301, constructing a fuel cell stack life decay model based on the degradation mechanism of nickel particle coarsening and oxidation of an anode-supported single solid oxide fuel cell; It should be noted that the fuel cell stack life degradation model is a simulink model.
[0030] S302: Based on the fuel cell stack life degradation model, obtain historical life degradation data of the fuel cell stack.
[0031] It should be noted that the historical life decay data refers to the historical life decay data of the fuel cell stack under different working conditions for a preset time, and the working conditions include at least one of load, temperature and flow rate. In a specific embodiment, the voltage decay of the stack under three different load fluctuations of 200A, 180A and 220A and different temperatures and different flows after working for 20,000 hours is simulated, wherein the fluctuations of the three different loads are as follows: Figure 4 As shown, the output voltage corresponding to three different load fluctuations is as follows Figure 5 shown.
[0032] In order to adjust the corresponding parameters so that the prediction effect of the target autoregressive integrated moving average model meets the requirements, in some embodiments, such as Figure 6 As shown, step S203 specifically includes: S601, predicting historical intrinsic mode component data based on a preset initial autoregressive integrated moving average model to obtain a prediction result and its corresponding evaluation index; It should be noted that the evaluation index includes at least one of the root mean square error and the R square index.
[0033] S602, judging whether the evaluation index reaches a preset range; S603: If the evaluation index does not reach the preset range, the parameters of the initial autoregressive integrated moving average model are adjusted, and the process returns to step S601; S604: If the evaluation index reaches a preset range, the initial autoregressive integrated moving average model is used as the target autoregressive integrated moving average model.
[0034] In order to better implement a fuel cell stack life prediction method in an embodiment of the present application, based on a fuel cell stack life prediction method, correspondingly, Figure 7As shown, the embodiment of the present application also provides a fuel cell stack life prediction device 700, comprising: The data acquisition unit 701 is used to acquire the life decay data to be measured of the fuel cell stack; A modal decomposition unit 702 is used to perform complete set empirical modal decomposition of adaptive noise on the life decay data to be measured, and obtain the intrinsic modal component data to be measured; The model prediction unit 703 is used to predict the eigenmode component data to be measured based on a preset target autoregressive integrated moving average model to obtain predicted eigenmode component data; The modal fusion unit 704 is used to fuse the predicted intrinsic modal component data to obtain predicted life decay data.
[0035] The fuel cell stack life prediction device 700 provided in the above embodiment can implement the technical solution described in the above fuel cell stack life prediction method embodiment. The specific implementation principles of the above units can refer to the corresponding contents in the above fuel cell stack life prediction method embodiment, which will not be repeated here.
[0036] like Figure 8 As shown, the present application also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802 and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0037] In some embodiments, the memory 802 may be an internal storage unit of the electronic device 800, such as a hard disk or memory of the electronic device 800. In other embodiments, the memory 802 may also be an external storage device of the electronic device 800, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 800.
[0038] Furthermore, the memory 802 may include both an internal storage unit of the electronic device 800 and an external storage device. The memory 802 is used to store application software installed in the electronic device 800 and various data.
[0039] In some embodiments, the processor 801 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 802, such as the fuel cell stack life prediction method in the present application.
[0040] In some embodiments, the display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 803 is used to display information on the electronic device 800 and to display a visual user interface. The components 801-803 of the electronic device 800 communicate with each other via a system bus.
[0041] In some embodiments of the present application, when the processor 801 executes the fuel cell stack life prediction program in the memory 802, the following steps may be implemented: Obtaining the life decay data of the fuel cell stack to be tested; Perform complete set empirical mode decomposition of adaptive noise on the life decay data to be measured, and obtain the intrinsic mode component data to be measured; Based on a preset target autoregressive integrated moving average model, the eigenmode component data to be measured is predicted to obtain the predicted eigenmode component data; The predicted intrinsic mode component data are fused to obtain the predicted life decay data.
[0042] It should be understood that: when the processor 801 executes the fuel cell stack life prediction program in the memory 802, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0043] Furthermore, the embodiment of the present application does not specifically limit the type of the electronic device 800 mentioned, and the electronic device 800 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic device may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present application, the electronic device 800 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0044] The above is a detailed introduction to a fuel cell stack life prediction method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
[0045] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.
Claims
1. A method for predicting the life of a fuel cell stack, characterized in that: include: Obtaining the life decay data of the fuel cell stack to be tested; Performing complete set empirical mode decomposition of adaptive noise on the life decay data to be measured to obtain eigenmode component data to be measured; Based on a preset target autoregressive integrated moving average model, predicting the intrinsic mode component data to be measured, to obtain predicted intrinsic mode component data; The predicted intrinsic mode component data are fused to obtain predicted life decay data.
2. The fuel cell stack life prediction method according to claim 1, characterized in that: The lifetime degradation data includes voltage.
3. The fuel cell stack life prediction method according to claim 1, characterized in that: The target autoregressive integrated moving average model is obtained by the following steps: Obtain historical life decay data of fuel cell stacks; Performing complete set empirical mode decomposition of adaptive noise on the historical life decay data to obtain historical intrinsic mode component data; A preset initial autoregressive integrated moving average model is fitted based on the historical intrinsic mode component data to obtain a target autoregressive integrated moving average model.
4. The fuel cell stack life prediction method according to claim 3, characterized in that: Obtain historical fuel cell stack life degradation data, including: Based on the degradation mechanism of nickel particle coarsening and oxidation in anode-supported single-unit solid oxide fuel cells, a fuel cell stack life decay model is constructed; Based on the fuel cell stack life decay model, historical life decay data of the fuel cell stack is obtained.
5. The fuel cell stack life prediction method according to claim 3, characterized in that: Obtain historical fuel cell stack life degradation data, including: Obtain historical life decay data of the fuel cell stack when it works for a preset time under different working conditions.
6. The fuel cell stack life prediction method according to claim 5, characterized in that: The operating condition includes at least one of load, temperature and flow.
7. The fuel cell stack life prediction method according to claim 3, characterized in that: The preset initial autoregressive integrated moving average model is fitted based on the historical intrinsic mode component data to obtain a target autoregressive integrated moving average model, including: S601, predicting the historical intrinsic mode component data based on a preset initial autoregressive integrated moving average model to obtain a prediction result and its corresponding evaluation index; S602, determining whether the evaluation index reaches a preset range; S603: If the evaluation index does not reach the preset range, adjust the parameters of the initial autoregressive integrated moving average model and return to step S301; S604: If the evaluation index reaches a preset range, the initial autoregressive integrated moving average model is used as a target autoregressive integrated moving average model.
8. The fuel cell stack life prediction method according to claim 7, characterized in that: The evaluation index includes at least one of a root mean square error and an R-squared index.
9. A fuel cell stack life prediction device, characterized in that: include: A data acquisition unit, used to acquire the life decay data to be tested of the fuel cell stack; A modal decomposition unit, used for performing complete set empirical modal decomposition of adaptive noise on the life decay data to be measured, to obtain intrinsic modal component data to be measured; A model prediction unit, used for predicting the to-be-tested intrinsic mode component data based on a preset target autoregressive integrated moving average model to obtain predicted intrinsic mode component data; The modal fusion unit is used to fuse the predicted intrinsic modal component data to obtain predicted life decay data.
10. An electronic device, characterized in that: including memory and processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the fuel cell stack life prediction method described in any one of claims 1 to 8 above.